Keynote Speech I
Biomedical Text Mining for Semantic Search and Knowledge Discovery
Professor Sophia Ananiadou
School of Computer Science
Director, National Centre for Text Mining
Manchester Interdisciplinary Biocentre
Due to increasing specialisation, silo effects and literature deluge, researchers are struggling to draw out general truths and to generate hypotheses to test. This is especially true when considering the needs of biomedicine. Natural language processing techniques are urgently needed, including aids to link the scientific literature with appropriate knowledge in scientific databases, and to provide textual evidence in hypothesis generation and semantic search. The evidence to generate hypotheses for comprehensive diagnostics, pharmacological interventions, treatments, etc., is hidden in text. In addition, the type of evidence needed is complex, requiring techniques beyond statistical keyword search mechanisms, such as question answering about facts, relations and events of biomedical relevance. The extraction of semantic metadata from text allows advanced semantic search. In my talk, I will discuss such issues and also present some of the biomedical text mining services developed at the UK National Centre for Text Mining addressing the needs of the biomedical community for semantic search and knowledge discovery.
Professor Sophia Ananiadou is Director of the UK National Centre for Text Mining (NaCTeM), and full Professor of Computer Science in the School of Computer Science, University of Manchester, UK. She is the main designer of the text-mining tools and services currently used in NaCTeM, i.e. terminology management, information extraction, intelligent searching, and association mining. Her research projects include text mining-based visualisation of biochemical networks, data integration using text mining (on infectious diseases, for the PathoSystems Resource Integration Center), building biolexica and bio-ontologies, and automatic event extraction of bioprocesses. She also leads work to support scientists in evidence finding via text mining based search, within the UK PubMed Central project, and collaborates with centres in the US and Japan to develop text mining infrastructures for the community.
She has been awarded the Daiwa Adrian prize (2004) and the IBM UIMA innovation award (2006, 2007,2008) for her work on interoperability of text-mining tools in biomedicine. She has over 160 publications in journals, conferences and books.
Keynote Speech II
Brain-Computer Interfaces: Progress, Problems, and Possibilities
Chief, Laboratory of Neural Injury and Repair
New York State Department of Health and State University of New York
Brain-computer interfaces (BCIs) have a promising future, with researchers in laboratories all over the world using many different brain signals, recording methods, and signal processing approaches to realize increasingly capable systems. These BCI systems can control a variety of external devices, from cursors and avatars on computer screens, to televisions and wheelchairs, to robotic arms and neuroprostheses. People with and without disabilities have tested these systems, and a few people who are severely disabled are already using them for important purposes in their daily lives. Furthermore, several groups are beginning to explore BCI-based methods for improving rehabilitation for people with strokes and other neuromuscular disorders. Thus, BCIs are poised to become a major new technology for people with disabilities, and possibly for the general population as well. At the same time, the realization of this bright future depends on advances in four critical areas. First, both non-invasive and invasive BCIs need better signal-acquisition hardware. Second, the real-life usefulness of BCI systems for people with disabilities requires convincing clinical validation. Third, effective strategies for BCI dissemination and ongoing support must be developed. Fourth, and perhaps most important, if non-invasive or invasive BCIs are to be widely used for anything more than the most basic communication functions, their reliability must be greatly improved. Better reliability may be achieved with BCI design strategies that are based on the principles underlying the excellent reliability of natural neuromuscular actions. These strategies include: effective engagement of brain adaptive capacities; task-appropriate distribution of control between the brain and the BCI; and BCI use of signals from multiple brain areas. Effective attention to these critical areas by scientists and engineers throughout the world can realize the exciting future envisioned for BCI technology.
Over the past 30 years, Dr. Wolpaw's laboratory has developed and used operant conditioning of spinal reflexes as a model for defining the plasticity underlying learning. His work has demonstrated operant conditioning of spinal reflexes, has showed that this conditioning changes the spinal cord physiologically and anatomically, and has begun to reveal the underlying mechanisms. His group’s recent work shows that reflex conditioning can guide spinal cord plasticity in spinal cord-injured rats and can thereby improve locomotion. Clinical researchers are now finding evidence that such conditioning can improve locomotion in people with partial spinal cord injuries. For the past 20 years, Dr. Wolpaw has also led development of EEG-based brain-computer interface (BCI) technology to provide non-muscular communication and control to people who are paralyzed. This work has shown that noninvasive EEG-based BCI technology can give movement control similar to that achieved by electrodes placed in the brain. Most recently, his group has begun to provide BCI systems to severely disabled people for daily use in their homes. This work is demonstrating that a BCI can restore communication ability to people for whom conventional assistive communication devices are inadequate. Dr. Wolpaw and his research group have been funded for many years by NIH, other Federal agencies, and a variety of private foundations, and have received numerous national and international awards.