Metal oxide semiconductor (MOS) gas sensors offer several advantages, including low cost, high accuracy, and ease of miniaturization. Thus, they are excellent candidates for environmental monitoring and food spoilage detection applications, particularly in the safe Internet of Things field or for portable instruments. Typically, there are two general routes for realizing low-power-consumption MOS gas sensors: room-temperature MOS gas sensors or MEMS MOS gas sensors. The review focuses on the detection of four typical gases, namely methane, hydrogen, carbon monoxide, and nitrogen dioxide, systematically summarizing and analyzing the most recent results of low-power-consumption MOS gas sensors. The 2D materials, MOS composites, and 3D structured composites exhibit excellent room-temperature gas detection capabilities. The mechanism of the room-temperature gas sensors is also discussed in detail. Another route is MEMS MOS gas sensors. First, the progress of the micro-hotplate research is introduced. Then, several of the latest reported MEMS MOS gas sensors are shown and compared. The gas sensing mechanism of these MEMS MOS gas sensors is also given. The paper will provide a valuable guide for researchers in the MOS gas sensor field, particularly for those working towards low-power-consumption MOS gas sensors.

As new energy vehicles and energy storage systems become more common, safety accidents caused by lithium-ion batteries overheating have become more of a concern. Early detection based on distinctive gases (such as H₂ and CO) can give an earlier warning than typical monitoring methods like temperature, voltage, or impedance. Nonetheless, attaining high-precision identification in intricate mixed-gas settings continues to be difficult because of the considerable cross-sensitivity of metal oxide semiconductor (MOS) gas sensors. This research presents an ISA-LSTM-TCN multi-task learning model utilizing an enhanced spatial attention mechanism for the swift identification and concentration forecasting of distinctive gases during lithium-ion battery thermal runaway. The model improves key feature extraction and anti-noise performance by combining the long-term temporal modeling ability of the Long Short-Term Memory (LSTM) network with the multi-scale feature extraction ability of the Temporal Convolutional Network (TCN). It also adds an Improved Spatial Attention (ISA) module with a residual multiplication structure. Moreover, in a multi-task learning framework, joint optimization of gas categorization and concentration regression is facilitated using a hard parameter-sharing method. Tests using a built MOS sensor array dataset show that the model is 99.23% accurate at classifying gases and that the $R^2$ values for predicting H₂ and CO concentrations are 0.9510 and 0.8400, respectively. Tests on public datasets and in different noisy environments show that the model is even better at generalizing and is more robust. The results show that the suggested method allows for quick, accurate detection of thermal runaway gases. This makes it an effective and smart way to monitor battery safety warning systems.