Raspberry Pi Based Intelligent Robot that Recognizes and Places Puzzle Objects

TL;DR

This paper presents a system that uses non-linear difference plots and neural networks to accurately diagnose congestive heart failure from ECG data, achieving perfect classification accuracy.

Contribution

It introduces a novel feature extraction method from ECG signals using SODP and demonstrates its effectiveness with neural networks for CHF diagnosis.

Findings

Neural network classifier achieved 100% accuracy in distinguishing CHF patients.

Feature vectors derived from SODP effectively represent ECG data.

System validated with both k-fold and patient-based cross-validation.

Abstract

In this study; in order to diagnose congestive heart failure (CHF) patients, non-linear secondorder difference plot (SODP) obtained from raw 256 Hz sampled frequency and windowed record with different time of ECG records are used. All of the data rows are labelled with their belongings to classify much more realistically. SODPs are divided into different radius of quadrant regions and numbers of the points fall in the quadrants are computed in order to extract feature vectors. Fisher's linear discriminant, Naive Bayes, and artificial neural network are used as classifier. The results are considered in two step validation methods as general kfold cross-validation and patient based cross-validation. As a result, it is shown that using neural network classifier with features obtained from SODP, the constructed system could distinguish normal and CHF patients with 100% accuracy rate.