Heart Disease Detection Using Feature Extraction and Artificial Neural Networks: A Sensor-Based Approach

Abstract

This study presents a novel technique for identifying individuals using feature extraction methods and signal processing approaches. It uses an artificial neural network (ANN) technique to identify scent patterns in individuals using ten metal oxide semiconductor sensors. Sensor data is scanned and extracted before using ANN patterns. Before using ANN patterns to generate patterns from sensor data, it is important to scan and extract sensory information from that data. Each participant is recognized and scanned for a totally of 1000 different characteristics during the course of the multiple investigations, which are conducted across a variety of time periods that include 5, 10, 15, and 20 people. Because of the varying time periods, signals from sensors are received in analog form, which is then transformed by Arduino into digital form. It is necessary to train an architecture on the data set that has been created. The benchmarks that are employed for the assessment of the model that is presented for the identification of human odor include sensitivity, f-measures, accuracy, and specificity, among other things. Experiments are carried out using the assessment measures, and the findings demonstrate that this model has an accuracy of greater than 85 % in most cases. The research demonstrates the potential of feature extraction methods in identifying individuals and enhancing human odor identification.

Keywords

• Heart disease
• deep learning
• ANN
• feature extraction
• sensor