Dr. Saeid Sanei, Surrey University, UK:
Man-machine Interaction and Motion Modelling
Biography: Saeid Sanei received his PhD from Imperial College London in 1991. He started his academic work in biomedical image processing and expanded his research into audio-video and acoustic signal processing. Later, he focused more on biomedical signal processing with major focus on brain signal and image understanding and processing. His recent contributions in tensor factorisation include an elegant solution to cocktail party problem which was later extended to blind separation of complex-valued convolutive signals. In another domain, he merged the new achievements in adaptive cooperative learning for communication networks with the estimation of brain connectivity in order to develop a new research direction in brain-computer interfacing and motion modelling. This new area of research has potential for the study of many cognitive, mental, and physical human abnormalities such as Dementia, Parkinson's and Cerebral Palsy. Out of his research he published three monograms and more than 300 papers in refereed journals and prestigious conference proceedings. Recently, he has been the Organizing Chair of the 15th International Conference on Digital Signal Processing, DSP2007, July 2007, Cardiff, UK, General Chair and Organizer of the 15th IEEE Workshop on Statistical Signal Processing, SSP2009 in Cardiff, UK, Honorary Chair of Biosignals 2010, Spain, and General Chair of 23rd IEEE Workshop on Machine Learning for Signal Processing, MLSP 2013, UK. He will be the Technical Chair of European Signal Processing Conference, EUSIPCO 2016, Budapest, Hungary, and General Chair of 44th IEEE Int. Conference on Acoustic, Speech, and Signal Processing, ICASSP in 2019 to be held in Brighton, UK. He has been the Deputy Head of Computing Department, Faculty of Physical Sciences, University of Surrey, UK, for the past three years. He has been the Associate Editor of the IEEE Signal Processing Magazine, IEEE Signal Processing Letters, and the Journal of Computational Intelligence and Neuroscience (JCIN), and the Editor, Guest Editor, and Associate Editor of many other journals.
Abstract: The study of intelligence and intelligent systems, with particular reference to cognitive processing and intelligent behaviour is in debt with the new technological advances in machine learning, cognitive processing, signal and information processing, brain-computer interfacing, and multimedia systems. The amazing area of research in thought-to-action modelling under the influence of a restricted and complex environment has been flourished recently in the light of new achievements in multi-node processing, multiway analysis, and motion modelling. Regularised approaches to motion modelling, which provides a simple but realistic model of thought-to-action, further enhance the performance of such systems under influence of the environment and human-based physiological, physical, and statistical constraints. In this talk, therefore, a new time-space adaptive approach to motion modelling mainly for brain-computer interfacing will be introduced and its applications to a number of other intelligent computational systems will be presented. This research has been inspired by the very recent developments in adaptive and cooperative multi-node networks.
Dr. Joan Lasenby, University of Cambridge, UK:
Applications of Dimensionality Reduction Techniques in Medical Data Analysis
Biography: JL is currently a Senior Lecturer in the Signal Processing Group, Department of Engineering, University of Cambridge, and a Fellow of Trinity College, Cambridge. Her research interests include: computer vision and 3D reconstruction; engineering applications of Geometric Algebra; medical signal and image processing; motion capture and motion analysis for sports and medical applications. She has co-organised a number of International conferences and is the Engineering Syndic for Cambridge University Press. She is also a co-founder of two Cambridge start-up companies and advises/consults in the field of medical signal processing.
Abstract: The talk will look at applying dimensionality reduction techniques to higher dimensional medical datasets, illustrating how such methods both enable real-time analysis and provide us with interesting insights. One application is the analysis of lung function in terms of whole chest-torso movement: the variability and complexity of extracted movement patterns are shown to be related to standard lung function metrics. Another application is gait analysis for rehabilitation: here we will look at how the whole skeleton-fitting pipeline can be streamlined and how changes in motion patterns can be characterised. The emphasis throughout will be carrying out the analysis in a reduced dimension space, working with modes that represent important features of the problems.
Prof. Danilo Mandic, Imperial College, UK:
Computational Intelligence and Wearable Bodysensor Networks
Biography: Dr Mandic is a Professor of Signal Processing at Imperial College London, UK, and has been working in the area of nonlinear, adaptive, and biomedical signal processing. He is a Fellow of the IEEE, member of the Board of Governors of the International Neural Networks Society (INNS), member of the Big Data Chapter within INNS, and has received several best paper awards in Brain Computer Interface. Prof Mandic runs the Smart Environments Lab at Imperial, has more than 300 publications in journals and conferences, and has received President Award for excellence in postgraduate supervision at Imperial.
Abstract: This talk will bring together the latest advances in computational intelligence and signal processing for body sensor networks, focusing on real-world applications for next-generation personalised healthcare, where the sensors must be unobtrusive, self-adminstred and discreet. To this end, we will discuss our own biosensing platform, equipped with multimodal miniatuarised sensors (ECG, EEG, respiration, etc.) and will use this platform to highlight the potential of computational intelligence, and in particular complexity science approaches, when dealing with some common problems of modern mankind such as fatigue, sleep and stress.
Prof. Jonathon Chambers, Newcastle University, UK:
Digital Signal Processing and Assistive Technologies
Biography: Jonathon Chambers FREng FIEEE is Professor of Signal and Information Processing within the School of Electrical and Electronic Engineering at the University of Newcastle and Head of the Communications, Sensors, Signal and Information Processing. He is an expert in adaptive signal processing and its application in biomedicine, communications and defence. He has served as a Senior Area Editor and Associate Editor for IEEE Trans. Signal Processing.
Abstract: The talk will provide an overview of opportunities for digital signal processing in assistive technologies, including assistive living and expression analysis.