Dr. Vasile Palade

Ensembles of Classifiers and Their Application to Bioinformatics Problems

Abstract: Machine Learning has become a very popular approach in addressing problems in the Computational Biology and Bioinformatics area.  In addition, multi-classifier systems have also gained popularity among researchers working in machine learning and applications for their ability to fuse together multiple models and obtain better overall accuracy and classification results. This talk is concerned with current issues in the design of multi-classifier systems and presents some multi-classifier developments for several bioinformatics problems. The talk will first present an overview and current status of machine learning methods in bioinformatics and computational biology.  The talk will then bring in some important issues in building ensembles of classifiers, with a focus on the diversity and combination of individual classifiers. Few diversification and combination schemes are presented along with guidelines for the selection of different training paradigms and performance metrics, based on the properties and distribution of the data. Then, the presentation will proceed with introducing our computational intelligence based multi-classifier developments for solving several bioinformatics problems, such as recognizing sequences in DNA strings, micro-array gene expression data analysis, protein structure prediction. The talk will also present related machine learning issues in developing such systems, such as learning from imbalanced datasets and using appropriate performance metrics for model selection and evaluation. The presented approaches and results will advocate that ensembles of classifiers can be used as effective modelling tools in solving challenging bioinformatics problems.

 

Biography: Dr. Vasile Palade is working with the Computing Laboratory, Oxford University, United Kingdom. His main research interests lie in the area of computational intelligence, and encompass hybrid intelligent systems, neural networks, fuzzy and neuro-fuzzy systems, various nature inspired algorithms including genetic algorithms and swarm optimization, ensembles of classifiers. Application areas include Bioinformatics problems, fault diagnosis, web usage mining, among others. Before joining the University of Oxford, Dr. Palade worked as a research associate with the Department of Engineering, University of Hull, UK, and as an Associate and Full Professor of the Department of Computer Science and Engineering, University of Galati, Romania. Dr. Palade is author and co-author of more than 80 papers in journals and conference proceedings and several books on computational intelligence and applications. He has also co-edited a few books and conference proceedings. He currently serves as Co-Editor-in-chief for the International Journal of Hybrid Intelligent Systems, and as Associate Editor for other journals, including Neurocomputing and the International Journal on Artificial Intelligence Tools. He was the General Chair for KES2003 – The 7th International Conference on Knowledge Based Intelligent Engineering Systems, Oxford - UK, September 2003, and Co-chair for ICMLA 2010 – The 9th International Conference on Machine Learning and Applications, Washington - USA, December 2010. Dr. Vasile Palade is an IEEE Senior Member and a member of the IEEE Computational Intelligence Society.


Dr. Allan K.Y. Wong

Trusted Ontology-Based Telemedicine Systems and Real-Time Discoveries

Abstract: A computer-based telemedicine system is trusted if its functions match the semantic paths in the given ontological construct. By its very nature, a telemedicine system seamlessly merges computing logic with contextual logic in medicine. A discovery is possible if we can successfully match a universally accepted logical expression with a classical contextual principle. In this keynote we make use of a trusted ontology-based TCM (Traditional Chinese Medicine) mobile-clinic (MC) system as the basis of our demonstration. This MC system has been deployed successfully and has been treating hundreds of patients daily in the Hong Kong SAR for the past few years. We will clearly explain the following:

  1. Enterprise medical ontology (EMO) in a generic sense
  2. EMO-based clinical system in the TCM context
  3. Trusted EMO-based TCM telemedicine system generation and example
  4. The novel generic “living ontology” concept to make ontological evolution possible
  5. Definitions of type-1 and type-2 discoveries and their real-time TCM connotations
  6. Some future research directions indicated by the TCM experience
  7. Demonstration – a TCM MC system with real-time discovery support in clinical practice

Biography: A/Professor Allan Wong is working at Department of Computer Science, Hong Kong Polytechnic University. His main research activities currently concentrate on the Telemedicine, which focuses on developing an Internet-based prototype for telemedicine in the TCM (Traditional Chinese Medicine) diagnostic perspective.
The research findings not only enrich the bodies of knowledge in Internet Computing and Data Mining, but also contribute to applying IT to telemedicine, which brings health care, in terms of TCM, to the local community and every corner of the world that may need it. In this aspect A/Professor Wong combines his IT expertise and his experience as a listed TCM (Traditional Chinese Medicine) practitioner by the Hong Kong TCM Medical Council.