This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
Zn-based thermal charging devices,utilizing the synergistic effect of ion thermoextraction and thermodiffusion,are able to efficiently convert thermal energy into electrical energy and storage in the devices,making th...Zn-based thermal charging devices,utilizing the synergistic effect of ion thermoextraction and thermodiffusion,are able to efficiently convert thermal energy into electrical energy and storage in the devices,making them a highly promising technology for low-grade heat recovery and utilization.However,the low output power density and energy conversion efficiency resulted by the slow diffusion kinetics of Zn^(2+)hinder their development.Herein,we present a highperformance thermal charging cell design using Zn^(2+)/NH_(4)^(+)hybrid ion electrolyte,which not only maintains the high output voltage of the Zn-based thermoelectric system,but also significantly enhances the output power density due to the fast diffusion kinetics of NH_(4)^(+).Based on this strategy,the thermal charging cell displays a high thermopower of 12.5 mV K^(-1)and an excellent normalized power density of 19.6 mW m^(-2)K^(-2)at a temperature difference of 35 K.The Carnot-relative efficiency is as high as 12.74%.Moreover,it can operate continuously for over 72 h when the temperature difference persists,achieving a balance between thermoelectric conversion and output.This work provides a simple and effective strategy for the design of high-performance thermal charging cells for low-grade heat conversion and utilization.展开更多
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
基金supported by the Leading Edge Technology of Jiangsu Province(BK20222009-X.Z.,BK20202008-X.Z.)Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)National Undergraduate Innovation Training Program of NUAA(202410287179Y).
文摘Zn-based thermal charging devices,utilizing the synergistic effect of ion thermoextraction and thermodiffusion,are able to efficiently convert thermal energy into electrical energy and storage in the devices,making them a highly promising technology for low-grade heat recovery and utilization.However,the low output power density and energy conversion efficiency resulted by the slow diffusion kinetics of Zn^(2+)hinder their development.Herein,we present a highperformance thermal charging cell design using Zn^(2+)/NH_(4)^(+)hybrid ion electrolyte,which not only maintains the high output voltage of the Zn-based thermoelectric system,but also significantly enhances the output power density due to the fast diffusion kinetics of NH_(4)^(+).Based on this strategy,the thermal charging cell displays a high thermopower of 12.5 mV K^(-1)and an excellent normalized power density of 19.6 mW m^(-2)K^(-2)at a temperature difference of 35 K.The Carnot-relative efficiency is as high as 12.74%.Moreover,it can operate continuously for over 72 h when the temperature difference persists,achieving a balance between thermoelectric conversion and output.This work provides a simple and effective strategy for the design of high-performance thermal charging cells for low-grade heat conversion and utilization.
