Workshop

Special Sessions

• Integrative Learning of Graphical Model
• Learning in evolving environments and its application on real-world problems
• Learning on the Web
• Machine Learning and Statistics in Genomics and Metagenomics
• Machine Learning for Biomedical Literature Analysis and Text Retrieval
• Machine Learning for Human Behavior Understanding and Assisted Living
• Machine Learning in Bioinformatics and Computational Biology
• Machine Learning in Energy Application
• Machine Learning in Medicine
• Machine Learning Methods in Cancer Diagnosis and Treatment
• Machine Learning with Multimedia Data
• Pattern Recognition in Communications

Integrative Learning of Graphical Model

It is crucial to develop novel algorithms addressing one or more of the following problems: i) improving networks structure learning accuracy, in particular under scarce training data by integrating various types of prior knowledge, and ii) Producing accurate quantitative predictions with a relative large network. This special session especially encourages submissions on the following (but not limited to) topics: novel algorithms on graphical model structure and/or parameter learning based on integrating training data with the available domain knowledge; novel algorithms that can capture and represent prior knowledge of different formats for effective graphical model learning.

Rui Chang ( University of California, San Diego, USA )
Qiang Ji ( Rensselaer Polytechnic Institute, USA )

Learning in evolving environments and its application on real-world problems

This special session looks to gather and discuss efficient techniques, methods and tools able to manage, to exploit and to interpret correctly the increasing amount of data in environments that are continuously changing. The goal is to build models for predicting the future system behavior, able to tackle and to govern the high variability of complex non-stationary systems. This session would solicit original research papers including but not limited to incremental learning methods, On-line classification and regression methods, and evolving structural components and systems modelling.

Moamar Sayed-Mouchaweh ( Research centre in Sciences and Technology of the Information and the Communication, University of Reims, France )
Edwin Lughofer ( University of Linz, Department of Knowledge-Based Mathematical Systems, Austria )

Learning on the Web

The aim of the special session is to provide an international forum of scientific research and development to explore the fundamental interactions between machine learning and information over the web. Examples of interesting topics are machine learning for online information retrival, web-based knowledge discovery, and social network mining.

Bo Luo ( University of Kansas, USA )
Xue-wen Chen ( University of Kansas, USA )

Machine Learning and Statistics in Genomics and Metagenomics

Next generation sequencing (NGS) is a highly parallelized approach for quickly and economically sequencing new genomes, re-sequencing large numbers of known genomes, or for rapidly investigating transcriptomes under different conditions. It produces genomic and metagenomic data on an unprecedented scale. These techniques are now driving the generation of knowledge (especially in biomedicine and molecular life sciences) to new dimensions. The massive data volumes being generated by these new technologies require new data storage, visualization, and analysis methods. We see a pressing need for and benefits in the interdisciplinary exchange and discussion of ideas. We anticipate that this workshop will shed light on research directions and provide the stimulus for creative breakthroughs. The objectives of this workshop are intended to bring together researchers from different disciplines and address the issues of applying machine learning and statistics to genomics and metagenomics.

Zhenqiu Liu ( University of Maryland at Baltimore, USA )

Machine Learning for Biomedical Literature Analysis and Text Retrieval

Advances in machine learning techniques can improve the analysis of biomedical information. We invite researchers to submit papers with their recent research on machine learning methods applied specifically to biomedical literature analysis and text processing. Papers are sought on a range of topics in this area that include, but are not limited to, Parsing, Classification, and Information Retrieval.

Rezarta Islamaj Dogan ( National Library of Medicine, NIH, USA )
Lana Yeganova ( National Library of Medicine, NIH, USA )

Machine Learning for Human Behavior Understanding and Assisted Living

With the growing need for assisted living technologies, the use of machine learning for human behavior understanding in assistive environments (both web-based and physical), as well as the design of newer machine learning algorithms to address the challenges, has increased in recent years. This special session solicits high-quality papers describing machine learning contributions from theoretical or application perspectives in human behavior understanding with a focus on assistive and rehabilitative technologies.

Vineeth N Balasubramanian ( Center for Cognitive Ubiquitous Computing, Arizona State University, USA )
Sethuraman Panchanathan ( Center for Cognitive Ubiquitous Computing, Arizona State University, USA )

Machine Learning in Bioinformatics and Computational Biology

This session will focus on machine learning methods developed for or applied in Bioinformatics and Computational Biology. The scope of this session includes drug targets identification and analysis of collateral effects, diagnosis devices including early-detection screening, bio-markers identification, analysis of signaling and metabolic pathways, data mining of heterogeneous data sources, and machine learning methods such as support vector machines, artificial neural networks, methods for cluster analysis, but not only, applied in any of the areas mentioned above. This session will bring together researchers in machine learning, bioinformatics, data mining, biology, and statistics to share their expertise to advance Bioinformatics and Computational Biology towards the goal of a better understanding of the complex phenomena of life as we know it.

We encourage submission of papers on novel bioinformatics and computational biology methods using machine learning techniques and focusing on drug targets identification and analysis of collateral effects, diagnosis, definition of biological markers, analysis of signaling pathways, data mining of heterogeneous data sources.

Sorin Draghici ( Wayne State University, USA )
Vasile Palade ( University of Oxford, UK )

Machine Learning in Energy Application

Energy is still one of the most important issues in the World under its various aspects: production and renewability, transport and distribution, management and quality. The recent researches and developments in the production of energy have been focused on alternating and renewable sources as the fossil energy sources are reducing day by day. The aim of this session is to provide a platform to present and discuss recent advancements on machine learning methods in energy and its applications. Papers are sought on a range of topics that include, but are not limited to, alternating energy sources, renewable energy sources, and energy production.

Ilhami Colak ( Gazi University, Turkey )

Machine Learning in Medicine

This special session will concentrate on machine learning applications in medicine. The goal is to bring into focus and foster research that shows advancement in performing medical tasks by using machine learning methods as well as research that brings-up or addresses issues in applying machine learning to medical settings, for example, issues such as human interpretability, lack of data availability, unbalanced data etc. Original research papers are invited that show the use of machine learning methods in areas including but not limited to: predicting diagnosis, deciding best drugs and treatments, predicting patient response and outcomes, clinical decision support systems, clinical data mining, classifying and analyzing patient records and reports. Papers advancing various machine learning techniques, for example, learning algorithms, feature selection strategies, learning under limited supervision, incorporating knowledge into learning etc. that are shown to be especially beneficial for some medical application are welcome. Papers demonstrating benefits and pitfalls of machine learning methods in medical settings are also encouraged for submission.

Rohit Kate ( University of Wisconsin-Milwaukee, USA )

Machine Learning Methods in Cancer Diagnosis and Treatment

This session would solicit original research papers on cancer detection and modeling treatment outcomes (radiotherapy, chemotherapy, etc.) of cancer patients as well as on general application of ML in cancer, including but not limited to the following topics: detection of cancer lesions in diagnostic images, computer-aided diagnosis of cancer.

Issam El Naqa ( McGill University, Canada )

Machine Learning with Multimedia Data

One important aim of this session is to bring together researchers working on different types of data, be it music, video, speech, images, and more. These tasks have much in common, and we hope to promote communication between researchers from these different fields. This session would solicit original research papers including but not limited to the following: Low level feature extraction, selection and transformation; High level feature extraction from multimedia/cross-media.

Jens Grivolla (Barcelona Media Innovation Centre, Spain )
Cyril Laurier (Universitat Pompeu Fabra, Music Technology Group, Spain )

Pattern Recognition in Communications

Researchers are invited to submit their work to present a forum in this area. Novel ideas, algorithms, comparisons of existing methods, etc are sought in this session. The work can either be of theoretical nature like mathematically proving and algorithm or a theorem, or can be a simulation.

Houssain Kettani (Polytechnic University of Puerto Rico, USA )