Soft Granular Mining: Concepts, applications and natural computing
Prof. Sankar K. Pal, Center for Soft Computing Research, Indian Statistical Institute, Kolkata, India

Outline: Different components of machine intelligence are explained. The role of rough sets in uncertainty handling and granular computing is highlighted. Relevance of its integration with fuzzy sets as a stronger paradigm for uncertainty handling, in soft computing paradigm, is explained. Generalized rough sets using the concept of fuzziness in granules and sets, rough-fuzzy entropy, fuzzy equivalence partition matrix and f-information measures are defined. Their significance in tasks like case generation, clustering, measuring image ambiguity and mutual information based feature selection for efficient mining is described. Concept of fuzzy granular computing and granular fuzzy computing is explained.

While rough-fuzzy case generation with variable reduced dimension is useful for mining data sets with large dimension and size, rough-fuzzy clustering is superior in terms of performance and speed. Rough-fuzzy image entropy takes care of the fuzziness in boundary regions as well as the rough resemblance among nearby pixels and gray levels. Effectiveness of these features is demonstrated for image/video analysis and bioinformatics problems.

The talk concludes with mentioning the future directions of research and other applications including the relevance to natural computing.

Prof. Sankar K. Pal ( is a Distinguished Scientist of the Indian Statistical Institute and its former Director. He is also a J.C. Bose Fellow of the Govt. of India and Chair Professor of Indian National Academy of Engineering. He founded the Machine Intelligence Unit and the Center for Soft Computing Research: A National Facility in the Institute in Calcutta. He received a Ph.D. in Radio Physics and Electronics from the University of Calcutta in 1979, and another Ph.D. in Electrical Engineering along with DIC from Imperial College, University of London in 1982. He joined his Institute in 1975 as a CSIR Senior Research Fellow where he became a Full Professor in 1987, Distinguished Scientist in 1998 and the Director for the term 2005-10.

He worked at the University of California, Berkeley and the University of Maryland, College Park in 1986-87; the NASA Johnson Space Center, Houston, Texas in 1990-92 & 1994; and in US Naval Research Laboratory, Washington DC in 2004. Since 1997 he has been serving as a Distinguished Visitor of IEEE Computer Society (USA) for the Asia-Pacific Region, and held several visiting positions in Italy, Poland, Hong Kong and Australian universities.

Prof. Pal is a Fellow of the IEEE, the Academy of Sciences for the Developing World (TWAS), International Association for Pattern recognition, International Association of Fuzzy Systems, and all the four National Academies for Science/Engineering in India. He is a co-author of seventeen books and more than four hundred research publications in the areas of Pattern Recognition and Machine Learning, Image Processing, Data Mining and Web Intelligence, Soft Computing, Neural Nets, Genetic Algorithms, Fuzzy Sets, Rough Sets and Bioinformatics. He visited about forty countries as a Keynote/ Invited speaker or an academic visitor.

He has received the 1990 S.S. Bhatnagar Prize (which is the most coveted award for a scientist in India), 2013 Padma Shri (one of the highest civilian awards) by the President of India and many prestigious awards in India and abroad including the 1999 G.D. Birla Award, 1998 Om Bhasin Award, 1993 Jawaharlal Nehru Fellowship, 2000 Khwarizmi International Award from the President of Iran, 2000-2001 FICCI Award, 1993 Vikram Sarabhai Research Award, 1993 NASA Tech Brief Award (USA), 1994 IEEE Trans. Neural Networks Outstanding Paper Award, 1995 NASA Patent Application Award (USA), 1997 IETE-R.L. Wadhwa Gold Medal, 2001 INSA-S.H. Zaheer Medal, 2005-06 Indian Science Congress-P.C. Mahalanobis Birth Centenary Gold Medal from the Prime Minister of India for Lifetime Achievement, and 2007 J.C. Bose Fellowship of the Government of India and INAE Chair Professorship.

Prof. Pal is/was an Associate Editor of IEEE Trans. Pattern Analysis and Machine Intelligence (2002-06), IEEE Trans. Neural Networks [1994-98 & 2003-06], Neurocomputing (1995-2005), Pattern Recognition Letters (1993-2011), Int. J. Pattern Recognition & Artificial Intelligence, Applied Intelligence, Information Sciences, Fuzzy Sets and Systems, Fundamenta Informaticae, LNCS Trans. Rough Sets, Int. J. Computational Intelligence and Applications, IET Image Processing, and J. Intelligent Information Systems; Editor-in-Chief, Int. J. Signal Processing, Image Processing and Pattern Recognition; a Book Series Editor, Frontiers in Artificial Intelligence and Applications, IOS Press, and Statistical Science and Interdisciplinary Research, World Scientific; a Member, Executive Advisory Editorial Board, IEEE Trans. Fuzzy Systems, Int. Journal on Image and Graphics, and Int. Journal of Approximate Reasoning; and a Guest Editor of IEEE Computer, IEEE SMC and Theoretical Computer Science.

Automated Human Activity Recognition from Video Clips
Prof. K. K. Biswas, Indian Institute of Technology, Delhi, India

Outline: Human action recognition for automatic understanding of video clips is becoming increasingly important. With the growing need of surveillance related applications, the research in the field of action recognition has been fueled in past few years. Action recognition systems can be used for surveillance purpose and can trigger alarm whenever some suspicious activity takes place. Action recognition systems also help in creating interactive environment which can respond to the actions performed by human actors. Assisted care applications to the elderly can also make use of action recognition techniques. Other possible applications are video summarization, and content based video retrieval, etc.

This talk will be in two parts. The first part will deal with action recognition from RGB video clips. It will be shown how shape based features and optical flow based motion features are extracted from the video frames. A short introduction to machine learning will be given to justify use of Support Vector Machine based approach for training the system. Results based on lab activities such as walking, sitting down, writing on board, opening a door, sliding on chair will be presented.

The second part of the talk will deal with small scale actions performed while sitting down on a chair, such as typing, reading, attending phone, engaged in discussion, drinking tea, texting, stretching and dozing. The objective will be to show how a depth based camera can be effectively used for collecting 3D data and improve the recognition rates using depth and body joints data. Results will be presented on actual case studies carried out at IIT Delhi.

Prof. K. K. Biswas did his B.Tech in Electrical Engineering from IIT Madras, followed by M.Tech in Control systems and PhD in signal estimation from IIT Delhi. After a brief stint at University of Roorkee, he joined the EE Department of IIT Delhi. He later shifted to Computer Science Engineering Department where he is currently serving as a Professor. His teaching career spans over 35 years. He has been a visiting professor at the University of Auckland, New Zealand and at the University of Central Florida, USA. He has also acted as UNESCO expert for development of curriculum at university of Nigeria. He has been collaborating with University of Oxford and University of Texas at Austin. He has been an active researcher with 15 PhD students, and more than 60 publications in reputed journals and international conferences. His current area of research interest is image and video processing, machine learning with applications in activity recognition and salient object detection. His other main research interest is handling fuzzy models in probabilistic domain. He is also working in the area of logic based knowledge representation in various domains.

Basic Science and Applied Engineering in Intelligent Systems Research: Can the Twain Meet?
Case Study of a Social Interaction Assistant for Individuals with Visual Impairments

Dr. Vineeth N Balasubramanian, Indian Institute of Technology, Hyderabad, India

Outline: Intelligent recognition systems bring together the strong theoretical science of machine learning and pattern recognition, with the rigorous engineering practices required for real-world end-products. Can the twain - basic and applied research - meet? This talk will attempt to provide a new perspective on this question through a case study of a Social Interaction Assistant system for individuals with visual impairments. Literature in psychology states that 65% of communication is non-verbal, which is inaccessible to individuals with visual disabilities. This presents fundamental challenges in the development of computational methods for understanding human behaviour, and the ability to effectively navigate and negotiate complex environments and social relationships, which can further be characterized by individual and contextual heterogeneity. However, advances in machine analysis of behavioural cues (e.g., gaze exchange, smiles, head nods, crossed arms, laughter) or social signals (e.g., attention, empathy, agreement) are still in their infancy. This talk will, in particular, describe two components developed for the Social Interaction Assistant: (i) Efficient conformal predictors for reliable person recognition; and (ii) Batch mode active learning for effective sample selection in video sequences. The talk will conclude with pointers to directions for future research in machine learning to achieve behavioural intelligence in real-world settings, which can be applied in a wide range of settings including smart healthcare, ubiquitous user interfaces, security and surveillance, and telecommunication.

Dr. Vineeth N Balasubramanian is an Assistant Professor in the Department of Computer Science and Engineering at the Indian Institute of Technology, Hyderabad, India. Until July 2013, he was an Assistant Research Professor at the Center for Cognitive Ubiquitous Computing (CUbiC) at Arizona State University (ASU). He holds dual Masters degrees in Mathematics (2001) and Computer Science (2003) from Sri Sathya Sai Institute of Higher Learning, India, and worked at Oracle Corporation until 2005. His PhD dissertation (2010) on the Conformal Predictions framework was nominated for the Outstanding PhD Dissertation at the Department of Computer Science at ASU. He was also awarded the Gold Medals for Academic Excellence in the Bachelors program in Math in 1999, and for his Masters program in Computer Science in 2003. His research interests include pattern recognition, machine learning, computer vision and multimedia computing within assistive and healthcare applications. He has over 40 research publications in premier peer-reviewed venues, 3 patents under review, and has received research grants from the US National Science Foundation in these fields. He is a member of the IEEE, ACM and AAAI.

Scalability in Unnatural Signal and Pattern Processing
Dr. A.P. James, Nazarbayev University, Republic of Kazakhstan

Outline: Machines far exceed the computational ability and speed of processing of human brain, yet they fail to compete with natural intelligence in terms of scalability and speed of response. Scalability of intelligence is closely coupled with physical constraints and functional requirement of an intelligent task. The physical constraints put further sanctions on signal quality during transmission and processing. In this talk, we provide an overview of this problem and discuss the historical, scientific and philosophical questions in the design of scalable learning machine, that can be taken up to solve the problems reflective of existing pattern classifiers and signal processing methods.

Dr. A.P. James is currently a faculty in Nazarbayev University, and heads the Advanced Microelectronics and Cyber-Physical Systems Group. He is also the CEO and Principal Scientist of the start-up ENVIEW R&D Labs LLP. His previous organisational engagements include IIITMK, Griffith University, HCL Tech., UCB, QIBT, He has a technical background in Electronics, Computer Science and Systems Engineering, and a PhD (2 years) from Griffith School of Engineering, Griffith University. A unique blend of algorithms and hardware design approach to data related problem solving for developing Neuromorphic Systems is his primary research focus. His recent work reflects novel and difficult to implement hardware based solutions to problems involving imaging applications. He has been a reviewer and author to several high quality journals. His biography is included in the 2012 who's who of the world listing. He was listed as one of the top reviewers for PRL in the last 5 years. He has served as Editorial board member of several international journals including currently serving as Editorial board member of Information Fusion Journal, Elsevier. He is currently the Editor in Chief of Int. J. of Applied Pattern Recognition. He is a member of several science and engineering societies, including member of IEEE, ACM and IET.

Tutorial: Designing Secure and Private RFID Communication Protocols
Dr. Robin Doss, Associate Head of School (Development and International)
School of Information Technology, Deakin University, Australia

Target Audience: Masters/PhD students, researchers interested in secure protocol design

Outline: RFID is a technology that enables the non-contact, automatic and unique identification of objects using radio waves. RFID technology was first used in the IFF (Identify Friend or Foe) aircraft system during World War II. However, its use for commercial applications has recently become attractive with RFID technology seen as the replacement for the optical barcode system that is currently in widespread use. It is projected that the RFID market will be worth more than US$25billion in 2018. However, for this growth and proliferation of RFID systems to be achieved, security and privacy concerns relating to RFID communication need to addressed.

RFID systems require unique security requirements and privacy properties to be guaranteed. The achievement of security and privacy in RFID systems is challenging due to the computational constraints on low-cost RFID tags. In addition, it is vital that any proposed security scheme is compliant with RFID industry standards such as the EPC Class-1 Gen-2 standard that specifies that tags are required to implement only a cyclic redundancy check (CRC) and pseudo random number generator (PRNG). In such RFID systems, it is estimated that there is approximately only 2.5K to 5K additional gates available for security purposes on an EPC Class-1 Gen-2 compliant RFID tag. This is insufficient for standard cryptographic techniques such as RSA, hash functions. Further, the limited processing and storage capabilities of RFID tags limit the effective use of cryptographic techniques. Although cheaper cryptographic alternatives such as Elliptic Curve Cryptography (ECC) exist, the practical implementation of ECC is still an open research problem. For instance, implementation of ECC would require between 8.2 K and 15 K equivalent gates. These factors make the design of secure and private RFID communication protocols a non-trivial problem.

In this tutorial, the topics covered will include: security and privacy properties in RFID systems; constraints on cryptographic primitives; secure protocol design with focus on mutual authentication, secure search, ownership transfer and grouping proofs; formal security analysis of RFID security protocols and open research problems and future research directions. This tutorial will also cover topics related to information leakage in RFID systems and the use of number theoretic properties, in particular minimum disclosure properties for effective design of RFID communication protocols.

Dr. Robin Doss joined the School of Information Technology, Deakin University, Australia, in 2003 and is currently the Associate Head of School (Development & International). Prior to joining Deakin University, he was part of the technical services group at Ericsson Australia and a research engineer at RMIT University. Robin received a Bachelor of Engineering in Electronics and Communication Engineering from the University of Madras, India in 1999, and a Master of Engineering in Information Technology and a PhD in Computer Systems Engineering from the Royal Melbourne Institute of Technology (RMIT), Australia in 2000 and 2004 respectively. His PhD thesis was on mobility prediction for next generation wireless networks. In 2007, he also completed a Graduate Certificate in Higher Education from Deakin University.

Dr. Doss is a senior researcher within the network security and computing research lab at Deakin University and has made significant contributions in the areas of network security, network design and protocol development for wireless networks. His research has been funded by the National Security Science and Technology (NSST) branch of the office of national security in collaboration with the Defence Signals Directorate (DSD), the Australian Research Council (ARC) and industry partners. Dr. Doss was part of the team of researchers funded through the Research Support for Counter Terrorism (RSCT) initiative of the Australian government to provide advice to the department of Prime Minister and Cabinet. In 2006, Dr. Doss was hosted as a visiting scientist by IBM Research at their Zurich Research Laboratory (ZRL), Switzerland where he contributed to the 'e-Sense' project (

Dr. Doss has served as the chair of several international symposia, workshops and conferences (ISSNIP RFID 2009, ISSNIP RFID2011, IEEE ISNIP RFID 2013, IEEE WiMob IoT2013) in the areas of wireless communication and network security. He serves on the technical programme committee for several conferences on wireless communications and is a regular reviewer for international journals and PhD theses. He is also an affiliate researcher with the ARC Research Network on Intelligent Sensors, Sensors Networks and Information Processing (ISSNIP). He has published widely and his research results have been published in the IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Information Forensics and Security, IEEE Communications Letters, Computer Networks and Ad Hoc Networks among others.

Keynote: Automatic Obligation Enforcement for Privacy Policy Compliance
Dr. Mukesh K. Mohania, STSM, IBM India Research Lab (Distinguished ACM Speaker)

Outline: It is becoming increasingly important for enterprises to have a well-defined privacy policy, to establish customer trust and to prevent misuse of privacy data and avoid litigation. Many standards exist for the publication of the privacy policy of an enterprise, which may be more complex than a simple 'allow' or 'deny' rule. The privacy policy may have rules that specify obligations to be executed in the case of certain data access. Currently these obligations are executed manually, with the inherent defects of not being scalable or auditable. In this talk, we discuss the architecture and technology for the automated execution of the obligations associated with a privacy policy that has been developed at IBM India Research Lab. We also present a prototype solution for the obligation enforcement, using IBM Content Manager as the data repository and IBM Record Manager for the obligation enforcement. The system also logs audit information and generates audit trails, to support auditing of the obligation enforcement. We also present a generic architecture for obligation execution associated with different kinds of policies.

Dr. Mukesh K. Mohania received his Ph.D. in Computer Science & Engineering from Indian Institute of Technology, Bombay, India in 1995. He was a faculty member in University of South Australia from 1996-2001. Currently, he is an STSM and IBM Master Inventor in IBM India Software Lab, and leading Information Management Software and Research group. He has worked extensively in the areas of distributed databases, data warehousing, data integration, and autonomic computing. He has published more than 100 papers and also filed more than 30 patents in these or related areas. He received the best paper award for his XML and data integration work in CIKM 2004 and CIKM 2005, respectively. He received an award from IBM Tivoli Software in 2004 for his research contribution to Policy Management for Autonomic Computing product. He was also a recipient of the "Excellence in People Management" award in IBM India in 2007. He received the "Outstanding Innovation Award" from IBM Corporation in 2008 for his Context-Oriented Information Integration work, and Technical Accomplishment Award in 2009 for his Policy work.

Keynote: Fraud Detection Using Artificial Neural Networks
Dr. Dhiya Al-Jumeily, Liverpool John Moores University, United Kingdom

Outline: Artificial neural networks have been used extensively for fraud detection and network securities. In this talk, two applications of artificial neural network architectures will be discussed. In the first application, artificial neural network was used for the detection of telecommunication fraud. Telecommunication fraud involves the theft of services or deliberate abuse of voice and data networks. In such cases, the perpetrator's intention is to completely avoid or at least reduce the charges for using the services. Data profiling was used to selected important information for premium rate line fraud detection using artificial neural network. In the second application, the concept of Autonomic Computing will be discussed. Remarkable advances in technology have introduced increasingly complex and large-scale computer and communication systems. Autonomic computing has been projected as a remarkable challenge that will allow systems to self-manage this complexity, using sophisticated objectives and policies defined by humans. Internet of things (IoT) has exponentially increased the scale and the complexity of existing computing and communication systems; the autonomy is thus an imperative property for IoT systems. Self-healing is one of the most important components of autonomic computing. It has the ability to modify its own behavior in response to changes in the environment (in real-time), by repairing the detected faults. Hence, the system is capable of performing a reconfiguration action in order to recover from current faults. A novel application of a modified Pipelined Recurrent Neural Network will be presented with experiments aimed to assess its applicability to online.

Dr. Dhiya Al-Jumeily is a Principal Lecturer in eSystems Engineering and leads the Applied Computing Research Group (ACRG) at the faculty of Technology and Environment. He has already developed fully the first online MSc and BSc Courses for Liverpool John Moores University. Dr. Dhiya Al-Jumeily has published numerous referred research papers in multidisciplinary research areas including: Technology Enhanced Learning, Applied Artificial Intelligence, Neural Networks, Signal Prediction, Telecommunication Fraud Detection, Image Compression and Multimedia databases. He is a PhD supervisor and an external examiner for the degree of PhD. He has been actively involved as a member of editorial board and review committee for a number peer reviewed international journals, and is the Series Conference Chair of the International Conference Series on Developments in eSystems Engineering DeSE ( Dr. Dhiya Al-Jumeily was appointed as a lecturer in Computer Systems in 1997. Prior to this, he was a scholar reading for a PhD in Applied Artificial Intelligence at Liverpool John Moores University, on the topic of Intelligent Tutoring Systems. He also worked at the same department as a research assistant in the area of statistical computing and managed to obtain his MPhil in 1995. Earlier, in 1987 he completed his BSc (first class) in Mathematics at Baghdad University. He worked as a research assistant at Baghdad University in 1987-1990, where he was involved, as part of a large research group, in a number of projects. He then studied the Postgraduate Diploma in Mathematics at Liverpool University in 1991. Dhiya is a member of the British Computer Society (BCS) and has achieved his Chartered IT Professional status in 2007.