Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis

Abstract

Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, k-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands ⟨ 3 , 8 ⟩ and ⟨ 8 , 15 ⟩ Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.

Discrimination of cycling patterns using accelerometric data and deep learning techniques

“…1(a). This selection resulted from the previous research [13,10,52,38] that compared classification results for sensors located at different parts of the body simultaneously recorded by 31 sensors of the perception neuron [5].…”

“…All datasets were acquired by a smartphone sensor that was located on the spine. This position was selected as the best location [10] enabling to distinguish different cycling activities with the highest accuracy.…”

“…Accelerometric data analyzed in the present paper form a simple and cheap information source while in other applications different sensors can be used. Their selection includes video and depth cameras for gait analysis [49], GPS systems for cycling monitoring [9], thermal cameras [44] for breath-ing evaluation, heart rate [10] and further biosensors for motion analysis during the sleep.…”

Cognition Meets Gait: Where and How Mind and Body Weave Each Other in a Computational Psychometrics Approach in Aging

“…AI could optimize individual treatment strategies by applying ML techniques, helping the transition to personalized, effective, and engaging medicine, built on the individual patient's needs. In the literature, ML is linked to diagnostic screening tools with subsequent analysis of the progression of the disease (Tack, 2019;Cavedoni et al, 2020;Charvatova et al, 2020). An innovative approach is applying ML to rehabilitation, allowing precise predictions on which motor or cognitive parameters are more predictive for the future maintenance of any improvements obtained.…”

Classification of Ataxic Gait

“…Motion sensors enable examination both in outpatient conditions and in the conditions of patients’ natural environment. The same motion sensors can be used in these patients, for example, to monitor cycling activities [ 8 ]. When monitoring walking outdoors, it is advisable to combine data from motion sensors with a global positioning system [ 9 ].…”