首页|Reports Outline Machine Learning Study Findings from Xi'an University of Technol ogy (Abnormal Samples Oversampling for Anomaly Detection Based On Uniform Scale Strategy and Closed Area)
Reports Outline Machine Learning Study Findings from Xi'an University of Technol ogy (Abnormal Samples Oversampling for Anomaly Detection Based On Uniform Scale Strategy and Closed Area)
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-Investigators publish new report on Ma chine Learning. According to news reporting originating in Xi'an, People's Repub lic of China, by NewsRx journalists, research stated, "The samples representing abnormal situation is usually very few in the dataset, which makes it difficult to learn the features of abnormal samples by machine-learning-based methods. To improve the accuracy of anomaly detection, the number of abnormal samples should be expanded to ensure the balance of the dataset." Financial supporters for this research include National Key R&D Pro gram of China, National Natural Science Foundation of China (NSFC), Natural Scie nce Foundation of Shaanxi Province, Natural Science Foundation of Shaanxi Provin cial Department of Education, Key Laboratory of Complex System Intelligent Contr ol and Decision, Beijing Institute of Technology. The news reporters obtained a quote from the research from the Xi'an University of Technology, "In this paper, a discrete synthetic minority oversampling techni que (D-SMOTE) is proposed to generate new samples. A closed area is constructed using the three nearest abnormal samples in the dataset. The new samples are the n uniformly interpolated in a closed area. By this means, the problem of the imb alance for the original dataset is handled, thus improving the data quality. Bas ed on the expanded datasets, a two-dimensional convolutional neural network (2D CNN) is constructed to detect abnormal samples. In experiments, three cases and different machine learning methods are considered for comparison. Several indexe s including accuracy, precision, confusion matrix, F1-score, and Recall have bee n used to evaluate the detection effectiveness."
Xi'anPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningXi'an University of Technolog y
NETL
NSTL
