Spectroscopic apparatus

Abstract

This invention pertains to the field of spectroscopic devices. Specifically, this invention relates to a computer-implemented method for determining stoichiometric data of an object, the method comprising: a) receiving spectral data associated with a spectral measurement of the object, object data associated with characteristics of the object, and environmental data associated with characteristics of the object's surrounding environment; b) using the spectral data, the object data, and the environmental data to determine stoichiometric data of the object; and c) outputting the stoichiometric data of the object.

Description

[0001] This invention pertains to the field of spectroscopic devices. The invention relates to a computer-implemented method for determining chemometric data of an object, the use of the chemometric data of the object obtained from the method as described in any of the preceding claims for applications in physical fitness, health, nutrition, agriculture, or recycling; a spectroscopic device for determining chemometric data of an object; a system for generating a chemometric model of an infrared spectrometer; and a non-transient computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform the method. Background Technology

[0002] Spectroscopy is a powerful tool for analyzing substances, such as their chemical composition. Traditionally, spectroscopy has been performed in laboratories using benchtop equipment. Recently, portable spectrometers have become commercially available. Miniaturized spectrometers integrated into portable devices such as smartphones will soon be available. However, due to strict space constraints, these miniaturized spectrometers have not yet reached the performance of benchtop equipment. Furthermore, portable spectrometers are exposed to environments that interfere with spectral measurements, which may reduce the accuracy and precision of the results. In addition, users of portable spectrometers generally have less experience operating them compared to laboratory spectrometers operated by professionals.

[0003] US Patent 11,448,594 discloses a method for determining the quality and authenticity of agricultural commodities based on near-infrared spectroscopy. Environmental parameters and product characteristics are used to iteratively improve a chemometric model. However, this data is not used to improve measurement results when inferring the chemometric model, but only for its training.

[0004] US Patent 2014 / 155760 discloses the use of quantitative spectroscopy in measuring body water by incorporating additional information. However, it does not provide specific details on how to incorporate the additional information.

[0005] US 2019 / 223780 discloses a wearable device that includes multiple sensors. However, it does not provide specific details on how the sensor data is combined.

[0006] US 2017 / 160131 discloses a method for determining object properties and receiving additional data using a spectrometer. However, it does not provide specific instructions on how to use the additional data.

[0007] US 2018 / 172510 discloses a system for analyzing food in kitchen appliances, which includes a sensor configured to generate a nonspectral signal. However, no specific instructions are given on how the nonspectral signal is used.

[0008] US Patent 2018 / 120155 discloses a method for determining object properties using a spectrometer that includes a sensor configured to generate a non-spectral signal. However, it does not provide specific instructions on how the signal is used. Summary of the Invention

[0009] In one aspect, the present invention relates to a computer-implemented method for determining stoichiometric data of an object, the method comprising:

[0010] a) Receive spectral data associated with spectral measurements of the object, object data associated with the characteristics of the object, and environmental data associated with the characteristics of the object's surrounding environment.

[0011] b) Using the spectral data, the object data, and the environmental data, determine the stoichiometric data of the object.

[0012] c) Output the stoichiometric data of the object.

[0013] In another aspect, the present invention relates to the use of chemometric data of an object obtained by the method of any one of the preceding claims for applications in physical fitness, health, nutrition, agriculture or recycling.

[0014] In another aspect, the present invention relates to a spectroscopic apparatus for determining stoichiometric data of an object, the spectroscopic apparatus comprising:

[0015] a) Spectral module, which measures objects and generates spectral data therefrom.

[0016] b) An input terminal for receiving object data associated with the characteristics of the object and environmental data associated with the characteristics that affect the measurement result.

[0017] c) A processor used to determine the stoichiometric data of the object using the spectral data, the object data, and the environmental data, and

[0018] d) Output terminal, which is used to output the stoichiometric data of the object.

[0019] In another aspect, the present invention relates to a non-transient computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising the following steps:

[0020] a) Receive spectral data associated with spectral measurements of the object, object data associated with the characteristics of the object, and environmental data associated with the characteristics that affect the measurement results.

[0021] b) Using the spectral data, the object data, and the environmental data, determine the stoichiometric data of the object.

[0022] c) Output the stoichiometric data of the object.

[0023] By utilizing both object data and environmental data to determine chemometric data from spectral data, chemometric data with higher accuracy and / or precision can be achieved. This enables the use of miniaturized spectrometers that produce spectra with lower precision and resolution. In particular, for spectrometers integrated into portable devices, object and environmental data are readily available, for example, since portable devices are equipped with the corresponding sensors anyway, thus eliminating the need for complex hardware adjustments. This invention further reduces the calibration requirements of spectrometers because minute spectrometer drift can be computationally compensated for using object and environmental data. Furthermore, the amount of training data required for the chemometric model can be reduced, making application development easier even when training data availability is limited.

[0024] The term "spectral device" can refer to a device capable of recording spectral data of an object. A spectroscopic device can be a spectrometer or a device integrated with a spectrometer. Spectroscopic devices can be portable or stationary, such as laboratory equipment. Portable spectroscopic devices can be handheld spectrometers or modules integrated into portable devices such as smartphones, tablets, or wearable devices (such as smartwatches). Portable spectroscopic devices can be communicatively coupled to computer devices, such as cloud computers or smartphones. Such computer devices can be configured to perform chemometric models. The computer device can be further configured to receive spectral data from the spectroscopic device. The computer device can store this spectral data or send it to a system used to determine chemometric data. The computer system can be further configured to use the chemometric data to derive action instructions, for example, recommending drinking water if low skin hydration is detected.

[0025] A spectroscopic device may include:

[0026] - An optical element configured to separate incident light radiation provided by the measuring object into a spectrum having constituent wavelength components;

[0027] - A photoelectric sensor, the photoelectric sensor including at least one photosensitive area configured to receive light radiation from the optical element, wherein the photoelectric sensor is configured to generate at least one photoelectric sensor signal based on the irradiation of the photosensitive area by the light radiation;

[0028] - A processor that processes photoelectric sensor signals into a spectrum.

[0029] The term "optical element" can refer to any element configured to influence light radiation. An optical element can be configured to at least partially disperse light radiation, at least partially filter light radiation, at least partially reflect (e.g., diffuse or direct reflection) light radiation, at least partially deflect light radiation, at least partially transmit light radiation, and at least partially absorb light radiation. An optical element can include at least one of a prism, grating, beam splitter, or interferometer (e.g., a Michelson interferometer). An optical element can be configured for use in mobile applications, such as in handheld spectrometer devices, and / or in spectrometer devices included in electronic communication devices such as smartphones or tablet computers. As another example, an optical element can include at least one optical filter element. The optical filter element can be configured to filter light radiation or, more specifically, at least one selected spectral range of light radiation. The optical filter element can be specifically positioned in the optical path before a photoelectric sensor. As an example, a portable spectrometer can include multiple photoelectric sensors, such as 5 to 20, for example, 8 to 12. The photoelectric sensors can be arranged in an array or matrix in the form of pixels. Portable spectrometers may include multiple optical filter elements. These optical filter elements may be positioned in the beam path prior to the photodetectors. The optical filter elements may be transmissive at different wavelengths within different wavelength regions. For example, each photodetector may be positioned relative to the beam path after an optical filter, where each optical filter is transmissive relative to the other optical filters at different wavelengths or in different wavelength regions.

[0030] Spectroscopic devices may include one or more photoelectric sensors. A photoelectric sensor may include at least one photosensitive region. The photosensitive region may be configured to receive light radiation from optical elements. The photoelectric sensor may be configured to generate at least one photoelectric sensor signal based on the illumination of the photosensitive region by light radiation. The term "sensor" may refer to a device configured to detect at least one condition or to measure at least one measured variable. A sensor may be able to generate at least one signal (e.g., a measurement signal) that is a qualitative or quantitative indication of the measured variable and / or measured characteristic (e.g., illumination of the sensor or a portion thereof). This signal may be or include an electrical signal, such as current, specifically photocurrent. The term "photoelectric sensor" may refer to a sensor or detector configured to detect or measure light radiation, for example, by using the photoelectric effect, such as detecting illumination and / or radiation spots generated by at least one light beam. A photodetector may include at least one substrate. As an example, a single photoelectric sensor may be a substrate having at least one single photosensitive region that generates a physical response, such as an electronic response, to illumination within a given wavelength range.

[0031] The term "photosensitive region" can refer to a unit of a photoelectric sensor, specifically a spatial region or volume that is part of the photoelectric sensor and is configured to be illuminated, or in other words, to receive light radiation, and to generate at least one signal, such as an electronic signal, in response to illumination. The photosensitive region can be located on the surface of the photoelectric sensor. Specifically, the photosensitive region can be a single, enclosed, and uniform photosensitive area. However, other options are also possible.

[0032] The spectroscopic device may include at least one light-emitting element configured to emit illumination light to illuminate the object in order to generate detection light from the object. The light-emitting element may be an incandescent lamp (e.g., a tungsten filament lamp or a halogen tungsten filament lamp), a light-emitting diode (LED), a laser diode, or a gas discharge lamp (e.g., a xenon lamp, a mercury vapor lamp, or a deuterium lamp).

[0033] The term "light" can refer to electromagnetic radiation in one or more of the infrared, visible, and ultraviolet spectral ranges. The term "ultraviolet spectral range" can refer to electromagnetic radiation with wavelengths from 1 nm to 380 nm, preferably from 100 nm to 380 nm (e.g., 280 nm to 315 nm (UV-B) or 315 nm to 380 nm (UV-A)). Further, in part according to the version of ISO-21348 effective as of the date of this document, the term "visible spectral range" can refer to the spectral range from 380 nm to 760 nm. The term "infrared spectral range" (IR) can refer to electromagnetic radiation from 760 nm to 1000 µm, wherein the range from 760 nm to 1.5 µm is generally referred to as the "near-infrared spectral range" (NIR), the range from 1.5 µm to 15 µm is referred to as the "mid-infrared spectral range" (MidIR), and the range from 15 µm to 1000 µm is referred to as the "far-infrared spectral range" (FIR). Preferably, the light used for the typical purposes of this invention is light in the infrared (IR) spectral range, more preferably light in the near-infrared (NIR) and / or mid-infrared spectral range (MidIR), especially light with wavelengths from 780 nm to 3 µm (e.g., 780 nm to 1.4 µm or 1.4 µm to 3 µm). These wavelength regions are particularly suitable for obtaining the material properties of objects.

[0034] Spectroscopic devices may include a processor for processing photoelectric sensor signals into spectral data, such as infrared spectra. The term "processor" can refer to a device configured to process, manipulate, or transform data according to a set of instructions. A processor may be able to execute software, algorithms, or computational tasks to achieve a desired output. Examples of processors may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a microcontroller, a field-programmable gate array (FPGA), or an application-specific integrated circuit (ASIC). A processor may be a component of a larger system, such as an embedded system, computer, or mobile device, and may interact with other components, such as memory, input / output devices, and sensors.

[0035] The processor can output spectral data, for example, to an interface for further processing or to a user interface. The processor can be further configured to apply a chemometric model and output chemometric data obtained through the chemometric model. The spectroscopic device may further include memory. The memory can be configured to store the chemometric model. The memory can be configured to store the spectral data.

[0036] The term "spectral data" can refer to data associated with spectral measurements of an object, particularly data associated with optical spectral measurements of an object. Spectral data can be or may include one or more spectra. The term "spectrum" can refer to a data structure in which several intensity values, or values ​​derived therefrom (such as the absorbance of radiation), are associated with a wavelength or wavelength range of radiation. Wavelengths or wavelength ranges can be those described above. The data structure can be a vector, where each element represents an intensity, and the position in the vector represents a wavelength or wavelength range, so the value at a certain position represents the intensity of that wavelength or wavelength range. The data structure can be a vector or matrix containing pairs of values, where one value represents a wavelength or wavelength range, and the other value represents the intensity at that wavelength or wavelength range. Spectra recorded by a spectrometer can be corrected using calibration coefficients to compensate for sensor defects or drift. A spectrum can represent the absorbance or transmittance of radiation after it has penetrated an object.

[0037] The term "object" can refer to any object that can be measured by a spectrometer. An object can be a living organism (e.g., a human) or an inanimate object. An object can refer to a whole object or a piece thereof, such as a sample extracted from an object. In the case of a living organism, an object can refer to a body part, such as a face or hand. An object can have any aggregate state, such as solid, liquid, gas, or supercritical. An object can be homogeneous, i.e., it does not contain phase boundaries between regions of size equal to or larger than the irradiated radiation, such as a plastic bottle or a blood sample. An object can be non-homogeneous, containing phase boundaries between regions of size equal to or larger than the irradiated radiation, such as a soil sample containing sand.

[0038] The term "object data" can refer to data associated with the properties of an object, such as its physical or chemical properties. Object data can refer to any data associated with the properties of an object obtained by methods other than spectroscopy. Object data can be associated with stoichiometric data to be determined. Object data can be associated with the same properties as the stoichiometric data to be determined, or with properties different from the stoichiometric data to be determined. Physical properties can include thermal properties, such as temperature, thermal conductivity, or specific heat capacity; macroscopic or microscopic states of matter, such as the shape or topology of the object, or crystallinity; mechanical properties, such as pressure, compressibility, or mechanoelasticity; optical properties, such as color, refractive index, optical conductivity, or absorption coefficient; and electromagnetic properties, such as electrical conductivity, dielectric constant, radio frequency-based permittivity, microwave complex permittivity, millimeter-wave complex permittivity, magnetic permeability, or magnetic susceptibility. The chemical properties of an object typically refer to: the chemical composition of the object, including material composition, such as the types and concentrations of certain chemical compounds, such as water content; and the state of matter, such as crystallinity or aggregate state, such as in a dispersed phase.

[0039] When the object is a living organism, particularly a human being, the object data may include or may be biomarkers. The term "biomarker" can refer to a measurable substance, process, or characteristic that indicates a biological state or condition. Biomarkers can refer to specific molecules, proteins, genetic sequences, or other measurable characteristics associated with a particular disease, symptom, or treatment response. Examples of biomarkers include: body dimensions such as height, head circumference, chest circumference, abdominal circumference, upper thigh length, and arm length; weight or body mass index; body morphology such as facial features, iris structure, fingerprints, and hand shape; muscle measurements such as muscle strength, muscle endurance, muscle agility and speed, balance, and coordination; cardiovascular measurements such as heart rate, heart rate variability, electrocardiogram, blood pressure, and blood oxygen saturation; and skin measurements such as skin conductivity, skin impedance, skin moisture level, skin sebum level, skin roughness, skin elasticity, skin pH, and skin blood flow. The levels of various substances include: skin perspiration rate; blood metabolites such as blood glucose, blood cholesterol, blood triglycerides, blood urea, blood creatinine, blood lactate, blood bilirubin, and blood pH; urine metabolites such as urine glucose, urine urea, urine creatinine, urine ketones, urine pH, and urine protein content; hormone levels such as thyroid hormone levels, insulin levels, growth hormone levels, cortisol levels, estrogen levels, progesterone levels, testosterone levels, and prolactin levels; and drug levels or drug metabolite levels such as alcohol, amphetamines, opioids, cocaine, cannabis, benzodiazepines, and barbiturates.

[0040] Object data can be obtained from sensors other than spectrometers, such as thermometers, rulers, scales, optical cameras, optical 3D scanner systems, conductivity or impedance meters (e.g., stratum corneum moisture meters, sweat rate monitors, or sweat patches), liquid chromatographs or gas chromatographs, mass spectrometers, nuclear magnetic resonance spectrometers or imagers, electrochemical sensors, immunoassays, and polymerase chain reaction (PCR) devices. Spectroscopic equipment can be integrated into portable devices, which further include sensors from which at least a portion of the object data is received.

[0041] Object data can also be obtained from storage devices or from a user interface (such as a graphical user interface), into which the user can input object data, for example, based on observations. When the object to be measured is a human, the object data can include: human characteristics, including body measurements such as height, waist circumference, leg length, arm length, head circumference, foot size, hand size, body type (e.g., categories such as ectomorphic, mesomorphic, endomorphic, etc.), weight, body mass index, body composition, skin color, hair color, and hair type; demographic characteristics such as age, sex, place of origin, and race; medical history, including current and past medications; nutritional habits, such as vegetarianism or a vegetarian diet; stimulant consumption, such as caffeine, alcohol, tobacco products, and drugs; and physical activity levels, such as occupation type (i.e., office work or physically demanding work), type of exercise, average exercise duration, and average sleep hours.

[0042] The term "environmental data" can refer to data relating to the characteristics of the object's surrounding environment (such as the physical or chemical properties of the object's surrounding environment). The characteristics of the object's surrounding environment may influence spectral measurements of the object or the object's properties (such as its physical or chemical properties). However, environmental data may not include the object's inherent characteristics.

[0043] Environmental data can include sensor data from sensors other than spectrometers. Environmental data can include the location of objects, such as geographic locations (e.g., GPC coordinates), altitude, distance to a reference point (e.g., spectrometer), acceleration, and orientation relative to gravity; weather conditions, such as air temperature, air pressure, air humidity, wind speed, wind direction, and ambient light intensity; time or date; and levels of air pollutants, such as CO2 concentration, CO concentration, ozone concentration, nitrogen oxide concentration, sulfur dioxide concentration, fine particulate matter concentration, and volatile organic compound levels.

[0044] Sensor data can be recorded by sensors capable of determining the sensor data. Sensors can be integrated into a spectrometer. Spectroscopic devices can be integrated into portable devices, which further include sensors from which at least a portion of environmental data is received. Sensors can be coupled to the spectrometer, for example, via wireless communication or via the Internet. Examples of sensors can be GPC receivers, accelerometers, gyroscopes, altimeters, goniometers, distance sensors (such as time-of-flight sensors, radar, or LiDaR), pressure sensors (such as MEMS sensors, piezoelectric sensors, or capacitive sensors), magnetometers, barometers, light sensors, thermometers, and gas sensors.

[0045] Environmental data may include data associated with the spectrometer, such as the spectrometer ID, version number, settings, temperature, lifespan, time since last calibration, lifespan of the illumination source, and the number of measurements performed by the spectrometer within its lifespan or within a specific period (e.g., last week or last month). Environmental data may further include data associated with spectral measurements of an object, such as sampling time, illumination intensity of the object by the spectrometer, or distance from the object to the spectrometer.

[0046] Environmental data can be received from a data storage medium. This medium can be part of a spectroscopic device or a remote storage device, such as a computer system or a cloud system. In response to a request containing time and / or geographic location, environmental data can be received from a database (e.g., a database on a remote storage system). A remote storage system can refer to a system located far from the object being measured, such as a cloud server or a database server. For example, a request containing the object's GPS coordinates and the time of the spectroscopic measurement can be sent to a cloud server that has a weather database. The cloud server can then respond by sending weather data corresponding to the requested time and location.

[0047] Spectral data, object data, and environmental data can be received via input terminals or input interfaces. These data can be received through the same input interface or through different input interfaces; for example, spectral data can be received through an input interface communicatively coupled to a spectrometer module, and object and environmental data can be received through input interfaces communicatively coupled to a sensor. Input terminals or input interfaces can be hardware or software components that facilitate the transfer of data from a computer system to external devices or systems. They can include ports, connectors, network cards, and wireless modules that support various data transmission protocols such as USB, HDMI, Ethernet, Bluetooth, and Wi-Fi. Output interfaces manage the encoding, formatting, and transmission of data to ensure compatibility with receiving devices. They can include USB ports for peripheral devices, HDMI ports for video and audio signals, or network interface cards for LAN or internet communication. Software components such as drivers and communication protocols can also be included to ensure correct data transmission. In a cloud-based environment, input interfaces can include virtual interfaces, such as APIs and web services, for data exchange between the local system and the cloud platform.

[0048] Chemometric data of an object can be determined using spectral data, object data, and environmental data. The term "chemometric data" can refer to data associated with any property of an object that can be obtained from spectral data. Chemometric data can be data associated with the physical or chemical properties of an object. Physical properties can include thermal properties such as temperature, thermal conductivity, or specific heat capacity; macroscopic or microscopic states of matter such as crystallinity; optical properties such as refractive index, optical conductivity, or absorption coefficient; and electromagnetic properties such as electrical conductivity, dielectric constant, magnetic permeability, or magnetic susceptibility. Chemical properties of an object typically refer to: the object's chemical composition, including material composition such as the types and concentrations of certain chemical compounds, such as water content; the object's molecular structure, such as the presence of functional groups like carbonyl groups or hydrogen bonds; molecular weight, such as the degree of polymerization of a polymer; and the state of matter, such as crystallinity or aggregated state, such as in a dispersed phase. Chemometric data can include biomarkers as defined above.

[0049] Chemometric data can be determined using chemometric models. The term "chemometric model" can refer to a model that is parameterized to take spectral data, object data, and environmental data as input and output chemometric data. A chemometric model can be parameterized to take spectral data as input and output intermediate chemometric data. Intermediate chemometric data can be chemometric data determined without considering object or environmental data. Intermediate chemometric data can be adjusted or corrected using object and environmental data, for example, by employing a refinement model. The refinement model can be a data-driven model that can be trained using historical data to adjust or correct the intermediate chemometric data. The refinement model can be a multiple linear or multinomial regression model, or it can be an artificial neural network.

[0050] Chemometric data obtained from a chemometric model can be associated with one or more properties (e.g., at least two or three properties). A chemometric model that outputs more than one property can be called a multi-label chemometric model. A multi-label chemometric model can contain several partial chemometric models, where each partial chemometric model can be configured to convert a spectrum into one property. A multi-label chemometric model can be configured to combine chemometric data obtained from at least two partial chemometric models, for example, to output a vector including values ​​for each property.

[0051] A chemometric model may include preprocessing methods and machine learning models to obtain chemometric data. A chemometric model may include preprocessing methods, feature selection filters, and machine learning models. If a chemometric model comprises two or more partial chemometric models, each partial chemometric model may include a separate preprocessing method, feature selection filter, and machine learning model. Alternatively, these partial models may use the same preprocessing method or feature selection filter.

[0052] The term "preprocessing" can refer to methods that reduce or eliminate spectral interferences (such as stray light, noise, or baseline drift) to enhance subsequent machine learning. Therefore, preprocessing methods can be applied before machine learning methods. Preprocessing can include one or more of baseline correction, scattering correction, smoothing, scaling, and aggregation.

[0053] The term "machine learning method" can refer to a model that converts spectra into corresponding object data. Therefore, machine learning methods can use spectra as input and derive object data from them. Machine learning methods can be considered as components of chemometric models. Machine learning methods can be supervised, semi-supervised, or unsupervised. They can include multivariate calibration, classification, pattern recognition, clustering, ensemble methods, neural networks and deep learning, or multivariate curve resolution.

[0054] The term "feature selection filter" can refer to a method used to select those portions of a spectrum that are relevant to the object data. Feature selection filters can facilitate machine learning methods for chemometric models, thereby avoiding overfitting and reducing the amount of training data required. A feature selection filter can take a spectrum as input, remove all unselected portions, and output a spectrum retaining only the selected portions. Therefore, the output of a feature selection filter can be a spectrum represented as a vector, with a dimension lower than the input vector. The output of a feature selection filter can be used as input to machine learning methods. Therefore, feature selection filters can be applied before machine learning methods. The input to a feature selection filter can be a received spectrum or a preprocessed spectrum, preferably a preprocessed spectrum. Therefore, feature selection filters can be applied after preprocessing methods.

[0055] A chemosiometric model can be or may contain a data-driven model. The chemosiometric model can be a trained data-driven model. Training may include adjusting the parameters of the chemosiometric model so that its output best fits the provided training data. Typically, training involves minimizing a loss or cost function, such as the minimum mean square value of the chemosiometric model output and the provided training data. The complete set of training data or a portion thereof can be used for training. A portion of the received training data can be used for training, and the remainder can be used to determine the predictive accuracy of the trained chemosiometric model. Alternatively, cross-validation, such as K-fold cross-validation, leave-one-out cross-validation, or hierarchical cross-validation, can be applied.

[0056] Chemometric models can be configured to determine physical and health information based on the spectrum of a person's skin, such as skin hydration levels or blood glucose or lactose content in the skin, or diseases such as diabetes or skin cancer. The results can be used to provide users with recommendations, for example, adjusting training plans based on skin hydration levels or blood lactose levels.

[0057] Chemometric models can be configured to analyze agricultural products, food products, or feed based on the spectra of: agricultural products, such as fruits, vegetables, meats, and dairy products; food products, such as bread, sauces, sausages, and confectionery; and feed products, such as roughage or forage. For example, a chemometric model can determine relevant content, such as sugar or protein content. The results can be used to provide recommendations, such as providing farmers with expected harvest dates or chefs with suitable recipes.

[0058] Stoichiometric models can be configured to determine recycling-related information based on the spectrum of the object to be recycled (e.g., plastic objects like bottles or metal objects like cans). For example, it can be determined what material the object is made of, such as a bottle being made of polyethylene terephthalate (PET). The results can be used to provide recommendations, such as the most suitable method for recycling the object or the most convenient location for placing the object so that it can be recycled.

[0059] Stoichiometric models can be configured to determine product quality during a production process. Determining product quality can mean defining parameters of a specification, such as the concentration of a component. Product quality can refer to the quality of input materials (e.g., received from a supplier), the quality of intermediates (i.e., materials that have undergone certain processing steps and will undergo further processing steps), and the quality of output materials (e.g., before they are packaged and shipped to the customer).

[0060] Chemometric data generated by a chemometric model can be output. The term "output" can refer to writing chemometric data to a non-transitory data storage medium, such as writing it to a file or database, displaying it on a user interface (e.g., a screen), or both. Chemometric data can also be output to a cloud system via an interface for storage and / or further processing. Output can be achieved through an output terminal or output interface for outputting the chemometric data of the object. The output terminal or output interface can be a hardware or software component that facilitates the transfer of data from a computer system to an external device or system. It can include ports, connectors, network cards, and wireless modules that support various data transmission protocols such as USB, HDMI, Ethernet, Bluetooth, and Wi-Fi. The output interface manages the encoding, formatting, and transmission of data to ensure compatibility with receiving devices. It can include a USB port for peripheral devices, an HDMI port for video and audio signals, or a network interface card for LAN or internet communication. Software components such as drivers and communication protocols can also be included to ensure correct data transmission. In a cloud-based environment, the output interface can include virtual interfaces, such as APIs and web services, for data exchange between the local system and the cloud platform.

[0061] The present invention further relates to a non-transient computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform the method according to the invention. The term "computer-readable data medium" can refer to any suitable data storage device or computer-readable storage device on which one or more sets of instructions (e.g., software) are stored, embodying any one or more of the methods or functions described herein. The instructions may also reside wholly or at least partially in main memory and / or processor during their execution by a computer, main memory, and processing device that can constitute a computer-readable storage medium. These instructions may further be transmitted or received over a network via a network interface device. Computer-readable data media include, for example, hard disk drives on servers, USB storage devices, CDs, DVDs, or Blu-ray discs. The computer program may contain all the functions and data required to perform the method according to the invention, or may provide an interface to allow portions of the method to be processed on a remote system (e.g., a cloud system). Attached Figure Description

[0062] Figure 1 It demonstrates how to acquire spectral data, object data, and environmental data from objects.

[0063] Figure 2 Two examples are shown demonstrating how chemometric data can be derived from spectral data, object data, and environmental data.

[0064] Figure 3 An example of the spectroscopic device of the present invention is shown.

[0065] Figure 4 Another example of the spectroscopic device of the present invention is shown.

[0066] Figure 5 An exemplary user interface of the system of the present invention is shown. Detailed Implementation

[0067] Figure 1This demonstrates the acquisition of spectral data, object data, and environmental data from an object. Spectrometer 101 can illuminate object 103, such as a nutrient, drug, or body part, with a beam 102. The spectrometer may include an infrared light source (e.g., an incandescent lamp or LED) and illumination optics. The infrared beam 102 may contain light within the infrared wavelength range (e.g., 780 nm to 3 µm). The infrared beam can illuminate the object and be reflected back to the spectrometer. This measurement mode is commonly referred to as the reflection mode. Alternatively, the beam 102 can penetrate object 103 and be guided back to spectrometer 101, for example, via a reflector. This measurement mode is commonly referred to as the transmission mode. Spectrometer 101 may include light-collecting optics for capturing the beam 102 propagating from object 103 to spectrometer 101. Spectrometer 101 may include optical elements that spatially or temporally separate different wavelengths of the infrared beam 102 propagating from object 103 to spectrometer 101; these optical elements may be, for example, linearly variable filters, interferometers, or dedicated filters for each sensor element. Spectrometer 101 may include one or more optical sensor elements that generate electrical signals based on the intensity of infrared light incident on the optical sensors. For example, intensity data can be correlated with wavelength data by a processor or microcontroller within the spectrometer. Therefore, spectrometer 101 can output spectral data 104, for example, as a vector of wavelength values ​​and an associated vector of intensity values. Spectral data 104 may be raw data, or it may be correction data, for example, by multiplying by calibration coefficients.

[0068] Sensor 105 can measure object 103 and output object data 106. For example, sensor 105 can be an RGB camera. In this case, object data 106 can be an RGB image of object 103 or characteristics obtained from an RGB image, such as its brightness, average color, or orientation. Obtaining this information may include a processor applying appropriate algorithms to the image. The processor can be part of sensor 105 or part of a computer system communicatively coupled to sensor 105.

[0069] Sensor 107 can record the physical or chemical properties of the environment surrounding object 103, which may affect the measurement results of spectrometer 101. For example, sensor 107 may be a thermometer, hygrometer, or pressure sensor that measures the air environment of object 103. In this case, environmental data 108 may be the temperature, humidity, or atmospheric pressure around the object.

[0070] Figure 2 Two examples are shown demonstrating how chemometric data can be derived from spectral data, object data, and environmental data. Figure 2In step a, spectral data 211 can be input into a chemometric model that includes preprocessing 221, feature selection 222, and a machine learning model 223. Spectral data 211 can include spectra obtained using a spectrometer, such as near-infrared spectra. Preprocessing 221 can include baseline correction (e.g., first-order derivation), scattering correction (e.g., standard normal variables), smoothing (e.g., moving average filtering), scaling (e.g., Pareto scaling), and aggregation (e.g., spatial median). The preprocessed spectral data can then undergo feature selection 222. Feature selection 222 can reduce the dimensionality of the spectral data 211, thus requiring less training data to train the machine learning model 223. Feature selection 222 can, for example, involve principal component regression (PCR). The thus preprocessed and feature-selected spectral data can be passed as input to the machine learning model 223, such as an artificial neural network. The machine learning model 223 can be parameterized to further receive object data 212 and environmental data 213 as further inputs. Object data 212 and environmental data 213 can be preprocessed before being input into the machine learning model 213, for example, to adjust the data format and units. The machine learning model 223 can be trained using historical data including spectral, object, and environmental data. The machine learning model 223 can output stoichiometric data 215. The advantage of using a stoichiometric model that utilizes spectral, object, and environmental data as input is that it can take into account the complex interactions between the spectral, object, and environmental data.

[0071] Figure 2b illustrates an alternative example for determining stoichiometric data from spectral data, object data, and environmental data. Spectral data 211 can be input into a stoichiometric model 231, which outputs intermediate stoichiometric data 232. The stoichiometric model 231 can be unparalleled to take into account object data 212 and environmental data 213. Therefore, the intermediate stoichiometric data 232 depends only on the spectral data 232. To obtain the desired stoichiometric data 234, a refinement model 233 can be employed. The refinement model 233 can be parameterized to receive the intermediate stoichiometric data 232, object data 212, and environmental data 213, and output the stoichiometric data 234. The refinement model 233 can include sub-models, one processing the object data 212 and another processing the environmental data 213. For example, a first sub-model can receive the intermediate stoichiometric data 232 and object data 212 as inputs and output refined stoichiometric data. A second sub-model can use the refined stoichiometric data and environmental data 213 as inputs and output the stoichiometric data 234. The refined model 233 can be a multivariate multinomial regression model that adjusts the intermediate chemometric data 232 based on the object data 212 and the environmental data 213 to obtain the chemometric data 234. The advantage of the refined model 233 is that the chemometric model 231 does not need to be retrained for new object data types or environmental data types.

[0072] Figure 3 An example of a spectroscopic device of the present invention is shown. The spectroscopic device 300 may be a smartphone, tablet computer, or wearable device (such as a smartwatch). The spectroscopic device 300 may include a spectrometer module 310. The spectrometer module 310 may include an illumination device 311. The illumination device 311 may be a light source, such as an incandescent lamp or an LED. The light source may produce electromagnetic radiation within a desired range, such as electromagnetic radiation in the near-infrared range. The illumination device 311 may further include optics for directing electromagnetic radiation from the light source to an object, such as lenses, mirrors, and / or apertures. The spectrometer module 310 may further include a controller 313, such as an ASIC. The illumination device 311 may be operatively coupled to the controller 313. The controller 313 may be powered, for example, from a battery of the portable device 300, and may turn the light source of the illumination device 311 on and off as needed.

[0073] The spectrometer module may further include a detector 312. Detector 312 may generate an electrical signal in response to electromagnetic radiation irradiating it. Detector 312 may comprise an array of photosensitive regions. Each photosensitive region may be covered by a filter such that electromagnetic radiation of a specific wavelength or wavelength range irradiates the photosensitive region. The photosensitive region may be sensitive to a wavelength region of interest (e.g., the near-infrared region). The photosensitive region may contain a photoconductor, such as PbS or PbSe. The photosensitive region may generate a current indicating the intensity of the electromagnetic radiation irradiating it. Detector 312 may include optics to collect the maximum amount of incident electromagnetic radiation. The optics may include mirrors, lenses, and / or apertures.

[0074] Detector 312 may be operatively coupled to controller 313. Controller 313 may collect one or more signals from detector 312 and forward these signals to processor 330. Controller 313 may convert the one or more signals from analog signals to digital signals. This may be achieved, for example, by integrating the current obtained from each photosensitive region and providing the result value in digital form. By combining these values ​​with the source of the photosensitive region (each photosensitive region measures electromagnetic radiation at a specific wavelength or wavelength range), controller 313 may collect spectral data and forward this data to processor 330.

[0075] The spectroscopic device 300 may further include a memory 320, such as RAM or flash memory. The memory 320 may store spectral data, for example, obtained from the spectrometer module 310. The memory may store object data, for example, obtained from different sensors of the spectroscopic device 300 or from a user interface to which the user has input object data. The memory 320 may store environmental data, for example, obtained from different sensors of the spectroscopic device 300 or from a user interface to which the user has input environmental data. The memory 320 may be operatively coupled to the processor 330, so that the processor 330 can receive spectral data, object data, and / or environmental data from the memory 320.

[0076] The spectroscopic device 300 may further include a communication interface 340, such as a Wi-Fi connection to a network or a connection to a telecommunications network. The communication interface 340 may be operatively coupled to the processor 330, so that the processor 330 can receive spectral data, object data, and / or environmental data from the communication interface 340 (e.g., from a cloud computing system).

[0077] The spectral device 300 may further include a camera 350, such as an RGB camera or an infrared camera. The camera 350 can be used to capture images of an object or its environment to obtain object data or environmental data. The camera 350 can be operatively coupled to a processor 330, so that the processor 330 can receive image data from the camera 350. The processor 330 can execute code configured to extract object data or environmental data based on the images received from the camera 350.

[0078] Processor 330 can execute code for the methods described above. Processor 330 can retrieve the code from memory 320. In this example, processor 330 can execute two types of code for the spectrometer, specifically code that uses spectral data, object data, and environmental data (e.g., by executing a chemometric model) to determine chemometric data. Portable device 300 may further include a display (360) for collecting user input and displaying measurement results, for example, via a graphical user interface (GUI).

[0079] Figure 4 Another example of the spectroscopic device of the present invention is shown. The spectroscopic device 420 may be a handheld spectrometer. The spectroscopic device 420 may include an illumination device 421, a detector 422, a controller 423, and a communication interface 424. The illumination device 421 may be a light source, such as an incandescent lamp or an LED. The light source may produce electromagnetic radiation within a desired range, such as electromagnetic radiation in the near-infrared range. The illumination device 421 may further include optics for directing electromagnetic radiation from the light source to an object, such as lenses, mirrors, and / or apertures. The controller 423 may be an ASIC or a microcontroller. The illumination device 421 may be operatively coupled to the controller 423. The controller 423 may be powered, for example, from a battery of the spectroscopic device 420, and may turn the light source of the illumination device 421 on and off as needed.

[0080] Detector 422 can generate an electrical signal in response to electromagnetic radiation incident on it. Detector 422 may comprise an array of photosensitive regions. Each photosensitive region may be covered by a filter such that electromagnetic radiation of a specific wavelength or wavelength range is incident on the photosensitive region. The photosensitive region may be sensitive to a wavelength region of interest (e.g., the near-infrared region). The photosensitive region may comprise a photoconductor, such as PbS or PbSe. The photosensitive region may generate a current indicating the intensity of the electromagnetic radiation incident on it. Detector 422 may include optics to collect the maximum amount of incident electromagnetic radiation. The optics may include mirrors, lenses, and / or apertures.

[0081] Detector 422 can be operatively coupled to controller 423. Controller 423 can convert the one or more signals from analog signals to digital signals. This can be achieved, for example, by integrating the current obtained from each photosensitive region and providing the result value in digital form. By combining these values ​​with the source of the photosensitive region (each photosensitive region measures electromagnetic radiation at a specific wavelength or wavelength range), controller 423 can collect spectral data.

[0082] Communication interface 340 may be a wireless connection to portable device 410. Communication interface 424 may be operatively coupled to controller 423, thus enabling communication interface 424 to transmit spectral data from controller 423 to portable device 410. Portable device 410 may be a smartphone or tablet computer. Portable device 410 may include communication interface 413 for receiving spectral data from spectral device 420. Portable device 410 may include processor 411, such as a CPU. Processor 411 may be operatively coupled to communication interface 413. Processor 411 may receive spectral data from communication interface 413. Processor 411 may be operatively coupled to memory 412. Memory 412 may store stoichiometric models, object data, and environmental data. Processor 411 may use the spectral data, object data, and environmental data to apply stoichiometric models retrieved from memory 412 to determine stoichiometric data. Portable device 410 may further include camera 414, such as an RGB camera, operatively coupled to processor 411. The processor 411 can receive an image of an object from the camera 414 and extract object data from the image, which can be used to determine stoichiometric data. The determined stoichiometric data can be stored in the memory 412 or displayed on the display 414, for example, on a user interface.

[0083] Figure 5An exemplary user interface of the system of the present invention is shown. The user interface can be an application on a computer, a web interface, or located on a spectroscopic device, such as a smartphone with an integrated spectroscopic module. The interface can display a window of a spectroscopic app (e.g., a fitness app 500 designed to measure and track a user's physical fitness level). The interface can have an NIR spectral area 510 displaying recently measured spectra, such as the NIR spectrum of a user's skin. A user can click a button labeled "Measure" 512 to trigger a new measurement, which can then be displayed in the NIR spectral area 510. The fitness app 500 can display an additional data area 520 designed to input or display object data 521 and environmental data 523. In this example, object data 521 could be the user's weight and heart rate. These values ​​can be entered manually or imported from memory or a sensor (e.g., a pulse oximeter). Import can be automatic or manual, such as by clicking a button 522. In this example, environmental data 523 is air temperature and humidity. These values ​​can be entered manually or imported from storage (e.g., a cloud server providing weather data) or sensors (e.g., a thermometer or hygrometer). Import can be automatic or manual, such as by clicking a button 524. The fitness app 500 can display a fitness score 530, which displays chemometric data obtained from a chemometric model that has received spectral data 511, object data 521, and environmental data 523 as inputs and outputs the fitness score. Example

[0084] Example 1: Skin Health

[0085] The health status of a person's skin can be determined. Skin on body parts (e.g., face or hands) can be analyzed. Skin health can be determined by determining skin moisture and / or skin lipid concentration, as skin barrier function depends primarily on these values. Spectroscopic measurements (e.g., by near-infrared spectroscopy) can be performed on the skin of the corresponding body part to collect spectral data. Skin impedance of the corresponding body part can be measured using a stratum corneum moisture meter to collect object data. Skin impedance is known to be related to skin hydration. Alternatively or additionally, skin temperature of the corresponding body part can be measured using a thermometer (e.g., an IR thermometer) to collect object data. Alternatively or additionally, skin color and / or uniformity can be determined using an RGB camera (e.g., a CMOS camera) to collect object data. Ambient temperature and / or humidity can be measured using a thermometer or hygrometer to collect environmental data.

[0086] Spectral data, object data, and environmental data can be input into a chemometric model that outputs skin moisture and / or skin lipid concentrations. Alternatively, the chemometric model can receive spectral data as input and output intermediate values ​​for skin moisture and / or skin lipid concentrations, which can be adjusted by a refinement model using object and environmental data. Skin moisture and / or skin lipid concentrations can be output, or these values ​​can be used to further determine skin health, such as numerical scores or classifiers indicating health status. This determination can be accomplished by comparing the determined skin moisture and / or skin lipid concentrations with reference values. The results can be output, for example, on the user interface of an app on a portable device.

[0087] Example 2: Dermatopathology

[0088] A patient's skin pathology can be determined, for example, to diagnose a disease or record its progression. Examples of skin diseases could be skin cancer, psoriasis, or atopic dermatitis. Regions of interest (ROIs) on a patient's skin (e.g., spots on the skin) can be analyzed using NIR spectroscopy to determine spectral data for these regions. As object data, skin parameters related to the disease or its condition can be collected: skin impedance can be measured using a stratum corneum moisture meter, skin temperature can be measured using a thermometer, skin color or evenness can be measured using a camera (e.g., an RGB camera), or the size of the ROI can be measured using a camera or ruler. As environmental data, geolocation can be determined via GPS sensors or manually entered through a user interface, or the concentration of harmful gases (e.g., benzene or formaldehyde) in the air in which the patient is frequently exposed (e.g., in the workplace) can be determined using gas sensors.

[0089] Spectral and object data can be fed into a chemometric model, which determines the probability of a disease based on the spectral and object data. Environmental data can be used to adjust the probability, such as the statistical correlation between geographical location or exposure to harmful gases and the disease. The output can be the adjusted probability or a classifier indicating positive or negative results based on the probability.

[0090] Example 3: Motion and Fitness Tracking

[0091] A person's physical fitness level can be determined, for example, to track the training process and thus optimize training programs. Biomarkers indicating physical fitness levels can be measured using spectroscopic methods (e.g., Raman spectroscopy). Examples of such biomarkers are blood lactate concentration, body hydration levels, or sweat volume. Spectral data can be collected by measuring specific body parts using a spectrometer. Chemometric models can be used to process spectral data to identify biomarkers.

[0092] Sensors other than spectroscopy can be used to collect object data related to a person's physical fitness level. For example, a thermometer can be used to measure body temperature or skin temperature; a pulse oximeter can be used to measure heart rate, heart rate variability, or peripheral capillary oxygen saturation (spO2); a pressure sensor or accelerometer (e.g., in a pedometer or stationary bike) can be used to measure muscle strength; an electrocardiogram monitor can be used to measure cardiac activity; a sphygmomanometer can be used to measure blood pressure; a scale can be used to measure weight; a ruler can be used to measure height, arm circumference, leg circumference, or abdominal circumference; and a sweat rate monitor can be used to measure sweat rate.

[0093] Environmental data related to human physical fitness levels can be collected using sensors other than spectroscopy. For example, GPS sensors or altimeters can be used to measure geographical location, including altitude; thermometers can be used to measure ambient air temperature; barometers can be used to measure ambient air pressure; humidity sensors can be used to measure ambient air moisture content; and gas sensors (such as electrochemical oxygen sensors) can be used to measure the composition of ambient air (i.e., oxygen or CO2 content).

[0094] Object and environmental data can be used to convert blood lactate concentration or skin moisture levels obtained from spectral data into fitness levels. For example, lactate levels at a specific muscle strength, taking into account ambient air conditions, can produce reliable fitness level results.

[0095] Example 4: Condition-Based Nutrition

[0096] It is desirable to monitor and recommend nutrients based on a person's physical condition or physical activity. A person's physical condition or physical activity can be determined. For this purpose, a spectrometer (e.g., an infrared spectrometer) can be used to record spectral data of the person. One or more characteristics related to a person's physical condition or physical activity can be obtained by feeding the spectral data into a chemometric model. The chemometric model can, for example, output body hydration, blood lactate levels, hemoglobin concentration, blood oxygen saturation, blood glucose levels, or core body temperature.

[0097] Object data can be correlated with a person's physical condition or physical activity determined using methods other than spectroscopy. For example, a thermometer can be used to measure body temperature or skin temperature; a pulse oximeter can be used to measure heart rate, heart rate variability, or peripheral capillary oxygen saturation (spO2); a pressure sensor or accelerometer (e.g., in a pedometer or stationary bike) can be used to measure muscle strength; an electrocardiogram monitor can be used to measure cardiac activity; a sphygmomanometer can be used to measure blood pressure; a scale can be used to measure weight; a ruler can be used to measure height, arm circumference, leg circumference, or abdominal circumference; and a sweat rate monitor can be used to measure sweat rate.

[0098] Environmental data related to human nutritional needs can be collected using sensors other than spectroscopy. For example, GPS sensors or altimeters can be used to measure geographical location, including altitude; thermometers can be used to measure ambient air temperature; barometers can be used to measure ambient air pressure; humidity sensors can be used to measure ambient air moisture content; gas sensors (such as electrochemical oxygen sensors) can be used to measure ambient air composition (i.e., oxygen or CO2 content); and photometers can be used to measure human sun exposure.

[0099] Chemometric data, object data, and environmental data can be used, for example, by using models or reference tables, to determine a person's nutritional requirements. Nutritional requirements can be translated into recommendations for food types and quantities corresponding to those requirements, for example, by using a database of foods with typical nutrient contents, or by using data given on available food packaging, such as the inventory of a supermarket, smart kitchen, or smart refrigerator that registers its food inventory along with food nutrients. Food recommendations can be output to a user interface. The data can be stored for future measurements.

[0100] Example 5: Nutrition Based on Health

[0101] Nutritional recommendations can be determined based on a person's health condition. One or more biomarkers indicative of health status can be identified using spectroscopy; for example, cholesterol levels can be measured using spectroscopy (such as UV-vis spectroscopy). UV-vis measurements can be performed on blood samples to generate spectral data. This spectral data can then be input into a chemometric model that outputs cholesterol levels.

[0102] Sensors other than spectroscopy can be used to collect object data related to a person's health status. For example, a thermometer can be used to measure body temperature or skin temperature; a pulse oximeter can be used to measure heart rate, heart rate variability, or peripheral capillary oxygen saturation (spO2); a pressure sensor or accelerometer (e.g., in a pedometer or stationary bike) can be used to measure muscle strength; an electrocardiogram monitor can be used to measure cardiac activity; a sphygmomanometer can be used to measure blood pressure; a scale can be used to measure weight; and a ruler can be used to measure height, arm circumference, leg circumference, or abdominal circumference.

[0103] Environmental data related to human nutritional needs can be collected using sensors other than spectroscopy. For example, GPS sensors or altimeters can be used to measure geographical location, including altitude; thermometers can be used to measure ambient air temperature; barometers can be used to measure ambient air pressure; humidity sensors can be used to measure ambient air moisture content; gas sensors (such as electrochemical oxygen sensors) can be used to measure ambient air composition (i.e., oxygen or CO2 content); and photometers can be used to measure human sun exposure.

[0104] Biomarkers, object data, and environmental data can be used to develop models for determining a person's nutritional needs. These nutritional needs can then be translated into food recommendations. These recommendations can be tailored to environmental data, such as geographic location, to take into account local dietary habits.

[0105] Example 6: Plant Identification

[0106] Plants or plant parts (such as fruits) can be identified to determine plant varieties and / or the edibility of, for example, mushrooms or berries. Spectral data from plants are obtained by measuring the plant or plant part using a spectrometer (such as an infrared spectrometer).

[0107] Object data related to plant varieties or edibility can be recorded, for example, using RGB images from a camera. Environmental data (such as geographic location) can be determined using GPS sensors or altimeters. Spectral and object data can be provided to stoichiometric models to determine the probabilities of various plant varieties. Environmental data can be used to select the most likely plant varieties, for example, based on the occurrence of such plant varieties in areas determined by geographic location. The resulting plant varieties can then be displayed to the user.

[0108] Example 7: Driver Monitoring

[0109] It can monitor drivers of vehicles (such as cars, trains, or ships) to ensure their driving ability. Spectral data of the driver (e.g., the driver's face) can be obtained from a spectrometer (e.g., a UV-Vis spectrometer). Using stoichiometric models, the spectral data can be used to determine the concentration of alcohol in the driver's breath.

[0110] It can record object data related to the driver's driving ability, such as using an accelerometer to record the driver's movement data, using a pulse oximeter or electrocardiogram monitor to record heart rate and respiratory rate, using facial recognition to record the driver's identity that may be associated with the recorded driver data, using a camera (e.g., a CMOS camera) to record the driver's optical appearance (e.g., redness of the face or eyes), using a thermometer (e.g., an IR thermometer) to record skin temperature or its distribution on the body, and using a ruler or scale, for example, integrated into the driver's seat, to record size and weight.

[0111] It can record environmental data related to the driver's driving ability, such as using GPS sensors to record geographical locations that may be combined with local regulations, using clocks to record the time of day, using thermometers to record ambient temperature, and using gas sensors to record ambient gas concentrations (such as CO2 concentration).

[0112] Data obtained from spectral, object, and environmental data can be combined by a model into indicators that demonstrate driving capabilities. Based on these indicators, access to vehicles can be granted or denied.

[0113] Example 8: Diagnosis of Diabetes

[0114] Early diabetes or a predisposition to developing diabetes can be diagnosed in patients. Spectroscopic data can be obtained from nails, hair, or skin using a spectrometer (such as a NIR spectrometer). Using chemometric models, the levels of glycated keratin can be determined using the spectral data.

[0115] It is possible to obtain object data related to risk factors for diabetes or early diabetes, such as obtaining skin color and structure using a camera (e.g., a CMOS camera), obtaining skin conductivity using a stratum corneum moisture meter, obtaining skin temperature using a thermometer, and measuring heart rate variability or peripheral capillary oxygen saturation (spO2) using a pulse oximeter.

[0116] It is possible to obtain environmental data related to risk factors for diabetes or early diabetes, such as using GPS sensors to obtain geographic location, using clocks to obtain the time of day, using thermometers to obtain ambient temperature, and using gas sensors to obtain ambient gas concentrations (e.g., CO2 concentration).

[0117] Spectral data can be used as an indicator to determine the risk of diabetes or the probability of having diabetes. This indicator can be adjusted using object data and environmental data, which represent risk factors or environmental stresses that can be used to optimize predictive accuracy.

[0118] Example 9: Diabetes Treatment

[0119] Blood glucose levels can be determined to monitor or adjust treatment for diabetic patients. Spectral data can be acquired by measuring body parts (such as skin, hair, or nails) using a spectrometer (e.g., an NIR spectrometer). This spectral data can then be converted into blood glucose levels using chemometric models. In the case of skin measurements, glucose can be detected directly from the blood. In the case of nail measurements, the glycation level of keratin can be determined, allowing for the inference of blood glucose levels.

[0120] It is possible to obtain object data related to blood glucose levels, such as using a blood glucose meter to measure glucose levels through invasive measurement, using a camera (e.g., a CMOS camera) to measure skin color and structure, using a stratum corneum moisture meter to measure skin conductivity, using a thermometer to measure skin temperature, using a pulse oximeter to measure heart rate variability or peripheral capillary oxygen saturation (spO2), and using a blood pressure monitor to measure blood pressure.

[0121] It can obtain environmental data related to blood glucose levels, such as using GPS sensors to obtain geographical location, using clocks to obtain the time of day, using thermometers to obtain ambient temperature, and using gas sensors to obtain ambient gas concentrations (e.g., CO2 concentration).

[0122] Spectral data and data on objects closely related to glucose levels can be used to determine blood glucose levels using chemometric models. Remaining object and environmental data can be further used to determine treatments, such as the amount of insulin or the timing of insulin administration. This information can be displayed to the patient or used to administer treatment, for example, by providing it to the interface of an insulin pump.

[0123] Example 10: Material Characterization

[0124] The composition of materials (such as plastics, fabrics, or wood) can be determined. Spectral data can be obtained using spectrometers (such as NIR spectrometers, UV-Vis spectrometers, or microwave spectrometers). The material composition, such as the classification of plastic types, can be obtained from the spectral data using chemometric models.

[0125] It is possible to obtain object data related to material composition, such as color or surface structure using a camera (e.g., a CMOS camera), radio frequency, microwave or millimeter wave permittivity using appropriate detectors, and conductivity using a conductivity detector.

[0126] It can record environmental data related to the material composition, such as using a thermometer to record ambient temperature, using a humidity sensor to record ambient air humidity, and using a gas sensor to record ambient gas concentration (e.g., CO2 concentration).

[0127] Object and environmental data can be used to improve the confidence level of material testing. For example, if materials are classified, a chemometric model can output the probability of each material type. Object and environmental data can be used to increase or decrease each probability based on the material's characteristics. If two categories have similar probabilities, object and environmental data can be used to more accurately select the correct category. Furthermore, object and environmental data can be used to reduce measurement interference, for example, by inputting them as additional parameters into the chemometric model.

[0128] Example 11: Identification of nutrients in food

[0129] The content of nutrients, such as the amount of fat, protein, carbohydrates, or water in a food, can be determined. This may be especially desirable for prepared foods, as producers do not provide nutritional data, such as for homemade foods (like smoothies or soups) or restaurant foods. Spectrometers (e.g., infrared spectrometers) can be used to record the spectral data of a food. The composition of a food can be obtained by feeding the spectral data into a stoichiometric model that outputs the composition (e.g., the content of fat, protein, carbohydrates, or water).

[0130] It is possible to obtain object data related to nutrient composition, such as obtaining components from images of ingredients or prepared food using a camera (e.g., a CMOS camera), obtaining viscosity using a rheometer, obtaining conductivity using a conductivity meter, or obtaining component weight using a scale (e.g., a scale integrated into a food processing machine).

[0131] It can record environmental data that affects the measurement results of nutrient composition, such as using a thermometer to record the storage temperature of food and using a humidity sensor to record the ambient air humidity.

[0132] Object and environmental data can be used to correct or adjust the nutrient content of food determined by spectroscopic methods. Alternatively, object and environmental data can be additional inputs to a stoichiometric model. Nutrient content can be displayed to the user, for example, on the display of a portable device.

[0133] This disclosure has also been described in conjunction with various preferred embodiments and examples. However, by studying the accompanying drawings, this disclosure, and the claims, those skilled in the art, as well as those who practice the claimed invention, will understand and implement other variations.

[0134] Any steps presented in this document can be performed in any order. The methods disclosed herein are not limited to a specific order of these steps. Nor is it required that different steps be performed in a particular place or on a particular computing node in a distributed system; that is, each step can be performed on different computing nodes using different devices / data processing.

[0135] As used herein, "determine" also includes "initiating or causing determination," "generate" also includes "initiating and / or causing generation," and "provide" also includes "initiating or causing determination, generation, selection, sending, and / or receiving." "Initiating or causing an action" includes any processing signal that triggers a computing node or device to perform a corresponding action.

[0136] In the claims and specification, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude multiple. A single element or other unit can perform the function of several entities or items recited in the claims. The fact that certain measures are recited only in mutually different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation. In the claims and specification, the word "comprising" or similar wording does not exclude other elements or steps and should not be construed as limiting to the listed elements or steps. The indefinite article "a" or "an" does not exclude multiple. A single element or other unit can perform the function of several entities or items recited in the claims. The fact that certain measures are recited only in mutually different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation or can include additional elements.

[0137] Within the scope of this disclosure, provision may include any interface configured to provide data. This may include application programming interfaces, human-machine interfaces (such as displays), and / or software module interfaces. Provision may include transmitting or submitting data to an interface, particularly displaying data to a user or using data by a receiving node, entity, or interface.

[0138] Various units, circuits, entities, nodes, or other computing components may be described as being “configured to” perform one or more tasks. “Configured to” should be interpreted as meaning “having a circuit system that performs one or more tasks during operation.” Units, circuits, entities, nodes, or other computing components may be configured to perform tasks even when the unit / circuit / component is not in operation. Units, circuits, entities, nodes, or other computing components forming a structure corresponding to “configured to” may include hardware circuitry and / or memory storing executable program instructions to perform the operation. For convenience in the description, units, circuits, entities, nodes, or other computing components may be described as performing one or more tasks. This description should be interpreted as including the phrase “configured to.” Any statement of “configured to” is not expressly intended to invoke the interpretation of 35 USC § 112(f).

[0139] Generally, the methods, apparatuses, systems, computer elements, nodes, or other computing components described herein may include memory, software components, and hardware components. Memory may include volatile memory (such as static or dynamic random access memory) and / or non-volatile memory (such as optical or magnetic disk storage devices, flash memory, programmable read-only memory, etc.). Hardware components may include any combination of the following: combinational logic circuit systems, clock storage devices (such as flip-flops, registers, latches, etc.), finite state machines, memory (such as static random access memory or embedded dynamic random access memory), custom-designed circuit systems, programmable logic arrays, etc.

[0140] Any disclosures and embodiments described herein relate to the methods, systems, apparatuses, devices, chemicals, materials, and computer program elements listed above, and vice versa. Advantageously, the benefits provided by any embodiments and examples also apply to all other embodiments and examples, and vice versa. All terms and definitions used herein are to be understood broadly and have their general meanings.

Claims

1. A computer-implemented method for determining stoichiometric data of an object, the method comprising: a) Receive spectral data associated with spectral measurements of the object, object data associated with the characteristics of the object, and environmental data associated with the characteristics of the object's surrounding environment. b) Using the spectral data, the object data, and the environmental data, determine the stoichiometric data of the object. c) Output the stoichiometric data of the object.

2. The method according to claim 1, wherein, The spectral data are correlated with absorption or transmission in the wavelength range of 780 nm to 3 μm.

3. The method according to claim 1 or 2, wherein, The object is a human, and the object's data includes biomarkers.

4. The method according to any one of claims 1 to 3, wherein, In response to a request that includes time and / or geographic location, environmental data is received from the database.

5. The method according to any one of claims 1 to 4, wherein, This chemometric data is correlated with skin health or pathology.

6. The method according to any one of claims 1 to 4, wherein, This chemometric data is correlated with exercise and physical fitness.

7. The method according to any one of claims 1 to 4, wherein, This chemometric data is related to nutrition.

8. The method according to any one of claims 1 to 4, wherein, This chemometric data is linked to the drivers of the monitored vehicles.

9. The method according to any one of claims 1 to 4, wherein, This chemometric data is associated with the diagnosis or treatment of diabetes.

10. The method according to any one of claims 1 to 4, wherein, This chemometric data is correlated with material characterization.

11. Chemometric data of an object obtained by the method of any one of the preceding claims for use in physical, health, nutrition, agricultural or recycling applications.

12. A spectroscopic apparatus for determining stoichiometric data of an object, the spectroscopic apparatus comprising: a) Spectral module, which measures objects and generates spectral data. b) An input terminal for receiving object data associated with the characteristics of the object and environmental data associated with the characteristics that affect the measurement result. c) A processor used to determine the stoichiometric data of the object using the spectral data, the object data, and the environmental data, and d) Output terminal, which is used to output the stoichiometric data of the object.

13. The spectroscopic device according to claim 12, wherein, This spectrometer is a spectrometer module integrated into a smartphone, tablet computer, or wearable device.

14. The spectroscopic device according to claim 12 or 13, wherein, The spectroscopic device is integrated into a portable device, which further includes sensors from which at least a portion of the object data or the environmental data is received.

15. A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising the following steps: a) Receive spectral data associated with spectral measurements of the object, object data associated with the characteristics of the object, and environmental data associated with the characteristics that affect the measurement results. b) Using the spectral data, the object data, and the environmental data, determine the stoichiometric data of the object. c) Output the stoichiometric data of the object.

Images