13 February 2023 in IEEE Sensors Journal
In this paper, a convolutional neural network (CNN)-based electronic nose system is proposed that utilizes time series features to classify the freshness of food. The electronic nose is composed of three elements: a highly sensitive miniaturized micro-electromechanical systems (MEMS) Metal Oxide Semiconductor (MOX) gas sensor array, a complementary metal-oxide-semiconductor (CMOS) integrated circuit, and a CNN-based classification unit. The gas sensors exhibit exceptional sensitivity, low power consumption and a small size. The interface circuit for sensor readout is fabricated using a standard 180 nm CMOS process, with an area of 1.5 mm×1.5 mm. The interface chip mainly consists of an analog-to-digital converter (ADC), an electrically erasable programmable read-only memory (EEPROM), an oscillator (OSC), power management, a heater driver and a digital control circuit. Fixed R(t) exposures are taken at specific intervals under gas input and output conditions. Time series features are extracted from a diverse set of sensor signals, which allows the subtle differences in various food odors at different freshness levels to be identified. The incorporation of time series feature extraction extends the data features, resulting in enhanced classification accuracy with a limited number of sensors. An abstract odor map input to the CNN is formed by combining the steady-state and transient information of the gas sensor response. The final freshness classification accuracy of 20 types of foods is 97.3%. The accuracy is improved by 6.5% after the implementation of time series feature extraction, demonstrating the significance of instantaneous fluctuation information for classification accuracy.
12 July 2022 in IEEE Sensors Journal
In this paper, we propose a dataset processing method for odor recognition using neural networks, which extracts the sensor multi-dimensional temperature information and high-dimensional time series information during the response process. In this “sniffing” system, 4 different Micro-Electro-Mechanical System (MEMS) Metal-Oxide-Semiconductor (MOX) gas sensors are utilized, and 4 different heating voltages are applied to the sensor array. After classifying 6 chemical gases closely related to food at 3 different concentrations each, we introduced 10 kinds of food for classification. To construct an abstract odor factor map as a feature map of odor samples, we process each group of different relatively low-bandwidth sensor signals with smoothing spline, Gaussian window, etc. By Inputting the feature map into a specific convolutional neural network, we successfully achieve 98.7% accuracy in chemical gas recognition and 95.8% accuracy in food classification.