Jia Rui He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jia Rui He has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jiawen Li
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China
2 shared publications - Jujian Lv
Guangdong Polytechnic Normal University
2 shared publications - Kaihan Lin
Guangdong Polytechnic Normal University
2 shared publications - Rongjun Chen
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China
2 shared publications - Jun Yuan
School of computer science Guangdong Polytechnic Normal University Guangzhou China
1 shared publication - Leijun Wang
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China
1 shared publication
Latest Publications
- Open Access
- 17 July 2026
- Published by MDPI AG in Veterinary Sciences
- Vol. 13 (7) , 697
BoviFusionNet: A Lightweight Edge-Deployable AI System for Cattle Behavior Recognition in Livestock Monitoring
This study aims to develop a lightweight, edge-deployable artificial intelligence (AI) system for real-time, non-contact recognition of cattle eating, standing, and lying behaviors in farm environments. Automated monitoring of these behaviors in cattle provides fundamental behavioral data for the future development of systems that analyze feeding duration, lying duration, and behavioral rhythms. Nevertheless, practical deployment on farms is hindered by data imbalance, dense animal groupings, scale variation, occlusion, and the need for low-cost edge computing. To address these challenges, we propose BoviFusionNet, a lightweight, edge-deployable AI system. A box balanced augmentation strategy rebalances training instances at the object level without altering the validation or test sets. Built upon YOLO11n, the model integrates three targeted enhancements: information-preserving downsampling (ADown), adaptive bidirectional feature fusion (BiFPN), and local window attention (C2CGA) to improve multi-scale representation and fine-grained behavior discrimination. Experimental results show that BoviFusionNet achieves 0.7851 recall, 0.7763 F1-score, 0.7976 mAP@0.50, and 0.6305 mAP@0.50:0.95, with only 5.4 GFLOPs and a 3.4 MB model size. Compared with the YOLO11n baseline, it improves mAP@0.50:0.95 by 9.92% and reduces the parameter count by 39.8%. After INT8 quantization and deployment on an RK3588S edge device, real-time inference reaches 28.08 frames per second (FPS). Therefore, BoviFusionNet offers an effective accuracy-complexity trade-off for on-farm edge AI applications. By enabling continuous, non-invasive monitoring of health-relevant behaviors, it provides fundamental behavioral data for the future development of veterinary health assessment tools without relying on cloud services or wearable sensors.
- 17 July 2026
- Published by MDPI AG in Veterinary Sciences
- Vol. 13 (7) , 697
Open AccessBoviFusionNet: A Lightweight Edge-Deployable AI System for Cattle Behavior Recognition in Livestock Monitoring
This study aims to develop a lightweight, edge-deployable artificial intelligence (AI) system for real-time, non-contact recognition of cattle eating, standing, and lying behaviors in farm environments. Automated monitoring of these behaviors in cattle provides fundamental behavioral data for the future development of systems that analyze feeding duration, lying duration, and behavioral rhythms. Nevertheless, practical deployment on farms is hindered by data imbalance, dense animal groupings, scale variation, occlusion, and the need for low-cost edge computing. To address these challenges, we propose BoviFusionNet, a lightweight, edge-deployable AI system. A box balanced augmentation strategy rebalances training instances at the object level without altering the validation or test sets. Built upon YOLO11n, the model integrates three targeted enhancements: information-preserving downsampling (ADown), adaptive bidirectional feature fusion (BiFPN), and local window attention (C2CGA) to improve multi-scale representation and fine-grained behavior discrimination. Experimental results show that BoviFusionNet achieves 0.7851 recall, 0.7763 F1-score, 0.7976 mAP@0.50, and 0.6305 mAP@0.50:0.95, with only 5.4 GFLOPs and a 3.4 MB model size. Compared with the YOLO11n baseline, it improves mAP@0.50:0.95 by 9.92% and reduces the parameter count by 39.8%. After INT8 quantization and deployment on an RK3588S edge device, real-time inference reaches 28.08 frames per second (FPS). Therefore, BoviFusionNet offers an effective accuracy-complexity trade-off for on-farm edge AI applications. By enabling continuous, non-invasive monitoring of health-relevant behaviors, it provides fundamental behavioral data for the future development of veterinary health assessment tools without relying on cloud services or wearable sensors.
- 26 May 2026
- Published by Wiley in Advanced Theory and Simulations
- Vol. 9 (5)
An Improved Data‐Driven Spatio‐Temporal Downscaling Framework for Photovoltaic Power Prediction
Photovoltaic (PV) power prediction methods often exhibit limited accuracy because they rely on low‐resolution numerical weather prediction data that fails to capture microclimate characteristics. To address it, this study proposes a hybrid data‐driven PV prediction framework built around a novel Meteorological Spatial Downscaling Module (MSDM). It first systematically extracts key data features through a Spatio‐Temporal Feature Engineering Module (ST‐FEM). Subsequently, within the MSDM, an Improved Spatial Averaging‐Based Meteorological Field Synthesis (I‐SAMS) method is employed to effectively fuse high‐quality, real‐time meteorological data from neighboring reference stations, generating a high‐resolution, localized meteorological field for the target station. The experimental results demonstrate that the proposed ST‐FEM+I‐SAMS framework achieves significant improvements in prediction performance, reducing the normalized Root Mean Square Error (nRMSE) and normalized Mean Absolute Error (nMAE) by 54.95% and 59.32%, respectively, compared to the baseline model without spatial information. Furthermore, it exhibits robustness under highly variable meteorological conditions. Therefore, these findings indicate that the I‐SAMS method is appropriate for integration with ST‐FEM, which effectively utilizes complex data from neighboring stations as virtual meteorological sensors, providing a cost‐effective, data‐driven solution to improve PV power prediction accuracy.
- 26 May 2026
- Published by Wiley in Advanced Theory and Simulations
- Vol. 9 (5)
An Improved Data‐Driven Spatio‐Temporal Downscaling Framework for Photovoltaic Power Prediction
Photovoltaic (PV) power prediction methods often exhibit limited accuracy because they rely on low‐resolution numerical weather prediction data that fails to capture microclimate characteristics. To address it, this study proposes a hybrid data‐driven PV prediction framework built around a novel Meteorological Spatial Downscaling Module (MSDM). It first systematically extracts key data features through a Spatio‐Temporal Feature Engineering Module (ST‐FEM). Subsequently, within the MSDM, an Improved Spatial Averaging‐Based Meteorological Field Synthesis (I‐SAMS) method is employed to effectively fuse high‐quality, real‐time meteorological data from neighboring reference stations, generating a high‐resolution, localized meteorological field for the target station. The experimental results demonstrate that the proposed ST‐FEM+I‐SAMS framework achieves significant improvements in prediction performance, reducing the normalized Root Mean Square Error (nRMSE) and normalized Mean Absolute Error (nMAE) by 54.95% and 59.32%, respectively, compared to the baseline model without spatial information. Furthermore, it exhibits robustness under highly variable meteorological conditions. Therefore, these findings indicate that the I‐SAMS method is appropriate for integration with ST‐FEM, which effectively utilizes complex data from neighboring stations as virtual meteorological sensors, providing a cost‐effective, data‐driven solution to improve PV power prediction accuracy.