Recently, Professor Li Mingjie from the School of Integrated Circuits at Guangdong University of Technology guided undergraduate students in publishing a research paper in ACS Sensors (Zone 1 of the Chinese Academy of Sciences, Impact Factor: 10.9), titled 'Overcoming Cross-Sensitivity for the Accurate Identification of Acetone, Isopropanol, and Clinical Mixtures Using a MEMS Dual-Sensor Array and Multi-task Deep Learning.' Undergraduates Yin Sihan, Li Jiasheng, and Chen Guanxi from the Class of 2023 served as the first, second, and third authors of the paper, respectively. Professor Li Mingjie and Professor Zhang Ming from Hunan University jointly served as the corresponding authors, with Guangdong University of Technology as the first affiliation. The research addresses the cross-sensitivity issue in semiconductor gas sensors by integrating PdO-modified SnO2/ZnO and MoS2/ZIF-67 onto a microelectromechanical systems (MEMS) microheater to construct a dual-sensor array. A multi-task model was established by combining a one-dimensional convolutional neural network with a bidirectional long short-term memory network, leveraging complementary dynamic response information to simultaneously achieve the identification and concentration prediction of acetone, isopropanol, and their simulated clinical mixture gases. Experiments covered acetone, isopropanol, and three predefined mixture gases at concentrations ranging from 5 to 25 ppm. The model, utilizing a 15-second time window, achieved an overall classification accuracy of 95.4% (including the air category) and a mean absolute error of 0.625 ppm for concentration prediction. Prediction results were updated every 15 seconds, reducing reliance on complete steady-state responses. Through the synergistic design of sensitive materials, MEMS devices, and multi-task deep learning, this study accomplished simultaneous gas identification and concentration prediction using only two sensors, effectively enhancing the ability to discriminate between single and mixed gases. It provides a new technological pathway for overcoming cross-sensitivity and developing miniaturized intelligent electronic noses, demonstrating potential applications in the field of portable breath analysis. The research was supported by projects such as the National Natural Science Foundation of China (U25A20491) and the National Key Research and Development Program (2024YFB3614200).