Journal of Intelligent & Fuzzy Systems - Volume 20, issue 1-2

Authors: Nguyen, Ngoc Thanh | Lim, Chee Peng | Jain, Lakhmi C. | Balas, Valentina E.

Article Type: Research Article

DOI: 10.3233/IFS-2009-0410

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 1-2, 2009

Authors: Song, Jae-Hoon | Jung, Jin-Woo | Lee, Sang-Wan | Bien, Zeungnam

Article Type: Research Article

Abstract: The main goal of this paper is to design an electromyogram (EMG) pattern classifier which is robust against muscular fatigue effects for powered wheelchair control. When a user operates a powered wheelchair using EMG-based interface for a long time, muscular fatigue often arises from sustained duration of muscle contraction. The recognition rate thus is degraded and controlling wheelchair gets more difficult. In this paper, an important observation is addressed that the variations of feature values due …to the effect of the muscular fatigue are consistent for sustained duration. Based on this observation, we design a robust pattern classifier through the adaptation process of hyperboxes of Fuzzy Min-Max Neural Network. We present, as a result, a significantly improved performance in terms of the continuous usage of wheelchair. Show more

DOI: 10.3233/IFS-2009-0411

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 3-12, 2009

Authors: Chakraborty, Jayasree | Konar, Amit | Jain, L.C. | Chakraborty, Uday K.

Article Type: Research Article

Abstract: This paper provides an alternative approach to the co-operative multi-robot path planning problem using parallel differential evolution algorithms. Both centralized and distributed realizations for multi-robot path planning have been studied, and the performances of the methods have been compared with respect to a few pre-defined yardsticks. The distributed approach to this problem out-performs its centralized version for multi-robot planning. Relative performance of the distributed version of the differential evolution algorithm has been …studied with varying numbers of robots and obstacles. The distributed version of the algorithm is also compared with a PSO-based realization, and the results are competitive. Show more

DOI: 10.3233/IFS-2009-0412

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 13-27, 2009

Authors: Yordanova, Snejana

Article Type: Research Article

Abstract: Most industrial plants are complex, nonlinear, time-varying with time delay, difficult to control. The single input fuzzy controllers (SI FCs) are promising in satisfying the high performance demands to the control systems of such plants and ensuring the fuzzy system stability, coping with system nonlinearity, plant model uncertainty and SI FC design. The aim of the present investigation is to derive robust stability requirements for an incremental PI-like SI FC closed loop system that serve the …development of a SI FC design method for the control of industrial plants with time delay and model uncertainty. The main contributions are: 1) modification of the Popov stability approach to study the SI FC system stability and to derive design rules; 2) derivation of robust stability criterion for a SI FC system and on its basis development of a SI FC tuning algorithm. The results are applied for the stabilisation of the air temperature in a furnace using MATLAB™. The advantages of the designed SI FC system are assessed in comparison with ordinary PI control system via simulations. The SI FC system preserves stability for a great range of plant uncertainties. The tradeoff is longer settling time of the nominal system transient responses. Show more

Keywords: Frequency domain, MATLAB, single input fuzzy controller design, system robust stability, temperature control, time delay

DOI: 10.3233/IFS-2009-0413

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 29-43, 2009

Authors: Ghosh, Madhumala | Konar, Amit | Jain, L.C. | Chakraborty, Uday K.

Article Type: Research Article

Abstract: The paper presents an analysis of chaos, limit cycles and stability in the antigen-antibody interactive dynamics. Both co-operation and competition of antibodies are considered in the dynamics. The classical approach of Lyapunov is employed here for the stability analysis of the dynamics. Computer simulations are undertaken to support the results of the analysis. Both temporal behaviors of the antibodies and their phase portraits are given to study their chaotic, limit cyclic and stable behavior. Results of …stability analysis of the dynamics are applied in garbage cleaning problem by a mobile robot. Show more

DOI: 10.3233/IFS-2009-0414

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 45-60, 2009

Authors: Datta, Ayan | Talukdar, Veera | Konar, Amit | Jain, Lakhmi C.

Article Type: Research Article

Abstract: The paper provides an alternative approach to protein structural class prediction employing artificial neural network. Existing works on protein structural class prediction are computationally intensive. The method employs SOFM for extraction of representative feature vectors, for the four different structural classes and then uses Principal Component Analysis for finding optimum feature vector dimension. Nearest neighborhood classification technique is finally utilised; to classify these protein datapoints to their respective classes. The proposed work …presented in this paper, maintains the same level of classification accuracy in minimum computation time, as it employs most prominent and reduced number of feature set for classification. Show more

Keywords: Bioinformatics, molecular biology, bio-computing, Evolutionary algorithm, soft computing, swarm intelligence, artificial neural network, protein folding, protein structure prediction

DOI: 10.3233/IFS-2009-0415

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 61-71, 2009

Authors: Leng, Jinsong | Fyfe, Colin | Jain, Lakhmi C.

Article Type: Research Article

Abstract: Temporal difference learning and eligibility traces are two mechanisms for solving reinforcement learning problems. The temporal difference technique bootstraps the state value or state-action value at every step as with dynamic programming, and learns by sampling episodes from experience as in the Monte Carlo approach. Eligibility traces is a mechanism that offers a means for recording the degree of which state is eligible for undergoing learning process. This paper aims to investigate the underlying mechanism of …eligibility traces strategies using on-policy and off-policy learning algorithms. In doing so, the performance metrics can be obtained by defining the learning problem in a simulation environment, in conjunction with different learning algorithms. However, measuring learning performance and analysing sensibility are very expensive because such performance metrics can only be obtained by running an experiment with different parameter values. This paper proposes a comparative study for analysing the mechanism of eligibility traces. The objective of this paper is to compare and investigate the influences on performance caused by those different approaches. Show more

Keywords: Temporal difference learning, eligibility traces, agent, decision-making

DOI: 10.3233/IFS-2009-0416

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 73-82, 2009

Authors: Tweedale, Jeffrey | Jain, Lakhmi C.

Article Type: Research Article

Abstract: Heuristic computing has consolidated into two streams of research (personification software and smart products) [1]. Cognitive Science is one of these fields and is attracting research effort based on Multi-Agent System (MAS). This research requires the formation of a voluntarily trust relationship in order for collaboration to occur, otherwise the imposed goal(s) may be aborted or fail completely [2,3]. An Agent Transportation Layer Adaption System (ATLAS) communications framework has been constructed to …pass messages between separate agent systems. Discussion about confined frameworks have recently been extended to enable individual students associated with our Knowledge-Based and Intellingent Information and Engineering Systems (KES) Centre to fast track the development of their research concepts. A Plug 'n' Play concept based on a multi-agent blackboard architecture forms the basis of this research. This paper highlights the core architecture, we believe is required for Multi-Agent System (MAS) developers to achieve such flexibility. Agent teams can provide the ability to adapt and dynamically organize. The model described, concentrates on the blackboard design constructs to represents all functional blocks required to automate the processes required to complete any decomposed goals. Discussion in this paper is limited to the formative work within the foundation layers of that framework. Show more

Keywords: ATLAS, autonomy, intelligent agents, teaming, trust

DOI: 10.3233/IFS-2009-0417

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 83-88, 2009

Authors: Kiewra, Maciej | Nguyen, Ngoc Thanh

Article Type: Research Article

Abstract: In this paper a fuzzy-based recommendation method is presented. Its main goal is to improve the recommendation recall maintaining high recommendation precision. The formal model has been built to describe the method and to analyze how the measures used in traditional Information Retrieval may be adapted to evaluate the effectiveness of recommendation process. The original contributions consist among others of proving several properties which show that the method is able to adapt to changing user's needs …and achieving the maximum effectiveness if the component methods work properly. Show more

DOI: 10.3233/IFS-2009-0418

Citation: Journal of Intelligent & Fuzzy Systems, vol. 20, no. 1-2, pp. 89-104, 2009