Dequan Guo

Non-contact behavioral monitoring is important for low-disturbance husbandry of captive forest musk deer, but variable illumination, shadows, partial occlusion, and low target-background contrast can reduce recognition reliability. This study developed HGS-YOLO26n, a lightweight real-time detector for continuous behavior recording under practical captive breeding conditions. HVIEnhanceStem was used to preserve shallow visual cues under weak illumination and low contrast, AdaGFB adapted feature extraction to posture-related shifts in local discriminative regions, and SDIoU improved bounding-box localization under occlusion and target-scale variation. The model was trained and evaluated using 6760 field images collected from 30 enclosures. HGS-YOLO26n achieved an mAP50–95 of 0.8409, exceeding the YOLO26n baseline by 3.74 percentage points, with 2.84 M parameters and an inference speed of 176.8 frames per second. Validation on continuous videos showed that its behavior-duration and event-count estimates were closer overall to blinded manual observations than those of the comparison models. By converting routine surveillance footage into longitudinal, individual-level records of behavior duration, event frequency, and temporal distribution, the system enables efficient review of behavioral activity across extended monitoring periods. Husbandry and veterinary staff can use these records to compare behavioral patterns across observation periods and return to corresponding video segments when specific changes require verification. This provides a low-disturbance source of quantitative behavioral information for routine husbandry, longitudinal observation, and conservation breeding of captive forest musk deer.

Non-contact behavioral monitoring is essential for the low-disturbance husbandry of captive forest musk deer, yet environmental factors such as variable illumination, shadows, and occlusion often hinder automatic recognition accuracy. To address these challenges, this study develops and evaluates a lightweight real-time detector, called HGS-YOLO26n, for behavior recording under practical captive breeding conditions. The model, which integrates visibility adaptation and geometric localization optimiza-tion, is trained on 6,760 field images from 30 enclosures. Results indicate that HGS-YOLO26n achieves an mAP50-95 of 0.8409, outperforming the baseline YO-LO26n by 3.74% while maintaining high efficiency with 2.84M parameters and an in-ference speed of 176.8 frames per second. Validation on continuous video segments demonstrate that the behavioral metrics of the system aligned closely with blinded manual assessments, yielding a consistency score of 96.0 compared to 89.9 for the baseline model. Consequently, this technology effectively converts ordinary surveil-lance footage into quantitative behavioral datasets. These experiments suggest that the proposed HGS-YOLO26n offers a robust, simple and efficient solution for wildlife daily management and welfare monitoring, facilitating standardized veterinary evaluation without imposing additional stress on captive forest musk deer.

In artificial breeding of forest musk deer (Moschus berezovskii), common diseases such as abscess, enteritis, pneumonia, and parasitic infections exhibit persistently high morbidity rates. The early symptoms of certain diseases are often insidious and difficult to discern. Conventional manual inspection routines not only fail to achieve accurate diagnosis but also frequently disturb the animals, induce stress responses, and consequently delay optimal treatment windows. To address this practical challenge, this study employs an improved BRW-GPLinker joint entity-relationship extraction approach to perform integrated extraction and structural organization of disease entities, symptom manifestations, etiological associations, and preventive and therapeutic measures from farming literature and clinical records, thereby constructing a disease knowledge graph for forest musk deer. Through the introduction of a Boundary-Aware Module for refined entity boundary detection, a Relative Distance Bias Module to mitigate pairing errors in dense contexts, and a Weighted Sparse Multi-label Cross-Entropy loss function to enhance recall for infrequent relations, the proposed model achieves an F1 score of 0.887 on a self-constructed dataset and demonstrates favorable generalization capability on medical-domain datasets. By transforming fragmented clinical logs and manuals into structured medical associations, this knowledge graph facilitates rapid retrieval of forest musk deer disease information, thereby enhancing veterinary decision-making efficiency and assisting forest musk deer health management.

The traditional monitoring of forest musk deer behavior primarily relies on direct human observation or the post hoc playback analysis of ordinary surveillance videos. This approach is not only time-consuming and labor-intensive but also highly subjective, easily leading to missing or misjudged critical behavioral information. Moreover, it is difficult to achieve real-time monitoring and anomaly warning. These limitations severely constrain the efficiency of the large-scale artificial breeding of forest musk deer and the effective advancement of wild population conservation. Thus, this study proposes a forest musk deer behavioral recognition method based on an improved YOLOv8-Pose. A forest musk deer behavior image dataset covering four typical behaviors was constructed, and 18 keypoints were systematically annotated. This study designs a Dilated Spatial Pyramid Pooling-Fast (DILATED-SPPF) module and a Multi-scale Depthwise Separable Context Mixer (MDSC-Mixer) module, and integrates them into YOLOv8-Pose. Experimental results show that the improved model outperforms the original YOLOv8-Pose and comparison models such as YOLOv11/v12-Pose on key metrics of object detection (Box-mAP50 0.929, Box-mAP50-95 0.814) and pose estimation (Pose-mAP50 0.879, Pose-mAP50-95 0.565). This study further develops a visual interactive interface that intuitively presents detection results and skeleton structures. This work provides a high-precision, low-cost automated behavior analysis tool for the artificial breeding and wild conservation of forest musk deer with significant application value for enhancing the intelligence level of endangered species protection.

Accurate and timely identification of insect pests is essential for ensuring high-quality and high-yield rice production. In this study, we present VDB-YOLO, an agriculture-oriented pest detection model based on the YOLOv8n architecture and systematically enhanced for complex field conditions. To address key challenges in rice pest detection, including small object size, cluttered backgrounds, and significant inter-class scale variation, we introduce several targeted architectural improvements. First, we augment the backbone with a State Space Model (SSM) mechanism by embedding a VSSBlock module, which combines global contextual modeling with efficient local feature extraction, thereby enhancing feature representation. Second, a densely connected structure is incorporated into the deeper backbone layers to promote feature reuse and reduce information loss during hierarchical propagation. Third, we redesign the neck using a weighted Bidirectional Feature Pyramid Network (BiFPN) to adaptively fuse multi-scale features, improving robustness and reducing scale-related detection errors. Extensive experiments show that VDB-YOLO achieves an mAP@0.5 of 93.3% and an mAP@0.5:0.95 of 59.6%, outperforming the baseline YOLOv8n by 3.5% and 3.3%, respectively. These results demonstrate improved accuracy and reliability in real-world paddy field environments, making VDB-YOLO a practical and generalizable solution for intelligent pest monitoring in precision agriculture.

Real-time recognition of disordered stacking and dumping in warehouse environments remains challenging because packaged goods are often densely stacked, partially occluded, visually similar, and captured from constrained viewpoints, while mobile or unmanned inspection platforms require compact models with low computational overhead. To address these visual and computational challenges, this study proposes GCSE-YOLO, a lightweight detection framework for agricultural cold-storage warehouses. The proposed model is developed from YOLOv5n by reconstructing the backbone with Ghost Convolution, C3Ghost, and ShuffleNetV2 modules to reduce redundant convolutional computation and decrease the model footprint. An Efficient Channel Attention module is incorporated to enhance discriminative feature representation in complex warehouse backgrounds, while Focaler-IoU is adopted to improve bounding-box regression for densely arranged and occluded targets without increasing inference-stage parameters. A real–synthetic warehouse disorder dataset was constructed using operational warehouse images and virtual simulation scenes, covering three disorder levels: slight mess, general mess, and serious mess. Experimental results show that GCSE-YOLO achieves a mean average precision of 97.27% with only 1.358×105 parameters and a model size of 0.54 MB. These results demonstrate that GCSE-YOLO provides an effective and lightweight visual detection framework for warehouse disorder monitoring and offers a practical basis for future integration into mobile or edge-side inspection systems.

Accurate velocity estimation and robust actuator control remain significant challenges for mobile electromechanical systems operating in unstructured and high-vibration environments. Traditional control strategies often suffer from performance degradation due to time-varying sensor noise and nonlinear load disturbances. To address these issues, this study proposes an adaptive closed-loop control framework integrating signal processing and metaheuristic optimization. First, an Adaptive Extended Kalman Filter (AEKF) with a sliding-window innovation covariance estimation is developed to dynamically suppress time-varying noises from BeiDou navigation signals, improving velocity measurement precision under severe vibrations. Subsequently, a mathematical trajectory-matching model is established to generate reference speeds for the execution motor. To achieve rapid and robust tracking, a hybrid Simulated Annealing and Lévy flight-enhanced Particle Swarm Optimization (SA-LPSO) algorithm is proposed to auto-tune the PID controller. The SA-LPSO balances global exploration and local exploitation, effectively overcoming the premature convergence of conventional PSO. Benchmark function tests verify the superior optimization capability of SA-LPSO. Furthermore, comprehensive hardware-in-the-loop and field experiments using a precision seeding system as a case study demonstrate the framework’s effectiveness. Results indicate that the AEKF reduces velocity root mean square error (RMSE) by nearly 50%, while the SA-LPSO significantly minimizes overshoot and settling time. The proposed system achieved a high operational qualification rate of 93% under field disturbances, proving its great potential for smart autonomous systems in complex terrains.

The expansion of captive breeding of the forest musk deer (Moschus berezovskii)—a first-class protected species in China with significant economic and medicinal value—has led to escalating disease threats, underscoring the need for intelligent disease management based on knowledge graphs. However, the unstructured nature of veterinary texts, characterized by nested entities, ambiguous boundaries, and sparse relations, poses substantial challenges to accurate joint entity-relation extraction. To address these issues, this study proposes BRW-GPLinker, an enhanced joint extraction model built upon the GPLinker framework. This model integrates a Boundary-Aware Module (BAM) for precise entity boundary detection, a Relative Distance Bias Module (RDBM) to minimize pairing errors in dense contexts, and a Weighted Sparse Multi-label Cross-Entropy (WSMCE) loss function to improve recall for infrequent relations. Experimental results on the constructed MS-Data dataset demonstrate that BRW-GPLinker achieves an F1 score of 0.887, outperforming the baseline GPLinker by 2.0 percentage points. It also exhibits strong generalization, with an F1 score of 0.590 on the general-domain CMeIE-V2 dataset. These findings confirm that the proposed model provides reliable support for constructing disease knowledge graphs in forest musk deer farming.