To invent, you need a good imagination and a pile of junk  - Thomas Edison 


Research Interests and Key Publications

Hybrid intelligent systems are becoming a very important problem solving methodology affecting researchers and practitioners in areas ranging from science, technology, business and commerce. It is well known that intelligent systems, which can provide human-like expertise such as domain knowledge, uncertain reasoning, and adaptation to a noisy and time-varying environment, are important in tackling practical computing problems.

 

My main research is on developing advanced intelligent systems using hybrid natural computation techniques. Research in natural computation includes a theoretical and empirical understanding of computing inspired from nature. Hybridization of different intelligent systems is an innovative approach to construct computationally intelligent systems consisting of artificial neural network, fuzzy inference systems, rough set, approximate reasoning and derivative free optimization methods such as evolutionary computation, swarm intelligence, bacterial foraging and so on. The integration of different learning and adaptation techniques, to overcome individual limitations and achieve synergetic effects through hybridization or fusion of these techniques, has in recent years contributed to a large number of new intelligent system designs.

 

We are already aware of several hybrid combinations like evolutionary computation- neural network, neural network - fuzzy inference system, fuzzy inference system- evolutionary computation, neural network- fuzzy inference system-evolutionary computation and so on. 

Important Research Publications

Intelligent Systems Generic Architectures

Integrated Hybrid Intelligent System Modeling

EvoNF: A framework to optimize fuzzy inference systems using evolutionary computation (global search) and neural network learning techniques (local search).

       EvoNF Applications

MLEANN: A framework for optimization of evolutionary artificial neural networks combining global search and local search techniques (MLEANN could be considered as a neural network that could learn how to learn).

       MLEANN Applications

i-Miner: A framework to cluster the data and perform function approximation/ classification.

 

Concurrent Hybrid Intelligent Systems

Cooperative Hybrid Intelligent Systems

Fusion of Soft Computing and Hard Computing

Ensemble of Intelligent Systems

Neuro-Fuzzy Systems

Hybrid Optimization Techniques

 

Computational Intelligence Applications Related Papers

Sensor Networks

Bioinformatics / Medical Informatics

Network Security

Information Security

Security in Computational Grids

Distributed Computing and Optimization (Computational Grids, P2P networks etc.)

Web Intelligence (Mining and Knowledge Discovery)

Web Services

Data Clustering

 

Data Mining and Applications

Decision Support Systems

Electricity Demand Analysis

Financial Modeling

Export Behavior Modeling

Weather Analysis

  • Ajith Abraham, Ninan Sajith and Babu Joseph, Will We Have a Wet Summer? Long-term Rain Forcasting Using Soft Computing Models, Modelling and Simulation 2001, Publication of the Society for Computer Simulation International, Kerckhoffs E.J.H. & Snorek M. (Eds.), ISBN 1565552253, Prague,  Czech Republic, pp. 1044-1048, 2001. 

  • Imran Maqsood, Muhammad Riaz Khan and Ajith Abraham, Intelligent Weather Monitoring Systems Using Connectionist Models, International Journal of Neural, Parallel & Scientific Computations, USA, Volume 10, pp. 157-158, 2002.

  • Imran Maqsood, Muhammad Riaz Khan and Ajith Abraham, Neural Network Ensemble Method for Weather Forecasting, Neural Computing & Applications, Springer Verlag London Ltd., Volume 13, No. 2, pp. 112-122, 2004.

  • Godfrey Onwubolu, Petr Buryan, Sitaram Garimella, Visagaperuman Ramachandran, Viti Buadromo and Ajith Abraham, Self organizing Data Mining for Weather Forecasting, Proceedings of the First European Conference on Data Mining, Lisbon, Portugal, ISBN: 978-972-8924-40-9, IADIS Press, pp. 81-88, 2007.

Knowledge Management in Social Regulation

  • Sonja Petrovic-Lazerevic, Ken Coghill and Ajith Abraham, Neuro-Fuzzy Support of Knowledge Management in Social Regulation, Knowledge Based Systems, Elsevier Science, Netherlands Vol. 17, Issue 2, pp. 57-60, 2003.

Image Processing

Intelligent Reactive Power Control

Fault Monitoring of Electronic Systems

Multi Criteria Decision Making

 

Other Research Interests