Convolutional Neural Network-Based Moving Ground Target Classification Using Raw Seismic Waveforms as Input

doi:10.1109/JSEN.2019.2907051

	Convolutional Neural Network-Based Moving Ground Target Classification Using Raw Seismic Waveforms as Input
	Wang, Yan 1; Cheng, Xiaoliu 2; Zhou, Peng1,3,4 ; Li, Baoqing 1; Yuan, Xiaobing 1
	2019-07-15
发表期刊	IEEE SENSORS JOURNAL (IF:4.3[JCR-2023],4.2[5-Year])
ISSN	1530-437X
卷号	19 期号:14 页码:5751-5759
发表状态	已发表
DOI	10.1109/JSEN.2019.2907051
摘要	Seismic vibration signatures are strong criteria to recognize moving ground targets in unattended ground sensor (UGS) systems. However, it is a challenging task because of the complexity of seismic waves and their high dependency on the underlying geology. In order to approach this problem, this paper proposes a novel method called "VibCNN" based on convolutional neural networks (CNNs). Instead of preprocessing signals to extract features, the proposed model takes raw waveforms as input. Another characteristic of the model is that it can handle very short input, which only contains 1024 sample points. The experimental results show that the model yields performance much better than benchmarks and generalizes quite well across different geological types. To further improve the performance of VibCNN, we introduce two auxiliary input channels based on seismic signals and add each auxiliary channel to the input layer of VibCNN separately. Furthermore, we explore different fusion rules of the auxiliary channels at three levels: sample level, feature level, and decision level. The best result achieves relative improvement of 2.05%. In addition, data augmentation for seismic data has not been deeply investigated yet. Thus, we conduce a data augmentation experiment to explore the influence of different augmentation techniques on the performance of the model. The appropriate augmentation improves the accuracy of the model from 93.44% to 95.20%.
关键词	Seismic sensor raw waveform convolutional neural network target classification signal-to-noise ratio standard deviation data augmentation
URL	查看原文
收录类别	EI ; SCIE ; SCI
语种	英语
资助项目	Science and Technology on Microsystem Laboratory[614280401020617]
WOS研究方向	Engineering ; Instruments & Instrumentation ; Physics
WOS类目	Engineering, Electrical & Electronic ; Instruments & Instrumentation ; Physics, Applied
WOS记录号	WOS:000472604000048
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20192707140641
EI主题词	Benchmarking ; Convolution ; Geology ; Neural networks ; Seismic waves ; Signal processing ; Signal to noise ratio ; Unattended sensors
EI分类号	Geology:481.1 ; Seismology:484 ; Earthquake Measurements and Analysis:484.1 ; Information Theory and Signal Processing:716.1 ; Control Instrumentation:732.2
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/34156
专题	信息科学与技术学院_硕士生
通讯作者	Li, Baoqing
作者单位	1.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Sci & Technol Microsyst Lab, Shanghai 201800, Peoples R China 2.ArcSoft Inc, Shanghai 200040, Peoples R China 3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yan,Cheng, Xiaoliu,Zhou, Peng,et al. Convolutional Neural Network-Based Moving Ground Target Classification Using Raw Seismic Waveforms as Input[J]. IEEE SENSORS JOURNAL,2019,19(14):5751-5759.
APA	Wang, Yan,Cheng, Xiaoliu,Zhou, Peng,Li, Baoqing,&Yuan, Xiaobing.(2019).Convolutional Neural Network-Based Moving Ground Target Classification Using Raw Seismic Waveforms as Input.IEEE SENSORS JOURNAL,19(14),5751-5759.
MLA	Wang, Yan,et al."Convolutional Neural Network-Based Moving Ground Target Classification Using Raw Seismic Waveforms as Input".IEEE SENSORS JOURNAL 19.14(2019):5751-5759.