首页|Wuhan University of Science and Technology Researchers Provide Details of New St udies and Findings in the Area of Machine Learning (Tunnel construction worker s afety state prediction and management system based on AHP and anomaly detection ...)
Wuhan University of Science and Technology Researchers Provide Details of New St udies and Findings in the Area of Machine Learning (Tunnel construction worker s afety state prediction and management system based on AHP and anomaly detection ...)
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-Investigators publish new report on artificial in telligence. According to news originating from Hubei, People's Republic of China , by NewsRx editors, the research stated, "Tunnels represent complex, highrisk, and technically demanding underground construction projects. The safety of cons truction workers in tunnels is influenced by various factors, including physiolo gical indicators, tunnel dimensions, and internal environmental conditions." Our news reporters obtained a quote from the research from Wuhan University of S cience and Technology: "Analyzing safety based solely on static factors is inade quate for modern tunnel engineering safety management requirements. To address t his challenge, this paper provides a comprehensive analysis of factors impacting safety and employs the Analytic Hierarchy Process (AHP) to identify seven signi ficant factors with high importance: body temperature, heart rate, internal temp erature, internal humidity, CO concentration, chlorine concentration, and the re lative positioning of personnel. Considering these factors essential for assessi ng worker safety, we introduce a novel model named Tunnel-APH-AD. For training m odels aimed at anomaly detection, we performed data augmentation and utilized fo ur distinct machine learning models. Additionally, ensemble learning techniques were applied to aggregate the predictions from individual models, thereby enhanc ing the effectiveness of detecting safety states for tunnel workers. We also eva luated the performance of these models on out-of-distribution (OOD) samples to t est their robustness and generalizability. The experimental results indicate that, under similar ventilation and tunnel conditions, the ensemble learning model exhibits superior overall performance compared to individual models, underscorin g the effectiveness of model combination in improving the accuracy and reliabili ty of safety alerts."
Wuhan University of Science and Technolo gyHubeiPeople's Republic of ChinaAsiaAlgorithmsCyborgsEmerging Techn ologiesEngineeringMachine Learning
NETL
NSTL
