Driving behavior recognition based on Frequency-Modulated Continuous-Wave (FMCW) radar systems has become a widely adopted paradigm. Numerous methods have been developed to accurately identify driving behaviors. Recently, deep learning has gained significant attention in radar signal processing due to its ability to eliminate the need for intricate signal preprocessing and its automatic feature extraction capabilities. In this article, we present a network that incorporates multi-scale and channel-time attention modules, referred to as MCT-CNN-LSTM. Initially, a multi-channel convolutional neural network (CNN) combined with a Long Short-Term Memory Network (LSTM) is employed. This model captures both the spatial features and the temporal dependencies from the input radar signal. Subsequently, an Efficient Channel Attention (ECA) module is utilized to allocate adaptive weights to the feature channels that carry the most relevant information. In the final step, domain-adversarial training is applied to extract common features from both the source and target domains, which helps reduce the domain shift. This approach enables the accurate classification of driving behaviors by effectively bridging the gap between domains. Evaluation results show that our method reached an accuracy of 97.3% in a real measured dataset.

In the context of the COVID-19 epidemic, enhancing the transport of analyte to a sensor surface is crucial for rapid detection of biomolecules since common conditions, including low diffusion coefficients, cause inordinately long detection times. Integrated microfluidic immunoassay chips are receiving increasing attention for their low sample volume and fast response time. We herein take advantage of asymmetric ICEO flow at a bipolar sinusoidal electrode to improve the rate of antibody binding to the reaction surface based on finite element modeling. Three different microfluidic cavities are proposed by changing the positions of the surface reaction area. We further investigate the relationship between binding enhancement and reaction surface positions, Damkohler number, and the voltage and frequency of the AC signal applied to the driving electrodes. Furthermore, the influence of the AC signal applied to the sinusoidal bipolar electrode on antigen–antibody-binding performance is studied in detail. Above all, the simulation results demonstrate that the microfluidic immune-sensor with a sinusoidal bipolar electrode could not only significantly improve the heterogeneous immunoassays but also enable efficient enhancement of assays in a selected reaction region within the micro-cavity, providing a promising approach to a variety of immunoassay applications, such as medical diagnostics and environmental and food monitoring.

This paper analyzes graphene irradiation effects using a molecular dynamic simulation software, large-scale atomic / molecular massively parallel simulator (LAMMPS). We propose a hypothesis for the effective range of incident ions based on simulation results of irradiation effects that were found using a suspended single-layer graphene. This explains the influence mechanism of irradiation density on the degree of material defects. This paper does key research on how copper substrate influences a single- and bi-layer graphene. The results show that for a single-layer graphene (SLG) the substrate increases the effective range of the incident ions. Within a certain range of the irradiation density, the substrate enhances the defect production on graphene in low-energy irradiation (<5 keV). However, due to the shielding effect of the substrate, the overall trend of graphene damage will be reduced. For the bi-layer graphene (BLG), the effect of the indirect action range is more obvious than that of the direct-action range. In the case of low irradiation density, the knock-on atoms of BLG are much less than suspended SLG.

Two-dimensional (2D) materials demonstrate significant potential in photodetector technology. They offer high sensitivity, wide spectral range, flexibility and transparency, especially in infrared detection, promising advancements in wearable and flexible electronics. This study explores the application of 2D materials in high-performance photodetectors. Rhenium diselenide (ReSe₂) was used as the channel, and graphene (Gr) was inserted between ReSe₂ and SiO₂ as the gate electrode to enhance device performance. A ReSe₂/Gr heterostructure field-effect transistor (FET) was fabricated to investigate the role of Gr in improving the optoelectronic properties of ReSe₂ phototransistors. Specifically, the ReSe₂ FET without Gr auxiliary layer demonstrates a responsivity (R) of 294 mA/W, an external quantum efficiency (EQE) of 68.75%, and response times as brief as 40/62 ms. Compared with the ReSe₂ phototransistor, the ReSe₂/Gr phototransistor exhibits significantly improved photoresponsivity and EQE, with the photoresponsivity enhanced by a factor of ap-proximately 3.58 and the EQE enhanced by a factor of approximately 3.59. These enhancements are mainly attributed to optimization of interfacial band alignment and the strengthened photogating effect by Gr auxiliary layer. This research not only underscores the pivotal role of Gr in boosting the capabilities of 2D photodetectors but also offers a viable strategy for developing high-performance photodetectors with 2D materials.

Electrocardiographic imaging (ECGI) is a noninvasive technique for reconstructing cardiac electrical activity by recording body-surface potentials and geometric information of the heart and torso. The ECGI forward problem is the cornerstone of ECGI. Depending on the forward model, ECGI can reconstruct epicardial/endocardial surface potentials, activation/recovery sequences, transmembrane voltages, and other electrophysiological quantities of interest. This article reviews the modeling process and research progress of forward modeling. This review systematically summarizes the mathematical methods used in the ECGI forward problem by classifying them into three representative models: the cardiac surface potential (CSP), equivalent double-layer (EDL), and transmembrane voltage (TMV) models, with detailed derivations and guidance on their practical applications.