Lot Of Paths Research Articles

A Comparative Study for Prediction of Heart Diseases Using Machine Learning

According to the World Health Organization, heart diseases are the leading causes of death all over the world. Among the heart diseases, Heart Attacks are the major causes of death. The prediction or detection of the presence of heart disease is a task that requires a high level of expertise in the related field. However, with the advancement of technological research in disciplines like Machine Learning and Deep Learning, a lot of paths have opened up in the direction of getting this task done more easily and efficiently. One of these paths led to the automation of this task. However, while automating the system, we have to keep the system accurate. Apart from the quality of data, the choice of algorithm for solving the problem also plays an important role in producing accurate output. This is because different algorithms can perform differently with different kinds of data. The problem at hand can be solved by more than one kind of algorithm. The goal is to apply various machine learning algorithms to the problem and make a comparative study on the efficiency of these algorithms in predicting the presence of heart disease in a person. The algorithms used for the same are Support Vector Classifier, Decision Tree Classifier, Random Forest Classifier, and k Nearest Neighbour Classifier. The implementation of algorithms is done on the heart disease dataset from the University of California Irvine machine learning repository. The accuracy scores for all the algorithms mentioned above are to be evaluated. The algorithm with the highest accuracy score will be the most suitable one for predicting the disease.

Detection of Crosstalk Faults in Digital Circuits by Testability Evaluation

The increase in dense interconnect as well as the clock frequency of digital circuits has led to an increasing number of crosstalk faults. A new test approach for crosstalk faults in digital circuits is presented in this paper, the approach aims at the faults of crosstalk induced pulse, uses controllability and observability measures of the signal lines to produce the test vectors of crosstalk faults. Choose a lot of paths from the fault site to the primary outputs of circuit, and carry out forward tracing and backward tracing, until every signal line is assigned a logic value and no conflict arises. Experimental results on a lot of digital circuits show that the test approach proposed in this paper can generate the test vectors of crosstalk faults, and can obtain high fault coverage.

On Statistical Estimation of Fault Efficiency for Path Delay Faults Based on Untestable Path Analysis

We propose a method to estimate fault efficiency of test patterns for path delay faults. In path delay fault testing, fault coverage of test patterns is usually very low, because circuits have not only a lot of paths but also a lot of untestable paths. Although fault efficiency would be better metric to evaluate test patterns rather than fault coverage, it is too difficult to compute it exactly, if we do not compute the total number of untestable paths exactly. The proposed method samples a part of paths after untestable path analysis, and estimate fault efficiency based on the percentage of untestable paths in the sample paths. Through our experimental results, we show that the proposed method can accurately estimate fault efficiency of test patterns in a reasonable time. Also, since the accuracy of fault efficiency estimated with the proposed method depends on how to sample the paths, we look into the influence of path sampling methods to the accuracy in the experiments.