Xijing University

To address challenges related to complex background interference and insufficient multi-scale target feature extraction in lettuce growth stage detection. The lightweight YOLOv10 detection model and the specific characteristics of lettuce field data were used. The CNCM channel non-local mixture mechanism and ASF adaptive spatial frequency attention mechanism were incorporated to optimize lightweight modules, including DownSample, Zoom_cat, and ScalSeq, within the original model. Consequently, an improved CCASF-YOLOv10 model was constructed, integrating multi-scale feature fusion and enhanced target feature extraction. Experimental results demonstrate that, in an NVIDIA A40 GPU testing environment, the model achieves an accuracy rate of 91.9%, a recall rate of 91.6%, mAP@0.5 of 95.3%, and mAP@0.5:0.95 of 72.9%. The parameter size is 11.9 M, and the single-frame inference speed is 24.76 ms, indicating a favorable balance between detection precision, model efficiency, and real-time inference. Furthermore, an intelligent machine vision detection system for lettuce growth-stage monitoring and precise field control was developed using the CCASF-YOLOv10 model. This system facilitates the industrial advancement of lettuce cultivation.

Modern communication systems increasingly leverage multiple information streams—including channel observations, statistical models, and contextual knowledge—to enhance decoding reliability. However, the varying and often unpredictable quality of these sources poses a critical challenge: rigid combination rules fail when source reliability fluctuates, while manual tuning cannot adapt to dynamic operating conditions. This paper presents a neural decoder architecture that automatically learns to assess and fuse heterogeneous information sources based on their instantaneous reliability. Central to our design is a learnable gating module that dynamically weights information streams, demonstrating emergent Bayesian-like behavior—increasing reliance on statistical models under high uncertainty while transitioning to observation-dominated processing as signal confidence improves. To combat the progressive dilution of auxiliary information in deep architectures, we propose a continuous injection strategy that refreshes auxiliary features at each processing layer through dedicated encoding pathways. The underlying message-passing network adopts a heterogeneous bipartite structure with direction-dependent edge parameterization, respecting the asymmetric computational roles inherent in iterative decoding algorithms. Comprehensive experiments validate that the proposed approach not only improves nominal performance but critically maintains robustness when auxiliary information quality degrades or becomes mismatched with actual conditions.

Student classroom behavior serves as a key indicator for evaluating teaching effectiveness and learning status, and its automated detection is crucial for the advancement of Smart Education. Addressing the limitations of existing classroom behavior detection methods—such as poor real-time performance, high computational complexity, insufficient accuracy in complex classroom settings, and weak differentiation of subtle behaviors—this paper proposes the SCB-YOLO algorithm specifically designed for student classroom behavior detection. Building upon the YOLOv11n framework, this algorithm first incorporates a lightweight Global Edge Information Transfer (GEIT) module to enhance the model’s ability to extract pose contour features such as hand-raising and writing. It then integrates a MANet_Star feature fusion module to improve multi-scale feature fusion efficiency. Experiments on the elementary school scene subset (SCB-Dataset3-S) of the public student classroom behavior dataset SCB-Dataset3 demonstrate that compared to the baseline YOLOv11n, the SCB-YOLO model achieves a 2.6% improvement in mAP@0.5 while maintaining comparable detection speed. Compared to advanced lightweight models like YOLOv12n and YOLOv10n, SCB-YOLO also demonstrates higher detection accuracy and overall superiority in complex classroom scenarios. This indicates that the SCB-YOLO algorithm can effectively address challenges in real teaching environments and possesses strong application potential.