Knowledge Resource Center for Ecological Environment in Arid Area
Discrete Synapse Recurrent Neural Network with Time-Varying Delays for Nonlinear System Modeling and Its Application on Seismic Signal Classification | |
Park, Hyung O.1; Dibazar, Alireza A.2; Berger, Theodore W.3 | |
通讯作者 | Park, Hyung O. |
会议名称 | International Joint Conference on Neural Networks (IJCNN) |
会议日期 | JUL 31-AUG 05, 2011 |
会议地点 | San Jose, CA |
英文摘要 | Discrete Synapse Recurrent Neural Network (DSRNN) using fully Recurrent Neural Network (RNN) structure and Extended Kalman Filter (EKF) algorithm for its training is improved with time-varying delay in its recurrent connection. An additional shadowing network is employed and learned to choose appropriate time delays at the right time in order to increase the memory depth inside the recurrent connection efficiently. As a lumped nonlinear model in capturing temporal dynamics related between input and output sequences, DSRNN with time-varying delay is applied to a task of seismic signal classification to discriminate footsteps and vehicles from background which are recorded in the deserts of Joshua Tree, CA. Even though the smaller sized network was trained from a smaller set of training data due to slow convergence in training, the proposed classifier showed 0.6% false recognition rate for the recognition of human footsteps, 0.8% for vehicle, and 0.0% for background. The models were able to reject quadrupedal animal's footsteps (in this study a trained dog). The system rejected the dog's footsteps with 0.1% false recognition rate. |
来源出版物 | 2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) |
出版年 | 2011 |
页码 | 2374-2381 |
EISBN | 978-1-4244-9636-5 |
出版者 | IEEE |
类型 | Proceedings Paper |
语种 | 英语 |
国家 | USA |
收录类别 | CPCI-S |
WOS记录号 | WOS:000297541202075 |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS研究方向 | Computer Science ; Engineering |
资源类型 | 会议论文 |
条目标识符 | http://119.78.100.177/qdio/handle/2XILL650/300035 |
作者单位 | 1.Univ Southern Calif, Lab Neural Dynam, 1042 Downey Way,DRB140, Los Angeles, CA 90089 USA; 2.Univ Southern California, Lab Neural Dynam, Biomed Engn, San Diego, CA USA; 3.Univ Southern California, Ctr Neural Engn, San Diego, CA USA |
推荐引用方式 GB/T 7714 | Park, Hyung O.,Dibazar, Alireza A.,Berger, Theodore W.. Discrete Synapse Recurrent Neural Network with Time-Varying Delays for Nonlinear System Modeling and Its Application on Seismic Signal Classification[C]:IEEE,2011:2374-2381. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。