Analyzing Wearables Dataset to Predict ADLs and Falls: A Pilot Study

TL;DR

This pilot study reviews wearable datasets for activity and fall detection, compares machine learning methods on the SisFall dataset, and finds that KNN performs best, with personalized data improving accuracy.

Contribution

It provides a comprehensive review of 39 wearable datasets and compares ML methods on SisFall, highlighting KNN's superior performance and the benefits of data personalization.

Findings

KNN outperforms other ML methods in accuracy, precision, and recall.

Personalized data enhances activity and fall detection accuracy.

Modifying sensor data improves model performance.

Abstract

Healthcare is an important aspect of human life. Use of technologies in healthcare has increased manifolds after the pandemic. Internet of Things based systems and devices proposed in literature can help elders, children and adults facing/experiencing health problems. This paper exhaustively reviews thirty-nine wearable based datasets which can be used for evaluating the system to recognize Activities of Daily Living and Falls. A comparative analysis on the SisFall dataset using five machine learning methods i.e., Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbor, Decision Tree and Naive Bayes is performed in python. The dataset is modified in two ways, in first all the attributes present in dataset are used as it is and labelled in binary form. In second, magnitude of three axes(x,y,z) for three sensors value are computed and then used in experiment with label attribute. The experiments are performed on one subject, ten subjects and all the subjects and compared in terms of accuracy, precision and recall. The results obtained from this study proves that KNN outperforms other machine learning methods in terms of accuracy, precision and recall. It is also concluded that personalization of data improves accuracy.