Signal and Noise Classification in Bio-Signals via unsupervised Machine Learning

TL;DR

This paper presents an unsupervised machine learning approach using K-means clustering to classify biosignals as clean or noisy and to categorize noise types, improving data quality for further analysis.

Contribution

It introduces a novel application of K-means clustering for biosignal noise classification and segmentation, enhancing data preprocessing for bio-signal analysis.

Findings

K-means reliably separates clean and noisy biosignals

High accuracy in identifying clean segments over noise categories

Enables selection of high-quality biosignal data for feature extraction

Abstract

Real-world biosignal data is frequently corrupted by various types of noise, such as motion artifacts, and baseline wander. Although digital signal processing techniques exist to process such signals; however, heavily degraded signals cannot be recovered. In this study, we aim to classify two things: first, a binary classification of noisy and clean biosignals, and next, to categorize various kinds of noise such as motion artifacts, sensor failure, etc. We implemented K-means clustering, and our results indicate that the algorithm can most reliably group clean segments from noisy ones, particularly strong performance in identifying clean data compared to various categories of noise. This approach enables the selection of only high-quality bio-signal segments and provides accurate results for feature engineering that may enhance the precision of machine learning models trained on biosignals.