Notice

 
Abstract
This talk considers a multiple-input multiple- output (MIMO) system with low-resolution analog-to-digital converters (ADCs). In this talk, we present a novel approach for solving data detection problems for the MIMO system with low-resolution ADCs. The underlying idea of the proposed framework is to exploit supervised learning. Specifically, in the period of training, the proposed approach sends a sequence of data symbols as pilots so that the receiver learns a nonlinear function that is determined by both a channel matrix and a quantization function of the ADCs. In the period of data transmission, using the estimated nonlinear function from labeled training data, the receiver detects which data symbols were transmitted. We propose three blind detection methods, which are connected to a K-nearest neighbors classification and a nearest-centroid classification. We also provide an analytical expression for the symbol-vector-error probability of the MIMO systems with one-bit ADCs when employing the proposed framework. One major observation is that the symbol- vector-error probability decreases exponentially with the inverse of the number of transmit antennas, the operating signal-to-noise ratio, and the minimum distance that can increase with the number of receive antennas. Simulations demonstrate the performance improvement against existing detection methods.
 
Speaker biography
Namyoon Lee is an assistant professor in the Electrical Engineering Department at POSTECH. He received his Ph. D. in the Department of Electrical and Computer Engineering at The University of Texas at Austin in 2014. He also received his M.S. degree in Electrical Engineering from KAIST, Daejeon in 2008 and B.E. degree from Korea University, Seoul, Korea in 2006. From February 2008 to June 2011, he was with Samsung Advanced Institute of Technology (SAIT) in Korea, where he designed next generation wireless communication systems and involved standardization activities of the 3GPP LTE-A. He was also with Nokia Research Center at Berkeley as a Senior Researcher, where he participated in the design of future WLAN systems (e.g., IEEE 802.11ax and 802.11ay) from December 2014 to May 2015. He was with Wireless Communications Research (WRC) at Intel Labs, Santa Clara, CA from May 2015 to Feb. 2016. His primal research interest is to develop and analyze future wireless communication systems using tools including multi-antenna network information theory, stochastic geometry, and machine learning algorithms. Mr. Lee was a recipient of the 2016 IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award, the 2009 Samsung Best Paper Award, the 2014 Student Best Paper Award (IEEE Seoul Section), and the Recognition Award in Intel Labs 2015. He was also an Exemplary Reviewer for IEEE Wireless Communications Letters in both 2013 and 2015.