Log in

Login to your account

Username *
Password *
Remember Me
From Brain Science to Intelligent Machines

HidInImage

Date: Wednesday 12/12/12
Venue: MS020
Time: 12.00 pm
Speaker: Mr Pratheepan Yogarajah
Affiliation: Research Associate, University of Ulster, Magee

 


 

HidInImage

Mr Pratheepan Yogarajah

Research Associate, University of Ulster, Magee

Abstract:

HidInImage enables the encryption and hiding of secret information (text or images) inside images using Steganography techniques. Secret information is hidden imperceptibly in that it cannot be detected by the human eye. Our innovative Steganograpy-based hiding solution plays a vital role in securing digital media content. It can authenticate imagery and enhance security. The steganography research field is proven and widely deployed - billions of watermarked content objects and hundreds of millions of watermark-enabled applications or devices exist worldwide. Users include major record labels, movie studios, broadcasters, advertisers, financial institutions and governmental document issuing agencies.


Short biography:


Pratheepan Yogarajah received the BSc (Hons) in Computer Science from the University of Jaffna, Sri Lanka, in 2001. He received his MPhil in Computer Vision in 2006 from the Oxford Brookes University, UK. Currently, he is a Research Associate and a part-time PhD student at the School of Computing and Intelligent Systems, University of Ulster, UK. His research interests include computer vision, image processing, steganography & digital watermarking and machine learning. School of Computing and Intelligent Systems, University of Ulster, UK. His research interests include computer vision, image processing, steganography & digital watermarking and machine learning.

 

Genetic and swarm optimisation algorithms for modelling and control of dynamic systems

Date: Wednesday 14/11/2012
Venue: MS020
Time: 1.00 pm
Speaker: Dr. Shafiul Alam
Affiliation: University of Dhaka, Bangladesh


 

Genetic and swarm optimisation algorithms for modelling and control of dynamic systems

By Dr. Shafiul Alam
University of Dhaka, Bangladesh

Abstract:

In evolutionary optimisation, genetic algorithms (GAs) and Particle swarm optimisation (PSO) are highly relevant for research and industrial applications, because they are capable of handling problems with multimodal characteristics, non-linear constraints and dynamic properties. On the other hand, a wide range of real-world problems requires multiple design objectives and constraints which are often competing in nature to be satisfied simultaneously. In such cases, the multi-objective GA or PSO algorithms can provide a set of trade-off solutions to the problem’s conflicting objectives in a single run. Here few modelling and control problems (of Robotics & Systems Biology) are discussed where single & multi-objective GA/PSO algorithms have been used as an alternative to conventional approaches.

Short biography:


Shafiul Alam is a Commonwealth Fellow in School of Computing, Engineering & Information Sciences, Northumbria University, Newcastle upon Tyne, under Commonwealth Fellowship Programme. He received his PhD from Department of Automatic Control and Systems Engineering, University of Sheffield, UK, in 2007 under same fellowship scheme. He also worked as a post-doc researcher in School of Computing, Informatics and Media, University of Bradford, UK, under an EU Erasmus Mundus project in 2009-2010. He completed B.Sc (Hons) and M.Sc degrees in Applied Physics and Electronics in 1995 and 1997 respectively from University of Dhaka, Bangladesh and currently he is an Associate Professor in the same department. His research interests include evolutionary algorithms, swarm intelligence, fuzzy logic control and artificial neural networks and its applications to modelling and control of dynamic flexible systems and Systems Biology.

 

A Case Study on neuroprosthetic applications Using Neural Network FPGA Based Hardware Modelling

Date: Wednesday 10/10/2012
Venue: MS020
Time: 1.00 pm
Speaker: Dr. Shufan Yang
Affiliation: Intelligent Systems Research Centre
University Of Ulster, Magee



A Case Study on neuroprosthetic applications Using Neural Network FPGA Based Hardware Modelling

By Dr. Shufan Yang
Intelligent Systems Research Centre
University Of Ulster, Magee

Abstract:

Integrating hardware into neural network modelling builds an effective bridge between electronic engineers and computational neuroscientists, allowing the latter to contribute more effectively in neuroengineering projects and thus speed up the time-to-market of neurotechnology products. In this work, we propose a neural mechanism for adaptive inhibitory control in a firing-rate type model based on current findings in animal electrophysiological and human psychophysical experiments. We then implement this model based on a field-programmable gate array (FPGA) prototyping system using dedicated real-time hardware circuitry. We anticipate that a fast FPGA-based prototyping platform with hardware evaluation framework will be useful in domains such as neuroprosthetic device, robotics, and bionic creativity engineering.

Short biography:

Dr Shufan Yang works on projects related with neural network FPGA based hardware modelling, led by Professor T.M. McGinnity at Intelligent Systems Research Centre, University of Ulster. She focuses on the development of methodologies to support the large scale simulation of Spiking Neural Networks (SNNs) on multiple FPGA platforms. She undertakes research in the general area of embedded system design with particular interests in bio-inspired and neuro-engineering and associated algorithm issues.
Shufan obtained her Ph.D in Computer Science from the University of Manchester (2010), supervised by Professor Steve Furber. Her Ph.D project was to implement a high-performance multiprocessor communication system for SpiNNaker chips that are used for the real-time modelling of large systems of spiking neurons. She did B.Sc. degree and M.Sc. degree at Hunan University, China. From 2003 to 2006, she was lecturer of Computer Science and chair of the Embedded and Networking Systems Laboratory in Hunan University, China. She was a software engineer from 1998 to 2000. Major projects in which she has been involved have included handset on-access layer implementation under VxWorks and implementation of embedded firewall on PowerPC boards.

IM-CLeVeR EU Project: “Intrinsically Motivated Cumulative Learning Versatile Robots”

Date: Wednesday 28/11/2012
Venue: MS020
Time: 1.00 pm
Speaker: Dr Yiannis Gatsoulis
Affiliation: Cognitive Robotics Team, ISRC, University of Ulster


IM-CLeVeR EU Project: “Intrinsically Motivated Cumulative Learning Versatile Robots”

By Dr Yiannis Gatsoulis
ISRC, University of Ulster

Abstract:

IM-CLeVeR is an Integrated Project (IP) project funded by the EC under FP7. It consists of eight European core partners from UK, Italy, Switzerland and Germany, and one consultant partner from USA. As an IP it brings together experts from different fields, those being robotics, machine learning, neuroscience and psychology.
IM-CLeVeR aims to develop a new methodology for designing robots controllers that can: a) cumulatively learn new efficient skills through autonomous development based on intrinsic motivations, and b) reuse such skills for accomplishing multiple, complex, and externally-assigned tasks. During skill-acquisition, the robots will behave like children at play which acquire skills autonomously on the basis of “intrinsic motivations”. During skill-exploitation, the robots will exhibit fast learning capabilities and a high versatility in solving tasks defined by external users due to their capacity of flexibly re-using, composing and re-adapting previously acquired skills.


Short biography:


Yiannis Gatsoulis is a Research Associate in the EU funded IP project "ImClever". He holds a PhD from University of Leeds and an MSc in Artificial Intelligence and Robotics from the University of Edinburgh. His research interests are in the areas of robotics and machine learning.

Graph Similarity -- Counting Through Matrices

Date: Wednesday 6/6/2012
Venue: MS020
Time: 1.00 pm
Speaker: Professor Hui Wang
Affiliation: School of Computing and Mathematics
University Of Ulster, Jordanstown

 



Graph Similarity -- Counting Through Matrices

 

By Professor Hui Wang
School of Computing and Mathematics
University Of Ulster, Jordanstown

Abstract:

Neighbourhood counting is a general methodology in designing combinatorial similarity, and is rooted in the concept of contextual probability. It has been specialised for different types of data, including multivariate, sequence and tree, resulting in different similarity measurements. In this talk, I will present recent work on graph similarity, which is inspired by the neighbourhood counting methodology.
I will first of all review the concepts of contextual probability and neighbourhood counting. I will then present a novel graph similarity, which is the number of all possible paths in a graph. An algorithm is devised to compute this similarity, which is based on adjacency matrix representation of graphs and is computed through matrix operations. This graph similarity is shown to be conceptually simple, mathematically concise, and practically tractable.
Short biography:
Hui Wang (BSc, MSc, DPhil) is Professor of Computer Science at the University of Ulster, Jordanstown Campus. His research interests include machine learning, data/text mining, uncertainty reasoning, and information retrieval. He has authored or co-authored 140+ journal/conference publications.
He is principal investigator of a number of regional, national and international projects (SAVASA, DEEPFLOW, BEACON, ICONS), and is co-investigator of several projects (STAR, TARSKI, UMIS). He is an associate editor of IEEE Transactions SMC-B, a member of the editorial board of International Journal of Computational Intelligence Systems, and an associate editor of International Journal of Machine Learning and Cybernetics.
He is chair of IEEE SMCS Ireland Chapter, and currently is a member of IEEE SMCS Board of Governors.