摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器学习的新研究是一篇报告的主题。根据中国人民日报天津的新闻报道,NewsRx编辑的研究表明:“海洋最终是塑料废物的汇。复杂的人工海岸线给沿海塑料废物监测带来了巨大挑战。”我们的新闻记者从天津工业大学的研究中获得了一句话：“随着机器学习方法的发展，可以获得很高的检测精度；然而，在用于塑料废物调查的各种网络模型中，存在许多假阳性。在本研究中，利用无人机对天津滨海东江港人工海岸线进行了深入调查,并将InceptionNeXt和LSK模块集成到网络中,增强了Dee P学习模型YOLOv8,提高了对塑料垃圾的检测精度,减少了游客被误认为塑料的情况。利用原模型和改进的YOLOv8模型共获得553幅高分辨率海岸线图像，检测到3488个项目，改进的YOLOv8s-IL模型的检出率为64.9%，比原模型显著提高11.5%，改进的YOLOv8s-IL模型的假阳性率降低到32.3%，多类f-sc矿石达到76.5%。"每幅图像的平均检测时间为only2.7s ."
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting out of Tianjin, People's Repu blic of China, by NewsRx editors, research stated, "Oceans are ultimately a sink of plastic waste. Complex artificial coastlines pose remarkable challenges for coastal plastic waste monitoring." Our news journalists obtained a quote from the research from the Tianjin Univers ity of Technology, "With the development of machine learning methods, high detec tion accuracy can be achieved; however, many false positives have been noted in various network models used for plastic waste investigation. In this study, exte nsive surveys of artificial coastlines were conducted using drones along the Don gjiang Port artificial coastline in the Binhai District, Tianjin, China. The dee p learning model YOLOv8 was enhanced by integrating the InceptionNeXt and LSK mo dules into the network to improve its detection accuracy for plastic waste and r educe instances of tourists being misidentified as plastic. In total, 553 high-r esolution coastline images with 3488 items of detected plastic waste were compar ed using the original and improved YOLOv8 models. The improved YOLOv8s-IL model achieved a detection rate of 64.9%, a notable increase of 11.5% compared with that of the original model. The number of false positives in the i mproved YOLOv8s-IL model was reduced to 32.3%, the multi-class F-sc ore reached 76.5%, and the average detection time per image was onl y 2.7 s."
NETL
NSTL