IPIARTI 2019

Keynote 1 : Professor DR. JANUSZ KONRAD

Department of Electrical and Computer Engineering, Boston University, USA

BIO:Janusz Konrad received the Master’s degree from Technical University of Szczecin, Poland and the PhD degree from McGill University, Montréal, Canada. He joined INRS-Télécommunications, Montréal, first as a post-doctoral fellow and then as a faculty member. Since 2000, he has been on faculty at Boston University. He is an IEEE Fellow and a recipient of several IEEE and EURASIP Best Paper awards. He has been actively engaged in the IEEE Signal Processing Society as a member of various boards and technical committees, as well as an organizer of several conferences. He has also been on editorial boards of various EURASIP journals. His research interests include video processing and computer vision, stereoscopic and 3-D imaging and displays, visual sensor networks, human-computer interfaces, and cybersecurity.

Title:User Authentication for Natural User Interfaces (NUIs)
The landscape of user interfaces has dramatically changed in the last two decades and transformed the way we interact with computing devices. We have become accustomed to interaction involving touch, speech or gesture, and use them daily on smartphones, laptops, smart speakers, wearables and AR/VR headsets. The interfaces that leverage these natural, intuitive, everyday user behaviors are known as Natural User Interfaces (NUIs). As NUI-enabled devices become prevalent, the risk of exposing private information will increase for such devices can be used to authorize various transactions, e,g., smartwatches and smart speakers now enable e-payments while airline smartphone apps allow updating passport information. Clearly, convenient and robust authentication mechanisms are needed to protect sensitive information and prevent unauthorized access. I will present a new authentication taxonomy for NUIs and describe state-of-the-art methods recently developed at Boston University and New York University. I will focus on user authentication from 2-D touch gestures performed on a multi-touch screen and from 3-D free-space gestures performed in front of a depth camera. Compared to traditional authentication methods based on memory, such as alphanumeric passwords, these new approaches require low mental effort and, compared to biometric methods, such as face, fingerprint or iris recognition, are renewable (can be changed if compromised). These are very appealing traits given the deluge of passwords one has to memorize today.

More details

Keynote 2 : AsSOCIATE Prof. Dr. Dhananjay Singh

Hankuk University, Korea

BIO:Dr. Dhananjay Singh is an Associate Professor in Electronics Engineering and the Director of ReSENSE Lab at Hankuk (Korea) University of Foreign Studies (HUFS), Seoul, South Korea. He received B. Tech. degree in Computer Science and Engineering from VBS Purvanchal University, India and M. Tech. degree in Wireless Communication & computing from IIIT-Allahabad, India. He received Ph.D. degree in Ubiquitous IT from Dongseo University, Busan, South Korea. Before joining the HUFS, he worked as a senior member of engineering staff with the division of Future Internet Architecture at ETRI, Korea and PostDoc research fellow with division of fusion and convergences of mathematical sciences for the developing future internet model at National Institute of Mathematical Sciences (NIMS), Daejeon, South Korea. He was also a Research Assistant in computer science and engineering dept. at MNNIT-Allahabad, India. He is also the Chief Technical Officer (CTO) at MtoV Inc., Daejeon, South Korea.

He is a senior member of ACM & IEEE Society. He is also a distinguished invited speaker in the Forum of Brazil-Korea on Science and Technology, deployment and Innovation at UNISINOS, Sao Leopoldo, Brazil. He is the author of 2 books, 5 chapters, 7 international patents and 100+ international research publications. He have delivered 50+ invited and keynote talks. He is very active TPC and an editorial board member of 100+ major conferences and journals especially in the field of Network and Communication. His research interests focus on the design, analysis, and implementation of algorithms and protocols based on network and communication with specialization in wireless and communications, embedded systems, mobile and cloud computing to solve real-world problems based on Internet-of-Things, Machine-to-Machine Communication, Smart City Technologies and Future Internet Architecture and services.

Title:Connected Vehicles for Driver's Safety and Vehicle Security

Nowadays, automotive vehicles related projects are evolving rapidly and users are shifting from local servers to community data centers. Therefore, automotive markets are desperately in need of solutions that can improve safety of driving, security of vehicles as well as the need to reduce the cost of ownership of a vehicle. The idea is to utilize OBD-II port and Internet of vehicle's dashboard camera to enhance the control and accident prevention/monitoring services. The proposed idea has capability to capture and share their real-time accident/traffic footage into text, audio and video format to the concerned authorities such as nearest vehicles, police staff, hospital, family members, insurance company and vehicle repairing authorities, instantly along with the location. In this talk, I would like to discuss about automotive technology solutions for both driver safety and vehicle safety for smart driving in the personal/public scenario. In addition, we will discuss about intelligent vehicular technologies and security challenges for their possible solutions with some simulation and testbed results.

More details

Keynote 3 : Dr. Farshid PirahanSiah

MiMOS, Malaysia

BIO:Dr. Farshid PirahanSiah is a senior researcher at MIMOS Berhad (Malaysia's national R&D center in ICT) in area of computer vision, video analysis and machine learning. He has received PhD and Master’s degrees in computer science from National University of Malaysia (UKM). He has written numerous papers on the topic of computer vision based on his research and consultative works. He conduct several workshops in computer vision, OpenCV, hands-on workshops in deep neural networks for computer vision, and deep reinforcement learning. He is the author of several international research publications, book chapters, patents, and delivered invited and keynote talks. His research include video processing and computer vision, robotics, camera calibration, image pyramid, optical flow, video stabilization, robot localization, fuzzy sets and systems. He was teaching assistant for several courses such as, OpenCV, Computer Vision, intelligent systems, research tools, and artificial intelligent system. His research interests include deep reinforcement learning, computer vision with Convolutional Neural Network (CNN), and robotics.

Title: Deep Learning utilization in Computer Vision Applications  

Continues improvement in machine learning methods has the huge influence in computer vision applications. Multiple methods such as, deep neural network, deep reinforcement learning, and GAN are hot topic today in terms of research and industry. The emerging field of deep learning and deep reinforcement learning has led to remarkable empirical results in rich and varied domains like robotics, strategy games, and multi agent interaction. I will present a recent advancement in machine learning. My focus is on latest applications on computer vision, Convolutional Neural Network, deep reinforcement learning.

More details