Prof. Mohd Zaid Bin Abdullah
Universiti Sains Malaysia, Malaysia
Biography: M. Z. Abdullah graduated from Universiti Sains Malaysia (USM) with a B. App. Sc. degree in Electronic in 1986 before joining Hitachi Semiconductor as a test engineer. In 1989, he commenced an M.Sc. in Instrument Design and Application at University of Manchester Institute of Science and Technology, UK. He remained in Manchester conducting research in Electrical Impedance Tomography at the same university, and received his Ph.D. degree in 1993. He joined USM in the same year. His research interests include microwave tomography, digital imaging, and ultra wide band sensing. He has published numerous research articles in international journals and conference proceedings. One of his papers was awarded The Senior Moulton medal for the best article published by the Institute of Chemical Engineering in 2002. Presently he is director of the Collaborative Microelectronic Design Excellence Centre (CEDEC), Universiti Sains Malaysia.
Speech Title: "Machine Learning for Harline Crack Detection in Cluttered Images"
Abstract: The problem of machine learning for hairline crack detection is considered. As binarisation is one the important pre-processing steps of defect analysis, a new challenge emerges when distinguishing crack pixels from the foreground especially with low-contrast, non-uniform and cluttered images. This problem is encountered in numerous applications, ranging from inspection of biological materials to assessment of manufactured goods. If a simple global thresholding is used then the binarised image would be dominated with regions which are either too-dark or too-bright. This causes difficulty in feature extraction and subsequently high false alarm. Cluttering makes the problem much worst because intensities of foreground and background pixels are scattered at different positions, leading to heterogeneously textured image. This problem requires a powerful image processing technique which has been met following the development of a novel framework to accurately segment crack pixels in very heterogeneous background. The rationale behind this framework is that the gradient of an image is an important indicator of the probable crack edges. A 3-dimensional threshold surface is then constructed by interpolating the image gray levels at points of gradients. A refined anisotropic diffusion filter (ADF) with double thresholding has been developed for this purpose. Meanwhile the Radon transform (RT) has been utilised for feature extraction, and machine learning has been established via the state-of-the-art Twin Support Vector Machine (TSVM). Two real-world engineering problems have been used to illustrate the practical applications of this new image processing approach. The first example is in manufacturing where the algorithm is used to automatically detect micro-crack defect in photoluminescence images of polycrystalline solar wafers. This innovation has resulted in a prototype which is now being commercialised by an industrial partner of this project. Meanwhile the second example deals with inspecting various types of hair-line cracks on eggshell in poultry farming. Algorithmic details together with instrumentation for image capturing will be discussed in the ensuing keynote lecture.
Seoul National University, South Korea
Biography: Prof. Taesung Park received his B.S. and M.S. degrees in Statistics from Seoul National University (SNU), Korea in 1984 and 1986, respectively and received his Ph.D. degree in Biostatistics from the University of Michigan in 1990. From Aug. 1991 to Aug. 1992, he worked as a visiting scientist at the NIH, USA. From Sep. 2002 to Aug. 2003, he was a visiting professor at the University of Pittsburgh. From Sep. 2009 to Aug. 2010, he was a visiting professor in Department of Biostatistics at the University of Washington. From Sep. 1999 to Sep. 2001, he worked as an associate professor in Department of Statistics at SNU. Since Oct. 2001 he worked as a professor and currently the Director of the Bioinformatics and Biostatistics Lab. at SNU. He served as the chair of the bioinformatics Program from Apr. 2005 to Mar. 2008, and the chair of Department of Statistics of SNU from Sep. 2007 and Aug. 2009. He has served editorial board members and associate editors for the international journals including Genetic Epidemiology, Computational Statistics and Data Analysis, Biometrical Journal, and International journal of Data Mining and Bioinformatics. His research areas include microarray data analysis, GWAS, gene-gene interaction analysis, and statistical genetics.
Speech Title: "Hierarchical Structural Component Analysis of Gene-Gene Interactions"
Abstract: While many statistical approaches have been proposed to detect gene-gene interactions (GGI), most of these focus primarily on SNP-to-SNP interactions. While there are many advantages of gene-based GGI analyses, such as reducing the burden of multiple-testing correction, and increasing power by aggregating multiple causal signals across SNPs in specific genes, only a few methods are available. In this study, we proposed a new statistical approach for gene-based GGI analysis, “Hierarchical structural CoMponent analysis of Gene-Gene Interactions” (HisCoM-GGI). HisCoM-GGI is based on generalized structured component analysis (GSCA), and can consider hierarchical structural relationships between genes and SNPs. For a pair of genes, HisCoM-GGI first effectively summarizes all possible pairwise SNP-SNP interactions into a latent variable, from which it then performs GGI analysis. HisCoM-GGI can evaluate both gene-level and SNP-level interactions. Through simulation studies, HisCoM-GGI demonstrated higher statistical power than existing gene-based GGI methods, in analyzing a GWAS of a Korean population for identifying GGI associated with body mass index.
Prof. Sung-Nien Yu
National Chung Cheng University, Taiwan
Biography: Prof. Sung-Nien Yu received both his B.S. and M.S. degrees in Electrical Engineering from the National Taiwan University, Taipei, Taiwan, in 1987 and 1991, respectively. He received his Ph.D. degree in Biomedical Engineering from the Case Western Reserve University, Ohio, USA, in 1996. After graduation, he entered the Department of Physical Therapy at Chang Gung University, Tao-Yuan County, Taiwan and served as an assistant professor from 1996 to 1999. After that, he joined the Department of Electrical Engineering at National Chung Cheng University, Chia-Yi County, Taiwan in 1999 and is currently a professor of the department and the director of the Biomedical Signal Processing and System Design Laboratory. He is a member of the IEEE Engineering in Medicine and Biology Society and a permanent member of the Taiwanese Society of Biomedical Engineering. His research interests include biomedical signal processing, biomedical image processing, and the application of pattern recognition and machine learning technologies to biomedical problems.
Speech Title: "Wavelet Decomposition and Higher Order Statistics for Electrocardiogram-Based Arrhythmia Recognition"
Abstract: Arrhythmias are disorders of the rhythmic beating of the heart. Serious arrhythmias usually lead to heart diseases, stroke, or even sudden death. The electrocardiogram (ECG) is a low-cost, convenient, and non-invasive method to detect the electro-activity changes of the heart. Thus, ECG is usually used in the hospital as a routine and crucial means for the diagnosis of heart diseases by differentiating the pattern changes of different arrhythmias. In order to build an effective computer-aided-diagnosis (CAD) system for heart diseases, our laboratory has been exploring the use of wavelet decomposition and higher order statistics (HOS) to recognize different types of arrhythmias based on ECG. The discrete wavelet transform (DWT) decomposes a signal into subband components. Features extracted from these components can efficiently characterize the original signal in different frequency subbands. On the other hand, the HOS has been demonstrated to effectively suppress the influence of noises. Thus, the integration of the two techniques provides an opportunity not only to extract features that may otherwise been hidden in the original signal but also to reduce the influence of noises at the same time. In this talk, I will explain the method of integrating DWT and HOS for ECG-based arrhythmia recognition. The advantages of this approach, in terms of the recognition rates and noise-tolerance capability when compared with other methods, will be discussed. I will also describe our recent work implementing this system on a smartphone for mobile health (mHealth) applications. Technologies will be addressed about how to transfer the algorithm onto a smartphone to achieve effective and real-time arrhythmia recognition.
Assoc. Prof. Dr. Dong Van Quyen
Vietnam Academy of Science and Technology, Vietnam
Biography: Dr. Quyen holds a PhD in Biochemistry and Molecular Biology from Sungkyunkwan University-School of Medicine, South Korea. After obtaining his PhD in 2006 he spent 1 year at Department of Bacteria and Parasitology, National Veterinary Research and Quarantine Service, South Korea and 2 years at Health Science Center, University of Tennessee, USA working on molecular biology of Neospora and angiogenesis. He returned Vietnam in 2010 and since then head of Molecular Microbiology Lab (MML), Institute of Biotechnology (IBT), Vietnam Academy of Science and Technology. His Lab specializes in the development and applications of diagnostic tests for microbial pathogens using modern molecular biology techniques. Our approaches provide highly accurate, rapid and sensitive tests for detection of emerging, reemerging and different important microbial pathogens and that have led to sensitive and specific tests for the detection of many tremendous pathogens such as hepatitis B virus, HIV, white spot syndrome virus, foot and mouth disease virus, influenza viruses (H5N1, H1N1) and respiratory viruses. Another research interest of MML is application of modern technologies such as adeno-associated viral vectors and virus-like particles for production of safe and highly efficient vaccines. His current interest is screening and purification of recombinant lysins against antibiotic-resistant bacteria from bacteriophages.
Dr. Quyen is also a visiting lecturer at Hai Duong Medical and Technical University, Graduate University of Science& Technology- Vietnam Academy of Science and Technology (VAST). Since 2014 he was assigned as co-director of Dept of Biotechnology and Pharmacology, University of Science and Technology of Hanoi (USTH)-VAST.
Senior Lecturer Jeff Kilby
AUT University, New Zealand
Biography: Jeff Kilby, was born Edmonton, Alberta, Canada, has a MEng (Hons) in Signal Processing from the AUT University, Auckland New Zealand. Senior Lecturer in Electronics and Computing in the School of Engineering at AUT University, Main research topic is in the field of Biomedical Signal Processing and Devices with other research interests are LabVIEW Applications Micro-controller Applications and Wireless Sensor Network Applications. He is an IEEE Engineering in Medicine and Biology Society Membership.