学术动态
当前位置: 学院首页 > 学术动态 > 正文

博士生商佐港参加高水平国际会议回国报告

发布时间:2024-04-23 点击数:

汇报时间:2024424日(星期三)930

汇报地点:创新港2号巨构5F-036会议室

国际会议信息

会议名称:2024 IEEE International Conference on Acoustics, Speech and Signal Processing

会议时间:April 14 – April 19, 2024

会议地点:COEX, Seoul, Korea

会议简介:The 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), Seoul, Korea, 14~19 April 2024, is hosted by the IEEE Signal Processing Society.  ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. It offers a comprehensive technical program presenting all the latest development in research and technology in the industry that attracts thousands of professionals annually.  



参会论文信息

Title: ANOMALY DETECTION FROM A FREQUENCY PERSPECTIVE: M-BAND WAVELET PACKET ANOMALY DETECTION NETWORK

Authors: Zuogang Shang, Zhibin Zhao, Xuefeng Chen, and Ruqiang Yan

Abstract: The autoencoder (AE) is widely utilized in deep anomaly detection, but it lacks explainability due to the complexity of nonlinear mapping. One approach to address this issue is incorporating wavelet theory, which shares similarities in decomposition and reconstruction procedures. However, the perfect reconstruction property of wavelet theory conflicts with AE-based anomaly detection. To tackle this problem, we introduce a novel deep anomaly detection method from a frequency perspective. A learnable M-band wavelet network (MWNet) is first designed that offers a flexible frequency band structure for signal representation. Subsequently, with the aid of sparsity constraint, MWNet dynamically focuses on key components within each frequency band. Furthermore, a learnable hard threshold function with a threshold maximization constraint is proposed to retain the essential frequency band of normal signals. Following training, the MWNet is exclusively capable of well reconstructing normal signals, thereby producing a noticeable reconstruction error difference between normal and abnormal signals. Extensive experiments on both simulated and experimental datasets validate the effectiveness of the proposed method.


地址:陕西省西安市咸宁西路28号 邮编:710049
           版权所有:西安交通大学机械学院     站点维护: 网络信息中心 陕ICP备06008037号