Keynote Speakers

Dr. Ammar BELATRACHE Northumbria University, Newcastle, UK

1. Dr. Ammar Belatreche received the Ph.D. degree in Computer Science from Ulster University, UK. He joined Northumbria University in May 2018. He is currently a Senior Lecturer in Computer Science and Programme Leader for the MSc ed Computer Science in the Department of Computer and Information Sciences. He is a member of the Computational Intelligence and Visual Computing (CIVC) research group. Previously he worked as a Research Associate in the Intelligent Systems Research Centre (ISRC), Ulster University, then as a Lecturer in Computer Science in the School of Computing and Intelligent Systems, Ulster University, Derry, UK. He has extensive experience across academic and R&D in the areas of bio-inspired intelligent systems, machine learning, face detection and recognition, structured and unstructured data analytics, capital markets engineering, image processing and understanding. He has led a number of research and consultancy projects and has successfully supervised/co-supervised 8 PhD students to completion. He is a fellow of the Higher Education Academy, an Associate Editor of Neurocomputing and has served as a Program Committee Member and a reviewer for several international conferences and journals.

Talk title:

On biologically inspired computational intelligence: opportunities and challenges

The existing literature documents extensive work on pattern recognition systems using various classical machine learning and traditional algorithmic techniques. However, robust and reliable pattern analysis remains a very challenging task. For instance, while the human brain performs object detection and recognition robustly and with apparent ease, computer algorithms continue to find this a difficult task due to changes in object appearance in still images and video sequences, camera viewpoint, scale, orientation, and other common visual variations. Given that such challenges still remain with traditional machine learning approaches, an exploration of biologically inspired solutions that behave adaptively and autonomously through learning may help account for the well documented superior human and primate recognition performance and offer unique opportunities for the design of brain and bio-inspired robust and reliable pattern analysis systems. In an effort to devise bioinspired approaches which mimics the way the brain encodes and processes information, this talk discusses biologically plausible brain-like neural network systems, the potential computational power they offer and their potential applications. Unlike traditional rate-based neural networks, spiking neural networks offer a more biologically plausible model of how real biological neurons represent and communicate multi-modal information for performing different cognitive and perceptual tasks. I will provide a historical perspective on the evolution of neural networks introducing the concept of spiking neurons and their biological plausibility. I will review existing spiking neuron models and outline the main differences with their classical rate-based counterparts as well as their main computational advantages and disadvantages. I will then delve into the various information encoding schemes used by the brain followed by a discussion of the concept of neural plasticity and the related learning paradigms. I will then describe some of the recent advances in applying spiking neural networks to solve real-world problems including some of our research on developing offline and online supervised and unsupervised learning methods for effective and efficient training of spiking neural networks with an illustration of a range of applications to pattern recognition, image understanding, biometric security systems and medical image analysis. Finally, I will highlight some of the remaining challenges and opportunities for the future.

pat

Srikanta Patnaik, Ph. D.

Professor, Department of Computer Science and Engineering

SOA University, Bhubaneswar India

Editor-in- Chief,

International Journal of Information and Communication Technology

International Journal of Computational Vision and Robotics

Springer Book Series on Modeling and Optimization in Science and Technology [MOST]

Advances in Computer and Electrical Engineering (ACEE) Book Series
Advances in Medical Technologies and Clinical Practice (AMTCP) Book Series

2. Dr. Srikanta Patnaik is a Professor in the Department of Computer Science and Engineering, SOA University, Bhubaneswar, India. He has received his Ph. D. (Engineering) on Computational Intelligence from Jadavpur University, India in 1999 and supervised 18 Ph. D. theses and more than 50 M. Tech theses in the area of Machine Intelligence, Soft Computing Applications and Re-Engineering. Dr. Patnaik has published more than 100 research papers in international journals and conference proceedings. He is author of 2 text books and edited more than 20 books and Special issues from various international journals, published by leading international publisher like Springer-Verlag, Elsevier, Kluwer Academic, etc.. Dr. Patnaik is the Editors-in-Chief of International Journal of Information and Communication Technology and International Journal of Computational Vision and Robotics published from Inderscience Publishing House, England and also Editors-in-chief of Book Series on “Modeling and Optimization in Science and Technology” published from Springer, Germany and also Editor-in-Chief of the book series "Automation, Control and Robotics" published from River Publishing House, Netherland.

He is Guest Professor at two Chinese universities i.e. Kunming University of Science and Technology, and Anhui Wenda University of Information and Engineering.

Dr. Patnaik has traveled widely across Asian and European countries such as China, Hong Kong, Singapore, Spain, Morocco, Algeria, Iran, South Korea, Malaysia, Indonesia, Philippines, Thailand, Vietnam on various assignments.

Nature Inspired Computational Intelligence

Nature-inspired Computational Intelligence is an interdisciplinary field and a branch of artificial intelligence that employs processes, which is involved in evolution of living beings, biology and nature for solving complex problems.Artificial Intelligence covers higher level processes like problem solving, reasoning, making inferences in abstract and virtual worlds that consist of precisely defined states and operations in closed systems unlike real world.

During the last decade, due to the convergence of bio, nano and information technology, an appreciable amount of research has been done on sensors and actuators, which leads to the design of many autonomous agents and robots and subsequently the development of Multi Agent Systems (MAS) for real world applications.
Usually real-time systems are complex, inconsistent, uncertain and imprecise, which is difficult to handle using traditional methods. But inspiring nature has leaded to finding clues for solution of unsolved problems of this kind. Nature-inspired computing has been existing since last many decades in the form of bio-inspired computing which includes small number of tools like evolutionary computing, neural networks, particle swarm optimization, and ant colony optimization. Gradually other forms of intelligence are added to nature-inspired computing such as artificial bee colony optimization, cuckoo search, firefly algorithm, bacteria foraging optimization algorithm, intelligent water drop optimization, gravitational search, and harmony search along with many more.
These computational techniques use biological or evolutionary processes as main component in the efficient design and implementation of the artificial intelligent algorithms. Nature-inspired computational intelligence can be applied to a variety of
problems, ranging from engineering and scientific research to manufacturing industry and business as they provide robust and flexible solutions along with learning and adaptability as compared to traditional optimization techniques. It can be applied to solve optimization issues in any domain and may be unified as Nature-inspired computing and optimization (NICO). While studying the nature, researchers found a number of cases from ant, bee, flock of birds, frog, cuckoo,
firefly, bat, crocodile etc., which can be modelled for real-world problem.

Looking at the emergence of bio, info and nano technology we are confident that the field of the nature-inspired computing and optimization can solve many complex real world problems.

richard

Pr. Richard CHBEIR, Ph.D. in Computer Science
Full Professor in Computer Science

Head of LIUPPA Laboratory
Université de Pau et des Pays de l'Adour (UPPA)

3. Pr. Richard Chbeir received his PhD in Computer Science from the University of INSA DE LYON-FRANCE in 2001and then his Habilitation degree in 2010 from the University of Bourgogne. He is currently a Full Professor in the Computer Science Department in IUT de Bayonne in Anglet France, and the head of the LIUPPA laboratory at Univ. Pau & Pays Adour. His current research interests are in the areas of multimedia information retrieval, Web Similarity, Event extraction, and digital ecosystems. Richard Chbeir has published in international journals, books, and conferences, and has served on the program committees of several international conferences. He is currently the Chair of the French Chapter ACM SIGAPP. Richard Chbeir teaches several courses in the Computer Science Department of the University of Pau University in Anglet-France.

Title talk: A multimedia sensor network

A multimedia sensor network is a sensor network that consists of at least one sensor outputting multimedia data (video, audio, etc.). This kind of sensor network is a fairly new research domain. Hence, techniques for processing complex events in the context of multimedia sensor networks remain underdeveloped as they have rarely been considered previously. In this talk, I will thoroughly survey existing studies so to show the requirements of a suitable language for processing complex events in multimedia sensor networks. I will show that no existing language can fully address all the necessary requirements. I will present some of the results of our research team. Particularly, i will briefly present GST-CEMID, a pipelining-based framework to support Complex Event ModelIng and Detection in MSNs. GST-CEMID relies on: (i) an extension of GStreamer (a framework for processing multimedia data in Linux- based operating systems); (ii) JSON-like configuration files; and (iii) an ontology-based data model. GST-CEMID allows users to model MSN infrastructure and complex events, and then dynamically generates an event processing pipeline according to the models provided by users. I will also show some interesting results conducted to validate our approach.

4. Pr. Okba KAZAR, Biskra University, Algeria

okba

https://www.researchgate.net/profile/Okba_Kazar
https://scholar.google.com/citations?user=atn9oSkAAAAJ&hl=fr
Professeur Okba Kazar was born at Biskra (Algeria) in 1962. He obtains his magister degree in 1997 from the Constantine University (Algeria) working on artificial intelligence field. Heobtained his PhD degree from the same university in 2005. He is a member of editorial board of some Journals. He is published more than 240 papers in international journals and communication in an international conference. He participates as a session chair in international conferences, he also publishes a book “Manual d’Intelligence artificielle” and five chapters book.His main research field is artificial intelligence, he is interested in the multi-agent systems and their applications, PHM in medical and industrial fields, ERP, advanced information systems, Web services, semantic Web, bigdata, internet of things and cloud computing and information communication technologies.
He had the status of visiting the professor in many universities in Europe especially in France. He completed the supervision of more than 50 magister dissertations and about 30 doctoral theses in science and LMD. He has chaired sessions and plenary lectures at international conferences.
He has published the book " Manual of Artificial Intelligence" in Switzerland, he also has five book chapters. He is a member of the national university commission and vice-president of the national pedagogical committee of mathematics and computer science and president of the subcommittee of informatics. Professor KAZAR is currently a full professor at the computer science department of the University of Biskra, which he contributed to its founding and director of the Smart computer science laboratory (LINFI). He is at the origin of several educational of license and master in computer science as well as doctorate LMD.

Talk Title: Affective computing

Artificial intelligence is omnipresent; this dominance of intelligence is part of an improvement of everyday life and the socio-economic sector. Artificial intelligence has addressed several aspects from a knowledge-based system to smart home, smart city, smartphone, smart watch, smart car and smart social network.

In the field of robotics, the artificial intelligence trend concerns a very important aspect inbehavioral and interactional analysis namely emotion. More exactly, human emotion has become a challenge and a scientific lock for researchers and
roboticists.
A field of autonomous field of autonomous research in computer science has become a promoter of development of expectations for research in robotic field; it is about affective computing whose challenges come from the fact that a robot must better understand humans.
Emotion recognition is a recent area of research that aims to detect and recognize types of feelings such as anger, disgust, fear, happiness, sadness and surprise. Deep learning is a learning process that seems to meet the specificities of such an objective.

Online user: 1

RSS Feed