Kim Le

Fuzzy relation compositions and pattern recognition

This paper first reviews some fuzzy relation compositions, then proposes some similarity relations, which can be used to adjust subjective similarities between objects, put objects in fuzzy clusters, find a representative for each cluster, and check how similar the clusters are. The use of the compositions to expand reduce data is also presented.

Testable design of large random access memories

Abstract In this paper we propose a method for testable design of large Random Access Memories. The design technique relies on modification of address decoders to achieve multi-writes and multi-reads during test mode. Almost no modification is required in the design of memory array. A number of different designs for decoders are proposed. In all the designs the objective has been to keep the extra hardware for enhancing testability to as small as possible while causing a minimal or no degradation at all in the speed performance of RAM. Use of extra control and observation points is allowed as long as such points cause only a very small increase in the number of extra pins. We also propose the design of decorders in which only a limited number of cells of RAM are written to or read from during test mode.

Information gain and adaptive neuro-fuzzy inference system for breast cancer diagnoses

This paper presents a new approach for breast cancer diagnosis using a combination of an Adaptive Network based Fuzzy Inference System (ANFIS) and the Information Gain method. In this approach, the ANFIS is to build an input-output mapping using both human knowledge and machine learning ability and the information gain method is to reduce the number of input features to ANFIS. An experimental result shows 98.23% accuracy which underlines the capability of the proposed algorithm.

Test Time Reduction to Test for Path-Delay Faults using Enhanced Random-Access Scan

Studies of random-access scan (RAS) architecture have largely limited their scope to reduce test application time, test volume and test power to detect conventional stuck-at faults. This paper proposed an enhanced RAS latch design for two pattern tests. The proposed latch is a minor modification of the RAS latch and is well suited for delay-fault tests. In contrast, the traditional serial scan latch needs a major enhancement. As a result the RAS may offer a hardware advantage while the test time is nearly halved over the serial scan design. The test time advantage in this paper was demonstrated for various test sets for benchmark circuits and the authors argued that the advantage is even larger when test sets are generated for RAS architecture in mind, as well as by the exploitation of unspecified bits in test vectors

A Novel Adaptive Shrinkage Threshold on Shearlet Transform for Image Denoising

Shearlet is a new multidimensional and multiscale transform which is optimally efficient in representing image containing edges. In this paper an adaptive shrinkage threshold for image de-noising in shearlet domain is proposed. Experimental results show that images de-noised with the proposed approach had higher qualities than those produced with some of the other denoising methods like wavelet-based, bandlet-based, shearlet-based and curvelet-based.

A Novel Image Quality Index for Image Quality Assessment

Image quality assessment (IQA) is provided as computational models to measure the quality of images in perceptually consistent manner. In this paper, a novel image quality index with highlighting shape of histogram of the image targeted is introduced to assess image qualities. The index will be used in place of existing traditional Universal Image Quality Index (UIQI) “in one go”. It offers extra information about the distortion between an original image and a distorted image in comparisons with UIQI. The proposed index is designed based on modelling image distortion combinations of four major factors: loss of correlation, luminance distortion, contrast distortion and shape distortion. This index is easy to calculate and applicable in various image processing applications. Experimental results show that the proposed image quality index plays a significantly role in the quality evaluation on the open source “Wireless Imaging Quality (WIQ) database”.

Chest X-Ray Analysis for Computer-Aided Diagnostic

X-ray is a classical method for diagnosis of some chest diseases. The diseases are curable if they are detected in their early stages. Detection of chest diseases is mostly based on chest X-ray images (CXR). This is a time consuming process. In some cases, medical experts had overlooked the diseases in their first examinations on CXR, and when the images were re-examined, the disease signs could be detected. Furthermore, the number of CXR to examine is numerous and far beyond the capability of available medical staff, especially in developing countries.

Fuzzy Analysis of X-Ray Images for Automated Disease Examination

This paper presents the design of a fuzzy decision system for Cancer and Tuberculosis detection based on X-ray lung images. The system is in a tuning stage based on advices from medical experts. With a training set of 40 positive and 10 negative images, the system can classify correctly 42% positive cases with no false negative results. This is a promising result; however the system needs further tuning with additional features and concise examination rules.

Chest X-ray analysis for an active distributed E-health system with computer-aided diagnosis

The quality of life of a countrys citizens is much depended on its healthcare system. People have the right to know the status of their health. Healthcare providers need to know the medical histories of patients to offer better treatment. Therefore, demand for improvement in the access of healthcare information has been increased. This paper presents the design of an active distributed E-health system, which is scalable, and more advanced softwares can be easily added. Some works on chest X-ray analysis are presented to demonstrate the capabilities of the system as CAD tools for some chest diseases like congestive heart failure, lung collapse, etc. Experimental result obtained with an algorithm to detect early nodules for lung cancer and TP is very encouraging. Data mining and other artificial intelligent techniques may be used to make the system becoming more active and powerful expert system

MEDADVIS: a medical advisory system

An advisory system has always been a central need for medical practitioners and specialists for the last few decades. Most of current medical retrieval systems are based on passive databases. Actually, the data stored in any information storage system is a rich source of knowledge, which needs appropriate techniques to discover. This paper introduces the design of a well-structured knowledge-base system that holds patient medical records. The proposed system will be equipped with data mining and AI techniques such as statistics, neural network, fuzzy logic, generic algorithm, etc., so that it becomes an active distributed medical advisory system.