In wideband cognitive radio networks, a key issue is how to choose a channel to sense. A uniformly random channel selection may be inefficient. A recommendation system is proposed to enhance the efficiency of channel selection by exploiting the redundancy of spectrum occupancy in space and time. In such a recommendation system, the secondary users are customers and the channels are different types of goods. When a secondary user finds an available channel, it sends out a recommendation about it. When a new secondary user emerges, it can consult another secondary user for available channels. In such a recommendation system, the following challenges will be addressed: (A) spectrum occupancy prediction: a recommender needs to be able to predict the spectrum occupancy of another location and an unsensed channel when being consulted by a new secondary user; we will apply Belief Propagation based matrix completion to accomplish the spectrum prediction; (B) flavor difference: it is possible that the recommender and the costumer have different flavors (the channel availability may be different for different secondary users); we will use the technique of collaborative filtering to tackle the flavor difference; (C) combating attackers: a recommender could be an attacker and send false recommendations; the anytime multi-armed bandit algorithm will be applied to take a robust action; (D) performance analysis: a recommendation system can be modeled as a Markov chain, in which the state is defined as the number of recommendations, as well as queue lengths at different secondary users.

Host: Lin Zhong

Biography of Husheng Li:
Husheng Li received the BS and MS degrees in electronic engineering from Tsinghua University, Beijing, China, in 1998 and 2000, respectively, and the Ph.D. degree in electrical engineering from Princeton University, Princeton, NJ, in 2005. From 2005 to 2007, he worked as a senior engineer at Qualcomm Inc., San Diego, CA. In 2007, he joined the EECS department of the University of Tennessee, Knoxville, TN, as an assistant professor. His research is mainly focused on statistical signal processing, wireless communications, networking and information theory. He is also interested in the theory of random matrices. Dr. Li is the recipient of the Best Paper Award of EURASIP Journal of Wireless Communications and Networks, 2005 (together with his PhD advisor: Prof. H. V. Poor).