Catálogo de publicaciones - revistas

<jats:p> This work presents performance analysis of machine learning algorithms such as logistic regression, naive bayes, decision tree, k nearest neighbour, random forest, support vector machine, and extreme gradient boosting in heart disease prediction. Machine learning algorithms are implemented in python using Scikit learn library in Jupiter notebook. Experiments are conducted by training and testing machine learning algorithms using kaggle heart disease dataset under six test cases. Performance of machine learning algorithms are evaluated using accuracy, precision, recall, F1 score and ROC as metrics. Results show random forest reported high accuracy, precision, recall, F1 score and ROC in heart disease prediction compared to other machine learning algorithms in all six test cases. Results show RF is effective in heart disease prediction in Case 3 with 80% train data and 20% test data. </jats:p>

<jats:p> This research investigates the novel techniques which provide the detailed information on the biometric images used along with the methods applied for biometric image pre-processing. It also describes the proposed methodology which was implemented with the method of optimized Particle Swarm Optimization (PSO) with Artificial Neural Network (ANN) algorithm for classification of attributes. In the current work, a big effort has been implemented for designing an efficient technique for recognizing the biometric images, especially for the modalities like finger print and retina image. Initially, the pre-processing module used the method of histogram equalization to enhance the contrasts of entire image in order to get the best image quality. This makes the image adaptable for further processing. Next, the feature extraction module has the involvement of two image sets (finger print and retina image). The Gray Level Co-occurrence Matrix (GLCM) was used for extracting the needed features in this module. Next is Feature Based Fusion Technique (FBFT) for reducing the features for authentication purpose. This research work uses the FBFT to get fused feature vector. Finally, deals with the non-recognition and recognition of the images. The images were tested by using Artificial Neural Network (ANN). Here, the recognition is done by ANN and the optimization is done by the sophisticated function of Particle Swarm Optimization Algorithm (PSOA). ANN does the classification of images as recognized and non-recognized and yields best results. </jats:p>