Abstract
Mobile and wearable devices now have a greater capability of sensing human activity ubiquitously and unobtrusively through advancements in miniaturization and sensing abilities. However, outstanding issues remain around the energy restrictions of these devices when processing large sets of data. This paper presents our approach that uses feature selection to refine the clustering of accelerometer data to detect physical activity. This also has a positive effect on the computational burden that is associated with processing large sets of data, as energy efficiency and resource use is decreased because less data is processed by the clustering algorithms. Raw accelerometer data, obtained from smartphones and smartwatches, have been preprocessed to extract both time and frequency domain features. Principle component analysis feature selection (PCAFS) and correlation feature selection (CFS) have been used to remove redundant features. The reduced feature sets have then been evaluated against three widely used clustering algorithms, including hierarchical clustering analysis (HCA), k-means, and density-based spatial clustering of applications with noise (DBSCAN). Using the reduced feature sets resulted in improved separability, reduced uncertainty, and improved efficiency compared with the baseline, which utilized all features. Overall, the CFS approach in conjunction with HCA produced higher Dunn Index results of 9.7001 for the phone and 5.1438 for the watch features, which is an improvement over the baseline. The results of this comparative study of feature selection and clustering, with the specific algorithms used, has not been performed previously and provides an optimistic and usable approach to recognize activities using either a smartphone or smartwatch.
Highlights
The idea of wearing on-board computing systems has been around since the 1980s [1]
The experiments have been repeated with the principle component analysis feature selection (PCAFS) datasets and the correlation feature selection (CFS) datasets, which utilize a subset of the baseline features to establish if the results can be improved
The CFS feature selection approach produced the best results in terms of high Dunn Index (DI) (5.1438) using both k-means and hierarchical clustering analysis (HCA), a high distance ratio (DR) using density-based spatial clustering of applications with noise (DBSCAN) (0.3452), and low EN using k-means (0.0515)
Summary
The idea of wearing on-board computing systems has been around since the 1980s [1]. recent advances in wireless communication technologies, embedded systems, and the lower costs of components (e.g., batteries, processors, and sensors) have enabled these devices to become more miniaturized and mainstream [2]. Every moment of daily life can be shared digitally and can be enriched in ways that we could not have imagined years ago [3]. Part of such developments has been the inception of wearable devices (e.g., smartwatches, health and fitness trackers, etc.) that have exploded onto the consumer market. By 2019, Cisco predicts that there will be 578 million wearable devices globally, which is a fivefold increase from 109 million in 2014 [4] These devices house a multitude of sensors that are capable of capturing a large amount and range of personal information. With all of this data readily available, end Informatics 2018, 5, 29; doi:10.3390/informatics5020029 www.mdpi.com/journal/informatics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
