CICS -2013

Accepted Papers

Neural Networks with Decision Trees for diagnosis issues
Y. Kourd¹, D. Lefebvre², and N. Guersi³,¹Mohamed Khider Biskra University, Algeria, ²GREAH - University of Havre 25 rue Philippe Lebon,France ,³University of Badji Mokhtar Annaba, Algeria..
ABSTRACT
This paper presents a new idea for fault detection and isolation (FDI) technique which is applied to industrial system. This technique is based on Neural Networks fault-free and Faulty behaviors Models (NNFMs). NNFMs are used for residual generation, while decision tree architecture is used for residual evaluation. The decision tree is realized with data collected from the NNFM's outputs and is used to isolate detectable faults depending on computed threshold. Each part of the tree corresponds to specific residual. With the decision tree, it becomes possible to take the appropriate decision regarding the actual process behavior by evaluating few numbers of residuals. In comparison to usual systematic evaluation of all residuals, the proposed technique requires less computational effort and can be used for on line diagnosis. An application example is presented to illustrate and confirm the effectiveness and the accuracy of the proposed approach.
Efficient Approach for Edge Detection in Digital Images by Intuitionistic Fuzzy Index and Divergence Value
A.Thilagavathy, S.Harifa Sulthana, B.Hemalatha, A.Chilambuchelvan, R.M.K Engineering College.India
ABSTRACT
Image processing is any form of signal processing for which the input is an image, such as a photograph or video frame; the output of image processing may be either an image or a set of characteristics or parameters related to the image. Soft computing is a term applied to a field within computer science which is characterized by the use of inexact solutions to computationally hard tasks such as the solution of NP-complete problems, for which there is no known algorithm that can compute an exact solution in polynomial time. In this paper the two efficient techniques Image Processing and Soft Computing are combined. Edge detection is an important task in the field of image processing. This has a wide range of applications. Here Fuzzy logic is used to detect the edges of images. The fuzzy technique is the one which gives exact behavior in the process of numerical evaluation. The proposed methodology initially splits the image into segments using a 3*3 binary matrix. Fuzzy inference system is designed with 8 inputs, which corresponds to 8 pixels of the matrix and one output. The output pixel tells whether the pixel under evaluation is 'black',' white' or 'edge' pixel. A set of sixteen rules are framed to classify the target pixel. The proposed method is compared with other edge detecting methods and comparison is shown in the form of histogram. Noise removal algorithms are applied to remove the distortions and it also smoothens the image by preserving the edges.


Home Paper Submission Program Committee Accepted Papers Contact us
Home Paper Submission Program Committee Accepted Papers Workshops Contact Us AIRCC	Accepted Papers Neural Networks with Decision Trees for diagnosis issues Y. Kourd¹, D. Lefebvre², and N. Guersi³,¹Mohamed Khider Biskra University, Algeria, ²GREAH - University of Havre 25 rue Philippe Lebon,France ,³University of Badji Mokhtar Annaba, Algeria.. ABSTRACT This paper presents a new idea for fault detection and isolation (FDI) technique which is applied to industrial system. This technique is based on Neural Networks fault-free and Faulty behaviors Models (NNFMs). NNFMs are used for residual generation, while decision tree architecture is used for residual evaluation. The decision tree is realized with data collected from the NNFM's outputs and is used to isolate detectable faults depending on computed threshold. Each part of the tree corresponds to specific residual. With the decision tree, it becomes possible to take the appropriate decision regarding the actual process behavior by evaluating few numbers of residuals. In comparison to usual systematic evaluation of all residuals, the proposed technique requires less computational effort and can be used for on line diagnosis. An application example is presented to illustrate and confirm the effectiveness and the accuracy of the proposed approach. Efficient Approach for Edge Detection in Digital Images by Intuitionistic Fuzzy Index and Divergence Value A.Thilagavathy, S.Harifa Sulthana, B.Hemalatha, A.Chilambuchelvan, R.M.K Engineering College.India ABSTRACT Image processing is any form of signal processing for which the input is an image, such as a photograph or video frame; the output of image processing may be either an image or a set of characteristics or parameters related to the image. Soft computing is a term applied to a field within computer science which is characterized by the use of inexact solutions to computationally hard tasks such as the solution of NP-complete problems, for which there is no known algorithm that can compute an exact solution in polynomial time. In this paper the two efficient techniques Image Processing and Soft Computing are combined. Edge detection is an important task in the field of image processing. This has a wide range of applications. Here Fuzzy logic is used to detect the edges of images. The fuzzy technique is the one which gives exact behavior in the process of numerical evaluation. The proposed methodology initially splits the image into segments using a 3*3 binary matrix. Fuzzy inference system is designed with 8 inputs, which corresponds to 8 pixels of the matrix and one output. The output pixel tells whether the pixel under evaluation is 'black',' white' or 'edge' pixel. A set of sixteen rules are framed to classify the target pixel. The proposed method is compared with other edge detecting methods and comparison is shown in the form of histogram. Noise removal algorithms are applied to remove the distortions and it also smoothens the image by preserving the edges.
Copyright (c) Aircc

Accepted Papers

ABSTRACT

ABSTRACT