Keynote Speaker

1.

Speaker: B Yegnanarayana, INSA Senior Scientist, IIIT Hyderabad
Title: Evolution of ANN architectures from learning to deep learning
Brief bio of the speaker
Dr. Bayya Yegnanarayana is currently INSA Senior Scientist at IIIT Hyderabad. He was Professor Emeritus at BITS-Pilani Hyderabad Campus during 2016. He was an Institute Professor from 2012 to 2016 and Professor & Microsoft Chair from 2006 to 2012 at the International Institute of Information Technology (IIIT) Hyderabad. He was a professor at IIT Madras (1980 to 2006), a visiting associate professor at Carnegie-Mellon University, Pittsburgh, USA (1977 to 1980), and a member of the faculty at the Indian Institute of Science (IISc), Bangalore, (1966 to 1978). He received BSc from Andhra University in 1961, and BE, ME and PhD from IISc Bangalore in 1964, 1966, and 1974, respectively. His research interests are in signal processing, speech, image processing and neural networks. He has published over 400 papers in these areas. He is the author of the book "Artificial Neural Networks", published by Prentice-Hall of India in 1999. He has supervised 30 PhD and 42 MS theses. He is a Fellow of the Indian National Academy of Engineering (INAE), a Fellow of the Indian National Science Academy (INSA), a Fellow of the Indian Academy of Sciences (IASc), a Fellow of the IEEE (USA) and a Fellow of the International Speech Communications Association (ISCA). He was the recipient of the 3rd IETE Prof.S.V.C.Aiya Memorial Award in 1996. He received the Prof.S.N.Mitra Memorial Award for the year 2006 from INAE. He was awarded the 2013 Distinguished Alumnus Award from IISc Bangalore. He was awarded "The Sayed Husain Zaheer Medal (2014)" of INSA in 2014. He received Prof. Rais Ahmed Memorial Lecture Award from the Acoustical Society of Inida in 2016. He was an Associate Editor for the IEEE Transactions on Audio, Speech and Language Processing during 2003-2006.

Abstract:
In this talk I will discuss the background for Artificial Neural Networks (ANN), and evolution of architectures of ANN for pattern recognition tasks. The key issue in this evolution is learning. Hence the issue of learning in ANN in relation to human learning is addressed. The shift from learning to deep learning to bridge the gap, and the resulting evolution of architectures are discusseed in some detail. This talk is a self-contained one, and does not assume any prior knowledge of this subject. Some basic understanding of principles of pattern recognition and statistics will be useful. The contents of the talk are as follows:

1. Background for ANN
2. Pattern recognition by ANN and humanbeing
3. Learning by feedforward networks: Backpropagation learning
4. Learning by feedback networks: Boltzmann learning
5. Deep learning: Restricted Boltzmann Machine and Deep Belief Networks
6. Current applications of deep learning
7. Deep learning by ANN vs human learning: What to expect in future

References:

1. B Yegnanarayana: Artificial Neural Networks, Prentice-Hall of India, 1999
2. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, August 2016, www.deeplearningbook.org
3. Yann LeCun, Yoshua Bengio and Geoffrey Hinton, Deep Learning, Nature, Vol 521, pp. 436-444, 28 May, 2015

2.

Speaker: Dr. EZRA MORRIS ABRAHAM, Universiti Tunku Abdul Rahman, Malaysia
Title: IoT: Ride the Next Innovation Wave
Brief bio of the speaker

Morris Ezra received his B. Eng degree from Bharathiar University, India, his M.E degree from Anna University, India and his Ph.D degree from Multimedia University, Malaysia. He joined Karunya Institute of Technology as a lecturer in 1993, before moving to Malaysia in 1998. In 2008 he joined as assistant professor with University Tunku Abdul Rahman, Kuala Lumpur Malaysia and became an associate professor in 2014. Since September 2015 he has been the Head of Program for graduate and post graduate programmes in engineering. His research area includes digital signal processing, wireless adhoc networks, optimization using PSO, GA/IGA and mobile communication. He has published over 40 papers in international journals and conferences. He is a currently a senior member of IEEE and member of IET.

Abstract:
Internet of Things (IoT) is increasingly becoming the topic of conversation both at the workplace and outside. Currently there are about 3 billion devices connected to the internet. By 2020 it is estimated that we will have about 30 billion devices connected to the internet. The rate at which we are generating data is outpacing our ability to analyze it. Most enterprises are finding it difficult to manage the data that is generated. The main challenge is to turn these massive data streams from a liability to asset. Descriptive and diagnostic analytics are commonly used to analyze the problems that arise in the industry. The next step is to move towards predictive and prescriptive analytics. IoT is expected to shift the operational model of IT industries. This talk will highlight the challenges faced by the industry and the current researches that are being conducted to solve complex problems using IoT and Data Analytics.

3.

Speaker: Dr. STELLA MORRIS, Universiti Tunku Abdul Rahman, Malaysia
Title: Intelligent Control of STATCOM & UPFC for Transient Stability Enhancement
Brief bio of the speaker:

Dr. Stella Morris received her B.E degree from Madurai Kamaraj University, India, her M.E degree from Anna University, India and her Ph.D degree from Multimedia University, Malaysia. She has been in the teaching industry since 1992 and has worked for various Engineering Institutions in India, Malaysia and New Zealand. Besides teaching undergraduate students, she has been actively involved in research in the areas of power systems stability, power system dynamics & control, FACTS devices & their control, soft computing, optimization, distributed generation, renewable & green energies, green vehicles and smart grid. She is a faculty member of Universiti Tunku Abdul Rahman (UTAR), Malaysia since 2008. She is associated with Lee Kong Chian Faculty of Engineering and Science. Over the past years, she has worked as a co-researcher in a number of external/internal research grants and award winning projects. She has about 50 research publications in referred journals and conference proceedings. She is a senior member of the IEEE and a life member of the ISTE.

Abstract:
Modern power systems are going through a paradigm change from centralized generation, to distributed generation, and further on to smart grids. The original concept of centralized bulk generation, highly available transmission system, radial distribution system and passive load does not seem to be sustainable. The highly variable renewable energy sources, heavily utilized transmission, distribution with bidirectional flows and loads/microgrids that can act as a resource are familiar drifts for the future.The growth in energy demand is increasing at a faster rate as compared to that of the transmission capability. Due to the difficulty in procuring rights-of-way to build new transmission lines and steady increase in energy demand, sustaining power system stability becomes a tough and very taxing problem. This has forced the transmission networksto their physical limits, where outage of lines or other equipment could result in the rapid failure of the entire system. This has increased the need of improvements in the transfer capability of the system while maintaining the system security and reliability.FACTS technologies with a suitable control strategy offer competitive solutions to today’s power systems and hence increase the system stability margin.

Although the basic controllers are easy to design, their performances deteriorate when the system operating conditions vary widely.In case of contingencies, changed operating conditions can cause poorly damped or even unstable oscillations.The lack of intelligence, learning, and adaptation capability in the control methods reveal the need for continuous expert intervention for the control of non-linear systems.Optimization based on genetic algorithms and intelligent control are defined to optimize the performance of the modern electrical network. Optimization and intelligent control are accomplished by self-adapting the controller gains and converters gains to achieve the best performance.The presentation will discuss the application of genetic algorithms and intelligent controls such as fuzzy control and ANN approach to STATCOM and UPFC for enhancing the transient stability of power systems.

4.

Speaker: Dr. SS Dash
Title: Issues and Challenges of Integration of Renewable Energy into Smart Grid

Brief bio of the speaker:
Subhransu Sekhar Dash is a Professor and Head of the Dept. of EEE at SRM University, Chennai, Tamilnadu, India. He has guided more than 20 PG students, and is currently guiding 15 research scholars. His areas of interest are power system operation, control and stability, power quality and FACTS.

Abstract:
The renewable energy sources have increased significantly due to environmental issues and fossil fuels elevated cost. Integration of renewable energy sources to utility grid depends on the scale of power generation. Large scale power generations are connected to transmission systems where as small scale distributed power generation is connected to distribution systems. There are certain challenges in the integration of both types of systems directly. Due to this, wind energy has gained a lot of investments from all over the world. However, due to the wind speed‘s uncertain behavior it is difficult to obtain good quality power, since wind speed fluctuations reflect on the voltage and active power output of the electric machine connected to the wind turbine. Solar penetration also changes the voltage profile and frequency response of the system and affects the transmission and distribution systems of utility grid.

Smart grid technology is the key for a reliable and efficient use of distributed energy resources. The recent resurgence of interest in use of renewable energy is driven mainly by the need to reduce the high environmental effects of fossil based energy systems and diminishing fossil fuel reserves. Amongst all the renewable sources solar power takes the prominent position due to its availability in abundance. From technological point of view, solar PV has reached maturity. The challenges faced by grid operators now have less to do with core technology and more to do with integrating PV system to the grid. Recently, the concept of smart grid has been successfully applied to the electric power systems.

5.

Speaker: Dr. Kyung-tae KIM, Prof. of ECE, KLU
Title: 4 Questions in Digital Signal Processing

Brief bio of the speaker:
Dr. Kyung-tae Kim received his bachelor and master degrees in Electronics Engineering at Kyung-bok National University and Yonsei university of Korea respectively and doctorate from Tohoku University, Japan. He has been in the teaching industry from 1985 and has worked for various research institutes and universities in Korea, Japan, USA. At present, he is a professor in the department of Electrical and Electronics Engineering, Kalasalingam University, India. His research interest includes speech processing, image processing and implementation of input/output system for 3 dimensional display.

Abstract:
In 1928, Harry Nyquist who was a Swedish born American electronic engineer introduced the work on determining the bandwidth requirements for transmitting information, and in 1949, based on Nyquist works, Claude Shannon who was born in Michigan(USA), known as ‘the father of information theory’, developed the sampling theorem which is the bridge of analogue and discrete worlds, that is, how to decide the sampling rate(frequency) for converting analogue signals into discrete-time signals with perfect recovering from discrete signals to analogue signals. Until mid of 1990, the area of digital signal processing was not spread practically, because of slow and expensive signal processing devices. But from the end of 1990, digital computer including micro-processor, micro-controller, digital signal processor have been developed very rapidly because of the technologies of integrated circuits. Then nowadays, the technologies of digital signal processing are spread in all of the fields in control system, communication, optimization, power plants, mechanical, chemical, civil, all design, medical fields as well as toys. Like this, most of the systems are digitalized except the contact points of input and output between real worlds and systems. Therefore, however much the importance of digital signal processing is emphasized, it is not enough. Despite of these very wide applications of digital signal processing, many students and researchers have been felt to be difficult, and tendency not to know the basic concepts clearly, true understandings, physical meanings of some equations and terminologies. For these, the speaker will deliver the 4 questions which are basics and necessary theories for digital signal processing. Those are: 1) -10 Hz is there? If yes, why do you need this? 2) Sampling frequency most of you know is correct? 3) The frequency components resulted from Fourier transform is reliable and correct? 4) What is the unit of sinusoidal function? And what can you do from this simple unit? From this keynote speech, all attendants of this international conference will get the confidences of their knowledge, and broaden their ways of thinking, and become aware of the simplicities and easiness of the digital signal processing.

6.

Speaker: Swagatam Das, Indian Statistical Institute, Kolkata, India
Title: Engineering Optimization with Differential Evolution

Brief bio of the speaker:
Swagatam Das is currently serving as a faculty member at the Electronics and Communication Sciences Unit of the Indian Statistical Institute, Kolkata, India. His research interests include evolutionary computing, pattern recognition, multi-agent systems, and wireless communication. Dr. Das has published one research monograph, one edited volume, and more than 200 research articles in peer-reviewed journals and international conferences. He is the founding co-editor-in-chief of “Swarm and Evolutionary Computation”, an international journal from Elsevier. He also serves as the associate editors of the IEEE Trans. on Systems, Man, and Cybernetics: Systems, IEEE Computational Intelligence Magazine, IEEE Access, Neurocomputing (Elsevier), Engineering Applications of Artificial Intelligence (Elsevier), and Information Sciences (Elsevier). He is an editorial board member of Progress in Artificial Intelligence (Springer), PeerJ Computer Science, International Journal of Artificial Intelligence and Soft Computing, and International Journal of Adaptive and Autonomous Communication Systems. Dr. Das has 11,000+ Google Scholar citations and an H-index of 50 till date. He has been associated with the international program committees and organizing committees of several regular international conferences including IEEE CEC, IEEE SSCI, SEAL, GECCO, and SEMCCO. He has acted as guest editors for special issues in journals like IEEE Transactions on Evolutionary Computation and IEEE Transactions on SMC, Part C. He is the recipient of the 2012 Young Engineer Award from the Indian National Academy of Engineering (INAE).

Abstract:
Differential Evolution (DE) is arguably one of the most powerful stochastic real-parameter optimization algorithms of current interest. DE operates through similar computational steps as employed by a standard Evolutionary Algorithm (EA). However, unlike traditional EAs, the DE variants perturb the current-generation population members with the scaled differences of distinct population members. Therefore, no separate probability distribution has to be used for generating the offspring. Since its inception in 1995, DE has drawn the attention of many researchers all over the world resulting in a lot of variants of the basic algorithm with improved performance. This talk will begin with a brief but comprehensive overview of the basic concepts related to DE, its algorithmic components and control parameters. It will subsequently discuss some of the significant algorithmic variants of DE for bound constrained single-objective optimization. Application of the DE family of algorithms in complex optimization scenarios like constrained, large-scale, dynamic and multi-modal optimization problems will also be included. The talk will finally discuss a few interesting applications of DE and highlight a few open research problems.

7.

Speaker: N Kumarappan, Professor, Annamalai University, India
Title: Cuckoo Search Based Power Dispatch in Microgrid

Brief bio of the speaker:
Dr. N. Kumarappan received his M.E and Ph.D in Power System Engineering from Annamalai University and Anna University respectively. He has 29 years of experience in teaching. His research work includes 115 publications in various areas of power system. He has guided 5 doctrate students and more than hundreds of PG students. He bagged various prizes and awards from IEEE and AICTE. At present, he is the chair of IEEE CIS Madras section and the head of Electrical department of Annamalai University.

Abstract:
In present scenario economic dispatch for the microgrid (MG) is better suited to the requirements of a system in actual operation because it not only considers the lowest cost in a scheduling cycle but also coordinates between different distributed generations (DGs) over many periods. Wind energy and solar energy are subjected to random variations and intervals, so there is a great difficulty in solving the economic dispatch problem. In this presentation, different distributed generations are employed in MG which includes photovoltaic arrays, wind turbine, fuel cell, diesel engines, gas-turbine and battery. In the present work the MG is considered to be operating in islanding mode. The main objective of this work is to minimize the generation cost and emission cost of the MG while satisfying system hourly demand and system constraints. Economic dispatch for MG involving DGs is an optimization problem and in this presentation Cuckoo Search Algorithm (CSA) is used to perform the optimization process. The results obtained from CSA is compared with Particle Swarm Optimization (PSO) algorithm and it is inferred that CSA shows better global convergence when compared to PSO and also gives good optimum solution by reducing system generation cost and emission cost.

8.

Speaker: Dr.S.Hosmin Thilagar
Title: Electric Vehicle Technology: Past Present & Future

Brief bio of the speaker:
Dr S Hosimin Thilagar has completed BE degree in Electrical and Electronics Engineering and ME Degree in Power Systems Engineering, both from Madurai Kamaraj University in the year 1992 and 1994 respectively. He pursued his PhD programme at IIT Madras in the area of Electrical Machines. Presently he is working as Associate Professor in the Department of Electrical and Electronics Engineering at Anna University, Chennai. He is also serving as Deputy Director of Academic Courses, Anna University. Three scholars have earned PhD under his guidance and presently he is guiding five more scholars. He has 22 research publications and out of which 14 in refereed international journals and 8 in refereed international conferences. He has completed 2 funded research projects as co-investigator sponsored by C-DAC Trivandrum and Bhabha Atomic Research Centre, Mumbai worth of 70.4 lakhs. Presently he is the Principal Investigator of a research project from CVRDE to study the electrical power flow of Arjun Tank Mark II worth of 19.55 lakhs. He also acted as the coordinator of National MEMS design centre and through which he initiated MEMS design activity at Anna University. More than 50 multi-disciplinary research project works were undertaken by the UG, PG students and PhD research scholars as part of their degree programme. He has one granted patent for the design of "CIRCULAR MICROGRIPPER". He has also applied for a second Patent on “MECHANICAL GRIPPERS FOR HANDLING PLURALITY OF MICRO COMPONENTS which is under examination. His general interest is popularisation of science amoung students and for which he had participated in number of activities in schools and colleges and sky watching programmes.

Abstract:
Exhaust emission of the conventional internal combustion engine vehicles (ICEV’s) is a major source of urban pollution, which increases the green house effect and in turn the global warming. Further, dependence on oil as the sole source of energy has economical and political implications, as the number of automobiles produced in the world have crossed a billion just in the last 15 years. Therefore, environmental and economic issues demand clean, efficient and sustainable vehicles for transportation. Indeed the increase in availability of electrical energy from renewable sources viz., solar and wind is heartening. With electrical energy as the major source, the electric vehicle (EV) technology along with its zero-emission features is a very promising and emerging automobile technology and going to be the next big revolution in auto-industry. Way back in 1900’s the EV technology emerged and occupied 38% of the automobile market. Due to the inconvenience of battery charging soon it disappeared. However with the growth of the enabling technologies and environmental and economic concerns renewed the interest in research and development of EV’s. General motors introduced the first EV in 1995 but soon got discontinued as it could not meet the consumer market for long distance transportation, where the battery storage limit was the bottleneck. In 1999, Toyota introduced Toyata Pirus - a Hybrid Electric Vehicle (HEV) powered by both the IC engine and the electric motor. This proved to be a competitor to conventional ICEV’s, both from the environmental and economic viewpoint. Thanks to the advancement in battery technology and the architecture of HEV’s its performance has improved and started slowly replacing the ICEV’s as a long distance vehicle too. Emergence of fuel cell technology is now sure to outsmart the limitations of battery source as it assures manifold increase in generation and continued supply of electrical energy during transportation. However, the cost of the fuel cell is proving to be a bottleneck. The next generation technology in EV’s is the Plug-in Electric Vehicles (PLEV’s). The idea is to have plug-in charging stations sufficiently dotted on the Highways/commercial complexes and ensure speedy charging of batteries. Commercial models are already out in the market that assures transport of the EV’s for a range of distance from 30 kM upto 300 kM. EV based automobile technology has advanced to such an extent that the vehicle reaches a speed of 200 kM/hour in just 7.1 seconds. Year 2017 is bound to see numerous EV’s, both light and heavy, for urban and long range transportations. Research is also being pursued in the direction of tapping the stored electrical energy from the batteries of PHEV’s and supply back to the grid at the hour of power shortage. However, this can only become a reality when the number of PHEV’s exponentially increases and replaces the ICEV’s in a big way. This can be made to happen when the cost factor is sufficiently addressed. Indeed the superiority of EV automotive technology and its research outcome shows that that day is not too far.

Baseline of Plug-in Electric Vehicles is 125 miles