A gas sensing device includes gas sensors for generating signal samples corresponding to a concentration of a gas; a heat source for heating the gas sensors according to a first temperature profile during recovery phases and according to a second temperature profile during sense phases, a preprocessing processor for preprocessing the received signal samples; a feature extraction processor for extracting feature values from the preprocessed signal samples; a humidity processor for estimating a humidity value of the mixture of gases, including a first trained model based algorithm processor, and wherein the humidity value is based on an output of the first algorithm processor; a gas concentration processor for creating sensing results, wherein the gas concentration processor comprises a second trained model based algorithm processor, wherein the sensing results are based on output values of the second algorithm processor, and wherein the sensing results depend on the humidity value.

Provided is a method and system for extracting features from raw data for machine learning processing. Using an array of gas sensors, raw data for at least one compound of interest are extracted based upon the type of output signals. Where the output signals are amplitude-variant, mean features are extracted by chunking the raw data into slices and calculating the mean area under the curve. Where the output signals are amplitude-and-time-variant, mean-plus-slope features are extracted by taking logarithmic values of the raw data and calculating the mean area under the curve.

A gas leak detection system that combines sensor units having an array of sensors that detect natural gas and the volatile organic compounds and variable atmospheric conditions that confound existing gas leak detection methods, a specially designed sensor housing that limits the variability of those atmospheric conditions, and a machine learning-enabled process that uses the wide array of sensor data to differentiate between natural gas leaks and other confounding factors. Multiple low-cost sensor units can be used to monitor gas concentrations at multiple locations across a site (e.g., a well pad or other oil or natural gas facility), enabling the gas leak detection system to model gas leak emission rates in two- or three-dimensional space to reveal the most likely origin of the gas leak.

Methods of the disclosed subject matter provide compensation for sensor drift in a hazard detection device having a plurality of sensors coupled to a processor to determine that a carbon monoxide sensor is drifting and to compensate for the drift by calculating a corrected carbon monoxide measurement value based on the ambient environmental conditions.

The present invention makes it possible to represent or synthesize any odor by separating the odor into a combination of a relatively small number of odors, similarly to separating a color into three primary colors. Since the “primary odors” corresponding to the primary colors have not yet been ascertained, the present invention provides a feasible method and apparatus in which, instead of presetting such fixed primary odors, the separation, synthesis, and the like can be performed by selecting a subset of odors from among a set consisting of a plurality of odors which subset or odors enables approximation of other odors as much as possible by mixture.

A gas sensing device includes chemo-resistive gas sensors; heating elements for heating each of the gas sensors; an information extraction block for receiving signal samples and for generating representations for the received signal samples; and a decision making block configured for receiving the representations, wherein the decision making block comprises a weighting block and a trained model based algorithm stage, wherein the weighting block receives feature samples of the representations and applies time-variant weighting functions to the feature samples of the respective representation in order to calculate a weighted representation including weighted feature samples.

According to an embodiment, it is a system, comprising, a specialized device comprising, a flow sub-system configured for sampling a gas sample, a gas chamber having a gas sensor array comprising a configurable sensor interface, wherein the specialized device is operable to collect an aroma signal from the gas sample, a microcontroller comprising a processor and a memory operable to digitalize the aroma signal to obtain aroma data, store and transfer an aroma data, perform an aroma analysis on the aroma data, and provide a feedback to a user, wherein the system is an aroma evaluation system operable to detect a target aroma in real-time, and wherein the system is operable to interface to at least one of a cloud platform and a smartphone.

A gas sensing device includes one or more chemo-resistive gas sensors; one or more heat sources; a preprocessing processor; a feature extraction processor; a discriminative embedding network processor for receiving sets of feature values and for creating for each of the sets of feature values a set of embedded feature values; a classification processor for receiving the sets of embedded feature values and for creating a classification value for each set of the embedded feature values, wherein the classification value indicates a class of a mixture of gases; and a quantification processor for receiving the sets of embedded feature values and the classification values, wherein the quantification processor is creates, for each of the gases, a sensing result for each of the sets of embedded feature values.

In accordance with an embodiment, a sensing device for sensing an environmental parameter includes a measurement module configured for providing a sequence of measurement values in dependence on the environmental parameter; a communication module configured for communicating with a further sensing device; and a function analysis module coupled to the measurement module and the communication module. The function analysis module configured for using a neural network for determining a first temporal feature on the basis of the sequence of measurement values, and determining, on the basis of the first temporal feature and on the basis of a second temporal feature provided by the further sensing device, information about a functional state of the measurement module.

Provided is a method for multi-information fusion of gas sensitivity and chromatography and on-site detection and analysis of flavor substances using an electronic nose instrument. The electronic nose instrument includes a gas sensor array module (I), a capillary gas chromatographic column module (II), an automatic headspace sampling module (III), a computer control and data analysis module (IV), an automatic lifter (V) for headspace sampling, a large-volume headspace vapor generation device (VI) and two auxiliary gas sources (VII-1, VII-2). The electronic nose instrument detects a large number of odorous samples to establish a big odor data. On this basis, the normalization fusion preprocessing is done, and the cascade machine learning model realizes both an on-site recognition of many foods, condiments, fragrances and flavors, and petroleum waxes and a real-time quantitative prediction of their odor quality grades and many key component concentrations.