# Comparative Evaluation of ECG and Motion Signals in the Context of Activity Recognition and Human Identification

## TL;DR

This study compares ECG and motion signals for recognizing activities and identifying individuals, finding that each performs better alone than combined.

## Contribution

The paper introduces a comparative evaluation of ECG and ACC signals for unsupervised activity recognition and human identification.

## Key findings

- ACC signals outperformed ECG in activity recognition with NMI = 0.728 and accuracy = 0.817.
- ECG signals showed higher discriminative power for subject identification with NMI = 0.641.
- Combining ACC and ECG signals reduced performance, indicating challenges in multimodal fusion.

## Abstract

This study presents a comparative analysis of electrocardiogram (ECG) and accelerometer (ACC) data in the context of unsupervised human activity recognition and subject identification. Recordings were obtained from 30 participants performing activities of daily living such as walking, sitting, lying, cleaning the floor, and climbing stairs. Distance-based signal comparison methods and clustering techniques were employed to evaluate the feasibility of each modality, both individually and in combination, to discriminate between individuals and activities. Results indicate that ACC signals provide superior performance in activity recognition (NMI = 0.728, accuracy = 0.817), while ECG signals show higher discriminative power for subject identification (NMI = 0.641, accuracy = 0.500). In contrast, combining ACC and ECG signals yielded lower scores in both tasks, suggesting that multimodal fusion introduced additional variability. These findings highlight the importance of selecting the most appropriate modality depending on the recognition objective and emphasize the challenges associated with multimodal approaches in unsupervised scenarios.