Driver distraction behavior is prone to induce traffic accidents. Therefore, it is necessary to detect them to caution drivers in time for traffic safety. In driver behavior recognition, the variety of behaviors and the diversity of the driving environment can have a certain effect on detection accuracy, and the information loss is severe in most existing methods. These make it challenging to improve the real-time accuracy of driver distraction behavior. In this paper, we propose an improved YOLOv7 based on the channel expansion and attention mechanism for driver distraction behavior detection, named CEAM-YOLOv7. The global attention mechanism (GAM) module focuses on the key information to improve accuracy. With the insertion of GAM into the Backbone and Head of YOLOv7, the global dimensional interaction features are scaled up to enable the network to extract key features. Furthermore, In the CEAM-YOLOv7 architecture, the convolution computation has been significantly simplified, which is conducive to increasing the detection speed. Combined with the Inversion and contrast limited adaptive histogram equalization (CLAHE) image enhancement algorithm, a channel expansion (CE) algorithm for data augmentation is presented to further optimize the detection effect of infrared (IR) images. On the driver distraction IR dataset of Hunan University of Science and Technology (HNUST) and Hunan University (HNU), the verification results show that CEAM-YOLOv7 achieved 20.26% higher mAP compared to the original YOLOv7 model, and the FPS reaches 156, which illustrate that CEAM-YOLOv7 outperforms state-of-the-art methods in both accuracy and speed.

The classification of GM and non-GM maize kernels is fundamental for further analysis of the gene action in maize. Therefore, a complete and novel detection scheme based on near-infrared spectra was designed to distinguish GM and non-GM maize kernels. Hyperspectral images (935–1720 nm) of 777 maize kernels from 3 kinds were captured, and the average spectra of the maize kernels were extracted for modeling analysis. The classical modeling methods based on feature engineering were first studied, and the backpropagation neural network–genetic algorithm model showed the best performance with a prediction accuracy of 0.861. Then, novel modeling methods based on deep learning were developed. To dig out the interactive information between different bands and match the application scenarios, the original spectra were transformed into two-dimensional matrices before establishing the deep learning models. A modified convolution neural network (i.e., VGG net) with dilated convolution was finally constructed to classify the maize kernels, and the prediction accuracy reached 0.961. This research provides a referential and novel way to detect GM maize kernels. Future research will improve the detection scheme for monitoring unauthorized GM organisms by introducing the visualization technology of deep learning.

In order to improve the fault-tolerant control (FTC) ability of the current sensor of the primary permanent magnet linear motor (PPMLM) drive system, the direct thrust force control (DTFC) strategy with single DC-link current sensor is proposed. According to the principle of voltage vector equivalence, the present basic voltage vector is equivalent to two adjacent sub-basic voltage vectors to achieve the equivalence of the present candidate voltage vector. The principle of different phases based on the fact that the DC-link current is equal to or opposite to one of the phase currents is introduced. The output sequence of the two sub-basic voltage vectors is determined by the principle of different phase mode to ensure that the measured currents in the two adjacent periods are any two-phase currents in the three phases, and then the third-phase current is calculated. Finally, the effectiveness and correctness of the proposed DTFC (P-DTFC) is verified by simulation and experiment.

Dual-channel CNN framework integrating 2D spectral domain and frequency features for enhanced SSC and pH detection in grapes and cherry tomatoes.

Transfer learning is widely used in battery remaining useful life prediction for its ability to improve performance with small-sample data. However, the capacity regeneration phenomenon in lithium batteries can reduce transfer learning effectiveness, impacting prediction accuracy. To address this, this paper proposes a remaining useful life prediction method that minimizes capacity regeneration interference during transfer learning. First, transfer learning is categorized into three research scenarios based on whether the source and target domains contain capacity regeneration data. Then, differentiated variational mode decomposition and transfer strategies are designed for each scenario, proposing component-wise independent transfer, feature selection transfer, and target domain independent transfer methods, respectively. Finally, a prediction model is established using a bidirectional long short-term memory neural network. The results show the proposed method effectively reduces capacity regeneration’s impact on transfer learning prediction accuracy across scenarios while maintaining good performance.

Under the “dual carbon” goals, Taiyuan, a prefecture-level administrative unit and energy-intensive region in Shanxi Province, China, has experienced changes in soil carbon storage and soil carbon flux under rapid urbanization and industrialization. To clarify the spatial patterns of soil carbon storage and flux, 26 field sampling sites, including 78 soil samples, were analyzed using laboratory measurements and an optimized tunable diode laser absorption spectroscopy–geographic information system (TDLAS–GIS) integrated monitoring approach. This study investigated the spatial patterns of soil carbon storage and flux and discussed their potentially associated factors, providing an exploratory workflow for regional carbon monitoring. The results showed clear spatial heterogeneity, with an average soil organic carbon (SOC) content of 10.86 g/kg. High-SOC areas were mainly located in the southern and southwestern plains, while lower SOC levels occurred in urban expansion zones and highly disturbed surfaces. The western mountainous areas were important ecological barriers but were not the highest measured SOC zones. At the site level, arable land and forestland showed higher mean SOC values than grassland, with average SOC contents of 12.47, 12.07, and 8.27 g/kg, respectively, although these land-use-related differences were not statistically significant. Soil carbon flux was relatively higher in some mountainous regions and industrial–ecological transition areas but lower in several urban expansion areas. The results suggest that urbanization and industrial activity may be associated with changes in SOC and soil-atmosphere CO₂ exchange. This study describes the spatial variation characteristics of soil carbon storage and flux, establishes a reproducible TDLAS–GIS workflow for regional carbon monitoring, and provides exploratory support for ecological sustainability, sustainable land management, and the “dual carbon” strategy in northern resource-based cities.