Manfred J. Schindler
Chair – 2015-2018 IEEE Conferences Committee
Chief Technology Officer – Anlotek Limited, USA
Title of the Talk: Wireless Communications, an RF Perspective
Abstract: Wireless communications have transformed our lives. Along the many contributing technologies that made this revolution possible, innovations in RF technology have played an important part. We will review some of the key contributing RF technologies, and how they evolved with the progression of mobile generations. We will also look at what is expected as the coming generation of networks and handsets come to market, and the technology challenges we anticipate.
Fred Schindler has spent his career in industry working on RF, microwave and mm-wave semiconductors, leading the development of advanced RF semiconductor products for commercial and defense applications. He currently works as an independent consultant and is Chief Technology Officer of Anlotek Ltd., an RF technology company. He has worked as an Engineering Director or Engineering Manager at Qorvo, RFMD, IBM, ATN Microwave and Raytheon. Fred earned a BSEE from Columbia University in 1979 and an MSECE from UMass Amherst in 1983. He holds 11 patents and has published over 40 technical articles. He has been active in the IEEE, the MTT Society and IEEE Conferences since 1990, including service as MTT President, VP and Secretary, Chair of the IEEE Conferences Committee, founding Chair of the Radio and Wireless Symposium, and Chair of the International Microwave Conference (IMS). He has contributed a column on Microwave Business to IEEE Microwave Magazine since 2011.
Prof. Shaikh Fattah, Postdoc (Princeton U, USA)
Professor, Dept. of EEEE & Director, INPE, BUET,
Associate Editor, CSSP (Springer)
Education Chair, IEEE Humanitarian Activity Committee (HAC)
Title of the Talk:
Machine Learning for Automatic Disease Detection from Capsul Endoscopy Images Based on Modeling of 2D data
Automatic disease detection is gaining high demand because of our excessive acquaintance with various types of digital devices. Automatic detection of Gastro-intestinal diseases from wireless capsule endoscopy (WCE) images has great demand because of its time consuming manual process and lack of ground truth data. In this talk, modeling the pixels of interest of WCE images utilizing probability density functions will be demonstrated, which we found very effective in classifying diseased and normal images. Here different machine learning techniques are applied to carry out the supervised classification. A special machine learning approach of handling multi-class disease detection problem will also be presented. Challenges involved in identifying a diseased image as well as detecting the affected region will be addressed in detail along with several results and analyses on practical WCE video data.
Brief Biography of Dr. Shaikh Fattah:
Shaikh Fattah received Ph.D. in ECE from Concordia University, Canada. He was a visiting Postdoctoral Fellow and later visiting Research Associate in the Department of EE at Princeton University, USA. He received the B.Sc. and M.Sc. degrees from BUET, Bangladesh, where he is currently serving as a Professor in the Department of EEE and Director of INPE. He was the winner of Concordia University’s the 2009 Distinguished Doctoral Dissertation Prize in ENS and was selected as one of the Great Grads of Concordia University in 2008-2009. During his Ph.D. program, he has received numerous awards. He is a recipient of the Dr. Rashid Gold Medal (in M.Sc.), URSI Canadian Young Scientist Award 2007, and Bangladesh Academy of Science-TWAS Young Scientists Prize 2014. Dr. Fattah has published more than 180 international journal and conference papers. His research interests include the areas of biomedical engineering, power and energy, signal processing, biometric, multimedia communication, robotics and artificial intelligence. His papers received Best Paper Awards in many conferences. Dr. Fattah is the recipient of most prestigious 2016 IEEE MGA Achievement Award, 2018 R10 Outstanding Volunteer Award, 2017 IEEE R10 Humanitarian Technology Activity (HTA) Outstanding Volunteer Award. He has been serving LRP Committee of IEEE PES and SDHT Committee of IEEE SSIT. He has been serving different committees of IEEE R10. He is the Education Chair of IEEE Humanitarian Activity Committee (HAC). He is the Senior Member of IEEE and Fellow of IEB.
Prof Celia Shahnaz (Concordia U, Canada)
Professor, Department of EEE, BUET, Dhaka, Bangladesh
Chair, IEEE Bangladesh Section
2018 Editorial board member, IET Signal Processing
Title of the Talk:
Capsule Network for Abnormality Detection in Musculoskeletal Radiographs
To treat the diseases or injuries of the joints, bones, muscles, and spine in both adult and pediatric imaging the musculoskeletal radiographs bring a signicant depth of expertise. Abnormality detection in the musculoskeletal study is backbreaking as more than 1.7 billion people are affected by musculoskeletal condition (BMU, 2017). Hence if we want to create enough opportunity to treat a maximum amount of patients, machine learning and deep learning can play a crucial role. CNN is an excellent deep learning method for image classication and other computer vision tasks. But CNN has exhibited some serious limitations when the images are rotated and deformed. Hence capsule network architecture is introduced in this paper for musculoskeletal radiographs abnormality detection and this capsnet architecture has shown very promising features that can help to vanquish the limitations of CNN. In addition, this capsule network has scored 10% higher kappa score than 169 layer densenet using less training data in the case of musculoskeletal radiographs abnormality detection. This feature of capsule network can help to use deep learning in such cases where an aggregate of a large amount of data is not possible. For image quality investigation, blind image spatial quality evaluator (BRISQUE) and naturalness image quality evaluator (NIQE) scores are measured and it is found that when the pixel size of the resized images are more close to the pixel size of the original images, we get a better approximation. Hence in the case of musculoskeletal radiographs abnormality detection, our method outperforms state-of-the-art method using a less amount of training data.
Celia Shahnaz received Ph.D. degree in electrical and computer engineering from Concordia University, Montreal, QC, Canada, in 2009. Currently she is serving as a Professor in the Department of Electrical and Electronic Engineering, BUET, from where she received her B.Sc. and M.Sc. degrees in 2000 and 2002, respectively. Dr. Celia is a senior member of IEEE, a fellow of IEB and has published more than 120 international journal and conference papers. Dr. Shahnaz was a recipient of the Canadian Commonwealth Scholarship and Fellowship for pursuing Ph.D. study in Canada in 2004. She is the recipient of Bangladesh-Academy of Science gold model for her contribution in science and Engineering in Bangladesh. She is the mentor of of 2nd prize winning project in the IEEE IAS CMD Robotics Contest 2018, USA and that of Ist prize winning project in the Category HEALTH FACILITY in IEEE IAS CMD Humanitarian Project Contest 2017, USA. She is the supervisor of 5th rank winning team in Signal processing cup (SPCUP) competition in ICASSP 2015, Australia. Recently, her papers have received best paper award of biomedical Engineering track at TENCON 2017, that of Humanitarian Challenge track at R10 HTC 2017, that of Biomedical Engineering track at IEEE WIECON-ECE 2016, and the best interactive poster award at icIVPR 2017. Her paper has been selected for top ten best paper award in the Student Paper Contest of the 2014 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), College Station, Texas, USA. She has received an award for supervising the 1st Prize winning project in Computer Group in the EEE Undergraduate Project Workshop (EUProW 2011), BUET, Bangladesh. Her paper was also selected for top ten best paper award in the Student Paper Contest of the 2008 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), Knoxville, TN, USA. She was the winner of the Best Student Paper Award in the 2008 IEEE International Conference on Neural Networks and Signal Processing (ICNNSP), Zhenjiang, China. She was selected as one of the finalists of the Student Research Presentation Competition in the 2009 SYTACOM Workshop, Montreal, QC, Canada. Her research interests include the areas of speech analysis, speech enhancement, multimodal emotion recognition, digital watermarking, audio-visual recognition for biometric security, multimedia communication, control system, robotics, signal processing, pattern recognition and machine learning for audio, video, biomedical and power signals. She is the member, Technical Committee, Image, Video, and Multimedia (IVM), Asia Pacific Signal and Information Processing Association (APSIPA).
Title of Talk : Application of Machine Learning in Imaging and Vision
Abstract: The development of Electroencephalography (EEG) sensor technology through wireless headsets and their connectivity with mobile devices has opened-up new ways of implementation of Brain Computer Interface (BCI) applications. Traditionally, EEG signals are used in diagnosing diseases. Since brain signals represent the physiological and behavioural information about a person, these signals are widely used in developing biometric, predictive, emotion and gaming applications. In the first part of the talk, analysis of EEG signals and few applications of EEG technology beyond clinical applications using brain-computer-interface (BCI), will be presented.
Balasubramanian Raman is a Professor in the Department of Computer Science and Engineering at Indian Institute of Technology Roorkee since December 2018. He was an Associate Professor in the Department of Computer Science and Engineering from September 2013 to December 2018. He had been with the Department of Mathematics, Indian Institute of Technology Roorkee from September 2004 to September 2013, where he was an Associate Professor and head of the Computer Vision, Graphics and Image Processing Laboratory. He was a Visiting Professor and a member of the Computer Vision and Sensing Systems Laboratory in the Department of Electrical and Computer Engineering at University of Windsor, CANADA during May – August 2009. He was a Lecturer of Computer Science and Information Systems at Birla Institute of Technology and Science, Pilani, India in 2003-04. He was a Post Doctoral Associate in the Department of Electrical and Computer Engineering (ECE), and a member of the Visualization Research laboratory (VIZ Lab), at Rutgers, The State University of New Jersey, USA from July 2002 to April 2003. He was also a Post Doctoral fellow in the Department of Computer Engineering and Computer Science (now the Department of Computer Science, CS), and member of the Computational Intelligence Research Laboratory (CIRL), at University of Missouri-Columbia (MU), Missouri, USA, from October 2001 to June 2002. He received his Ph.D. in Mathematics (2001) from Indian Institute of Technology Madras, India. He obtained his B.Sc and M.Sc in Mathematics from University of Madras in 1994 and 1996 respectively.