Prof. Danny Z. Chen
Professor
Department of Computer Science and Engineering
University of Notre Dame
USA
Title
Computational Medicine: When Computer Science Meets Modern Health Care
Abstract
Computer technology plays a vital role in modern medicine, health care, and life sciences, especially in diagnostic imaging, human genome study, clinical diagnosis and prognosis, treatment planning and optimization, and medical data management. As computing technology continues to evolve, computer science research and development will inevitably become an integral part of modern medicine. Active participation of computational research and applications in modeling, formulating, and solving core problems in medicine and health care is crucially needed. Since computational problems and solutions in modern medicine have direct impacts on the quality of life and well-being in society, the development of effective computational approaches and techniques for medical problems is highly critical. This is the charge and mission of the emerging area of computational medicine.
In this talk, we present a set of important computational problems and approaches in modern medical research, clinical practice, and applications. In particular, we discuss computational problems that arise in medical imaging, clinical diagnosis, and treatment optimization. These include identification and distribution analysis of immune cells (for diagnosis and prognosis of breast cancer, inflammation diseases, and auto-immune diseases, and in stem cell study of leukemia bone marrow micro-environments), image analysis for many 3D medical objects (e.g., blood clots, joint structures, retinal layers, airway and vascular networks, etc), motion tracking of massive swarming bacteria in image movies, optimized radiation cancer treatment, etc. We demonstrate new models for formulating such problems as computational problems, and provide effective approaches for solving them. Further, we show experimental data and results to illustrate the clinical applications of our approaches. Finally, we highlight some important future research trends and problems in this exciting emerging area.
Biography
Prof. Danny Z. Chen received the B.S. degrees in Computer Science and in Mathematics from the University of San Francisco, California, USA in 1985, and the M.S. and Ph.D. degrees in Computer Science from Purdue University, West Lafayette, Indiana, USA in 1988 and 1992, respectively. He has been on the faculty of the Department of Computer Science and Engineering at the University of Notre Dame, Indiana, USA since 1992, and is currently a full Professor. Prof. Chen's main research interests are in computational biomedicine, biomedical imaging, computational geometry, algorithms and data structures, data mining, and VLSI. He has published many journal and conference papers in these areas. He also holds 5 US patents for technology development in computer science and engineering and biomedical applications.
Prof. Chen is a Fellow of IEEE and a Distinguished Scientist of ACM. He received the CAREER Award of the US National Science Foundation (NSF) in 1996, the James A. Burns, C.S.C. Award for Graduate Education of the University of Notre Dame in 2009, and was given a Laureate Award in the 2011 Computerworld Honors Program for the work of his team on "Arc-Modulated Radiation Therapy".
Dr Sriram Chellappan
Associate Professor
Department of Computer Science and Engineering
University of South Florida
U.S.A.
Title
Designing Pervasive Technologies for Managing Mood Disorders– Experimental Studies, Algorithms and App Development
Abstract
Human interactions with Computers (and especially the Internet) are ever increasing, As a consequence, the field of CyberPsychology, which studies the “thinking, behavior and attitudes of the person using the computer” is becoming critical. As of today, existing studies in Cyberpsychology collect Internet usage by means of self-reported surveys only. Unfortunately this method suffers from human errors, social desirability bias, and limits in volume and dimensionality of obtained Internet data. In the first part of the talk, we will present results on numerous experimental studies we have conducted on the feasibility of leveraging statistics from real Internet data collected continuously, unobtrusively, and preserving privacy to assess mood (specifically, mood disorders) using data mining and machine learning algorithms. The second half of the talk will briefly focus on the speaker’s recent efforts in app development to enable superior smart-phone based designs for mood management. In this half, practical challenges in designing technologies for mental healthcare applications will be emphasized as well.
Biography
Sriram Chellappan is an Associate Professor in The Department of Computer Science and Engineering at University of South Florida, where he directs the SCoRe (Social Computing Research) Group. His primary interests lie in many aspects of how Society and Technology interact with each other, particularly within the realms of Smart Health and Cyber Security. He is also interested in Mobile and Wireless Networking, Cyber-Physical Systems, Distributed and Cloud Computing. Sriram's research is supported by grants from National Science Foundation, Department of Education, Army Research Office, National Security Agency, DARPA and Missouri Research Board. Prior to this appointment, he was an Associate Professor in the Computer Science Dept. at Missouri University of Science and Technology . Sriram received the PhD degree in Computer Science and Engineering from The Ohio-State University in 2007. Sriram received the NSF CAREER Award in 2013. He also received the Missouri S&T Faculty Excellence Award in 2014, the Missouri S&T Outstanding Teaching Commendation Award in 2014, and the Missouri S&T Faculty Research Award in 2015.
Prof. Lei Xie
Professor
School of Computer Science
Northwestern Polytechnical University
China
Title
Orange Speech Technologies: Towards a Healthy, Happy and Warm Society
Abstract
Speech is the primary natural communication means between humans. Also, Speech is the most important biosignal humans can produce and perceive. Therefore, speech information processing will definitely contribute a lot to the orange technologies and benefit a healthy, happy and warm modern society. In this invited talk, I will share with you some latest research activities in the area of orange speech technologies conducted in the audio, speech and language processing group in NPU (ASLP@NPU). Specifically, my talk will mainly cover there interesting research topics, namely, voice conversion, personalized and expressive text-to-speech and talking avatars. In each topic, I will talk about their links to an orange society, some technical details about our proposed cutting-edge approaches, experimental evaluations and some demos. Finally, I will point out some promising research directions in orange speech technologies.
Biography
Lei Xie received the Ph.D. degree in computer science from Northwestern Polytechnical University, Xi’an, China, in 2004. From 2001 to 2002, he was with the Department of Electronics and Information Processing, Vrije Universiteit Brussel, Brussels, Belgium, as a Visiting Scientist. From 2004 to 2006, he was a Senior Research Associate with the Center for Media Technology, School of Creative Media, City University of Hong Kong, Hong Kong, China. From 2006 to 2007, he was a Postdoctoral Fellow with the Human-Computer Communications Laboratory, Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong. He is currently a Professor with School of Computer Science, Northwestern Polytechnical University, Xi’an, China. He has published more than 120 papers in major journals and conference proceedings, such as IEEE Transactions on Audio, Speech and Language Processing, IEEE Transactions on Multimedia, Pattern Recognition, ACM/Springer Multimedia Systems, Springer Multimedia Tools and Applications, ACL, ACM Multimedia, ICASSP, Interspeech, ICPR, and ICME. His current research interests include speech and language processing, multimedia, and human-computer interaction. Dr. Xie is a senior member of IEEE and a senior member of China Computer Federation. He serves as the Vice Director of the Speech Information Processing Technical Committee for the Chinese Information Processing Society of China. He has served as program chair, organizing chair, and program/organizing committee member for various major conferences. He was the publication chair of Interspeech2014. He serves as the technical program chair of ICOT2015 and ISCSLP2016.
Dr Guoliang Xing
Associate Professor
Department of Computer Science and Engineering
Michigan State University
U.S.A.
Title
Unobtrusive Smartphone-based Mobile Health Systems: Experiences with Biological Rhythm Monitoring
Abstract
Biological rhythms play a central role in maintaining our daily productivity and well-being, and can be found in almost every essential human body function, including sleep/wakefulness, respiration, walking/running, feeding, etc. In this talk, I will describe two novel smartphone systems for personalized, in-place monitoring of important human biological rhythms, including sleep cycle and running rhythm. We have developed iSleep -- a practical smartphone App to monitor an individual's sleep quality. iSleep uses the built-in microphone to detect the events that are closely related to sleep quality, including body movement, cough and snore, and infers quantitative measures of sleep quality. iSleep adopts a lightweight decision-tree-based algorithm to classify various events based on carefully selected acoustic features. Research has suggested that a proper running rhythm -- the coordination between breathing and strides -- helps to improve exercise efficiency and postpone fatigue. I will present iBreath - the first smartphone-based system for continuous running rhythm monitoring. We propose a novel approach that integrates ambient sensing based on accelerometer and microphone and a physiological model called Locomotor Respiratory Coupling (LRC) to obtain reliable running rhythm measurement. Last, I will briefly discuss several other projects on Cyber-Physical System (CPS), including real-time volcano monitoring, aquatic monitoring using smartphone-based robotic fish, and hardware platforms for building smartphone-based data-intensive embedded sensing applications.
Biography
Guoliang Xing is currently an Associate Professor of Computer Science and Engineering at Michigan State University. His research interests include mobile health, Cyber-Physical Systems for sustainability, smartphone systems, and wireless networking. He received the B.S. degree from Xi’an Jiao Tong University, China, in 1998, and the M.S. and D.Sc. degrees from Washington University in St. Louis, in 2003 and 2006, respectively. His group has developed several mobile health Apps, which won two awards from the Mobile App Competition at MobiCom 2013 and 2014. He is an NSF CAREER Award recipient in 2010. He received two Best Paper Awards and five Best Paper Nominees at ICNP, IPSN, PerCom, and SECON conferences. He received the Withrow Distinguished Junior Faculty Award from Michigan State University in 2014.
Prof. Chung-Hsien Wu
Distinguished Professor
Department of Computer Science and Information Engineering
National Cheng Kung University
Taiwan
Title
Mood Disorder Detection Based on Elicited Speech Responses Using Latent Affective Structure Modeling
Abstract
Mood disorders, including unipolar depression (UD) and bipolar disorder (BD), are reported to be the most common mental illness in recent years. In diagnostic evaluation on the outpatients with mood disorder, a high percentage of BD patients are initially misdiagnosed as having UD. As current research focused on long-term monitoring of the mood disorders, short-term detection which could be used in early detection and intervention and thus reduce the severity of symptoms is desirable. In this work, eliciting emotional videos were firstly used to elicit the patients’ emotions. Speech responses of the patients were collected through the interviews by a clinician after watching each of six emotional video clips. The support vector machine (SVM)-based classifier was adopted to obtain emotion likelihoods for each speech response. Hierarchical spectral clustering was employed to adapt the eNTERFACE emotion database to fit the collected mood database for training a denoising autoencoder to deal with the data bias problem. Finally, a latent affective structure model (LASM) is proposed to characterize the structural relationship among the speech responses to six emotional videos for mood disorder detection. Speech responses from the participants with UDs, BDs and healthy controls were collected to construct the CHI-MEI mood database. Eight-fold cross validation was adopted for the evaluation of the proposed LASM-based approaches. The experimental results show that the proposed LASM-based method achieved a mood detection accuracy of 66.7%, improving by 8.5% compared with the commonly used classifiers like SVM and DNN.
Biography
Chung-Hsien Wu received the B.S. degree in electronics engineering from National Chiao Tung University in 1981, and the M.S. and Ph.D. degrees in electrical engineering from National Cheng Kung University (NCKU), Taiwan, in 1987 and 1991, respectively. Since 1991, he has been with the Department of Computer Science and Information Engineering, NCKU. He became the distinguished professor in 2004. From 1999 to 2002, he served as the Chairman of the Department. He served as the deputy dean of the College of Electrical Engineering and Computer Science, NCKU, in 2009~2015. He also worked at Computer Science and Artificial Intelligence Laboratory of Massachusetts Institute of Technology (MIT), Cambridge, MA, in summer 2003 as a visiting scientist. He received the Outstanding Research Award of National Science Council in 2010 and the Distinguished Electrical Engineering Professor Award of the Chinese Institute of Electrical Engineering, Taiwan, in 2011. He was the associate editor of IEEE Trans. Audio, Speech and Language Processing (2010~2014) and IEEE Trans. Affective Computing (2010~2014). He is currently the associate editor of ACM Trans. Asian and Low-Resource Language Information Processing, and APSIPA Transactions on Signal and Information Processing. Dr. Wu served as the Asia Pacific Signal and Information Processing Association (APSIPA) Distinguished Lecturer and Speech, Language and Audio (SLA) Technical Committee Chair in 2013~2014. His research interests include affective computing, speech recognition/synthesis, and spoken language.
Prof. Ichiro Satoh
Professor
Information Systems Architecture Research Division
National Institute of Informatics (NII)
Japan
Title
Personal-Level Carbon Emission Allowance
Abstract
Carbon Emission Allowance/Credtis are useful to control the quantity of green-house gas (GHG) emission, including carbon dioxide and provide economic incentives for achieving reductions in the emissions of GHG. I proposed a new approach to carbon credit trading with pervasive computing technologies, particularly RFID (or barcode) technology. It introduces RFID tags or barcodes as certificates for the rights to claim carbon credits in carbon offsetting and trading. It enables buyers, including end-consumers, that buy products with carbon credits to hold and claim these credits unlike existing carbon offsetting schemes. It also supports the simple intuitive trading of carbon credits by trading RFID tags or barcodes coupled to the credits.
The approach was already constructed and evaluated in several social experiments with real customers and real carbon credits in a real supply chain, including department stores and super markets, e.g., Sogo and Ito-yokado. One of them was the world-first experiment on trading of personal-level carbon emission credit/allowance. It could also be used to encourage industries and homes to reduce greenhouse gas emissions.
Biography
Ichiro Satoh received his B.E., M.E, and Ph.D. degrees in Computer Science from Keio University, Japan in 1996. From 1996 to 1997, he was a research associate in the Department of Information Sciences, Ochanomizu University, Japan and from 1998 to 2000 was an associate professor in the same department. Since 2001, he has been an associate professor in National Institute of Informatics (NII), Japan, and has been the advisor to the Director General of NII. His current research interests include distributed computing. He has been the chairman of technical working group on personal data in the Japan Cabinet Secretariat.
Dr Shyh-Nan Liou
Associate Professor
Institute of Creative Industries Design
National Cheng Kung University
Taiwan
Title
Cyber I, and Cyber We - How the Internet Creates New Self-identity and Social Life
Abstract
In this talk, I will demonstrate the extent to which the Internet is starting to substitute a friend or work team member as a partner in sharing the daily cognitive tasks and knowledge processing. I will continue discussing the impact of Google effect that people incorporate the Internet into a subjective sense of self, as “the internet has become the external hard drive for our memories” (Wegner & Wade, 2013). I will also highlight the new threatening that the advancement of mobile communication and the social technology makes us well connected but more alone in social media, we now “expect more from technology and less from each other” (Turkle, 2012). How we confuse online sharing with authentic communication and thus setting us up the troubles in how we relate to each other, and blur the lines between mind and machine. In the final, I will discuss Cyber I as new self-identity constructed in internet word, and Cyber we as new social life created by the social media. I reflect the new interaction between cyber world and real world, and identify the challenges and opportunities for future life, in particular for self-identity and social life. I propose research for the creating of an “Inter-mind co-creation” which promote transdisciplinary collaboration among cyber I and cyber we and reflect implications for creativity of the human minds and technology development.
Biography
Dr Shyhnan Liou is currently an associate professor in the Institute of Creative Industries Design, National Cheng Kung University (NCKU). He got his Ph. D. from Dept. of Psychology in National Taiwan University in 1999. He is also the consultant of the Center of Service System Technology in Industry Technology Research Institute (ITRI). He was a visiting scholar at Institute of Social Research and Dept. of Psychology at University of Michigan. He also was the CEO of the Research Center of Creativity, Innovation, and Entrepreneurship at NCKU. He has served as consultant for many research & development institutes include: Biomedical Technology Research & Development Institute in ITRI (2011), Metal Industries Research & Development Center of Biotechnology (2008, 2010).
Dr Liou’s research area is mainly on team creativity processing, organizational innovation in both R&D institutes and creative industries, and transdisciplinary collaboration in integrative research. He have published three books on creativity and decision making, and about fifty journal papers and international conference papers since 1999. Dr Liou recently has promoted establishing the Chinese University of Hong Kong – National Cheng Kung University Joint Research Centre for Positive Social Science to seek to seed and grow an innovative and rigorous integrative positive social science that promotes community building; empowerment and rejuvenation; humanized technology; civic virtues; and personal and collective wellbeing.
Prof. Giovanni Pau
Smart Mobility Chair Professor, Sorbonne University Paris 6
Adjunct Professor, Department of Computer Science, University of California Los Angeles
Title
Social Pervasive Sensing
Abstract
The opportunities offered by the consumer market to mobile computing platforms have been so far mainly exploited with smartphones and a few other gadgets. This is true for both the exchange of data and personal communication purposes, but also for sensing operations. Efficient sensing operations, however, may not always be performed embedding sensor hardware in smartphones or other commonly used hardware devices (e.g., portable music players, etc.). This emerges when addressing the problem of sensing physical quantities (e.g., air pollution), which can hardly be detected from a sensor mounted on a smartphone closed into a pocket.
This talk argues for a Human in the loop approach to pollution sensing thus integrating actual sensor data with perceived pollution data. We will present preliminary results from a several-month long study of Sina Weibo comments and how they are positively or negatively related to the actual pollution levels in some of the world largest cities. Pollution is one of the factors that influences the mood of already distressed urban population.
Biography
Giovanni Pau is the ATOS/Renault smart mobility Chair Professor at the University Pierre at Marie Curie, Paris France. He holds the Italian Laura in Computer Science and the PhD in Computer Engineering awarded by the University of Bologna in 1998 and 2002 respectively. Before Joining UPMC, Prof. Pau was a Senior Research Scientist at the UCLA Computer Science Department where he retains the position of Adjunct Professor.
Prof. Pau core research interests are in Network Systems with focus on Vehicular Networks and pervasive mobile sensor systems. He designed and built the UCLA campus vehicular testbed and the UCLA/MPI urban sensing testbed designed to enable hands-on studies on vehicular communications and urban sensing. His research contributions lead to the VERGILIUS and CORNER simulation suites designed to support mobility and propagation modeling in urban environments. More recently, Prof. Pau designed and developed VNDN the Named Data Network (NDN) protocol stack specifically adapted to work on mobile-to-mobile scenarios.
Prof. Keith Chan
Dean of Students
Professor
Department of Computing
The Hong Kong Polytechnic University
Hong Kong
Title
Big Data Analytics and Smart Home Technology for Autism Spectrum Disorder Diagnosis and Therapy
Abstract
In recent years, autism spectrum disorder (ASD) has been considered the most common developmental disability in many parts of the world. There has been a record number of cases of children diagnosed to have the disease at a very young age. Despite over 60 years of effort to investigate into the causes, the etiology of ASD is still not clear. There has been some evidence that both genetic and non-genetic factors may probably have a role to play. Families that have ASD children may find their situations most difficult to cope as they are usually not only under tremendous emotional pressure having to look after their children but also have to bear great financial burden having to pay for the therapy. What is most unfortunate is that, although there are some therapies or treatments available, such as applied behavioral analysis (ABA), speech & language therapy, sensory integration, and acupuncture, there is still no effective drug except through the slow process of education and training.
According to the National Center on Birth Defects and Development Disabilities of the Centers for Disease Control and Prevention in the U.S., early identification is the most powerful tool one can use right now to make a difference in the lives of children with autism. For the purpose of diagnosing ASD at an earlier age, various methodologies have been developed and are being utilized. Most of them involves the use of behavioral checklists. Even though they were developed in the old days, ASD checklist is still the most popular among doctors and other clinical professionals. Despite being widely accepted, these checklists do not represent the most effective way to diagnose ASD. To a large extent, these checklists can only be used subjectively by non-experts who may not be trained to observe and properly use them. Very often, there are reports of false diagnosis and false alarms. As a result, it is hard for parents to accept the diagnosis results based on the ASD checklist. As diagnosis can be error-prone, there is a requirement of well-trained clinical professionals to make use of the checklist. But as such clinical professionals are in short-supply, the traditional checklist method can be very expensive.
More recently, some attempts have been made to improve the accuracy of ASD diagnosis while keeping the costs low. The idea is to make use of various smart devices to try to perform diagnosis more objectively. These devices are used to measure skin conductance, tracks eye movement and even electroencephalograph (EEG) etc. While these new technologies have not been proven effective as yet, there have been some concerns that diagnosing ASD cannot be done in a single modality. Also, some parents find the use of such devices too intrusive for their children.
In the age of the Internet of Things (IoT), we propose to use Smart Home technology that are equipped with sensors to monitor behaviors of children to see if those with ASD behave differently from those without. By the use of Big Data Analytics, we believe that the two groups of children can be accurately differentiated. We also believe that it can better differentiate children among those diagnosed with ASD in the sense that the degree of severity can also be modeled given the large amount of data that can be analyzed for the construction of the model.
Biography
Prof. Chan obtained his B.Math. (Hons.) in Computer Science and Statistics in 1984 and M.A.Sc. and Ph.D. in Systems Design Engineering in 1985 and 1989 respectively from the University of Waterloo, Waterloo, Ontario, Canada. Soon after graduation, he joined the IBM Canada Laboratory in Toronto, Ontario, Canada as a software analyst and was involved in the development of multimedia and software engineering tools. He joined Ryerson University in Toronto, Ontario, Canada, as an Associate Professor in 1993. In 1994, he returned to Hong Kong to join The Hong Kong Polytechnic University where he is currently a Professor in the Department of Computing. Chan’s research interests are in Big Data Analytics, Bioinformatics, Machine Learning, Evolutionary Computation, Fuzzy Systems, Artificial Intelligence and Software Engineering. He has published over 250 research papers in refereed journals and conference proceedings and has also been serving actively as organizer and Program Committee member of numerous conferences in his research areas. Chan’s research has been supported by government funding agencies and the industry. He has been active in “knowledge transfer” through consulting and contract research.