首页|Researchers from Department of Computer Sciences and Engineering Detail Findings in Machine Learning (An Intelligent Machine Learning-enabled Cattle Reclining Risk Mitigation Technique Using Surveillance Videos)
Researchers from Department of Computer Sciences and Engineering Detail Findings in Machine Learning (An Intelligent Machine Learning-enabled Cattle Reclining Risk Mitigation Technique Using Surveillance Videos)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learning have been published. According to news reporting originating in Punjab, India, by NewsRx journalists, research stated, "Public highways are, in reality, the cornerstone of the country's transportation system. Accidents are unavoidable with this mode of transportation." The news reporters obtained a quote from the research from the Department of Computer Sciences and Engineering, "Collisions involving resting livestock on national highways occur in most countries around the world. It endangers both the drivers and the animals. This paper proposes a method for mitigating the risk of accidents caused by deceased animals, notably cattle that are generating traffic and congestion on national highways and may constitute a safety risk. We have proposed an Internet of Things (IoT) fog-based framework for reclining livestock identification techniques for roadways, data are collected using the IoT-enabled video recording surveillance cameras. We use feature extraction, characteristic expression, assessment criteria, and an unrestricted approach for detecting deceased livestock (such as cows or buffalos), as well as recommendations on whether their placement is harmful to highway traffic. In this study, you only look once (YOLO) image recognition algorithm is implemented for reclining cattle on roadways using the fog layer for training and evaluating datasets. The performance parameters of the proposed framework, such as accuracy, recall, precision, mean average precision (mAP), and interference time, have been measured, and a comparison with existing state-of-the-art techniques has been presented. The obtained findings indicate that the suggested framework surpasses the present approaches, with a higher accuracy of 98% and an interference time of 4.68 ms. Artificially intelligent surveillance system can spot reclined livestock utilizing surveillance videos on roadways."
PunjabIndiaAsiaCyborgsEmerging TechnologiesMachine LearningDepartment of Computer Sciences and Engineering
NETL
NSTL
