The implementation of low-cost sensitive and selective gas sensors for monitoring fruit ripening and quality strongly depends on their long-term stability. Gas sensor drift undermines the long-term reliability of low-cost sensing platforms, particularly in precision agriculture. We present a real-time drift compensation framework based on a lightweight Temporal Convolutional Neural Network (TCNN) combined with a Hadamard spectral transform. The model operates causally on incoming sensor data, achieving a mean absolute error below 1 mV on long-term recordings (equivalent to <1 particle per million (ppm) gas concentration). Through quantization, we compress the model by over 70%, without sacrificing accuracy. Demonstrated on a combustion-type gas sensor system (dubbed GMOS) for ethylene monitoring, our approach enables continuous, drift-corrected operation without the need for recalibration or dependence on cloud-based services, offering a generalizable solution for embedded environmental sensing—in food transportation containers, cold storage facilities, de-greening rooms and directly in the field.

This is a second part of the paper presenting a miniature, combustion-type gas sensor (dubbed GMOS) based on a novel thermal sensor (dubbed TMOS). The TMOS is a micromachined CMOS-SOI transistor, which acts as the sensing element and is integrated with a catalytic reaction plate, where ignition of the gas takes place. Part 1 focused on the chemical and technological aspects of the sensor. In part 2, the emphasis is on the physical aspects of the reaction micro-hot plate on which the catalytic layer is deposited. The three main challenges in designing the hot plate are addressed: (i) How to design a hot plate operating in air, with a low thermal conductivity; (ii) how to measure the temperature of the hot plate during operation; (iii) how to reduce the total consumed power during operation. Reported simulated as well as analytical models and measured results are in good agreement.

There is an ongoing effort to fabricate miniature, low-cost, and sensitive thermal sensors for domestic and industrial uses. This paper presents a miniature thermal sensor (dubbed TMOS) that is fabricated in advanced CMOS FABs, where the micromachined CMOS-SOI transistor, implemented with a 130-nm technology node, acts as a sensing element. This study puts emphasis on the study of electromagnetic absorption via the vacuum-packaged TMOS and how to optimize it. The regular CMOS transistor is transformed to a high-performance sensor by the micro- or nano-machining process that releases it from the silicon substrate by wafer-level processing and vacuum packaging. Since the TMOS is processed in a CMOS-SOI FAB and is comprised of multiple thin layers that follow strict FAB design rules, the absorbed electromagnetic radiation cannot be modeled accurately and a simulation tool is required. This paper presents modeling and simulations based on the LUMERICAL software package of the vacuum-packaged TMOS. A very high absorption coefficient may be achieved by understanding the physics, as well as the role of each layer.

A novel uncooled thermal sensor based on a suspended transistor, fabricated in standard CMOS-SOI process, and released by dry etching, dubbed Digital TMOS, has been developed. Using the transistor as the sensing element has advantages in terms of internal gain, low power, low-cost technology, and high temperature sensitivity. A two channel radiometer, based on the new nano-metric CMOS-SOI-NEMS Technology, enables remote temperature sensing as well as emissivity sensing of the forehead and body temperatures of people, with high accuracy and high resolution. Body temperature is an indicator of human physiological activity and health, especially in pediatrics, surgery, and general emergency departments. This was already recognized in past pandemics such as SARS, EBOLA, and Chicken Flu. Nowadays, with the spread of COVID-19, forehead temperature measurements are used widely to screen people for the illness. Measuring the temperature of the forehead using remote sensing is safe and convenient and there are a large number of available commercial instruments, but studies show that the measurements are not accurate. The surface emissivity of an object has the most significant effect on the measured temperature by IR remote sensing. This work describes the achievements towards high–performance, low-cost, low power, mobile radiometry, to rapidly screen for fever to identify victims of the coronavirus (COVID-19). The main two aspects of the innovation of this study are the use of the new thermal sensor for measurements and the extensive modeling of this sensor.

This is the fourth part of a study presenting a miniature, combustion-type gas sensor (dubbed GMOS) based on a novel thermal sensor (dubbed TMOS). The TMOS is a micromachined CMOS-SOI transistor, which acts as the sensing element and is integrated with a catalytic reaction plate, where ignition of the gas takes place. The GMOS measures the temperature change due to a combustion exothermic reaction. The controlling parameters of the sensor are the ignition temperature applied to the catalytic layer and the increased temperature of the hotplate due to the released power of the combustion reaction. The solid-state device applies electrical parameters, which are related to the thermal parameters. The heating is applied by Joule heating with a resistor underneath the catalytic layer while the signal is monitored by the change in voltage of the TMOS sensor. Voltage, like temperature, is an intensive parameter, and one always measures changes in such parameters relative to a reference point. The reference point for both parameters (temperature and voltage) is the blind sensor, without any catalytic layer and hence where no reaction takes place. The present paper focuses on the study of the effect of humidity upon performance. In real life, the sensors are exposed to environmental parameters, where humidity plays a significant role. Humidity is high in storage rooms of fruits and vegetables, in refrigerators, in silos, in fields as well as in homes and cars. This study is significant and innovative since it extends our understanding of the performance of the GMOS, as well as pellistor sensors in general, in the presence of humidity. The three main challenges in simulating the performance are (i) how to define the operating temperature based on the input parameters of the heater voltage in the presence of humidity; (ii) how to measure the dynamics of the temperature increase during cyclic operation at a given duty cycle; and (iii) how to model the correlation between the operating temperature and the sensing response in the presence of humidity. Due to the complexity of the 3D analysis of packaged GMOS, and the many aspects of humidity simultanoesuly affecting performane, advanced simulation software is applied, incorporating computational fluid dynamics (CFD). The simulation and experimental data of this study show that the GMOS sensor can operate in the presence of high humidity.

This is the third part of the paper presenting a miniature, combustion-type gas sensor (dubbed GMOS) based on a novel thermal sensor (dubbed TMOS). The TMOS is a micromachined CMOS-SOI transistor, which acts as the sensing element and is integrated with a catalytic reaction plate, where ignition of the gas takes place. The first part was focused on the chemical and technological aspects of the sensor. In Part 2, the emphasis was on the physical aspects of the reaction micro-hot plate on which the catalytic layer is deposited. The present study focuses on applying several advanced simulation tools, which extend our understanding of the GMOS performance, as well as pellistor sensors in general. The three main challenges in simulating the performance are: (i) how to define the operating temperature based on the input parameters; (ii) how to measure the dynamics of the temperature increase during cyclic operation at a given duty cycle; (iii) how to model the correlation between the operating temperature and the sensing response. The simulated and analytical models and measured results are shown to be in good agreement.