Bacterial classification

Abstract

A method, computer program product, and computer system for classifying bacteria. The method includes extracting morphological features corresponding to one or more bacteria and extracting motility features corresponding to the one or more bacteria. The method further includes merging the morphological features and the motility features into a merged vector feature and classifying the one or more bacteria based on the merged vector feature.

Description

Technical Field

[0001] The exemplary embodiments relate generally to the classification of bacteria, and more particularly to the classification of bacteria based on bacterial morphology and motility. Background Art

[0002] Industry (such as food and health industry) is concerned about the existence of bacteria, such as Escherichia coli, Salmonella, Listeria and Campylobacter in consumer foods. Because these bacteria are bred and grown when environment and nutritional conditions are correct, they can quickly grow into microcolonies and further grow into thin biofilms visible to the naked eye, which only cause potential threats to consumers in a few hours. For this reason, it is necessary for food suppliers (such as meat and agricultural product producers) to limit this type of bacteria in the product to very low amounts, such as 10 colony forming units (cfu) or 10 cfu / ml per milliliter. The current method for the type of bacteria in the food industry is to include an enrichment process for determining that the sample is tested in 8-24 hours, during which time the bacterial count increases to 104 cfu / ml. Once this bacterial concentration can be used for testing, polymerase chain reaction (PCR) or DNA sequencing methods are used to identify specific types of bacteria based on their DNA, but these methods lack efficiency and simplicity.

[0003] Therefore, there is a need in the art to solve the above problems. Summary of the Invention

[0004] From a first aspect, the present invention provides a computer-implemented method for classifying bacteria, the method comprising: extracting morphological features corresponding to one or more bacteria; extracting motility features corresponding to the one or more bacteria; merging the morphological features and the motility features into a merged vector feature; and classifying the one or more bacteria based on the merged vector feature.

[0005] Viewed from another aspect, the present invention provides a computer program product for classifying bacteria, the computer program product comprising a computer-readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit to perform a method for performing the steps of the present invention.

[0006] Viewed from another aspect, the invention provides a computer program stored on a computer readable medium and loadable into the internal memory of a digital computer, comprising software code portions for performing the steps of the invention when said program is run on a computer.

[0007] From another aspect, the present invention provides a computer program product for classifying bacteria, the computer program product comprising: one or more non-transitory computer-readable storage media and program instructions stored on the one or more non-transitory computer-readable storage media capable of executing a method, the method comprising: extracting morphological features corresponding to one or more bacteria; extracting motility features corresponding to the one or more bacteria; merging the morphological features and the motility features into a merged vector feature; and classifying the one or more bacteria based on the merged vector feature.

[0008] From another aspect, the present invention provides a computer system for classifying bacteria, the computer system comprising: one or more computer processors, one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media, the program instructions being configured to be executed by at least one of the one or more processors capable of executing a method comprising: extracting morphological features corresponding to one or more bacteria; extracting motility features corresponding to the one or more bacteria; merging the morphological features and the motility features into a merged vector feature; and classifying the one or more bacteria based on the merged vector feature.

[0009] Exemplary embodiments disclose methods, computer program products, and computer systems for identifying bacteria based on morphology and motility. The method may include extracting morphological features corresponding to one or more bacteria and extracting motility features corresponding to the one or more bacteria. The method may further include combining the morphological features and motility features into a combined vector feature and classifying the one or more bacteria based on the combined vector feature.

[0010] According to some embodiments, extracting morphological features may be based on comparing the morphology of the one or more bacteria and a model that relates bacterial morphology to bacterial type.

[0011] In an embodiment, the model relating bacterial morphology to bacterial type may include features selected from the group consisting of cell size, cell shape, cell length, cell diameter, cell volume, and Gram stain type.

[0012] According to some embodiments, extracting the motility feature may be based on comparing the motility of the one or more bacteria to a model that relates bacterial motility to bacterial type.

[0013] In an embodiment, the model relating bacterial motility to bacterial type may include features selected from the group consisting of run length, average run length, run speed, average run speed, tumble length, average tumble length, tumble speed, average tumble speed, and tumble interval.

[0014] According to some embodiments, the model relating bacterial motility to bacterial type may further include a characteristic replication rate.

[0015] In an embodiment, the morphological features, the kinematic features, and the combined vector features may be generated via an artificial intelligence algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The following detailed description, which is given by way of example and is not intended to limit the exemplary embodiments thereto, will be best understood in conjunction with the accompanying drawings, in which:

[0017] Figure 1 An exemplary schematic diagram of a bacteria classification system 100 is depicted in accordance with an exemplary embodiment.

[0018] Figure 2 Depicted is an exemplary flow chart 200 illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in documenting bacteria using a smart device microscope, according to an exemplary embodiment.

[0019] Figure 3 Depicted is an exemplary flow chart 300 illustrating the general operation of the bacteria classifier 134 of the bacteria classification system 100 in classifying bacteria using morphological and motility characteristics, according to an exemplary embodiment.

[0020] Figure 4 Depicted is an exemplary flow chart 400 illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in extracting bacterial morphological features, according to an exemplary embodiment.

[0021] Figure 5 Depicted is an exemplary flow chart 500 illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in extracting bacterial motility characteristics, according to an exemplary embodiment.

[0022] Figure 6 Depicted are the runs and tumbles of bacteria analyzed during the generation of motility signatures according to an exemplary embodiment.

[0023] Figure 7 An example of bacteria classifier 134 classifying E. coli bacteria is depicted, according to an exemplary embodiment.

[0024] Figure 8 An example of bacteria classifier 134 classifying Bacillus subtilis bacteria is depicted, according to an exemplary embodiment.

[0025] Figure 9 Depicting a depiction according to an exemplary embodiment Figure 1FIG. 1 is an exemplary block diagram of hardware components of the interlocutor identification system 100 .

[0026] Figure 10 A cloud computing environment is depicted according to an exemplary embodiment.

[0027] Figure 11 Abstract model layers according to an exemplary embodiment are depicted.

[0028] The accompanying drawings are not necessarily drawn to scale. The accompanying drawings are merely schematic representations and are not intended to depict specific parameters of the exemplary embodiments. The accompanying drawings are intended only to depict typical exemplary embodiments. In the accompanying drawings, the same reference numerals represent the same elements. DETAILED DESCRIPTION

[0029] Detailed embodiments of the claimed structures and methods are disclosed herein; however, it should be understood that the disclosed embodiments are merely illustrative of the claimed structures and methods, which may be implemented in different forms. The exemplary embodiments are merely illustrative, however, may be implemented in many different forms and should not be construed as limited to the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided to make this disclosure comprehensive and complete and to fully convey the scope of the exemplary embodiments to those skilled in the art. In the description, details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the presented embodiments.

[0030] References in the specification to "one embodiment," "an embodiment," "an exemplary embodiment," etc., indicate that the described embodiment may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered that it is within the knowledge of those skilled in the art to implement such feature, structure, or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0031] In order not to obscure the presentation of exemplary embodiments, in the following detailed description, some processing steps or operations known in the art may have been grouped together for presentation and illustration purposes, and in some cases may not have been described in detail. In other cases, some processing steps or operations known in the art may not be described at all. It should be understood that the following description focuses on the distinguishing features or elements according to various exemplary embodiments.

[0032] The industry of for example food and health industry is concerned about the existence of bacterium, and bacterium is for example the Escherichia coli, Salmonella, Listeria and Campylobacter in consumer food.Because these bacterium are bred and grown when environment and nutritional conditions are correct, they can grow into microcolony quickly and further grow into thin biofilm visible to the naked eye, and it causes potential threat to consumer in just a few hours.For this reason, need food supplier (for example meat and agricultural product producer) to limit this type of bacterium in product to very low amount, for example every milliliter 10 colony forming units (cfu) or 10 cfu / ml. The current method that food industry is used to determine the type of bacterium in food comprises enrichment process, wherein test sample in 8-24 hours, during this period, bacteria count increases to 104 cfu / ml.Once this bacterial concentration can be used for testing, just use polymerase chain reaction (PCR) or DNA sequencing method to identify specific type of bacterium based on its DNA, but these methods lack efficiency and simplicity.

[0033] The exemplary embodiments disclose an apparatus for imaging bacteria using a low-cost microscope and then classifying them based on multi-layer or deep learning neural networks and computer vision techniques. Key features of the exemplary embodiments include a customized low-cost microscope for imaging and classifying bacteria in liquids or on solid surfaces using artificial intelligence models. The exemplary embodiments improve upon existing solutions by not only utilizing artificial intelligence algorithms to identify individual bacteria, but also doing so using a low-cost microscope in a faster, more efficient, less expensive, and more accurate manner.

[0034] Figure 1 A bacteria classification system 100 is depicted according to an exemplary embodiment. According to an exemplary embodiment, the bacteria classification system 100 may include a smart device 120 and a bacteria classification server 130 that may be interconnected via a network 108. While the programming and data of the exemplary embodiment may be stored and accessed remotely across several servers via the network 108, the programming and data of the exemplary embodiment may alternatively or additionally be stored locally on as few as one physical computing device or other computing devices in addition to those depicted. For example, in an embodiment, the bacteria classifier 134 and necessary components may be stored entirely on the smart device 120 for local use without being connected to the network 108. The operation of the bacteria classification system 100 is described in more detail herein.

[0035] In an exemplary embodiment, network 108 can be a communication channel that can transmit data between the devices connected. Therefore, the components of bacteria classification system 100 can represent network components or network devices interconnected via network 108. In an exemplary embodiment, network 108 can be the Internet, representing a global collection of networks and gateways for supporting communication between the devices connected to the Internet. In addition, network 108 can utilize various types of connections, such as wired, wireless, optical fiber, etc., which can be implemented as an intranet, local area network (LAN), wide area network (WAN) or its combination. In another embodiment, network 108 can be a Bluetooth network, Wi-Fi network or its combination. In another embodiment, network 108 can be a telecommunications network for facilitating telephone calls between two or more parties, including landline networks, wireless networks, closed networks, satellite networks or its combination. Typically, network 108 can represent any combination of the connection and protocol for supporting communication between the devices connected.

[0036] In an exemplary embodiment, smart device 120 includes an optical adapter 122 and a bacteria identification client 124, and can be an enterprise server, laptop, notebook, tablet, netbook computer, personal computer (PC), desktop computer, server, personal digital assistant (PDA), rotary phone, push-button phone, smartphone, mobile phone, virtual appliance, thin client, IoT device, or any other electronic device or computing system capable of receiving and sending data to and from other computing devices. In an embodiment, smart device 120 can be a measurement instrument, such as a digital camera, imager, compound light microscope, stereo microscope, digital microscope, USB computer microscope, pocket microscope, electron microscope, scanning probe microscope, acoustic microscope, etc., preferably having an optical resolution of 1 micron or greater. Smart device 120 can have an adjustable optical resolution, but in an exemplary embodiment, for imaging bacteria with a length of 1-10 microns, smart device 120 can have an optical resolution of 1 micron. It should be understood that the optical resolution of smart device 120 can vary based on the application, and it will be further understood that achieving such optical resolution may require the use of enhancement devices, such as optical adapter 122, as described in more detail herein. Although the smart device 120 is shown as a single device, in other embodiments, the smart device 120 may be composed of a cluster or multiple computing devices that work together or independently in a modular manner. The smart device 120 is described in more detail with reference to Figure 9 Hardware implementation, reference Figure 10 Part of and / or reference to a cloud implementation Figure 11 Leverage functional abstraction layers for processing.

[0037] In an exemplary embodiment, the optical adapter 122 may be a device capable of enhancing sensory data collection. In an exemplary embodiment, such modifications may include magnification, illumination, resolution, processing, filtering, noise reduction, and the like. For example, the optical adapter 122 may be a lens capable of magnifying images captured by a smartphone (smart device 120) for more advanced analysis. It may also include specialized lenses for imaging with very low image distortion, special illumination, and optics for obtaining bacterial images with good contrast against the background. The optical adapter 122 may improve the optical resolution of images captured by the smart device 120 and may magnify images with a resolution of, for example, one micron (e.g., 15 to 100 times). In other embodiments, the optical adapter 122 may include a light source, zoom and focus adjusters, hardware for mounting the optical adapter 122 to the smart device 120, a microfluidic containment cell for holding bacterial culture samples, a sample stage for observing the samples, and other equipment. The microfluidic containment cell for holding bacterial culture samples may store 3-10 μl of bacterial culture samples. It should be understood that in embodiments where the smart device 120 is capable of achieving a desired optical resolution without the use of the optical adapter 122 (such as a digital microscope), such enhancement via the optical adapter 122 may not be necessary and, therefore, omitted from such embodiments.

[0038] The bacteria classification client 124 may act as a client in a client-server relationship and may be a software and / or hardware application capable of communicating with a server and providing a user interface for a user to interact with the server and other computing devices via the network 108. Furthermore, in an exemplary embodiment, the bacteria classification client 124 may be capable of transmitting data from the smart device 120 to and from other devices via the network 108. In an embodiment, the bacteria classification client 124 utilizes various wired and wireless connection protocols for data transmission and exchange, including Bluetooth, 2.4 GHz and 5 GHz Internet, near field communication, Z-Wave, Zigbee, etc. Figures 2 to 5 Describe in more detail.

[0039] In an exemplary embodiment, the bacteria classification server 130 may include one or more bacteria classification models 132 and bacteria classifiers 134, and may act as a server in a client-server relationship with the bacteria classification client 124. The bacteria classification server 130 may be an enterprise server, a laptop, a notebook, a tablet computer, a netbook computer, a PC, a desktop computer, a server, a PDA, a rotary phone, a push-button phone, a smartphone, a mobile phone, a virtual device, a thin client, an IoT device, or any other electronic device or computing system capable of receiving and sending data to and from other computing devices. Although the bacteria classification server 130 is shown as a single device, in other embodiments, the bacteria classification server 130 may include a cluster or multiple computing devices working together or independently. The bacteria classification server 130 is described in more detail with reference to Figure 9 Hardware implementation, reference Figure 10 Part of, and / or reference to, the cloud implementation of Figure 11 Use functional abstraction layer for processing.

[0040] The bacterial classification model 132 can be one or more algorithms that model the correlation between one or more types of bacteria and one or more characteristics or features exhibited by the one or more types of bacteria. For example, such bacteria may include Escherichia coli, Bacillus, Salmonella, Listeria, Campylobacter and other Staphylococcus bacteria, and such relevant features may include bacterial morphology (e.g., bacterial size, shape, length, diameter, volume, color, etc.), bacterial motility (e.g., movement, swimming speed, running time, rolling time), colony pattern growth rate, reproduction rate, staining reaction, and other data sources that can undergo artificial intelligence analysis. In an exemplary embodiment, the bacterial classification model 132 can be generated separately for specific bacteria, as well as separately for different life stages of bacteria in two liquid cultures, biofilms, and on solid surfaces. The bacterial classification model 132 can be generated using machine learning methods such as neural networks, deep learning neural networks, computer vision techniques, particle tracking algorithms, etc., in order to model the likelihood of one or more features indicating a bacterial type. In an embodiment, such features can be weighted by the model based on the likelihood that the feature indicates the correct bacteria, and such weights can be adjusted by using a feedback loop. The bacterial classification model 132 references Figure 2-5 Describe in more detail.

[0041] In an exemplary embodiment, the bacteria classifier 134 can be a software and / or hardware program capable of receiving a bacteria culture sample and receiving adjustments to the focus and zoom of the bacteria culture sample. The bacteria identifier is further capable of recording a video of the bacteria at a specific frame rate with the adjusted zoom and focus for a given lapse duration. The bacteria classifier 134 is further capable of extracting sequential frames of the bacteria culture sample from the recorded video and extracting morphological and motility vector features of the bacteria culture sample. The bacteria classifier 134 is capable of merging the morphological and motility vector features and classifying the bacteria culture sample based on comparing the merged vector features to a model. Figures 2 to 5 The bacteria classifier 134 is described in more detail.

[0042] Figure 2 Depicted is an exemplary flow chart illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in documenting bacteria using a smart device microscope, according to an exemplary embodiment.

[0043] The bacteria classifier 134 can receive a bacterial culture sample (step 202). In an exemplary embodiment, the bacteria classifier 134 can receive a culture sample present in a liquid or on a solid surface. In embodiments where the bacterial culture sample is classified in a liquid, the sample can be 3-10 microliters, and in embodiments utilizing the optical adapter 122, the sample can be contained in a microfluidic sample holding cell. In embodiments where bacteria are classified on a surface, the surface can be several square centimeters. In both liquid and solid surface embodiments, the bacterial culture sample can be centered within the viewing or sample stage of the smart device 120 or the optical adapter 122. For example, the bacterial culture sample can be a 4 microliter microfluidic cell containing unknown bacteria. In other embodiments, the bacteria classifier 134 can be mounted on an xy translation stage to scan a larger area, such as a desktop work surface.

[0044] The bacteria classifier 134 may receive a microscope focus adjustment (step 204). In an exemplary embodiment, the bacteria classifier 134 may receive a microscope focus adjustment to change the focal plane of the smart device 120 by electrically controlling the physical actuator via a physical actuator (e.g., a knob, slider, button, etc.) or via a digital device (e.g., a touch screen with a digital knob, slider, button, etc.). In an embodiment, the bacteria classifier 134 may receive the focus adjustment via the smart device 120, or in an embodiment where image enhancement is implemented via the optical adapter 122, the bacteria classifier 134 may receive the focus adjustment via the optical adapter 122. For example, the optical adapter 122 may have a knob for adjusting the distance or angle between one or more lenses of the optical adapter 122 and the smart device 120, thereby changing the focus of the smart device 120.

[0045] The bacteria classifier 134 may receive a microscope zoom adjustment (step 206). In an exemplary embodiment, the bacteria classifier 134 may receive the microscope zoom adjustment via a physical actuator (e.g., a knob, slider, button, etc.) or via a digital device (e.g., a touch screen with a digital knob, slider, button, etc.) to change the viewing angle of the smart device 120. In an embodiment, the bacteria classifier 134 may receive the zoom adjustment via the smart device 120, or in an embodiment where image enhancement is implemented via the optical adapter 122, the bacteria classifier 134 may receive the zoom adjustment via the optical adapter 122. For example, the optical adapter 122 may have a knob for adjusting the distance or angle between one or more lenses of the optical adapter 122 and the smart device 120, thereby changing the focus of the smart device 120.

[0046] The bacteria classifier 134 can record video at different frame rates for a given elapsed time (step 208). In an embodiment, the bacteria classifier 134 can record bacteria for a duration of 1-2 minutes at a resolution of 1 micron and a frame rate of 25-250 frames per second. However, it should be understood that the bacteria classifier 134 can be configured to record bacteria at various resolutions, frame rates, and durations based on the bacteria, device, and application. In an example embodiment, the recorded video can be transmitted from the bacteria classification client 124 to the bacteria classification server 130 via the network 108, while in other embodiments, the recorded video can be stored and analyzed locally on the smart device 120.

[0047] Figure 3 An exemplary flow chart illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in classifying bacteria using morphological and motility characteristics is depicted in accordance with an exemplary embodiment. It should be understood that Figure 3 A general overview of the operation of the bacteria classifier 134 is depicted, and Figure 4-5 More detailed descriptions for analyzing bacterial morphology and motility are provided, respectively.

[0048] The bacteria classifier 134 can extract sequential frames from the recorded video (step 302). In an exemplary embodiment, the bacteria classifier 134 can extract any number of frames within the video frame rate over any recording duration sufficient to analyze the morphology and motility of the bacteria. Thus, and depending on the type of bacteria, the bacteria classifier 134 can extract a number of frames sufficient to identify the shape of the bacteria (e.g., size, diameter, volume, etc.), as well as a number of frames and duration sufficient to analyze bacterial movement (e.g., running, rolling, reproduction / replication). In embodiments, the desired frame rate can be fixed and periodic (e.g., one frame per second), while in other embodiments, the frame rate can increase or decrease over time (e.g., extracting at an increased frame rate at a later time in the overall duration). In further embodiments, frames can be analyzed for specific phenomena, and frames can be extracted or the rate of frame extraction can be increased when a specific phenomenon occurs. Similarly, the duration for extracting frames can be fixed or variable, with some embodiments implementing a fixed duration and other embodiments implementing a shortened or extended duration based on bacterial activity or the occurrence of a specific phenomenon.

[0049] Referring to an illustrative example, bacteria classifier 134 may extract frames at a rate of 25 frames per second for a duration of 2 minutes from a 3 minute recorded video depicting one or more bacteria.

[0050] The bacteria classifier 134 may extract morphological features (step 304). In an exemplary embodiment, the extracted morphological features are representations of characteristics of the bacteria, such as whether the bacteria are pathogenic or non-pathogenic, Gram stain type, shape, length, cell diameter, cell volume, etc. The bacteria classifier 134 may then determine the similarity of the extracted morphological features with the morphological features of the classified bacteria in order to classify the unknown bacteria. Figure 4 The operation of the bacteria classifier 134 with respect to extracting morphological features is described in more detail.

[0051] Continuing with the illustrative example introduced above, the bacteria classifier 134 extracts morphological features of the bacteria captured within the extracted frames.

[0052] The bacteria classifier 134 extracts motility features (step 306). In an exemplary embodiment, the extracted motility features are indicative of the ability of the bacteria to move independently relative to the bacteria's use of metabolic energy. The motility features may include characteristics such as the length / duration of bacterial runs, the speed and average speed of bacterial runs, the length / duration of bacterial tumbles and rolls, the bacterial reproduction / replication rate, etc. The bacteria classifier 134 may then determine the similarity of the extracted motility features with the motility features of the classified bacteria in order to classify the unknown bacteria. Figure 5 The operation of the bacteria classifier 134 with respect to extracting motility features is described in more detail.

[0053] Referring again to the illustrative example introduced previously, the bacteria classifier 134 extracts motility characteristics of the bacteria captured within the extracted frames.

[0054] The bacteria classifier 134 may combine the morphological features and the motility features into a combined vector feature (step 308). In an exemplary embodiment, the morphological and motility vector features are combined into a combined vector representing a combined feature. The bacteria classifier 134 may then compare the combined vector with the model using a threshold comparator, with the result of the comparison indicating the type of bacteria present in the bacterial culture sample with a specified confidence level.

[0055] Returning to the illustrative example, the bacteria classifier 134 combines the morphological features with the motility features to produce a merged vector feature.

[0056] The bacteria classifier 134 may classify and quantify the bacterial culture sample (step 310). In an exemplary embodiment, the bacteria classifier 134 may classify the bacterial culture sample into one or more individual bacterial types based on a threshold comparison between the combined vector and the model. For example, based on determining that the combined vector exceeds a similarity threshold with the combined vectors of one or more known bacteria, the bacteria classifier 134 may classify the unknown bacteria as a known bacteria.

[0057] In addition, because the bacteria classifier 134 is able to classify individual bacteria, the bacteria classifier 134 is able to quantify the concentration of the classified bacteria. In an embodiment, the bacteria classifier 134 may be further configured to detect bacterial reproduction / replication based on morphological and motility analysis, thereby allowing the bacteria classifier 134 to consider bacterial reproduction rates when classifying bacteria. For example, the bacteria classifier 134 can compare the observed reproduction / replication rate with known bacterial reproduction / replication rates and then consider the similarity between the determined rates when classifying bacteria. In addition, the bacteria classifier 134 can also be configured to utilize the detection of bacterial reproduction in order to distinguish between live and non-live cells. For example, the bacteria classifier 134 can determine that a cell is non-live based on detecting a very low reproduction rate and / or detecting a hysteresis period in the life cycle of bacteria.

[0058] With reference to the illustrative example presented above, the bacteria classifier 134 compares the combined vector of the bacterial culture sample with the combined vectors of known bacteria to determine whether the bacterial sample contains Escherichia coli and Bacillus subtilis, e.g. Figure 7-8 shown.

[0059] The bacteria classifier 134 may adjust the model (step 312). In embodiments, the bacteria classifier 134 may utilize the received feedback to modify the bacteria classification model 132 and improve accuracy, speed, efficiency, etc. Thus, the bacteria classification model 132 may be configured to continuously modify / improve the bacteria classification model 132 as feedback information becomes available. The bacteria classifier 134 may receive feedback in several ways, such as user input, supervised / unsupervised training, extended analysis of additional information as the bacterial culture is further studied, etc. For each type and life stage of bacteria, such modifications to the bacteria classification model 132 may include adding / removing features, merging features, increasing / decreasing weights associated with specific features, etc. For example, the bacteria classifier 134 may increase the weights associated with features relied upon when inferring bacteria classifications that were confirmed to be correct through feedback, while decreasing the weights associated with features relied upon when inferring bacteria that were incorrectly identified. In the simplest form, for embodiments that implement a rigorous training phase for the bacteria classification model 132 upon initialization, the bacteria classifier 134 may receive feedback from a user or administrator indicating whether correct or incorrect bacteria were identified. In the event that the bacteria classifier 134 infers bacteria below a certainty / probability threshold, etc., the bacteria classifier 134 may randomly request such feedback from the user or administrator at periodic intervals. In more complex embodiments, the bacteria classifier 134 may be configured to confirm a previous bacteria classification at a later time based on allowing the bacterial colonies to further develop, thereby reducing the difficulty of identifying them. Figure 4-5 The training of the bacteria classification model 132 is described in more detail.

[0060] Referring again to the example described previously, bacteria classifier 134 prompts the user to confirm that the classified bacteria are E. coli and Bacillus subtilis. Alternatively, bacteria classifier 134 may reanalyze the bacteria after allowing several minutes to pass in order to collect more data and verify the results. Upon receiving confirmation that bacteria classifier 134 identified the correct bacteria, bacteria classifier 134 may increase the weight associated with the features relied upon in making that determination.

[0061] Figure 4 Depicted is an exemplary flow chart illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in extracting bacterial morphological features 304 , according to an exemplary embodiment.

[0062] The bacteria classifier 134 can train a model that correlates the morphology of cells with bacterial classes (step 402). In an exemplary embodiment, the bacteria classifier 134 can train one or more models (i.e., one or more bacteria classification models 132) that are capable of classifying one or more types, quantities, and life stages of bacteria based on one or more morphological characteristics exhibited by one or more bacteria. In an exemplary embodiment, the bacteria classifier 134 is trained to identify and weight specific characteristics or features of bacteria that indicate their identity, and use those weighted features to calculate a value that indicates the class of the bacteria. The bacteria classifier 134 can be configured to identify any type of bacteria that exhibits identifiable characteristics, and such bacteria can include Escherichia coli, Salmonella, Listeria, Campylobacter, etc., and characteristics associated with bacteria can include size, length, cell diameter, cell volume, cell shape, cell color, Gram stain type, cell proliferation, cell proliferation rate, etc. In this exemplary embodiment, bacteria classifier 134 can be trained to recognize and associate such features with bacteria through a supervised and / or unsupervised training process, in which bacteria classifier 134 observes features of various bacteria in liquids and on solid surfaces at all stages of the bacterial life cycle. In some embodiments, bacteria classifier 134 can be trained by presenting it with images / videos of various bacteria and configuring it to associate the recognized features with annotated bacteria types. In such an embodiment, bacteria classifier 134 can then be tested and tuned using additional annotated images, but this time with the bacteria types hidden, and bacteria classification model 132 adjusted based on the bacteria types later revealed. In other embodiments, supervised learning can be implemented, in which a moderator or administrator identifies bacteria within the image and bacteria classifier 134 modifies the weights accordingly. Bacteria classifier 134 can then use the generated model as a reference for comparison with unknown bacteria, as described in more detail below.

[0063] To further illustrate the operation of bacteria classifier 134, reference is now made to an illustrative example in which bacteria classifier 134 is trained to identify bacteria types Escherichia coli, Campylobacter, Listeria, and Salmonella. Here, bacteria classifier 134 is trained using the following features: pathogenic bacteria vs. non-pathogenic bacteria, Gram stain, shape, length, cell diameter, and cell volume, as shown in Table 1:

[0064]

[0065] Table 1 - Bacterial characteristics

[0066] Bacteria classifier 134 may collect samples of outlines and blob shapes from unknown bacteria within the extracted image frame (step 404). In an exemplary embodiment, bacteria classifier 134 may use techniques such as edge detectors and Sobel filters to discern the outlines and blobs of individual bacteria within the extracted frame. Images may also be pre-processed to reduce noise and enhance bacterial image segment features. In addition to identifying bacterial edges within the frame, bacteria classifier 134 may further determine the size, Gram stain type, shape, length, cell diameter, and cell volume of each identified cell within the image frame.

[0067] Continuing with the illustrative example introduced previously, the bacteria classifier 134 extracts the shape, length, diameter, and volume of the unknown bacteria.

[0068] The bacteria classifier 134 can apply the trained model to the image frame of bacteria (step 406). In an embodiment, the bacteria classifier 134 can be configured to apply the bacteria classification model 132 to the image frame of bacteria to classify one or more types of one or more bacteria. As previously described, the one or more bacteria classification models 132 weight bacterial features and correlate them with known bacterial classifications. Thus, using the known correlations identified during the training phase, the bacteria classifier 134 can apply the same model to unknown bacteria, resulting in a value indicating the most likely type of bacteria within the image. In an embodiment, the bacteria classifier 134 can be configured to apply a similarity measure (such as Siamese network similarity) to the known bacteria in the model and the unknown bacteria in the image frame to determine a similarity measure for the two bacteria. Based on the similarity level exceeding a certain threshold, the bacteria classifier 134 can classify the unknown bacteria as a known classification. In addition, the model can be configured to weight such features according to accuracy, so that features that are proven to be highly correlated with specific bacteria are weighted more heavily and relied upon more heavily during analysis. Conversely, those features that, while still valuable, have less relevance are weighted less in the determination. Additionally, the bacteria classifier 134 can further adjust and refine these weights by using feedback loops, as described in more detail herein.

[0069] Referring again to the example introduced previously, the bacteria classifier 134 compares the morphological characteristics (eg, shape, size, etc.) of the imaged bacteria to the imaged bacteria.

[0070] The bacteria classifier 134 may generate a multi-class prediction vector (step 408). In an exemplary embodiment, the generated multi-class prediction vector is a mapping from a feature set to a set of features. The bacteria classifier 134 utilizes a machine learning model that identifies the class to which the bacteria belongs as an output in the form of a vector. For example, the bacteria classifier 134 may determine whether the bacteria is Escherichia coli or Bacillus subtilis based on a binary classification of a vector of length 1. Similarly, this classification can be between multiple classes of bacteria, with each vector value representing a class.

[0071] Referring again to the example introduced previously, the bacteria classifier 134 generates a multi-class prediction vector to determine that E. coli and B. subtilis are the most likely bacteria present in the sample based on bacterial morphology, relying heavily on cell length and cell diameter to classify the bacteria as E. coli and B. subtilis (see Figure 7-8 ).

[0072] Figure 5 An exemplary flow chart illustrating the operation of the bacteria classifier 134 of the bacteria classification system 100 in extracting bacterial motility characteristics 306 is depicted, according to an exemplary embodiment. It should be understood that in order to extract bacterial motility characteristics, bacterial runs and tumbles must be distinguished from random motion. To distinguish runs and tumbles from random movement, the bacteria classifier 134 utilizes comparisons to Brownian random motion, as described in more detail below.

[0073] The bacteria classifier 134 may track one or more bacteria tracks across one or more extracted image frames (step 502). In an exemplary embodiment, the bacteria classifier 134 may track one or more bacteria tracks by, for example, identifying outlines and spots of bacteria in a first frame using an edge detector and later identifying the same bacteria in subsequent image frames. Based on the distance traveled by the bacteria between image frames and the time elapsed between image frames, the bacteria classifier 134 may determine the tracks of the detected bacteria.

[0074] Referring again to the above example, the bacteria classifier 134 detects bacteria within the first frame and the same bacteria has moved a distance of 0.5 μm between frames captured 38 milliseconds apart.

[0075] The bacteria classifier 134 may obtain swimming motion (running) and tumbling motion for the sample subset (step 504). Based on the identified trajectories, the bacteria classifier 134 may obtain the running motion and tumbling motion of the bacteria. In an exemplary embodiment, the bacteria classifier 134 may detect running / swimming motion by identifying relatively straight lines within the trajectory of the bacteria (e.g., lines that do not deviate significantly from the path) (see FIG. Figure 6). Such linear motion may have a minimum threshold to be considered swimming, and may require, for example, an absolute linear distance or a linear distance relative to, for example, the size or aspect ratio of the bacteria. Such a distance may be, for example, 10 bacterial lengths. The bacteria classifier 134 may be able to identify instances where a bacterium has crossed its own path one or more times (see Figure 7 ) to additionally identify tumbling or movement of bacteria such as turning, spinning, and rotating.

[0076] Referring again to the above example, the bacteria classifier 134 identifies bacteria that have linear motion prior to tumbling.

[0077] The bacteria classifier 134 may calculate motility characteristics for the sample subset (step 506). In an exemplary embodiment, the bacteria classifier 134 may use the trajectory of the bacteria to calculate the motility characteristics. For example, such motility characteristics may include the length of a run, the average length of a run, the speed of a run, the average speed of a run, the length of a tumble, the average length of a tumble, the speed of a tumble, the average speed of a tumble, the interval between tumbles, etc. In this exemplary embodiment, the bacteria classifier 134 may calculate such characteristics by inferring the distance covered by the bacteria in the amount of time between image frames, and thereby inferring the movement rate.

[0078] In the above example, for example, the bacteria classifier 134 determined that bacteria that had moved a distance of 51 μm in a duration of 3 seconds exhibited an average run length of 17 μm, an average run speed of 17 μm / second, and tumbles at intervals of 1 second.

[0079] The bacteria classifier 134 may identify the bacterial signature as a distribution of pairs for each classification (step 508). In an exemplary embodiment, the bacteria classifier 134 generates motility signatures as a distribution of pairs for each classification, ie, average speed and tumbling interval.

[0080] Referring to the above example, the bacteria classifier 134 may generate a motility signature based on an average running speed of 17 μm / second and a distribution of tumbling at 1 second intervals.

[0081] The bacteria classifier 134 can obtain the positional displacement of the bacteria relative to the passage of time (step 510). To distinguish running and tumbling of bacteria from random motion, the bacteria classifier 134 obtains the positional displacement of the bacteria relative to the passage of time. Here, the bacteria classifier 134 uses the trajectory of bacteria across frames to calculate the positional displacement over time. For example, the bacteria classifier 134 can measure the distance traveled by bacteria within the sample between frames extracted at periodic intervals. Based on the time between frames and the distance, the bacteria classifier 134 can infer the positional displacement of the bacteria relative to the passage of time.

[0082] Continuing with the above example, the bacteria classifier 134 obtains the displacement with respect to the passage of time based on the movement of bacteria over time.

[0083] The bacteria classifier 134 can extract the variance of the position shift from the position shift distribution over time (step 510). In an exemplary embodiment, the bacteria classifier 134 generates the position shift distribution and determines the variance data of the position shift over time. In an exemplary embodiment, the bacteria classifier 134 examines the position shift distribution of bacteria of different sizes, where the variance of smaller-sized bacteria will have a larger variance, and vice versa. Because this will also depend on the bacterial culture temperature, in an embodiment, both samples are maintained at approximately the same temperature.

[0084] The bacteria classifier 134 may classify the bacterial motility features into a distribution of pairs for each classification (step 512). In an exemplary embodiment, the bacteria classifier 134 generates motility features as a distribution of pairs for each classification, i.e., variance and time lapse. In an exemplary embodiment, the motility features and / or signature distributions may be collected, for example, via trajectory vectors, movement rates in a particular direction, speed, diffusion, etc.

[0085] Returning to the example introduced previously, the bacteria classifier 134 generates a motility signature based on the distribution of pairs of variance and time lapse of bacteria.

[0086] Figure 6 Depicted are the running and tumbling of bacteria analyzed during the generation of motility signatures according to an exemplary embodiment.

[0087] Figure 7 An example of a bacteria classifier 134 is depicted that classifies E. coli bacteria according to an exemplary embodiment.

[0088] Figure 8 An example of a bacteria classifier 134 is depicted classifying Bacillus subtilis bacteria according to an exemplary embodiment.

[0089] Figure 9 Depicted is a diagram according to an exemplary embodiment Figure 1 It should be understood that Figure 9 This merely provides an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications may be made to the depicted environments.

[0090] As used herein, an apparatus may include one or more processors 02, one or more computer-readable RAMs 04, one or more computer-readable ROMs 06, one or more computer-readable storage media 08, a device driver 12, a read / write driver or interface 14, a network adapter or interface 16, all interconnected by a communications fabric 18. The communications fabric 18 may be implemented with any architecture designed to pass data and / or control information between processors (such as microprocessors, communications and network processors, etc.), system memory, peripheral devices, and any other hardware components within the system.

[0091] One or more operating systems 10 and one or more application programs 11 are stored on one or more of the computer-readable storage media 08 for execution by the one or more processors 02 via one or more corresponding RAMs 04 (which typically include cache memory). In the illustrated embodiment, each of the computer-readable storage media 08 may be a magnetic disk storage device such as an internal hard disk, a CD-ROM, a DVD, a memory stick, a magnetic tape, a magnetic disk, an optical disk, a semiconductor memory device such as a RAM, a ROM, an EPROM, a flash memory, or any other computer-readable tangible storage device that can store computer programs and digital information.

[0092] The device used herein may also include a read / write drive or interface 14 for reading from and writing to one or more portable computer-readable storage media 26. The application 11 on the device may be stored on one or more portable computer-readable storage media 26, read through the corresponding read / write drive or interface 14, and loaded into the corresponding computer-readable storage medium 08.

[0093] The device used herein may also include a network adapter or interface 16, such as a TCP / IP adapter card or a wireless communication adapter (e.g., a 4G wireless communication adapter using OFDMA technology). Application programs 11 on the computing device can be downloaded to the computing device from an external computer or external storage device via a network (e.g., the Internet, a local area network, other wide area network, or wireless network) and the network adapter or interface 16. The program can be loaded from the network adapter or interface 16 onto a computer-readable storage medium 08. The network may include copper wires, optical fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers.

[0094] As used herein, a device may also include a display screen 20, a keyboard or keypad 22, and a computer mouse or touchpad 24. The device driver 12 interfaces with the display screen 20 for imaging, the keyboard or keypad 22, the computer mouse or touchpad 24, and / or the display screen 20 for pressure sensing of alphanumeric characters and user selections. The device driver 12, the read / write driver or interface 14, and the network adapter or interface 16 may include hardware and software (stored on the computer-readable storage medium 08 and / or ROM 06).

[0095] The programs described herein are identified based on the applications in which they are implemented in the specific exemplary embodiments of the exemplary embodiments. However, it should be understood that any specific program terminology herein is used merely for convenience, and thus the exemplary embodiments should not be limited to use only in any specific application identified and / or implied by such terminology.

[0096] Based on the above, a computer system, method, and computer program product have been disclosed. However, various modifications and substitutions may be made without departing from the scope of the exemplary embodiments. Therefore, the exemplary embodiments are disclosed by way of example and not limitation.

[0097] It should be understood that although the present disclosure includes detailed descriptions about cloud computing, the implementation of the teachings described herein is not limited to a cloud computing environment. Instead, the exemplary embodiments can be implemented in conjunction with any other type of computing environment now known or later developed.

[0098] Cloud computing is a service delivery model that enables convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage devices, applications, virtual machines, and services) that can be quickly provisioned and released with minimal management effort or interaction with the service provider. The cloud model can include at least five characteristics, at least three service models, and at least four deployment models.

[0099] Features are as follows:

[0100] On-demand self-service: Cloud consumers can unilaterally and automatically provision computing capabilities, such as server time and network storage, as needed, without requiring human interaction with the service provider.

[0101] Broad Network Access: Capabilities are available over the network and accessed through standard mechanisms that facilitate the use of heterogeneous thin-client or thick-client platforms (e.g., mobile phones, laptops, and PDAs).

[0102] Resource pooling: A provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, where different physical and virtual resources are dynamically assigned and reassigned as needed. There is a sense of location independence, as consumers typically do not have control or knowledge of the exact location of the provided resources, but may be able to specify the location at a higher level of abstraction (e.g., country, state, or data center).

[0103] Rapid elasticity: The ability to quickly and elastically provision capacity, in some cases automatically scaling down and releasing capacity to scale up quickly. To the consumer, the capacity available for provisioning typically appears unlimited and can be purchased in any quantity at any time.

[0104] Metered Services: Cloud systems automatically control and optimize resource usage by leveraging metering capabilities at a level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both providers and consumers of the utilized services.

[0105] The service model is as follows:

[0106] Software as a Service (SaaS): The ability provided to consumers is to use the provider's applications running on a cloud infrastructure. Applications are accessible from various client devices through a thin client interface such as a web browser (e.g., web-based email). Consumers do not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, storage, or even individual application capabilities, with the possible exception of limited user-specific application configuration settings.

[0107] Platform as a Service (PaaS): The capability provided to consumers is to deploy applications created or acquired using programming languages ​​and tools supported by the provider onto cloud infrastructure. Consumers do not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, or storage, but do have control over the deployed applications and the configuration of the application hosting environment.

[0108] Infrastructure as a Service (IaaS): The capabilities provided to consumers are processing, storage, networking, and other basic computing resources on which consumers can deploy and run arbitrary software, including operating systems and applications. Consumers do not manage or control the underlying cloud infrastructure, but rather have control over the operating system, storage, deployed applications, and potentially limited control over selected networking components (e.g., host firewalls).

[0109] The deployment model is as follows:

[0110] Private cloud: Cloud infrastructure is operated solely for an organization. It can be managed by the organization or a third party and can exist on-premises or off-premises.

[0111] Community cloud: Cloud infrastructure is shared by several organizations and supports a specific community with shared concerns (e.g., mission, security requirements, policies, and compliance considerations). It can be managed by the organization or a third party and can exist on-premises or off-premises.

[0112] Public cloud: Cloud infrastructure is made available to the public or large industry groups and is owned by the organization that sells cloud services.

[0113] Hybrid cloud: A cloud infrastructure is a combination of two or more clouds (private, community, or public) that remain unique entities but are bound together by standardized or proprietary technologies that enable data and application portability (e.g., cloud bursting for load balancing between clouds).

[0114] Cloud computing environments are service-oriented and focus on statelessness, low coupling, modularity, and semantic interoperability. The core of cloud computing is the infrastructure that consists of a network of interconnected nodes.

[0115] Now see Figure 10 , an illustrative cloud computing environment 50 is described. As shown, the cloud computing environment 50 includes one or more cloud computing nodes 40 with which local computing devices used by cloud consumers can communicate, such as, for example, personal digital assistants (PDAs) or cellular phones 54A, desktop computers 54B, laptop computers 54C, and / or automobile computer systems 54N. The nodes 40 can communicate with each other. They can be grouped physically or virtually (not shown) in one or more networks, such as private clouds, community clouds, public clouds, or hybrid clouds, or a combination thereof, as described above. This allows the cloud computing environment 50 to provide infrastructure, platforms, and / or software as services for which cloud consumers do not need to maintain resources on local computing devices. It should be understood that Figure 10 The types of computing devices 54A-N shown in are intended to be illustrative only, and computing nodes 40 and cloud computing environment 50 may communicate with any type of computerized device over any type of network and / or network-addressable connection (eg, using a web browser).

[0116] Now see Figure 11 , showing the cloud computing environment 50 ( Figure 10 ) provides a set of functional abstraction layers. It should be understood in advance that Figure 11 The components, layers, and functions shown in are intended to be illustrative only, and the exemplary embodiments are not limited thereto. As described, the following layers and corresponding functions are provided:

[0117] The hardware and software layer 60 includes hardware and software components. Examples of hardware components include: mainframes 61; servers based on RISC (Reduced Instruction Set Computer) architecture 62; servers 63; blade servers 64; storage devices 65; and network and networking components 66. In some embodiments, software components include web application server software 67 and database software 68.

[0118] Virtualization layer 70 provides an abstraction layer from which the following examples of virtual entities can be provided: virtual servers 71 ; virtual storage 72 ; virtual networks 73 , including virtual private networks; virtual applications and operating systems 74 ; and virtual clients 75 .

[0119] In one example, the management layer 80 may provide the functionality described below. Resource provisioning 81 provides dynamic procurement of computing and other resources for performing tasks within the cloud computing environment. Metering and pricing 82 provides cost tracking when utilizing resources within the cloud computing environment and bills or invoices the consumption of these resources. In one example, these resources may include application software licenses. Security provides authentication for cloud consumers and tasks, as well as protection for data and other resources. User portal 83 provides access to the cloud computing environment for consumers and system administrators. Service level management 84 provides cloud computing resource allocation and management so that required service levels are met. Service level agreement (SLA) planning and implementation 85 provides pre-arrangement and procurement of cloud computing resources in anticipation of future requirements for the cloud computing resources according to the SLA.

[0120] The workload layer 90 provides examples of functionality that can utilize a cloud computing environment. Examples of workloads and functionality that can be provided from this layer include: mapping and navigation 91; software development and lifecycle management 92; virtual classroom education delivery 93; data analytics processing 94; transaction processing 95; and bacterial processing 96.

[0121] The exemplary embodiments may be systems, methods and / or computer program products of any possible degree of technical detail integration. The computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for causing a processor to perform various aspects of the exemplary embodiments.

[0122] Computer-readable storage media can be a tangible device that can retain and store the instructions used by the instruction execution device.Computer-readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the above. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), portable compact disc read-only memories (CD-ROM), digital versatile discs (DVD), memory sticks, floppy disks, mechanical encoding devices such as punch cards, or projection structures in the grooves with instructions recorded thereon, and any suitable combination of the above. Computer-readable storage media as used herein should not be interpreted as temporary signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (for example, light pulses passing through fiber optic cables), or electrical signals emitted by wires.

[0123] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network), or downloaded to an external computer or external storage device. The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0124] The computer-readable program instructions for performing the operation of exemplary embodiments can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, configuration data of integrated circuits or source code or object code written in any combination of one or more programming languages, and these one or more programming languages ​​include object-oriented programming languages ​​(such as Smalltalk, C++ etc.) and process programming languages ​​(such as " C " programming languages ​​or similar programming languages).Computer-readable program instructions can be performed completely on user's computer, partly on user's computer, performed as independent software package, partly on user's computer, partly on remote computer or performed completely on remote computer or server.In the latter case, remote computer can be connected to user's computer by any type of network (including local area network (LAN) or wide area network (WAN)), or can be connected to external computer (for example, using internet service provider through the internet).In certain embodiments, the electronic circuit comprising for example programmable logic circuit, field programmable gate array (FPGA) or programmable logic array (PLA) can make electronic circuit personalization perform computer-readable program instructions by utilizing the state information of computer-readable program instructions, so as to perform the aspects of exemplary embodiments.

[0125] Various aspects of the exemplary embodiments are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to the exemplary embodiments. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0126] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the functions / actions specified in the flowchart and / or block diagram or multiple blocks. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner, so that the computer-readable storage medium having the instructions stored therein includes an article of manufacture containing instructions that implement aspects of the functions / actions specified in the flowchart and / or block diagram or multiple blocks.

[0127] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable apparatus, or other device to produce computer-implemented processing, so that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / actions specified in the flowchart and / or block diagram or multiple boxes.

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions and operations of possible implementations of the systems, methods and computer program products according to different exemplary embodiments. To this end, each box in the flowchart or block diagram may represent a module, segment or portion of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions annotated in the box may not occur in the order annotated in the figure. For example, depending on the functions involved, the two blocks shown in succession may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs a specified function or action or performs a combination of dedicated hardware and computer instructions.

Claims

1. A computer-implemented method for classifying bacteria, the method comprising: extracting morphological features corresponding to one or more bacteria; extracting a motility feature corresponding to the one or more bacteria based on comparing the motility of the one or more bacteria to a model relating bacterial motility to bacterial type, wherein the model relating bacterial motility to bacterial type includes a feature replication rate; merging the morphological feature and the kinematic feature into a merged vector feature; and The one or more bacteria are classified based on the combined vector features.

2. The method according to claim 1, wherein Extracting the morphological features is based on comparing the morphology of the one or more bacteria with a model that relates bacterial morphology to bacterial type.

3. The method according to claim 2, wherein: The model relating bacterial morphology to bacterial type comprises features selected from the group consisting of cell size, cell shape, cell length, cell diameter, cell volume and Gram stain type.

4. The method according to claim 1, wherein The model relating bacterial motility to bacterial type comprises features selected from the group consisting of run length, average run length, run speed, average run speed, tumble length, average tumble length, tumble speed, average tumble speed, and tumble interval.

5. A method according to any one of the preceding claims, wherein The morphological features, the kinematic features and the combined vector features are generated by an artificial intelligence algorithm.

6. A computer program product for classifying bacteria, the computer program product comprising: A computer-readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit to perform the method according to any one of claims 1 to 5.

7. A computer-readable medium storing a computer program, said computer program being loadable into the internal memory of a digital computer, comprising software code portions for executing the method according to any one of claims 1 to 5 when said program is run on a computer.

8. A computer system for classifying bacteria, the computer system comprising: One or more computer processors, one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media for execution by at least one of the one or more processors capable of performing a method comprising: extracting morphological features corresponding to one or more bacteria; extracting a motility feature corresponding to the one or more bacteria based on comparing the motility of the one or more bacteria to a model relating bacterial motility to bacterial type, wherein the model relating bacterial motility to bacterial type includes a feature replication rate; merging the morphological features and the kinematic features into a merged vector feature; and The one or more bacteria are classified based on the combined vector features.

9. The computer system according to claim 8, wherein: Extracting the morphological features is based on comparing the morphology of the one or more bacteria with a model that relates bacterial morphology to bacterial type.

10. The computer system according to claim 9, wherein: The model relating bacterial morphology to bacterial type comprises features selected from the group consisting of cell size, cell shape, cell length, cell diameter, cell volume and Gram stain type.

11. The computer system according to claim 8, wherein: The model relating bacterial motility to bacterial type comprises features selected from the group consisting of run length, average run length, run speed, average run speed, tumble length, average tumble length, tumble speed, average tumble speed, and tumble interval.

Images