Conference Paper

Neuro Fuzzy Classification and Detection Technique for Bioinformatics Problems

Dept. of Control & Instrum., Univ. Teknologi Malaysia, Skudai
DOI: 10.1109/AMS.2007.70 Conference: Modelling & Simulation, 2007. AMS '07. First Asia International Conference on
Source: IEEE Xplore

ABSTRACT Bioinformatics is an emerging science and technology which has lots of research potential in the future. It involves multi-interdisciplinary approaches such as mathematics, physics, computer science and engineering, biology, and behavioral science. Computers are used to gather, store, analyze as well as integration of patterns and biological data information which can then be applied to discover new useful diagnosis or information. In this study, the focus was directed to the classification or clustering techniques which can be applied in the bioinformatics fields based on the Sugeno type neuro fuzzy model or ANFIS (adaptive neuro fuzzy inference system). It is very important to identify new integration of classification or clustering algorithm especially in neuro fuzzy domain as compared to conventional or traditional method. This paper explores the suitability and performance of recurrent classification technique, fuzzy c means (FCM) act as classifier in neuro fuzzy system compared to subclustering method. A package of software based on neuro fuzzy model (ANFIS) has been developed using MATLAB software and optimization were done with the help from WEKA. A set diabetes data based on real diagnosis of patient was used

  • [Show abstract] [Hide abstract]
    ABSTRACT: Diabetes is a type of disease in which the body fails to regulate the amount of glucose necessary for the body. It does not allow the body to produce or properly use insulin. Diabetes has widespread fallout, with a large people affected by it in world. In this paper; we demonstrate that a fuzzy c-means-neuro-fuzzy rule-based classifier of diabetes disease with an acceptable interpretability is obtained. The accuracy of the classifier is measured by the number of correctly recognized diabetes record while its complexity is measured by the number of fuzzy rules extracted. Experimental results show that the proposed fuzzy classifier can achieve a good tradeoff between the accuracy and interpretability. Also the basic structure of the fuzzy rules which were automatically extracted from the UCI Machine learning database shows strong similarities to the rules applied by human experts. Results are compared to other approaches in the literature. The proposed approach gives more compact, interpretable and accurate classifier.
    Australasian physical & engineering sciences in medicine / supported by the Australasian College of Physical Scientists in Medicine and the Australasian Association of Physical Sciences in Medicine 08/2012; 35(3):257-70. · 0.85 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Due to the advantages of the intrinsically safe circuit, people are increasingly willing to make use of it in comprehensive automatization system and communication equipment. If practical non-explosive testing methods can be constructed base on discharge theory of intrinsically safe circuit, the designers will find it easier to grasp the performance of the circuit, thus resulting in the achievement of shorter researching time and lower costs. This thesis has established the non-explosive assessment system of the intrinsically safe circuit with ANFIS as its core. ANFIS input Eigenvector has been affirmed according to the circuit quality, experimental gas types, discharge power, maximum value of the instantaneous power, the energy comparison of the average power value and the discharge time. The system uses the explosive experimental data from the spark test system to extract the Eigenvector to perform ANFIS training. After succeed training, the established circuit discharge models are used to extract the Eigenvector to make the assessment of the non-explosive intrinsically safe performance of the intrinsically safe circuit. According the explosive experiment, this system boasts high accuracy and practical value.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper a genetic algorithm-polynomial neural network approach is used in order to model the effect of important parameters on heat transfer as well as fluid flow characteristics for a double-pipe helical heat exchanger by using numerical-certified results. In this way, overall heat transfer coefficient (Uo), inner and annular pressure drop (ΔPin, ΔPan) are modeled with respect to the variation of inner and annular dean number, inner and annular Prandtl number, and pitch of coil which are defined as input (design) variables. The numerical-certified data was randomly divided into test and train sections which the former is used for benchmark. The GA-PNN structure was instructed by 75 percent of the numerical-validated data. 25 percent of the primary data which had been considered for testing procedure were entered into GA-PNN proposed models and results were compared by statistical criteria.
    ASME 2013 Summer Heat Transfer Conference; 07/2013

Full-text (4 Sources)

Available from
Jun 4, 2014