Abstract

Device-free Wi-Fi indoor localization is a key enabling technology for Internet of Things (IoT) applications. Machine learning-based location estimators, such as deep neural networks (DNNs), carry proven potential in achieving high-precision localization performance by automatically learning discriminative features from the noisy wireless signal measurements. However, the inner workings of DNNs are not transparent and not adequately understood especially in wireless applications. We provide quantitative and visual explanations for the DNN learning process as well as the critical features that DNN has learned during the process. The results provide insightful views and plausible explanations of the DNN in device-free Wi-Fi indoor localization using channel state information (CSI) fingerprints.

Bio:

Ronald Y. Chang received the B.S. degree in electrical engineering from National Tsing Hua University (NTHU), Hsinchu, Taiwan, in 2000; the M.S. degree in electronics engineering from National Chiao Tung University (NCTU), Hsinchu, in 2002; and the Ph.D. degree in electrical engineering from the University of Southern California (USC), Los Angeles, CA, USA, in 2008. He is currently an Associate Research Fellow (Associate Professor) at the Research Center for Information Technology Innovation (CITI), Academia Sinica, Taipei, Taiwan. He was a recipient of the Best Paper Award from the IEEE Wireless Communications and Networking Conference (WCNC), in 2012, and the Outstanding Young Scholar Award from the Ministry of Science and Technology, Taiwan, in 2015 and 2017, respectively. He was an Exemplary Reviewer of the IEEE Communications Letters, in 2012, the IEEE Transactions on Communications, in 2015, and the IEEE Transactions on Wireless Communications, in 2017.

All faculties and students are welcome to join.