MLMingjie Li

Mingjie Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mingjie Li has a total of 45 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Dual-temperature MEMS sensors for progressive thermal-runaway-related gas prediction via a CNN–transformer network

    by Mingjie Li, Jiasheng Li, Sihan Yin, Sha Xu, Ming Zhang

    Early detection of lithium-ion battery (LIB) thermal runaway is essential to prevent disastrous failures. While gas sensor arrays detect characteristic off-gases (H 2 , CO, CH 4 ), a large amount of sensing elements may increase heating power and hardware complexity. We propose a dual-temperature sensing system comprising only two MoS 2 @ZIF-67 microelectromechanical systems (MEMS) gas sensors with a dual-history convolutional neural network (CNN)-Transformer for progressive gas-concentration estimation. The sensors operate simultaneously at constant heater voltages of 2.5 and 3.0 V, providing two resistance channels. Independent CNN–Transformer encoders process short and longer signal histories to estimate H 2 , CO and CH 4 concentrations, followed by causal smoothing using an exponentially weighted moving average (EWMA). Exploratory evaluation on separately acquired 100 and 200 ppm records yielded a total-concentration mean absolute error (MAE) of 31.25 ppm after EWMA smoothing across gas-exposure and clean-air windows. These results establish a proof of concept for progressive three-component concentration estimation in prescribed thermal-runaway-related mixtures using a compact two-sensor configuration with a combined nominal heater power of approximately 48 mW.

  • H 2 and CO identification and concentration prediction using a pulse-driven MEMS gas sensor with multi-feature, multi-task learning

    by Yijun Liu, Wenxin Luo, Sihan Yin, Mingjie Li

    Metal-oxide-semiconductor (MOS) gas sensors are attractive for compact monitoring but remain constrained by cross-reactivity and reliance on steady-state measurements. Here, a suspended Cu–SnO 2 microelectromechanical systems chemiresistor was integrated with a multi-feature, multi-task temporal network for hydrogen (H 2 )/carbon monoxide (CO) identification and quantification. The heater cycled between approximately 90 °C for 0.8 s and 350 °C for 1.6 s at an average power of 19.8 mW. Currents recorded at 10 Hz during 200–900 ppm exposures were transformed into 4.8 s moving-average, Hilbert-envelope, and temporal-derivative channels. Sliding time windows were analyzed using a multi-scale convolutional neural network-squeeze-and-excitation-bidirectional long short-term memory architecture with attention-based classification and gas-specific regression heads. For separately acquired test sequences at 200 and 250 ppm, the three-model ensemble achieved classification accuracy of 99.95% and a gas-only mean absolute error of 25.79 ppm using a 12 s window with a 0.1 s stride in offline replay. These results demonstrate a compact, low-power approach to multi-task gas identification and concentration prediction using a single microsensor.

  • Overcoming Cross-Sensitivity for the Accurate Identification of Acetone, Isopropanol, and Clinical Mixtures Using a MEMS Dual-Sensor Array and Multi-task Deep Learning

    by Sihan Yin, Jiasheng Li, Guanxi Chen, Jianhao Li, Qiaoling Xing, Jin Li, Yichen Li, Wenxin Luo, Ming Zhang, Mingjie Li

    Accurate detection of exhaled acetone (ACE) and isopropanol (IPA) mixtures is critical for the non-invasive screening of diabetic ketoacidosis and the continuous monitoring of lipid metabolism in type 1 diabetes mellitus. However, the broad clinical application of this approach remains severely constrained by the inherent cross-sensitivity of metal oxide semiconductor (MOS) sensors. To address this, a microelectromechanical systems (MEMS) dual-sensor array integrating PdO-modified SnO2/ZnO and MoS2/ZIF-67 nanocomposites was developed for simultaneous gas identification and concentration regression. By pioneering the extraction of distinct transient thermokinetic responses of the materials, combined with a multi-task learning architecture featuring a 1D Convolutional Neural Network and a Bidirectional Long Short-Term Memory (CNN-BiLSTM) network, the system efficiently analyzed dynamic sensing data using a sliding time window (K). At an optimal 15-s window, the model demonstrated robust real-time predictive capabilities, achieving 95.4% classification accuracy and a regression mean absolute error (MAE) of 0.625 ppm across clinical IPA/ACE ratios. This deep learning-enabled framework circumvents traditional steady-state limitations, providing a scalable, low-power solution for precise clinical breathomics and metabolic disease screening.


  • Open Access

    Real-time thermokinetic combinatorial fingerprinting of toxic gases with a MEMS e-nose

    by Jianhao Li, Jiasheng Li, Sihan Yin, Guanxi Chen, Wenxin Luo, Sha Xu, Jing Liu, Shuting Cai, Ming Zhang, Mingjie Li

  • Open Access

    Optimizing dynamic pulsing characteristics for highly sensitive and energy-efficient MEMS hydrogen sensors

    by Wenjun Yan, Wenxin Luo, Sihan Yin, Jianhao Li, Shuting Cai, Ming Zhang, Mingjie Li

    This study characterizes the effects of dynamic pulsing parameters on hydrogen (H2) gas detection using a novel microheater-integrated metal oxide semiconductor (MOS) sensor. The proposed single-device system operates through duty cycling by utilizing repeated pulsed power inputs. The impact of pulse characteristics, specifically the pulse period and duty cycle, on the overall sensor performance is systematically evaluated. The results demonstrate that operating at an optimal pulse period of 2.4 s with a 67% duty cycle provides a 32% enhancement in the hydrogen response without compromising the response time. In addition, this designed duty-cycling strategy significantly reduces energy consumption, achieving a low average power consumption of ∼19.8 mW. Fabricated using wafer-level batch processing techniques, this compact and energy-efficient sensor platform represents a highly scalable and commercially viable solution for integration into power-constrained Internet of Things monitoring applications.


  • Dual-Transduction MEMS Gas Sensor for H 2 and CO Identification Across Humidity

    by Mingjie Li, Wenxin Luo, Jianhao Li, Sihan Yin, Sha Xu, Jing Liu, Yijun Liu, Shuting Cai, Ming Zhang, Wenjun Yan

    Selective discrimination between explosive H2 and CO gases while preserving moisture resistance is of paramount importance. Conventional metal–oxide–semiconductor (MOS) gas sensors suffer from poor selectivity, and reliable multigas identification with a single device remains challenging. Here, we report a microelectromechanical systems (MEMS) gas sensor that integrates two transduction mechanisms, enabling single-sensor gas identification. We demonstrate this innovative approach through the simultaneous measurement of chemiresistive response and temperature change of the sensing layer. Due to gas-specific catalytic exothermic reaction and distinct redox rates on the MOS surface, and maintaining stability under humidity, the relatively independent resistive and calorimetric signals allow robust classifications of H2 and CO gases across humidity conditions using linear discriminant analysis (LDA). We hope our work could resolve the key bottleneck in multigas identification via a single device and offer guidance for intelligent gas sensor technology with compact MEMS platforms.


  • Top Cited Papers

    Identification of H 2 and NH 3 gases using calorimetric signals and transient response through machine learning

    by Wenxin Luo, Yingcong Zheng, Yijun Liu, Mingjie Li

    Selectivity remains a significant challenge for gas sensors. In contrast to conventional gas sensors that depend solely on conductivity to detect gases, we exploited a single NiO-doped SnO 2 sensor to simultaneously monitor transient changes in both sensor conductivity and temperature. The distinct response profiles of H 2 and NH 3 gases were attributed to differences in their redox rates and enthalpy changes during chemical reactions, which provided an opportunity for gas identification using machine learning (ML) algorithms. The test results indicate that preprocessing the extracted calorimetric and chemi-resistive parameters using the principal component analysis (PCA), followed by the application of ML classifiers for identification, enables a 100% accuracy for both target analytes. This work presents a facile gas identification method that enhances chip-level sensor applications while minimizing the need for complex sensor arrays.


  • Top Cited Papers
    Open Access

    Pulse-driven MEMS gas sensor combined with machine learning for selective gas identification

    by Wenxin Luo, Fa Dai, Yijun Liu, Xin Wang, Mingjie Li

    The sensing and identification of trace gases are essential for ensuring chemical safety and protecting human health. This study introduces a low-power electronic nose system that utilizes a single sensor driven by repeated pulsed power inputs, offering a viable alternative to conventional sensor array-based methods. The sensor’s compact design and suspended architecture facilitate a rapid thermal response, effectively decoupling the influences of temperature, physisorption, and charge exchange on the conductivity of the sensing material. This mechanism generates distinct gas sensing responses, characterized by alternating dual responses within a single time period. The unique dynamics of the dual signals, which vary with gas type and concentration, enable precise identification of multiple gas species using machine learning (ML) algorithms. Microfabricated through wafer-level batch processing, our innovative electronic nose system holds significant potential for battery-powered mobile devices and IoT-based monitoring applications.


  • A Single MEMS Sensor Based on SnO₂ Nanosheets for Selective Gas Identification

    by Wenxin Luo, Jianhao Li, Mingjie Li

    In recent years, the challenge of poor selectivity in a single gas sensor has received significant interest. This work presents a facile method for the concurrent analysis of sensor temperature variations and conductivity changes in a SnO2 nanosheets-based gas sensor, enabling the selective detection of various gases (such as H2, NH3, and CO). When exposed to reducing gases, the sensor typically exhibits increases in temperature (calorimetric readout) and current (chemo-resistive readout), resulting from the exothermic reaction between the gases and surface oxygen species. The integrated assessment of temperature elevation and conductivity alterations in a single sensor offers an innovative strategy for gas identification and concentration measurement.