An Activity Recognition Framework Deploying the Random Forest Classifier and A Single Optical Heart Rate Monitoring and Triaxial Accelerometer Wrist-Band

Abstract

Wrist-worn sensors have better compliance for activity monitoring compared to hip, waist, ankle or chest positions. However, wrist-worn activity monitoring is challenging due to the wide degree of freedom for the hand movements, as well as similarity of hand movements in different activities such as varying intensities of cycling. To strengthen the ability of wrist-worn sensors in detecting human activities more accurately, motion signals can be complemented by physiological signals such as optical heart rate (HR) based on photoplethysmography. In this paper, an activity monitoring framework using an optical HR sensor and a triaxial wrist-worn accelerometer is presented. We investigated a range of daily life activities including sitting, standing, household activities and stationary cycling with two intensities. A random forest (RF) classifier was exploited to detect these activities based on the wrist motions and optical HR. The highest overall accuracy of 89.6 ± 3.9% was achieved with a forest of a size of 64 trees and 13-s signal segments with 90% overlap. Removing the HR-derived features decreased the classification accuracy of high-intensity cycling by almost 7%, but did not affect the classification accuracies of other activities. A feature reduction utilizing the feature importance scores of RF was also carried out and resulted in a shrunken feature set of only 21 features. The overall accuracy of the classification utilizing the shrunken feature set was 89.4 ± 4.2%, which is almost equivalent to the above-mentioned peak overall accuracy.

Consequences of chronic diseases and other limitations associated with old age – a scoping review

“…Furthermore, cognitive disorders, along with the needs arising from such disorders, represent another important concern [53–55]. Cognitive disorders, besides generating numerous problems for old people in their ADLs, could even result in malnutrition [30, 34], or injures and fractures.…”

Hybrid Feature Extraction for Detection of Degree of Motor Fluctuation Severity in Parkinson’s Disease Patients

“…Instead of learning single decision trees, which tends to overfit, the RF algorithm uses an ensemble classifier approach that learns multiple weak decision trees (high variance but low bias) using a randomly selected subset of feature vectors and feature attributes. The RF classifier has received increasing attention in many applications due to its generalization ability and robustness to noise as well processing speed for high-dimensional data [ 31 , 32 , 33 , 34 ]. The algorithm grows the decision trees in the ensembles by drawing a subset of feature vectors through a bagging approach (i.e., feature vectors are replaced back).…”

Toward privacy in IoT mobile devices for activity recognition

“…Random Forest (RF for short) was chosen for the multi-class classification tasks, respectively classes referring to activity recognition and classes associated to user identities in case of an adversary willing to misuse the classifier to re-identify users. In general, the RF algorithm is a supervised classifier having fast training time and very high performance without fine tuning [25]. RF operates by building a large ensemble of decision trees, where each tree is built on a bootstrapped sample of the original data [10].…”