Improved air quality monitoring system and methods

Abstract

Air quality monitoring technology to continuously monitor an environment and determine if an event has occurred based on received sensor information. Various actions may be taken based on the determined event. For example, an alert may be generated. Additionally, predictive models may be updated, recommendations may be made, and estimated times for remediation may be made. Remediation may be monitored and determined to be occurring, incomplete, or complete.

Description

IMPROVED AIR QUALITY MONITORING SYSTEMS AND METHODSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority to U.S. Provisional Application No. 63 / 607,767, filed December 8, 2023, which is hereby incorporated by reference in its entirety.BACKGROUND

[0002] Air quality plays a crucial role in maintaining a healthy environment, particularly in higher-risk environments such as hospitals, laboratories, industrial manufacturing plants, agricultural facilities, wastewater treatment plants, and food processing plants. Monitoring of air quality may protect human safety in these environments, where particulate matter, toxic gases, chemicals, or bioaerosols need to be monitored or contained. Air quality monitoring helps detect hazards and protects the safety of workers and the surrounding environments.

[0003] Hospitals, as centers for treating illnesses and infections, are vulnerable to a variety of contaminants, including airborne pathogens, chemicals, and particulate matter. As an environment where air quality directly impacts patient recovery and the overall well-being of staff and visitors, hospitals should seek to promptly implement remediation and / or mitigation efforts to preserve air quality. These measures are essential not only to prevent the spread of infections, but also to ensure a safe environment for all. Thus, effective air quality management in hospitals is a key aspect of healthcare that safeguards against further health complications and promotes a healthier atmosphere.

[0004] Current technology, however, lacks the ability to automatically monitor, identify, and take remediation actions based on real-time air quality information. Also, to the extent that hospitals monitor air quality and take actions based on such monitoring, those decisions often rely on out-of-date scientific information and infrequent testing. Thus, it remains desirous to have an air quality monitoring system that can automatically monitor, update, and alert based on real-time data acquisition and environmental factors.

[0005] It is with respect to these and other considerations that the technologies described below have been developed. Also, although relatively specific problems have been discussed, it should be understood that the embodiments should not be limited to solving the specific problems identified in the introduction.BRIEF SUMMARY

[0006] It is to be understood that both the foregoing introduction and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the innovative technologies as claimed.

[0007] The technology generally relates to methods and devices for real-time, continuous monitoring of air quality. Aspects of the technology relate to using information captured from sensors to determine the safety of an environment. Various actions may be taken based on the determined information. For example, alerts and notifications may be generated. This includes warnings that an environment is not considered safe or notifications that an environment that was previously unsafe is now considered safe. Additionally, predictive models may be updated, remediation actions may be recommended, and time periods for remediation may be predicted.

[0008] In one example, the technology includes a computer-implemented method. The computer-implemented method includes receiving sensor information from one or more sensors. In some examples, at least one of the one or more sensors is an optical sensor. In certain aspects, the sensor information includes air quality data regarding particulate matter in an environment. The computer-implemented method further includes determining, based on the sensor information, that an event has occurred. The computer-implemented method may further include taking an action based on the determining that an event has occurred operation.

[0009] In examples, the received sensor information may include information related to dust, silica, soot, smoke, oil aerosols, salt aerosols, asbestos, fiberglass particles, dust mites, pet dander, detritus, bioaerosols, pollen, mold spores, bacteria spores, fungal spores, viruses, endotoxins, mycotoxins, airborne pollutants, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, heavy metals, pesticides, phthalates, dioxins, industrial solvents, gases, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, ethylene oxide, chlorine, relative humidity, moisture, temperature, wind speed, thermal images, barometric pressure, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, and electromagnetic interference.

[0010] In examples, the one or more sensors may be one or more from the group including optical sensors, electrochemical sensors, metal-oxide semiconductor sensors, photoacoustic sensors, ionic sensors, humidity sensors, temperature sensors, electrostatic sensors, non-dispersive infrared sensors, micro-electro-mechanical sensors, laser scattering sensors, light scattering sensors, light-induced fluorescence sensors, nephelometers, or photoionization detectors.

[0011] In examples, the optical sensor may be from the group including photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, or light detection and ranging.

[0012] In aspects of the technology, air quality data may include air quality data related to dust, silica, soot, smoke, oil aerosols, salt aerosols, asbestos, fiberglass particles, dust mites, pet dander, detritus, bioaerosols, pollen, mold spores, bacteria spores, fungal spores, viruses, endotoxins, mycotoxins, airborne pollutants, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, heavy metals, pesticides, phthalates, dioxins, industrial solvents, gases, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, ethylene oxide, and chlorine.

[0013] In additional examples, the computer-implemented method may further include comparing the sensor information to a threshold. The method may further include determining that the sensor information exceeds the threshold. In aspects of the technology, the threshold is established using one or more of scientific databases, safety data sheets, environmental regulations, and standard operating procedures.

[0014] In examples, the threshold may include an upper limit for the sensor information, a lower limit for the sensor information, absence of the sensor information, presence of the sensor information, a rate of increase for sensor information, or a rate of decrease for sensor information.

[0015] In examples, the computer-implemented method includes taking action. The action may comprise changing temperature, changing fan speed, changing pressure settings, generating an alert, recommending remediation actions, estimating remediation times, storingdata, comparing data with a third-party database, comparing data with predicted computer models, or updating a predictive computer model.

[0016] In additional examples, the computer-implemented method may further include receiving new sensor information. The sensor information may indicate that a remediation action has occurred. The computer-implemented method may further include estimating a period of time for remediation to occur, based on, at least in part, the new sensor information. The computer-implemented method may further include receiving additional sensor data after the period of time for remediation. In aspects of the technology, the estimating operation may be performed using a deep neural network.

[0017] In aspects of the technology, the computer-implemented method may further include determining that the environment is not considered safe, based on, at least in part, the additional sensor data. The computer-implemented method may further include updating a computer model, based on the determination that the environment is not considered safe. The computer-implemented method may further include estimating a time to resolution for remediation.

[0018] In additional aspects of the technology, the computer-implemented method may include determining that the environment is considered safe, based on, at least in part, the additional sensor data. The computer-implemented method may further include sending a notification that the environment is considered safe.

[0019] In examples, the computer-implemented method may include normalized sensor information. In additional examples, the computer-implemented method further includes receiving sensor information from a first sensor, wherein the sensor information includes air quality data regarding particulate matter in an environment. The computer-implemented method may further include assigning a first time stamp to the received sensor information. The computer-implemented method may further include determining, based on the first time stamp, a first time interval. In aspects of the technology, the computer-implemented method may further include receiving sensor information from a second sensor. The computer- implemented method may further include assigning a second time stamp to the received sensor information. The computer-implemented method may further include determining, based on the second time stamp, a second time interval. In aspects of the technology, the computer-implemented method may further include receiving sensor information from atleast one additional sensor. The computer-implemented method may further include assigning at least one additional time stamp to the received sensor information. The computer-implemented method may further include determining, based on the at least one additional time stamp, at least one additional time interval.

[0020] In additional examples, the computer-implemented method may include normalizing received sensor information. The computer-implemented method may further include sending normalized sensor information. In aspects of the technology, normalizing received sensor information is performed on a peer-to-peer network. In additional aspects of the technology, sending normalized sensor information may further include sending the normalized sensor information to a predictive computer model.BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Illustrative embodiments of the present invention are described in detail below with reference to the attached drawings, wherein:

[0022] FIG. 1A illustrates an example environment in which the systems and methods described herein may operate.

[0023] FIG. IB illustrates an additional example environment in which the systems and methods described herein may operate.

[0024] FIG. 2 illustrates an example computer architecture for facilitating improved air quality monitoring and remediation.

[0025] FIG. 3A is an example method of monitoring air quality.

[0026] FIG. 3B is an example method of normalizing air quality data

[0027] FIG. 4 is an example method of determining an event has occurred based on a threshold.

[0028] FIG. 5 is an example method of taking an action based on determining an event has occurred.

[0029] FIG. 6 is an example method of updating a predictive computer model.

[0030] FIG. 7 is an example method of monitoring remediation.

[0031] FIG. 8A is an example diagram of a distributed computing system in which aspects of the present invention may be practiced.

[0032] FIG. 8B is one embodiment of the architecture system in which aspects of the present disclosure may be practiced.

[0033] FIG. 9 illustrates an exemplary architecture of a computing device that can be used to implement aspects of the present disclosure.

[0034] FIG. 10 is a block diagram illustrating additional physical components (e.g., hardware) of a computing device.DETAILED DESCRIPTION

[0035] While various embodiments and examples have been described for purposes of this disclosure, various changes and modifications may be made which are well within the scope of the disclosed methods. Numerous other changes may be made which will readily suggest themselves to those skilled in the art and which are encompassed in the spirit of the disclosure.

[0036] In general, the terms and phrases used herein have their art-recognized meaning, which can be found by reference to standard texts, journal references, and contexts known to those skilled in the art. The following definitions are provided to clarify their specific use in the context of this description.

[0037] A “device” is a combination of components operably connected to produce one or more desired functions.

[0038] A “component” is used broadly to refer to an individual part of a device.

[0039] Sensor information” broadly refers to information regarding physical, chemical and biological agents that may directly or indirectly affect the safety of an environment and inform on conditions of an environment. Sensor information may include the presence, absence, levels, and / or concentrations of particulate matter, bioaerosols, pollutants, gases, chemicals, light waves, sound waves, temperature, humidity, moisture, pressure and / or other environmental conditions.

[0040] “Air quality data” refers to sensor information regarding particulate matter, bioaerosols, pollutants, gases, and chemicals.

[0041] “Members” broadly refers to individual parts of a computing system.

[0042] “Historical” broadly refers to stored information and / or data from previously monitored air quality events.

[0043] A “threshold” refers to a predefined numerical value, that represents a limit. A threshold may represent a lower limit and / or an upper limit. A threshold may be a rate of increase or decrease. One or more thresholds may be used in combination with other thresholds.

[0044] A “remediation event” refers to an occurrence or intervention where specific actions are taken to remove, neutralize, and / or reduce a hazard.

[0045] An “environment” refers to a specific place, setting, or area where a detector, events, and actions are occurring or may occur.

[0046] A “remediator” refers to agents (often chemical agents or physical agents) used to decontaminate an area or neutralize a hazard. Remediators may, for example, interact with pollutants or chemicals to break them down via oxidation or degradation. Remediators may reduce or eliminate harmful or unwanted organisms. Many agents may act as remediators, a few examples are listed to enhance clarity. Example chemical agent remediators include gases and chemicals such as ozone, chlorine, chlorine dioxide, ethylene oxide, sulfur dioxide, formaldehyde, ammonia, methyl bromide, methanol, and hydrogen peroxide. Examples of physical agent remediators include ultraviolet light (ultraviolet radiation), heat, filters, electrostatic precipitators, cold plasma (non-thermal plasma), ultrasonic waves (high frequency sound waves), photocatalytic oxidation (PCO) and pressure changes.

[0047] It will be appreciated that while the illustrated examples are related to monitoring air quality, the disclosed methods and principles are equally applicable to monitoring additional applications, including, but not limited to, surface water, groundwater, ocean water, soil and land, various indoor and industrial environments, and / or meteorological concerns.

[0048] FIG. 1A illustrates an example environment 100 in which the systems and methods described herein may operate. As illustrated, FIG.l includes a first computing device 108 containing an alert and notification application 118, a second computing device 110 containing an operational control application 120, a third computing device 112 containing a predictive model application 122, and a fourth computing device 124 storing a client application 102. It will be appreciated that though the applications are shown on multiple computing devices, the applications may be run on a single computer or more computers than as shown. Additionally illustrated is server 104, detection computing device 106, and database 114. Each of the first computing device 108, the second computing device 110, the third computing device 112, the fourth computing device 124, the server 104, the detection computing device 106, and the database 114 is in electronic communication via a network 116.

[0049] Detection computing device 106, in examples, captures sensor information from one or more sensors and, via network 116, may send sensor information to server 104, database 114, first computing device 108, second computing device 110, third computing device 112, and / or fourth computing device 124 (collectively referred to as “System 100”). In examples, the one or more sensors may be any sensor, including sensors suited to capture air quality data. Such sensors include optical sensors, electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, humidity sensors, temperature sensors, electrostatic sensors, and micro-electro-mechanical sensors. Suitable optical sensors include sensors such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection and ranging (LiDAR). Such sensors may capture sensor information regarding the concentrations and / or levels of gases such as ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, chlorine, and radon. Sensor information may also include data regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, barometric pressure, dust, silica, oil aerosols, salt aerosols, asbestos, fiberglass particles, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, explosive residues, perfluorinated compounds, combustiblegases, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, methanol, and industrial solvents. It will be appreciated that while a single detector is illustrated, multiple detectors, comprised of one or more sensors, may be employed, and multiple ancillary devices may be employed within detection computing device 106 without deviating from the scope of the technology. For example, filters, enclosures, hoods, lighting, power supply, a cleaning system, brackets and mounting devices may comprise detection computing device 106. Detection computing device 106 may be designed to operate indoors, outdoors, in hazardous areas, and / or 24 hours per day. Detection computing device 106 and its components may be waterproof, water-resistant, fire-resistant, explosion proof, and / or any properties that may be necessary to maintain proper functioning in the environment where the technology is employed.

[0050] Detection computing device 106 may collect, process, and send sensor information, via network 116, to all or individual components of System 100 automatically and / or manually (such as when requested by a user). Example detection computing devices, such as detection computing devices 106, includes one or more sensors configured to capture information from the surrounding environment, such as physical, chemical, optical, or acoustic data. The captured information may then be locally processed by one or more computing components, which may include processors, memory, and algorithms designed to analyze, interpret, transform and / or store the sensor data into meaningful outputs. Once processed, the device may transmit the resulting information over a network, which may include wireless (e.g., Wi-Fi, Bluetooth, cellular, or satellite), wired (e.g., Ethernet or fiber optic), or hybrid communication protocols, enabling integration with other systems or devices for further analysis, storage, or action. In examples, detection computing device 106 is adaptable to various applications, including monitoring, automation, and data aggregation.

[0051] For example, detection computing device 106 may transmit sensor information, via network 116, to server 104 continuously, in real time, upon request, and / or at specific time intervals. In certain examples, a user may request sensor information be sent to the fourth computing device 124 via client application 102 for real time monitoring of air quality data. In another example, detection computing device 106 may continuously send sensor information to server 104. In some examples, when sensor information reaches a prespecified threshold, server 104 may send information to various computing devices, such as first computing device 108, such that alert and notification application 118 generates an alert,which may be sent to various client applications, such as client application 102. The alert may be an audible alarm in a building, or result in a visual warning, such as flashing lights. In another example, server 104 may send information to second computing device 110, such that operational control application 120 may adjust operational parameters of a heating, ventilation and air conditioning system (HVAC). Such operational parameters include fan speed, temperature, and air pressure settings. In additional examples, operational control application 120 may adjust the rate at which air enters detection computing device 106.

[0052] In certain examples, detection computing device 106 may send information to third computing device 112, providing information such that predictive model application 122 may update a predictive computer model of air quality conditions. In additional examples, server 104 may send information regarding sensor information to fourth computing device 124, such that client application 102 displays real time sensor information regarding air quality data to users.

[0053] In non-limiting examples, detection computing device 106 may send sensor information to server 104. Server 104 may determine that sensor information exceeds a threshold. Server 104 may send information to all other members of System 100, such that alert and notification application 118 generates one or more alerts, operational control application 120 adjusts HVAC operational parameters, predictive model application 122 updates a predictive computer model, and client application 102 displays both real time sensor information and displays an alert, and sensor information is added to database 114. It will be appreciated that server 104 may monitor sensor information in relation to a threshold and perform calculations during remediation processes. Though only one detection computing device is illustrated, it will be appreciated that multiple detection computing devices may be present and in electronic communication via network 106 with the various elements of environment 100.

[0054] Client application 102 may be interacted with using a graphical user interface (GUI). Client application 102 may receive sensor information from detection computing device 106 and server 104, as well as other data from System 100. Using some or all received information or data, client application 102 may display information such as real time sensor information, historical sensor information (received from database 114, server 104, and / or locally stored), predicted computer models, and / or alert notifications. Client application 102 may include features that allow a user to control operational parameters, such as fan speed,temperature and pressure settings. In examples, client application 102 may automatically adjust operational parameters and / or send information to operational control application 120. It will be appreciated that client application 102 may perform calculations, monitor sensor information as compared to a threshold, and generate alerts. Client application 102 may send sensor information and / or data to System 100. In certain non-limiting examples, client application 102 may determine sensor information exceeds a threshold. In additional examples, client application 102 may generate an alert, which may be one or more of a text display, e-mail alert, text message alert, an audible alarm and / or flashing lights. In examples, a user may disable an alert via client application 102.

[0055] Fourth computing device 124 may include a GUI and, as illustrated, store client application 102. It will be appreciated that fourth computing device 124 may be one or more of any computing devices suitable for housing client application 102, such as desktop computers, laptop computers, notebook computers, tablets, smartwatches, and smart TVs.

[0056] Alert and notification application 118 may receive information from any or all other components of System 100. It will be appreciated that alert and notification application 118, in certain examples, may receive sensor information from detection computing device 106. In examples, alert and notification application 118 may determine sensor information exceeds a threshold. In specific examples, alert and notification application 118 may generate one or more alert, such as e-mail alerts, text message alerts, an audible alarm and / or flashing lights, based on, at least in part, received information from one or more components of System 100. In certain examples, alert and notification application 118 may send information to client application 102, such that client application 102 displays an alert. It will be appreciated that alert and notification application 118 may send information to any or all components of System 100. As illustrated, first computing device 108 houses alert and notification application 118. Various other computing devices may also house alert and notification application without deviating from the scope of the innovative concepts described herein.

[0057] Operational control application 120 may receive information from any or all other computing devices, databases, servers, etc., of System 100. It will be appreciated that operational control application 120 may, in certain examples, receive sensor information from detection computing device 106. In examples, operational control application 120 may determine that sensor information exceeds a threshold. In specific examples, operationalcontrol application 120 may adjust operational parameters such as fan speed, temperature, and / or pressure settings, based on, at least in part, received information from one or more members of System 100. In certain examples, operational control application 120 may send information to client application 102 such that client application 102 may adjust operational parameters. It will be appreciated that operational control application 120 may send information to any or all members of System 100. As illustrated, second computing device 110 houses operational control application 120.

[0058] Predictive model application 122 may receive information from any or all other computing devices, databases, servers, etc., of System 100. It will be appreciated that predictive model application 122 may, in certain examples, receive sensor information from detection computing device 106. In specific examples, predictive model application 122 may receive information from database 114. Information received from database 114 may be used to create or update predictive models. In examples, predictive model application 122 may determine sensor information exceeds a threshold. In specific examples, predictive model application 122 may update a predictive model based, at least in part, on received information from one or more members of System 100. In certain examples, predictive model application 122 may send information to client application 102 such that client application 102 may display one or more predictive models. It will be appreciated that predictive model application 122 may send information to any or all members of System 100. In certain examples, predictive model application 122 may send information regarding predictive computer models to database 114. As illustrated, third computing device 112 houses predictive model application 122.

[0059] In examples, a predictive model is a computational system designed to analyze input data and estimate future trends or outcomes based on a combination of sensor data, environmental parameters, and theoretical frameworks. The model may take information from sensors that capture real-time measurements and integrate it with environmental variables, such as the size of a room or other contextual conditions, which may be captured or input at a GUI of a client. It may further utilize scientific literature, established principles, and historical data specific to the application to refine its predictions. For example, if the sensor has previously operated under certain environmental conditions, such as specific HVAC settings, weather patterns, or humidity levels, the model may leverage this historical information to infer likely trends and outcomes.

[0060] Database 114 may receive information from any or all other members of System 100. It will be appreciated that database 114 may, in certain examples, receive sensor information from detection computing device 106. Database 114 may store received information, as well as information and / or data from scientific databases, safety data sheets, environmental regulations, and / or standard operating procedures. It will be appreciated that database 114 may send information to any or all other members of System 100. In specific examples, database 114 may send information regarding historical sensor information to predictive model application 122 such that predictive computer models may be compared to additional historical data, and / or predictive computer models may be updated. In aspects of the technology, database 114 may send information such as historical sensor information, data from scientific databases, safety data sheets, environmental regulations, and / or standard operating procedures to server 104, client application 102, first computing device 108, second computing device 110, third computing device 112, and / or fourth computing device 124. Information from database 114 may be used to set thresholds.

[0061] Network 116 facilitates communication between various computing devices, such as the computing devices illustrated in FIG. 1A. Network 116 may be the Internet, an intranet, or another wired or wireless communication network. For example, network 116 may include a GLOBAL Mobile Communications (GMS) network, a code division multiple access (CDMA) network, 3rdGeneration Partnership Project (GPP) network, an Internet Protocol (IP) network, a wireless application protocol (WAP) network, a Wi-Fi network, a satellite communications network, or an IEEE 802.11 standards network, as well as various communications thereof. Other conventional and / or later developed wired and wireless networks may also be used.

[0062] FIG. IB illustrates an example environment 140 in which the systems and methods described herein may operate. It will be appreciated that elements numbered the same as the elements numbered in Fig. 1A have the same or similar property as those described with reference to Fig. 1A. Fig. IB illustrates an example of a plurality of detection computing devices in a peer-to-peer networks with each other. As particularly illustrated, FIG. IB includes first detection computing device 150, second detection computing device 152, third detection computing device 154, fourth detection computing device 156, and fifth detection computing device 158 (collectively Sensor System 140 in electronic communication as participants in a peer-to-peer network (collectively peer-to-peer network160). In examples, other computing devices (not shown) may participate in the peer-to-peer network 160. It will be appreciated that these other computing devices may share information, processing power, and / or bandwidth with peer-to-peer network 160. The other computing devices may be any acceptable computing device, including, but not limited to a desktop computer, laptop computer, notebook computer, tablet, smartwatch, smart phone, and smart TV. In aspects of the technology, more than one computing device may participate in peer-to-peer network. In certain examples, other computing devices may be absent.

[0063] It will be appreciated by one skilled in the art that each participant in the peer-to- peer network 160 may communicate directly with any other participant, and that each participant may share information, processing power, and / or network bandwidth with one another. Additionally, in some examples, any participant may leave or join the network at any time without disruption of the overall system. If any individual participant in peer-to-peer network 160 fails or leaves the network, the network may continue to function. Likewise, additional participants may be added to peer-to-peer network 160 at any time without disruption of service, in example, which, for some applications, aids in increasing the potential processing power of the plurality of sensors and may reduce the strain on network 116 (as discussed more fully herein. While five sensors are illustrated, it will be appreciated that Sensor System 140 may be comprised of more or less sensors. In certain embodiments, Sensor System 140 may be comprised of a single sensor. In alternative embodiments, Sensor System 140 may be comprised of twelve or more sensors. Additionally, although each sensor of Sensor System 140 is illustrated separately, one or more sensors may be housed together in a single detection device.

[0064] The illustrated peer-to-peer network 160, allows a plurality of detection computing devices, such as first detection computing device 150, second detection computing device 152, third detection computing device 154, fourth detection computing device 156, and fifth detection computing device 158, to communicate directly with one another without reliance on a centralized server. In examples, communication involves a combination of discovery protocols, such as Distributed Hash Tables (DHTs) or bootstrapping through known nodes, to identify and locate peers within the network. Once identified, peers may exchange data using standardized protocols, like BitTorrent for file sharing or WebRTC for real-time communication. These communications are facilitated over various network types, including Wi-Fi, cellular networks (e.g., 4G, 5G), Ethernet, or other internet-connectedmediums, allowing decentralized interaction and resource sharing across diverse physical and digital environments.

[0065] In specific examples, each detection device of the plurality of detection computing devices may have similar or the same sensors as other detection computing devices in the peer-to-peer network. In other examples, the sensors may be different. For example, first detection computing device 150 may include a temperature sensor collecting sensor information related to temperature in an environment, while second detection computing device 152 may include a pressure sensor, collecting sensor information related to barometric pressure in the environment. Third detection computing device 154 may include a humidity sensor, collecting sensor information related to the relative humidity of the environment. Fourth detection computing device 156 may include an optical sensor, such as a light-induced fluorescence sensor, collecting sensor information regarding particulate matter in the air and bioaerosols in the environment, while fifth detection computing device 158 may include a gas detector, such as a metal-oxide semiconductor sensor, collecting sensor information related to gas levels and / or concentrations in the environment.

[0066] Each detection computing device may collect sensor information at different time intervals. For example, first detection computing device 150 may collect temperature data every minute, while fourth detection computing device 156 may collect particulate matter sensor information every 20 minutes. Additionally, each detection computing device may include a computing device to, at least partially, process and normalize sensor information data.

[0067] In examples where sensor readings are collected at differing intervals, the rate of change over time can be determined by normalizing the data and interpolating values to achieve a consistent temporal resolution. In examples, timestamps of all readings may be aligned to a common temporal scale. For sensors with less frequent readings, interpolation methods such as linear interpolation, spline fitting, or polynomial regression can estimate intermediate values. For sensors with more frequent readings, down-sampling or averaging within the target intervals may achieve normalization of the dataset.

[0068] The rate of change may be calculated by taking the derivative of the interpolated or normalized data over the chosen time intervals. Adjustments can be made based on the type of measurement, expected trends in the data, and specific environmental factors. Forexample, periodic variations in environmental conditions may require domain-specific models to estimate dynamic changes accurately. This approach allows for estimating the temporal rate of change while accounting for the nature of the data and varying sensor reporting frequencies.

[0069] For example, a detection computing device may detect and store particulate matter every 20 minutes, which may be normalized to every minute by extrapolating how the 20-minute data aggregation may occur in a minute-by-minute way. Normalizing sensor data may be performed such that relatively longer periods of time (such as collecting every 20 minutes) may be extrapolated to shorter time periods (such as every minute). By extrapolating at the detection computing devices, the processing load on a server, such as server 104, may be reduced. Alternatively, by removing data (e.g., going from every minute to every 20 minutes) the bandwidth used transmitting information from the plurality of detection computing devices to a server or other device may be reduced. This may, in examples, reduce the bandwidth usage by requiring sensor information to be communicated via peer-to-peer network 160 less frequently.

[0070] Continuing with the example, transmitting, processing and normalizing sensor information using, at least in part, hardware and / or firmware included in the sensor, may reduce required processing speed and / or capacity at server 104. It will be appreciated that hardware may include one or more of central processing units (CPUs), graphics processing units (GPUs), motherboards, network interface cards (NICs), LTE / 5G modems, hard drives, solid-state drives, flash drives, single-board computers (SBCs), loT devices, applicationspecific integrated circuits (ASICs), routers, gateways, and / or antennas. Firmware may include one or more of router firmware, device firmware (such as Wi-Fi or Bluetooth handling connection protocols), drive firmware, system firmware, cryptographic firmware, real-time operating systems (RTOS), or any other conventional or later developed firmware suitable for the utilized hardware of the participant.

[0071] It will be appreciated that each detection computing device described with reference to Fig. 1A or Fig. IB may each be any suitable sensor for air quality monitoring. Such sensors include one or more suitable optical sensors such as photoacoustic sensors, non- dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and / or LiDAR. Itwill likewise be appreciated that any individual sensor of any detection computing device described with reference to Fig. 1A or Fig. IB may be any suitable sensor for air quality monitoring, including, but not limited to optical sensors, electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, humidity sensors, temperature sensors, electrostatic sensors, and / or micro-electro-chemical sensors. A detection computing device may have one or more sensors.

[0072] FIG. 2 is an example block diagram 200 of an example computer architecture for facilitating improved air quality monitoring and remediation. As illustrated, detector 206 is comprised of one or more sensors, which capture sensor information that may be sent to server 204 via communication channel 244 and / or client application 202 via communication channel 246.

[0073] The illustrated detector 206 includes optical sensor 216 and additional sensor 226. Optical sensor 216 may be comprised of one or more of any suitable optical sensors, including photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and / or LiDAR. Additional sensor 226 may be comprised of one or more of any suitable sensors, including optical sensors, electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, humidity sensors, temperature sensors, electrostatic sensors, and / or micro-electro-chemical sensors. It will be appreciated that additional sensor 226 may be comprised of one or more of any suitable optical sensors. In examples, optical sensor 216 and additional sensor 226 capture sensor information. In examples, sensor information may include information regarding gases, such as ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, chlorine. In certain examples, sensor information may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and / or barometric pressure. In specific examples, sensor information may include air quality data, such as information regarding dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dustmites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, methanol, and chlorine.

[0074] The illustrated server 204 includes event determination engine 214, calculation engine 224, and update model engine 234. Server 204 is in communication with detector 206 via communication channel 244 and with client application 202 via communication channel 242

[0075] Event determination engine 214 uses sensor information to determine if an event has occurred. In specific examples, event determination engine 214 determines sensor information has exceeded a threshold. In certain aspects, it may be determined that dust, silica, or other particulate matter concentrations in the air are in excess of a threshold for safety. In certain examples, event determination engine 214 may determine a remediation event has begun. For example, sensor information may indicate the presence of ozone, along with a reduction in mold spore levels, where event determination engine 214 may determine a remediation event has begun. In additional examples, event determination engine 214 may determine sensor information no longer exceeds a threshold. For example, it may be determined that mold spore levels no longer exceed a threshold for safety. In aspects of the technology, it may be determined that sensor information is no longer detected, such as, as a non-limiting example, the absence of mold spores. In certain examples, event determination engine 214 may determine sensor information is below a threshold. As a non-limiting example, event determination engine 214 may determine oxygen levels in an environment are below a threshold for safety. In certain aspects of the technology, event determination engine 214 may use a deep neural network (DNN) or machine learning algorithm to aid in making determinations. In specific examples, server 204 may send event determination information to client application 202.

[0076] Calculation engine 224 calculates predictions based on, at least in part, sensor information, historical sensor information, and / or data from scientific databases. In certain, non-limiting examples, calculation engine 224 may calculate thresholds for safety, based on, at least in part, data from scientific databases, safety data sheets, environmental regulations, and / or standard operating procedures. In additional, non-limiting examples, calculation engine 224 may calculate a period of time until a safe environment will no longer be safe. Forexample, using sensor information and / or data from scientific databases, calculation engine 224 may predict a period of time for oxygen levels in an environment to reduce to levels that are below a lower limit threshold for safety. In specific examples, calculation engine 224 predicts a time period for remediation to occur until an environment is considered safe. Calculation engine 224 may predict a period of time until sensor information is below an upper limit threshold for safety. In specific examples, calculation engine 224 may use sensor information regarding temperature and / or relative humidity to standardize results by controlling for variations in data output due to temperature and / or humidity. In examples, calculation engine 224 may output a predictive computer model. In certain examples, the predictive computer model may be sent to client application 202. In certain aspects of the technology, calculation engine 224 may use a DNN.

[0077] Update model engine 234 updates predictive computer models based on, at least in part, received sensor information and / or information from calculation engine 224. In examples, a predictive computer model may display a period of time for a remediation event to occur. In specific examples, update model engine 234 may use received sensor information and / or information from calculation engine 224 to update the predictive computer model. In certain aspects of the technology, server 104 may send information from update model engine 234 to client application 202. In certain aspects of the technology, update model engine 234 may use a DNN.

[0078] The illustrated client application 202 includes display engine 212, control engine 222, and alert engine 232. As illustrated, client application 202 is in communication with server 204 via communication channel 242 and in communication with detector 206 via communication channel 246. It will be appreciated that other architectures may be employed without deviating from the scope of the innovative technologies described herein.

[0079] Display engine 212 displays data and / or information via a GUI. Display engine 212 may, for example, display sensor information in real time, display operational parameter settings, display predictive computer models, display thresholds for safety, display alerts, and / or display calculations / predictions for a period of time for a remediation event to occur. It will be appreciated that display engine 212 may display received information from detector 206, server 204, control engine 222, and / or alert engine 232. In certain examples, display engine 212 may display historical sensor information (such as sensor information stored by database 114 as shown in FIG. 1A and FIG. IB) and / or historical remediation event data. Inspecific examples, display engine 212 may display an alert indicating sensor information exceeds a threshold. In additional examples, display engine 212 may display a notification indicating a remediation event is occurring. In certain aspects of the technology, display engine 212 may display a notification that a remediation event is complete.

[0080] Control engine 222 may update operational parameters of detector 206 and / or an HVAC. In examples, control engine 222 may adjust HVAC operational parameters including temperature, fan speed, and pressure settings. In specific examples, control engine 222 may adjust air flow rates to detector 206. In examples, operational parameters are adjusted manually using control engine 222. In certain examples, control engine 222 may adjust operational parameters automatically. In certain aspects of the technology, control engine 222 may use a DNN.

[0081] Alert engine 232 may generate alerts and notifications based on received information. Alert engine 232 may receive information / sensor information from server 204 and / or receive sensor information from detector 206. In examples, alert engine 232 may send information to display engine 212 such that display engine 212 may display an alert and / or notification. In certain examples, alert engine 232 may generate an alert based on, at least in part, received information from server 204. For example, alert engine 232 may receive information from server 204 indicating sensor information exceeds a threshold. Alert engine 232 may generate an alert and / or notifications indicating an environment is not considered safe. Alerts and notifications may be in response to a number of events, including, but not limited to sensor information in excess of an upper limit threshold, below an upper limit threshold, in excess of a lower limit threshold, and below a lower limit threshold. In aspects of the technology, an alert and / or notification may be generated by the presence of sensor information or the absence of sensor information. Alerts and / or notifications may be generated when sensor information indicates a remediation event has begun, a remediation event is occurring, or a remediation event is completed. Alerts and / or notifications may be one or more of audible alarms, flashing lights, displays on a GUI, e-mail alerts / notifications and / or text message alerts / notifications. Alert engine 232 may generate alerts and / or notifications automatically. In certain aspects of the technology, alert engine 232 uses a DNN.

[0082] In specific examples, optical sensor 216 may be a nephelometer suited to capture information regarding particulate matter and bioaerosols. Additional sensor 226 may becomprised of multiple sensors suited to capture temperature, relative humidity, and ozone information in an environment. Detector 206 may send sensor information to client application 202 and server 204. Client application 202 may receive the sensor information from detector 206, which may be displayed by display engine 212 via a GUI. Server 204 may receive sensor information from detector 206, where sensor information may be processed. In certain aspects, sensor information sent from detector 206 to client application 202 and server 204 may include total particulate matter levels, bioaerosol detection, temperature data, relative humidity data, and ozone levels in an environment. Bioaerosol detection information may include information regarding fluorescence-induced emitted wavelengths. Calculation engine 224 may determine, based on bioaerosol detection information, a level of mold spores in the environment. Calculation engine 224 may use temperature and relative humidity information to adjust the calculated level of mold spores to account for temperature and humidity affects in detection. Event determination engine 214 may determine the level of mold spores in the environment are in excess of a threshold. Server 204 may send information that the level of mold spores in the environment are in excess of the threshold to client application 202. Alert engine 232 may generate an alert that the environment is not considered safe and generate a notification to remediate the environment. Display engine 212 may display the alert that the environment is not considered safe and display the notification to remediate the environment. Update model engine, using, at least in part, information from calculation engine 224 and scientific databases, may update (or generate) a predictive model showing a period of time for a remediation event to occur. Detector 206 may capture additional sensor information including total particulate matter levels, bioaerosol detection, temperature data, relative humidity data, and ozone levels. Server 204 may receive the additional sensor information, and calculation engine 224 may determine ozone is present in the environment. Event determination engine 214 may determine a remediation event is occurring. Client application 202 may receive information from server 204 indicating a remediation event is occurring. Alert engine 232 may generate a notification that a remediation event is occurring in the environment. Display engine 212 may display the notification that a remediation event is occurring in the environment. After the period of time for a remediation event to occur, detector 206 may capture new sensor information including total particulate matter levels, bioaerosol detection, temperature data, relative humidity data, and ozone levels. Server 204 may receive the new sensor information, and calculation engine 224 may determine mold spores are present in the environment. Update model engine 234 may update a predictive model showing a new period of time for a remediation event tooccur. In additional examples, server 204 may receive the new sensor information and calculation engine 224 may determine mold spores are absent from the environment. Client application 202 may receive information from server 204 indicating mold spores are absent from the environment. Alert engine 232 may generate an alert indicating the remediation event is complete. Display engine 212 may display the alert that the remediation event is complete.

[0083] FIG. 3A is an example method 300 of monitoring air quality. Method 300 begins with operation 302. In operation 302, sensor information is received. Sensor information may be captured from one or more sensors. In examples, sensor data is captured from one or more optical sensors, such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection and ranging (LiDAR). In specific examples, sensor data is captured from one or more of nephelometers, laser scattering sensors, and light-induced fluorescence sensors. In aspects of the technology, sensor information is received from one or more sensors, including sensors such as electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, and micro- electro-mechanical sensors. In non-limiting examples, sensor information may include levels and / or concentrations of gases, including ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. Sensor information, in examples, may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and barometric pressure. In specific examples, sensor information may include air quality data regarding air quality concerns such as dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. In specific examples, air quality data mayinclude information regarding bioaerosols such as pollen, mold spores, bacterial spores, viruses, fungal spores, endotoxins, and mycotoxins.

[0084] In determine event operation 304, a determination is made based on, at least in part, received sensor information. In examples, sensor information is compared to a threshold. The threshold may be established using one or more of scientific databases, safety data sheets, environmental regulations, and standard operating procedures. The threshold may set an upper limit for sensor information and / or a lower limit for sensor information. The threshold may be set such that the presence or absence of sensor information exceeds the threshold. In certain examples, sensor information may be determined to be in excess of the threshold. In specific examples, sensor information may be levels of bioaerosols such as pollen, mold spores, bacterial spores, viruses, fungal spores, endotoxins, and mycotoxins. In certain aspects, levels of bioaerosols may be in excess of a determined threshold. In specific examples, it may be determined that a remediation event is occurring. In certain aspects, it may be determined that a remediation event is occurring when sensor information includes information regarding the presence of a remediator, such as ozone. In certain examples, determine event operation 304 is performed using a DNN.

[0085] In operation 306, an action is taken based on, at least in part, a determination that an event has occurred. In examples, the action may be generating an alert. In specific examples, an alert is generated to inform that sensor information exceeds a threshold in an environment. In aspects of the technology, an alert and / or notification may be one or more of audible alarms, flashing lights, displays on a GUI, e-mail alerts / notifications and / or text message alerts / notifications. In certain examples, the action may be generating a notification that a remediation event is occurring. In aspects of the technology, taking action may be recommending remediation actions and / or estimating remediation times (such as a period of time for a remediation event to occur). In examples, take action operation 306 may include one or more of comparing data (such as sensor information) with third-party data (such as data from scientific databases, safety data sheets, environmental regulations, or standard operating procedures), comparing data with predicted models, and / or updating a predictive computer model. In certain examples, take action operation 306 may be performed using a DNN.

[0086] FIG. 3B is an example method 320 of normalizing air quality data. Method 320 begins with operation 322 receive sensor information. Sensor information may be capturedfrom one or more sensors. It will be appreciated that the one or more sensors may be participants in a peer-to-peer network. In examples, sensor data is captured from one or more optical sensors, such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection and ranging (LiDAR).

[0087] In specific examples, sensor data is captured from one or more of nephelometers, laser scattering sensors, and light-induced fluorescence sensors. In aspects of the technology, sensor information is received from one or more sensors, including sensors such as electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, and micro- electro-mechanical sensors. In non-limiting examples, sensor information may include levels and / or concentrations of gases, including ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. Sensor information, in examples, may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and barometric pressure. In specific examples, sensor information may include air quality data regarding air quality concerns such as dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. In specific examples, air quality data may include information regarding bioaerosols such as pollen, mold spores, bacterial spores, viruses, fungal spores, endotoxins, and mycotoxins.

[0088] It will be appreciated that sensor information may include one type of sensor information, such as bioaerosol levels, or multiple types of sensor information, such as temperature, pressure, relative humidity, ozone levels, and bioaerosol levels.

[0089] Method 320 then proceeds to operation 324, assign time stamp. Received sensor information is associated with a date and time that the information was captured. In a non-limiting example, bioaerosol levels may be captured as sensor information and assigned a date and time. It will be appreciated that date format may be month / day / year format, include day of the week (for example Monday) or any other conventional date format. Likewise, it will be appreciated that time format may be hour: minute: second or any other conventional format for time capture.

[0090] Method 320 then proceeds to operation 326, determine time interval. In certain examples, sensor information may be captured for the first time. For example, a new sensor for the detection of bioaerosols may be added to a peer-to-peer network. Sensor information may be received once, and thus, a time interval may not be determined until additional sensor information is received. Operation 326 may proceed to operation 322, receive sensor information, and operation 324, assign time stamp to determine a time interval for received sensor information.

[0091] Method 320 then proceeds to operation 328, normalize sensor information. It will be appreciated that various types of sensor information may be captured and / or received at different time intervals. For example, sensor information related to temperature may be received in 1-hour time intervals, sensor information related to bioaerosol concentrations may be received in 1 -minute time intervals, and sensor information related to ozone gas levels may be received in 20-minute time intervals. In normalize sensor information operation 328, sensor information may be normalized to a common date and time scale. Sensor information may be normalized using a variety of methods including, but not limited to, interpolation, extrapolation, and / or aggregation. In one example, relatively larger time intervals, such as information determined to be received in 1-hour time intervals, may be divided evenly across 20-minute intervals to align with sensor information determined to be received in 20-minute time intervals. In alternative examples, sensor information determined to be received in 20- minute time intervals, may be extrapolated to 1-hour time intervals. In certain examples, normalization may be informed by one or more of scientific databases, sensor capabilities, and / or historical sensor information. In specific examples, normalization of sensor information may be performed by a peer-to-peer network as described in FIG. IB.

[0092] Method 320 then proceeds to operation 330, additional sensor data. In examples, normalized sensor information may be incomplete. For example, ozone levels, temperature, pressure, and humidity information may be normalized, while bioaerosol sensor information is not normalized and / or has not been received. Method 320 may then proceed to receivesensor information operation 322. Sensor information regarding bioaerosol levels may be received, and, in operation 324, receive a time stamp. In operation 326, a time interval may be determined for the received sensor information regarding bioaerosol levels. The received sensor information may then be normalized to the normalized sensor information regardng ozone levels, temperature, pressure, and humidity information.

[0093] Method 320 then proceeds to operation 332, send normalized information. The normalized information may be sent to one or more of a predictive computer model, a client application, a server for further processing, a database for storage, and / or to be viewed using a GUI. A predictive computer model may use normalized sensor information to create or update an existing predictive computer model. It will be appreciated that normalized sensor information may be communicated via a cellular networks, LANs, WANs, IP networks, VPNs, Ad Hoc networks, such as bluetooth, mesh networks, satellite networks, blockchain networks, or any other conventional and / or later developed wired and wireless network.

[0094] In a specific example, a first type of sensor information is received in operation 322 from a first sensor. The first type of sensor information may be information regarding ozone levels. The received sensor information is assigned a time stamp in operation 322 and a time interval of receiving sensor information every second is determined in operation 324. Method 320 repeats operation 322 and 324 for 60 iterations, receiving sensor information regarding ozone levels from the first sensor. A second type of sensor information is received, from a second sensor, regarding bioaerosol levels. The second type of sensor information is assigned a time stamp and a time interval of receiving sensor information every minute is determined. Method 320 may iterate, receiving sensor information regarding ozone levels from the first sensor every second and sensor information regarding bioaerosol levels from the second sensor every minute. A third type of sensor information may be received from a third sensor regarding temperature. The third type of sensor information may be assigned a time stamp and a time interval of receiving sensor information every hour. In operation 328, the received sensor information regarding ozone levels may be normalized to a 1-hour time period, reducing the quantity of sensor information to be transmitted and reducing the required bandwidth capacity of a network. The received sensor information regarding bioaerosol levels may be normalized to a 1-hour period, reducing the quantity of sensor information to be transmitted and reducing required bandwidth capacity of the network. In this example, the received sensor information regarding temperature may be normalized tothe normalized data regarding ozone levels and bioaerosol levels. The normalization of sensor information may be performed on a peer-to-peer network, where the first sensor, the second sensor, and the third sensor may normalize the received sensor information. It will be appreciated that received sensor information regarding bioaerosol levels and temperature may be extrapolated and normalized to 1 second time intervals. Such processing of sensor information may be performed on a peer-to-peer network, the first sensor, the second sensor, and the third sensor may normalize the received sensor information. In send normalized information operation 332, normalized sensor information may be sent to a server and / or predictive computer model for further processing. Normalization performed on a peer-to-peer network by hardware / firmware of the first sensor, the second sensor, and the third sensor may save processing time and processing power requirements of the server and / or predictive computer. Additionally, sending normalized sensor information that was, at least in part, processed by hardware / firmware of the first sensor, the second sensor, and the third sensor reduces the amount of data transmitted and reduce the required bandwidth capacity of the network. It will be appreciated that sensor information may be received, normalized, and further processed by any participant on a peer-to-peer network.

[0095] FIG. 4 is an example method 400 of determining an event has occurred based on a threshold. Method 400 begins with operation 402. In operation 402, sensor information is received from one or more sensors. In examples, the one or more sensors includes at least one optical sensor, including, but not limited to, photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and LiDAR. In certain examples, the one or more sensors includes one or more of electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, humidity sensors, temperature sensors, electrostatic sensors, and micro-electro-mechanical sensors. In specific examples, the at least one optical sensor may include one or more of laser scattering sensors, light scattering sensors, laser particle counters, light-induced fluorescence sensors, and nephelometers.

[0096] In examples, sensor information may include information regarding one or more of environmental conditions, pollutants, gases, methanol, particulate matter, bioaerosols, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, and electromagnetic interference. In additional examples, sensorinformation may include information regarding environmental conditions such as relative humidity, moisture, temperature, wind speed, thermal images and barometric pressure. In certain aspects of the technology, sensor information may include information regarding pollutants, such as radioactive particles, explosive residues, perfluorinated compounds, combustible gases, heavy metals, pesticides, phthalates, dioxins, and industrial solvents. In specific examples, sensor information may include information regarding gases, particulate matter, and bioaerosols. In certain examples, information regarding gases may include one or more ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, chlorine, and radon. In specific examples, information regarding particulate matter may include one or more dust, silica, soot, smoke, oil aerosols, salt aerosols, asbestos, fiberglass particles, dust mites, pet dander, detritus, and bioaerosols. In additional specific examples, information regarding bioaerosols may include one or more of pollen, mold spores, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, and mycotoxins. It will be appreciated that the received sensor information may be normalized.

[0097] Method 400 then proceeds to operation 404. In operation 404, sensor information is analyzed. In examples, sensor information may be analyzed such that calculations are performed to quantify levels and / or concentrations of sensor information. In certain examples, sensor information may be analyzed for the presence or absence of information regarding environmental conditions, pollutants, gases, particulate matter, bioaerosols, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, and electromagnetic interference. In specific examples, sensor information may be analyzed for information regarding temperature, relative humidity, particulate matter, bioaerosols, and / or gases. In certain aspects of the technology, total particulate matter levels and total bioaerosol levels may be analyzed. In certain aspects of the technology, analyze sensor information operation 404 may be performed using a DNN.

[0098] Method 400 then proceeds to optional operation 406. In optional operation 406, air quality data is analyzed. Air quality data may include information regarding particulate matter, bioaerosols, pollutants, and / or gases. In certain, non-limiting examples, air quality data may include information regarding bioaerosols and gases. In specific examples, information regarding bioaerosols may include fluorescence-induced emitted wavelength information. Analysis of sensor information may include analyzing wavelength information to determine the type of bioaerosol detected. In certain examples, analysis of bioaerosolinformation may determine the presence (or absence) of one or more of pollen, mold spores, bacteria spores, viruses, fungal spores, endotoxins, and / or mycotoxins. In certain aspects of the technology, analyze air quality data operation 406 may be performed using a DNN.

[0099] Method 400 then proceeds to operation 408, compare to threshold. In operation 408, sensor information and, optionally, air quality data, are compared to a threshold. In specific examples, the threshold may be a rate of increase of sensor information. In additional aspects, the threshold may be a rate of decrease of sensor information. For example, the threshold may be a rate of increase of particulate matter in an environment. Such rates may be set based on historical sensor information indicating the environment became unsafe after a similar rate of increase. In certain aspects of the technology, the threshold may set to a rate of increase based on information from scientific databases. It will be appreciated that thresholds set to a rate of increase or rate of decrease of sensor information may be set for any received sensor information. In alternative examples, the threshold may be the presence or absence of sensor information and / or air quality data. In certain examples, the threshold may be an upper limit of sensor information levels and / or concentrations, or, in certain aspects, a lower limit of sensor information levels and / or concentrations. In specific examples, air quality data, such as bioaerosol levels, may exceed an upper limit threshold. In certain aspects, bioaerosol levels may include levels of mold spores, bacteria spores, fungal spores, and / or viruses. In certain examples, sensor information may be below an upper limit threshold, such as, but not limited to, mold spore levels below an upper limit threshold. In additional examples, sensor information may be below a lower limit threshold, including, but not limited to, oxygen levels below a lower limit threshold. In specific examples, analysis of sensor information and / or air quality data may include the presence of ozone gas, mold spore levels in excess of a threshold, and temperature data. In certain aspects, compare to threshold operation 408 may be performed using a DNN.

[0100] After compare to threshold operation 408, method 400 proceeds to determine event operation 410. In determine event operation 410, a determination is made, at least in part, based upon comparing analyzed sensor information and, optionally, analyzed air quality data, to a threshold. In examples, it may be determined that an environment is not considered safe. In additional examples, it may be determined that a remediation event is occurring. In certain examples, it may be determined that an environment is considered safe. In specific examples, air quality data including information regarding mold spore levels in anenvironment may be analyzed and compared to a threshold for an upper limit of safety for mold spore levels. It may be determined that the environment is not considered safe. In additional examples, the presence or absence of sensor information, such as the presence of ozone, may lead to a determination that a remediation event is occurring. In certain aspects, determine event operation 410 may be performed using a DNN.

[0101] FIG. 5 is an example method 500 of taking an action. Method 500 begins with operation 502. In operation 502 sensor information is received. Sensor information may be captured from one or more sensors. In examples, sensor data is captured from one or more optical sensors, such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection and ranging (LiDAR). In specific examples, sensor data is captured from one or more of nephelometers, laser scattering sensors, and light-induced fluorescence sensors. In aspects of the technology, sensor information is received from one or more sensors, including sensors such as electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, and micro- electro-mechanical sensors. In non-limiting examples, sensor information may include levels and / or concentrations of gases, including ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. Sensor information, in examples, may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and barometric pressure. In specific examples, sensor information may include air quality data regarding air quality concerns such as dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. In specific examples, air quality data may include information regarding bioaerosols such as pollen, mold spores, bacterial spores,viruses, fungal spores, endotoxins, and mycotoxins. It will be appreciated that the received sensor information may be normalized sensor information.

[0102] Method 500 then proceeds to operation 504. In determine event operation 504, a determination is made based on, at least in part, received sensor information. In examples, sensor information is compared to a threshold. The threshold may be established using one or more of scientific databases, safety data sheets, environmental regulations, and standard operating procedures. The threshold may set an upper limit for sensor information and / or a lower limit for sensor information. The threshold may be set such that the presence or absence of sensor information exceeds the threshold. In certain examples, sensor information may be determined to be in excess of the threshold. In specific examples, sensor information may be levels of bioaerosols such as pollen, mold spores, bacterial spores, viruses, fungal spores, endotoxins, and mycotoxins. In certain aspects, levels of bioaerosols may be in excess of a determined threshold. In specific examples, it may be determined that a remediation event is occurring. In certain aspects, it may be determined that a remediation event is occurring when sensor information includes information regarding the presence of a remediator, such as ultra-violet radiation. In additional examples, it may be determined that a remediation event is complete. In certain aspects, a remediation event may be determined complete when sensor information is absent, such as the absence of mold spores. In specific examples, a determination may be made that an environment is not considered safe, based on sensor information compared to a threshold. In additional examples, a determination may be made that an environment is considered safe, based on sensor information compared to a threshold. In certain examples, determine event operation 504 is performed using a DNN.

[0103] Method 500 then proceeds to determine action operation 506. In operation 506, actions are determined based on, at least in part, information from determine event operation 504. In examples, it may be determined that sensor information is in excess of a threshold. In additional examples, it may be determined that sensor information is present or absent. In certain aspects, the determined action may be one or more of changing operational parameters (such as temperature, fan speed, and / or pressure settings), generating an alert and / or notification, recommending remediation actions, estimating remediation times, storing data, comparing data with a third-party database, comparing data with predicted computer models, and updating a predictive computer model. In specific examples, it may be determined (in determine event operation 504), that particulate matter levels are in excess ofa threshold. The determined action may be one or more of changing operational parameters, generating an alert and / or notification, recommending remediation actions, and comparing data with a third-party database. In another example, it may be determined that a remediation event is occurring. The determined action may be one or more of changing operational parameters, generating a notification, estimating a period of time for the remediation event to occur, comparing data with predicted computer models and / or updating a predictive computer model. In certain examples, determine action operation 506 may be performed using a DNN.

[0104] In operation 508 action is taken based on, at least in part, the determined action. In examples, the action may be changing operation parameters (such as temperature, fan speed, and pressure settings), generating an alert and / or notification, recommending remediation actions, estimating remediation times, storing data, comparing data with a third- party database, comparing data with predicted computer models, and updating a predictive computer model. In certain examples, a determination may be made to generate an alert and / or notification. In examples, an alert and / or notification may be one or more of audible alarms, flashing lights, displays on a GUI, e-mail alerts / notifications and / or text message alerts / notifications. In specific examples, it may be determined that particulate matter levels (such as silica) are in excess of a threshold and an environment is not considered safe. A determination may be made to generate an alert and recommend remediation actions. Take action operation 508 may be generating a text message alert and audible alarm, and recommending remediation actions, including changes to an operational parameter, such as HVAC fan speed. In another example, it may be determined that a remediation event is occurring and determined action may be generating a notification and estimating a period of time for a remediation event to occur. Take action operation 508 may be generating an e-mail notification that a remediation event is occurring and estimating a period of time for the remediation event to occur.

[0105] FIG. 6 is an example method 600 of updating a predictive computer model. Method 600 begins with operation 602. In operation 602, sensor information is received. Sensor information may be captured from one or more sensors. In examples, sensor data is captured from one or more optical sensors, such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and lightdetection and ranging (LiDAR). In specific examples, sensor data is captured from one or more of nephelometers, laser scattering sensors, and light-induced fluorescence sensors. In aspects of the technology, sensor information is received from one or more sensors, including sensors such as electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, and micro-electro-mechanical sensors. In non-limiting examples, sensor information may include levels and / or concentrations of gases, including ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. Sensor information, in examples, may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and barometric pressure. In specific examples, sensor information may include air quality data regarding air quality concerns such as dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. In specific examples, air quality data may include information regarding bioaerosols such as pollen, mold spores, bacterial spores, viruses, fungal spores, endotoxins, and mycotoxins. In specific examples, sensor information may include information regarding mold spore levels in an environment. It will be appreciated that the received sensor information may be normalized sensor information.

[0106] In determine event operation 604, a determination is made based on, at least in part, received sensor information. In examples, sensor information is compared to a threshold. The threshold may be established using one or more of scientific databases, safety data sheets, environmental regulations, and standard operating procedures. The threshold may set an upper limit for sensor information and / or a lower limit for sensor information. The threshold may be set such that the presence or absence of sensor information exceeds the threshold. It will be appreciated that the threshold may set a rate of increase or decrease of sensor information. In specific examples, sensor information may include levels of bioaerosols such as pollen, mold spores, bacterial spores, viruses, fungal spores, endotoxins,and mycotoxins. In certain aspects, levels of bioaerosols may be in excess of a threshold. In specific examples, sensor information may include the presence of ozone or other gases. A determination may be made, in certain, non-limiting examples, that a remediation event is occurring based on the presence of ozone and / or other gases, such as nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and chlorine. In additional examples, it may be determined that a remediation event is complete, due to, as a non-limiting example, bioaerosol levels below a threshold. In certain examples, determine event operation 604 is performed using a DNN.

[0107] Method 600 then proceeds to operation 606, compare data. In operation 606, sensor information is compared to additional data sources, which may include scientific databases, third-party databases, stored historical data, and / or a predictive computer model. In examples, sensor information is compared to additional data sources to inform calculations for a predictive computer model. In specific examples, a determination is made that a remediation event is occurring. Sensor information regarding bioaerosol levels and ozone levels are compared to additional data sources to inform a period of time for the remediation event to occur. In additional examples, sensor information may be compared to additional data sources, such as scientific databases, to determine a threshold. In certain examples, sensor information may be compared to additional data sources to determine if an environment may be considered safe. In certain aspects, compare data operation 606 may be performed using a DNN.

[0108] In optional operation 608, an outcome may be predicted based on, at least in part, compare data operation 606. In specific examples, a period of time for a remediation event to occur may be estimated. In certain aspects of the technology, a period of time until an environment is no longer safe may be estimated. For example, sensor information, such as oxygen levels, may be declining in an environment. A period of time until oxygen levels will be below a threshold may be estimated. In examples, predict outcome operation 608 may be performed using a DNN.

[0109] Method 600 then proceeds to operation 610. In operation 610, a predictive computer model is updated. In specific examples, an estimated period of time for a remediation to occur may be compared to the actual time period the remediation occurred. The estimated period of time may be derived from a predictive computer model. In certain examples, the actual time period may be greater than the estimated period of time. In otherexamples, the actual time period may be less than the estimated period of time. The predictive computer model may be updated based on the actual time period. Update model operation may be performed using a DNN.

[0110] FIG. 7 is an example method 700 of monitoring remediation. Method 700 begins with operation 702. In operation 702, sensor information is received. Sensor information may be captured from one or more sensors. In examples, sensor data is captured from one or more optical sensors, such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection and ranging (LiDAR). In specific examples, sensor data is captured from one or more of nephelometers, laser scattering sensors, and light-induced fluorescence sensors. In aspects of the technology, sensor information is received from one or more sensors, including sensors such as electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, and micro- electro-mechanical sensors. In non-limiting examples, sensor information may include levels and / or concentrations of gases, including ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. Sensor information, in examples, may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and barometric pressure. In specific examples, sensor information may include air quality data regarding dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. In specific examples, sensor information may include information regarding bioaerosols such as pollen, mold spores, bacterial spores, viruses, and fungal spores. In certain aspects, sensor information may include information regarding bioaerosols and gases, including, but not limited to, ozone and oxygen. In non-limiting aspects of the technology, the presence of gases, such as ozone, nitrous dioxide, ammonia, hydrogenperoxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine may indicate a remediation event is occurring. It will be appreciated that the received sensor information may be normalized sensor information.

[0111] In operation 704, a period of time for a remediation event to occur is estimated, based on, at least in part, received sensor information. In examples, the period of time for remediation to occur is determined based on a predictive computer model. In certain aspects of the technology, data from scientific databases, safety data sheets, environmental regulations and / or standard operating procedures may be used, at least in part, to predict the period of time. In additional examples, historical data from previous remediation events may be employed to estimate the period of time. In specific examples, data from scientific databases and historical data may be used to inform a predictive computer model. In certain examples, estimate time operation 704 may be performed automatically or manually. Estimate time operation 704 may be performed using a DNN.

[0112] In operation 706 additional sensor information is received after a period of time for remediation to occur, as estimated in estimate time operation 704. Additional sensor information may be captured from one or more sensors. In examples, sensor data is captured from one or more optical sensors, such as photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection and ranging (LiDAR). In specific examples, sensor data is captured from one or more of nephelometers, laser scattering sensors, and light-induced fluorescence sensors. In aspects of the technology, additional sensor information is received from one or more sensors, including sensors such as electrochemical sensors, metal-oxide semiconductor sensors, ionic sensors, and micro- electro-mechanical sensors. In non-limiting examples, sensor information may include levels and / or concentrations of gases, including ozone, nitrous dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. Additional sensor information, in examples, may include information regarding particulate matter, smoke, aerosols, pollen, mold spores, bioaerosols, radon, radioactive particles, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, electromagnetic interference, relative humidity, moisture, temperature, wind speed, thermal images, and barometric pressure. In specific examples, additional sensorinformation may include air quality data regarding dust, silica, soot, oil aerosols, salt aerosols, pollen, mold spores, asbestos, fiberglass particles, bioaerosols, bacteria spores, viruses, fungal spores, endotoxins, mycotoxins, dust mites, pet dander, detritus, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, airborne pollutants, heavy metals, pesticides, phthalates, dioxins, industrial solvents, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, oxygen, ethylene oxide, and / or chlorine. In specific examples, additional sensor information may include information regarding bioaerosols such as pollen, mold spores, bacterial spores, viruses, and fungal spores. In certain aspects, additional sensor information may include information regarding bioaerosols.

[0113] In operation 708, the safety of an environment in which a remediation event is occurring is determined. For example, received additional sensor information may be used to determine safety. In examples, additional sensor information may be compared to a threshold. In certain examples, additional sensor information may be in excess of the threshold. In specific examples, bioaerosol levels may be above a threshold. The threshold may be determined using one or more of scientific databases, safety data sheets, environmental regulations (including, but not limited to, OSHA guidelines, EPA guidelines, and FDA guidelines), and / or standard operating procedures. In certain aspects, a determination that the environment is not considered safe may be made when bioaerosol levels are in excess of the threshold. In non-limiting examples, a determination that the environment is considered safe may be made when bioaerosol levels are below the threshold. In certain aspects the determination that the environment is considered safe may be made when bioaerosols are no longer present. Determine safety operation 708 may be performed using a DNN.

[0114] Method 700 then proceeds to optional operation 710. In operation 710, a predictive computer model may be updated. For example, a period of time for a remediation event to occur, as performed in estimate time operation 704, may have been estimated based on sensor information. After the period of time, additional sensor information may indicate the remediation event is not complete. The predictive computer model may be updated based on, at least in part, the additional sensor information. Update model operation 710 may be performed using a DNN.

[0115] In operation 712, action is taken based on, at least in part, additional sensor data. In examples, the action may be one or more of changing operation parameters (such astemperature, fan speed, and pressure settings), generating an alert and / or notification, recommending remediation actions, estimating remediation times, storing data, comparing data with a third-party database, and comparing data with a predictive computer model. In specific examples, a remediation event may have occurred in an environment for a period of time. After the period of time, the environment may not be considered safe. The action may be one or more of generating a notification indicating the environment is not considered safe, recommending continued remediation efforts, and estimating a new period of time for the remediation event to occur. In additional examples, a remediation event may have occurred in an environment for a period of time. After the period of time, the environment may be considered safe. A notification may be generated indicating the environment is considered safe.

[0116] FIG. SA is an example diagram of a distributed computing system in which aspects of the present invention may be practiced. According to examples, any computing devices, such as a modem 802A, a laptop computer 802B, a tablet 802C, a personal computer 802D, a smartphone 802E, and a server 802F, may contain engines, components, etc., for controlling the various equipment associated with air quality monitoring. Additionally, according to aspects discussed herein, any of the computing devices may contain the necessary hardware for implementing aspects of the disclosure. Any and / or all of these functions may be performed, by way of example, at network servers and / or when computing devices request or receive data from external data providers by way of a network 820.

[0117] FIG. 8B is one embodiment of the architecture system in which aspects of the present disclosure may be practiced. Content and / or data interacted with, requested, and / or edited in association with one or computing devices may be stored in different communication channels or other storage types. For example, data may be stored using a directory service, a web portal, a mailbox service, an instant messaging store, or a compiled networking service for image detection and classification. The distributed computing system 800 may be used for running the various engines to perform sensor information capture and determination. The computing devices 818A, 818B, and / or 818C may provide a request to a cloud / network 820, which is then processed by a network server 806 in communication with an external data provider 817. By way of example, a client computing device may be implemented as any of the systems described herein and embodied in the personal computing device 818A, the tablet computing device 818B, and / or the mobile computing device 818C(e.g., a smartphone). Any of these aspects of the systems described herein may obtain content from the external data provider 817.

[0118] In various examples, the types of networks used for communication between the computing devices that make up the present invention include but are not limited to, the Internet, an intranet, wide area networks (WAN), local area networks (LAN), virtual private networks (VPN), GPS devices, SONAR devices, cellular networks, and additional satellitebased data providers such as the Iridium satellite constellation which provides voice and data coverage to satellite phones, pagers, and integrated transceivers, etc. According to aspects of the present disclosure, the networks may include an enterprise network and a network through which a client computing device may access an enterprise network. According to additional aspects, a client network is a separate network accessing an enterprise network through externally available entry points, such as a gateway, a remote access protocol, or a public or private Internet address.

[0119] Additionally, the logical operations may be implemented as algorithms in software, firmware, analog / digital circuitry, and / or any combination thereof, without deviating from the scope of the present disclosure. The software, firmware, or similar sequence of computer instructions may be encoded and stored upon a computer-readable storage medium. The software, firmware, or similar sequence of computer instructions may also be encoded within a carrier-wave signal for transmission between computing devices.

[0120] FIG. 9 illustrates an exemplary architecture of a computing device 910 that can be used to implement aspects of the present disclosure. Operating environment 900 typically includes at least some form of computer-readable media. Computer-readable media can be any available media that can be accessed by a processor such as processing device 980 depicted in FIG. 9 and processor 1002 shown in FIG. 10 or other devices comprising the operating environment 900. By way of example, and not limitation, computer-readable media may comprise computer storage media and communication media.

[0121] Computer storage media includes volatile and nonvolatile, and removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program engines, or other data. Computer storage media includes RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magneticcassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium which can be used to store the desired information. Computer storage media does not include communication media.

[0122] Communication media embodies computer-readable instructions, data structures, program engines, or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above should also be included within the scope of computer- readable media.

[0123] The operating environment 900 may be a single computer operating in a networked environment using logical connections to one or more remote computers. The remote computer may be a personal computer, a GPS device, a monitoring device such as a static-monitoring device or a mobile monitoring device, a pod, a mobile deployment device, a server, a router, a network PC, a peer device, or other common network nodes, and typically includes many or all of the elements described above as well as others not so mentioned. The logical connections may include any method supported by available communications media. Such networking environments are commonplace in enterprise- wide computer networks, intranets, and the Internet.

[0124] FIG. 10 is a block diagram illustrating additional physical components (e.g. hardware) of a computing device 1000 with which certain aspects of the disclosure may be practiced. Computing device 1000 may perform these functions alone or in combination with a distributed computing network such as those described with regard to FIGS. 8A and 8B which may be in operative contact with personal computing device 818A, tablet computing device 818B, and / or mobile computing device 818C which may communicate and process one or more of the program engines described herein.

[0125] In a basic configuration, the computing device 1000 may include at least one processor 1002 and a system memory 1010. Depending on the configuration and type of computing device, the system memory 1010 may comprise, but is not limited to, volatilestorage (e.g., random access memory), non-volatile storage (e.g., read-only memory), flash memory, or any combination of such memories. The system memory 1010 may include an operating system 1012 and one or more program engines, such as engines 1014, 1016, 1018, 1020, and 1022. The operating system 1012, for example, may be suitable for controlling the operation of the computing device 1000. Furthermore, aspects of the disclosure may be practiced in conjunction with a graphics library, other operating systems, or any other application program and are not limited to any particular application or system.

[0126] The computing device 1000 may have additional features or functionality. For example, the computing device 1000 may also include an additional data storage device (removable and / or non-removable) such as, for example, magnetic disks, optical disks, or tape. Such additional storage is illustrated in FIG. 10 by storage 1004. It will be well understood by those of skill in the art that storage may also occur via the distributed computing networks described in FIG. 8A and FIG. 8B. For example, the computing device 1000 may communicate via network 820 in FIG. 8A and data may be stored within network servers 806 and transmitted back to computing device 1000 via network 820 if it is determined that such stored data is necessary to execute one or more functions described herein. Additionally, computing device 1000 may communicate via network 820 in FIG. 8B and data may be stored within network server 806 and transmitted back to computing device 1000 via a network, such as network 820, if it is determined that such stored data is necessary to execute one or more functions described herein.

[0127] As stated above, a number of program engines and data files may be stored in the system memory 1010. While executing the at least one processor 1002, the program engines 1014, 1016, 1018, 1020, and 1022 (e.g., the engines described with reference to FIG. 2) may perform processes including, but not limited to, the aspects described herein.

[0128] While various embodiments and examples have been described for purposes of this disclosure, various changes and modifications may be made which are well within the scope of the disclosed methods. Numerous other changes may be made which will readily suggest themselves to those skilled in the art and which are encompassed in the spirit of the disclosure.

[0129] It will be clear that the systems and methods described herein are well adapted to attain the ends and advantages mentioned as well as those inherent therein. Those skilled inthe art will recognize that the methods and systems within this specification may be implemented in many manners and as such is not to be limited by the foregoing exemplified embodiments and examples. In other words, functional elements being performed by a single or multiple components and individual functions can be distributed among different components. In this regard, any number of the features of the different embodiments described herein may be combined into one single embodiment and alternate embodiments having fewer than or more than all of the features herein described as possible.

Claims

CLAIMSWhat is claimed:

1. A computer-implemented method, the method comprising: receiving sensor information from one or more sensors, wherein at least one of the one or more sensors is an optical sensor, wherein the sensor information includes air quality data regarding particulate matter in an environment; determining, based on the sensor information, that an event has occurred; and taking an action, based on the determining that an event has occurred operation.

2. The computer-implemented method of claim 1, wherein sensor information includes at least one of the group comprising: dust, silica, soot, smoke, oil aerosols, salt aerosols, asbestos, fiberglass particles, dust mites, pet dander, detritus, bioaerosols, pollen, mold spores, bacteria spores, fungal spores, viruses, endotoxins, mycotoxins, airborne pollutants, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, heavy metals, pesticides, phthalates, dioxins, industrial solvents, gases, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, ethylene oxide, chlorine, relative humidity, moisture, temperature, wind speed, thermal images, barometric pressure, ultraviolet radiation, light intensity, sound waves, noise, decibel readings, chemical markers, microwave radiation, and electromagnetic interference.

3. The computer-implemented method of claim 1, wherein the one or more sensors comprises: optical sensors, electrochemical sensors, metal-oxide semiconductor sensors, photoacoustic sensors, ionic sensors, humidity sensors, temperature sensors, electrostatic sensors, non-dispersive infrared sensors, micro-electro-mechanical sensors, laser scattering sensors, light scattering sensors, light-induced fluorescence sensors, nephelometers, or photoionization detectors.

4. The computer-implemented method of claim 1, wherein the optical sensor comprises:photoacoustic sensors, non-dispersive infrared sensors, laser scattering sensors, light scattering sensors, laser particle counters, optical particle sizers, light-induced fluorescence sensors, photoionization detectors, nephelometers, aerosol optical depth sensors, ultraviolet absorption sensors, and light detection or ranging.

5. The computer-implemented method of claim 1, wherein air quality data comprises one or more of: dust, silica, soot, smoke, oil aerosols, salt aerosols, asbestos, fiberglass particles, dust mites, pet dander, detritus, bioaerosols, pollen, mold spores, bacteria spores, fungal spores, viruses, endotoxins, mycotoxins, airborne pollutants, radioactive particles, explosive residues, perfluorinated compounds, combustible gases, methanol, heavy metals, pesticides, phthalates, dioxins, industrial solvents, gases, radon, ozone, nitrogen dioxide, ammonia, hydrogen peroxide, sulfur dioxide, methane, carbon monoxide, ethylene oxide, and chlorine.

6. The computer-implemented method of claim 1, wherein determining that an event has occurred includes: comparing the sensor information to a threshold; and determining that the sensor information exceeds the threshold.

7. The computer-implemented method of claim 6, wherein the threshold is established using one or more of: scientific databases, safety data sheets, environmental regulations, and standard operating procedures.

8. The computer-implemented method of claim 6, wherein the threshold comprises: an upper limit for the sensor information, a lower limit for the sensor information, absence of the sensor information, presence of the sensor information, a rate of increase for sensor information, or a rate of decrease for sensor information.

9. The computer-implemented method of claim 1, wherein taking action comprises:changing temperature, changing fan speed, changing pressure settings, generating an alert, recommending remediation actions, estimating remediation times, storing data, comparing data with a third-party database, comparing data with predicted computer models, or updating a predictive computer model.

10. The computer-implemented method of claim 1, further comprising: receiving new sensor information, wherein the sensor information indicates that a remediation action has occurred; estimating a period of time for remediation to occur, based on, at least in part, the new sensor information; and after the period of time for remediation, receiving additional sensor data.

11. The computer-implemented method of claim 10, further comprising: determining that the environment is not considered safe, based on, at least in part, the additional sensor data; updating a computer model, based on the determination that the environment is not considered safe; and estimating a time to resolution for remediation.

12. The computer-implemented method of claim 10, further comprising: determining that the environment is considered safe, based on, at least in part, the additional sensor data; and sending a notification that the environment is considered safe.

13. The computer-implemented method of claim 1, wherein receiving sensor information further comprises receiving normalized sensor information.

14. The computer-implemented method of claim 1, wherein receiving sensor information further comprises:receiving sensor information from a first sensor, wherein the sensor information includes air quality data regarding particulate matter in an environment; assigning a first time stamp to the received sensor information; and determining, based on the first time stamp, a first time interval.

15. The computer-implemented method of claim 14 further comprising: receiving sensor information from a second sensor; assigning a second time stamp to the received sensor information; and determining, based on the second time stamp, a second time interval.

16. The computer-implemented method of claim 15 further comprising: receiving sensor information from at least one additional sensor; assigning at least one additional time stamp to the received sensor information; and determining, based on the at least one additional time stamp, at least one additional time interval.

17. The computer-implemented method of claims 15 or 16 further comprising: normalizing received sensor information; and sending normalized sensor information.

18. The computer-implemented method of claim 17, wherein normalizing received sensor information is performed on a peer-to-peer network.

19. The computer-implemented method of claim 17, wherein sending normalized sensor information further comprises sending the normalized sensor information to a predictive computer model.

Images