讲座时间：2012年12月10日（周一）下午2：30-6：00

讲座地点：海韵园行政楼C505报告厅

1、Verity: a wearable sensor system and intelligent processing for ambient assisted living of the elderly and infirm

Public healthcare is facing serious difficulties due to the rapidly growing aging population. Today, there are 7m homes with at least one senior person, with a further 1.2m disabled also living independently. These individuals have a desire to live independently rather than relying on intrusive care and support. They are also at higher risk of suffering from illness, accidents, and injuries in their day-to-day activities. Consequently there is a need for a system that can be conveniently wearable to monitor vital physiological parameters and check health conditions of a user, whilst communicates with health service providers. This talk will present a system Verity intended for the monitoring of the elderly and those requiring passive care, with a wrist-wearable wireless sensor node and a mobile platform to form a remotely accessible body area network. The system utilises a state-of-the art SoC, using an ultra-low power sensor interface and RF communication.Ambient/skin temperatures, accelerations and heart rate of the wearer are measured for real-time monitoring.Due to the high dimension and nonlinearity of the collected sensor data, it is necessary to develop effective behaviour recognition techniques which can find low-dimensional meaningful behaviour patterns hidden in the raw sensor data. The scientific problem for this non-intrusive care scenario is how to extract manageable low-dimensional features for behaviour classification and recognition from high dimensional, multi-modal, nonlinear, temporal and spatial log data of the sensors, which has been demonstrated to be difficult by using the classical techniques. In the Verity system, nonlinear dimension reduction is taken as a general framework for Bayesian estimation of behaviour patterns and abnormality detection is carried out in a low-dimensional space based on a hidden Markov model.

Bio:Ping Jiang is Professor in Computer Science at the University of Hull, UK, where he is the group leader of Intelligent Systems. He received B. Eng., M. Eng. and Ph.D. degrees in Information and Control Engineering from Xi'an Jiaotong University, Xi'an, P.R. China, in 1985, 1988 and 1992, respectively. He was Lecturer, Senior Lecturer and Reader in Robotics and Distributed Systems at University of Bradford from 2003. He was Lecturer in the Department of Electrical Engineering atTongji University, Shanghai, in 1992 and promoted to Associate Professor, in 1994. From 1997, he was Professor in Department of Information and Control Engineering at Tongji University and led the research group of Intelligent Robotics and Intelligent Control.

His research work mainly focuses on intelligent robotics, automation and control, wireless/distributed sensor and actuator networks, multi-agent and virtual organisation. He has been involved in twenty academic research projects funded by British, Chinese, EU and German foundations and published more than 170 research papers. In addition to academic research, he has hands-on experience on hardware and software development and has been involved in more than twenty industrial knowledge transfer projects. From 1998 to 2000, he was an Alexander von Humboldt Research Fellow at Universitaet Erlangen-Nuernberg, Germany. From 2002 to 2003, he was a senior research fellow in Computing at Glasgow Caledonian University for the IST Project DIECoM. In his career, four practical robots were developed, which include a 5DOF educational robot (received the National Scientific and Technical Achievement Award in 1989 and a Silver Medal in the 1990 Beijing International Industry Expo), a 4DOF direct-drive glass-cutting robot, a wheeled mobile robot and recently an autonomous wheelchair controlled by wireless visual sensors.

 2、 Spatial Coding for Large-scale Partial-duplicate Image Search

Bag-of-visual-words model is widely used in the state-of-the-art large-scale image retrieval system. It represents each image as a bag of visual words by quantizing local image descriptors to the closest visual words. However, feature quantization reduces the discriminative power of local features, which causes many false visual word matches. Recently, some geometric verification methods are proposed to check the geometric consistency of matched features in a post-processing step. Although retrieval precision is improved, either the computational cost is too expensive to ensure real-time response, or they are limited to local verification. To address this dilemma, we propose a novel scheme, Spatial Coding, designed for large scale partial-duplicate image retrieval. The spatial relationships among visual words are encoded in global region maps. Based on the region maps, a spatial verification approach is developed, which can detect false matches of local features efficiently, and consequently improve retrieval performance greatly.

Experiments in partial-duplicate image retrieval, using a database of one million images from Image-Net, reveal that our approach can effectively detect duplicate images with rotation, scale changes, occlusion, and background clutter with very low computational cost. The spatial coding achieve an 53% improvement in mean average precision and 46% reduction in time cost over the baseline Bag-of-Visual-Words approach, respectively. They perform even better than full geometric verification while being much less computationally expensive. Our demo on 10-million dataset further reveals the scalability of our approach.

Bio:Qi Tian is currently an Associate Professor in the Department of Computer Science, the University of Texas at San Antonio (UTSA). During 2008-2009, he took one-year Faculty Leave at Microsoft Research Asia (MSRA) in the Media Computing Group. He received his Ph.D. in ECE from University of Illinois at Urbana-Champaign (UIUC) in 2002. Dr. Tian’s research interests focus on multimedia information retrieval and published over 180 refereed journal and conference papers. He received the Best Paper Award in ACM ICIMCS 2012, a Top 10% Paper Award in MMSP 2011, the Best Student Paper Award in ICASSP 2006, and was a co-author of a Best Paper Candidate in PCM 2007. His research projects are funded by NSF, ARO, DHS, Google, FXPAL, NEC, SALSI, CIAS, Akiira Media Systems, HP and UTSA. He received 2010 ACM Service Award. He is the Guest Editors of IEEE Transactions on Multimedia, Journal of Computer Vision and Image Understanding, etc, and is the Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) and in the Editorial Board of Journal of Multimedia (JMM) and Journal of Machine Vision and Applications (MVA).  He is currently a Guest Professor in USTC, Zhejiang University, Xidian University, Xi’an Jiaotong University and a Chaired Professor in Tsinghua University.

 3、Forwarding Games in MANETs

We examine the optimal forwarding problem in mobile ad hoc networks (MANETs) based on a generalized two-hop relay with limited packet redundancy f (f-cast) for packet routing. We formulate such problem as a forwarding game, where each node individually decides a probability p (i.e., a strategy) to deliver out its own traffic and helps to forward other traffic with probability 1−p, while its payoff is the achievable throughput capacity of its own traffic. We derive closed-form result for the per node throughput capacity (i.e., payoff function) when all nodes play the symmetric strategy profiles, identify all the possible Nash equilibria of the forwarding game, and prove that there exists a Nash equilibrium strategy profile that is strictly Pareto optimal. Finally, for any symmetric profile, we explore the possible maximum per node throughput capacity and determine the corresponding optimal setting of f to achieve it.

Bio:Dr.Xiaohong Jiang is currently a full professor of Future University Hakodate, Japan. Before joining Future University, Dr.Jiang was an Associate professor, Tohoku University, from Feb.2005 to Mar.2010. Dr. Jiang’s research interests include computer communications networks, mainly wireless networks and optical networks, interconnection networks for massive parallel computing systems, routers/switches design for high performance networks, network coding for wireless networks, VoIP over wireless networks, network security, VLSI/WSI systems, etc. He has published over 200 technical papers at premium international journals and conferences, which include over 30 papers published in top IEEE journals and top IEEE conferences, like IEEE/ACM Transactions on Networking, IEEE Journal of Selected Areas on Communications, IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Communications, IEEE INFOCOM. Dr. Jiang was the winner of the Best Paper Award and Outstanding Paper Award of IEEE WCNC 2012, IEEE WCNC 2008, IEEE ICC 2005-Optical Networking Symposium, and IEEE/IEICE HPSR 2002. He is a Senior Member of IEEE, a Member of IEICE.