Human Activity Recognition in WSN: A Comparative Study

Abstract

Human activity recognition is an emerging field of ubiquitous and pervasive computing. Although recent smartphones have powerful resources, the execution of machine learning algorithms on a large amount of data is still a burden on smartphones. Three major factors including; classification algorithm, data feature, and smartphone position influence the recognition accuracy and time. In this paper, we present a comparative study of six classification algorithms, six data features, and four different positions that are most commonly used in the recognition process using smartphone accelerometer. This analysis can be used to select any specific classification algorithm, data feature, and smartphone position for human activity recognition in terms of accuracy and response time. The methodology we used is composed of two major components; a data collector, and a classifier. A set of eleven activities of daily living, four different positions for data collection and ten volunteers contributed to make it a worth-full comparative study. Results show that K-Nearest Neighbor and J48 algorithms performed well both in terms of time and accuracy irrespective of data features whereas the performance of other algorithms is dependent on the selected data features. Similarly, mean and mode features gave good results in terms of accuracy irrespective of the classification algorithm. A short version of the paper has already been presented at ICIS 2014.

A systematic review of smartphone-based human activity recognition methods for health research

“…Therefore, it is essential that studies collect data from as many body locations as possible to ensure the generalizability of results. In the reviewed literature, study participants were often instructed to carry the device in a pants pocket (either front or back), although a number of studies also considered other placements, such as jacket pocket 46 , bag or backpack 47 , 48 , and holding the smartphone in the hand 49 or in a cupholder 50 .…”

“…The desired performance optimum was obtained by making use of dataset remodeling (e.g., by replacing the oldest observations with the newest ones), low-cost classification algorithms, limited preprocessing, and conscientious feature selection 45,86 . Computation time was sometimes reported for complex methods, such as deep neural networks 20,82,111 and extreme learning machine 112 , as well as for symbolic representation 85,86 and in comparative analyses 46 . A comprehensive comparison of results was difficult or impossible, as discussed below.…”

Semantic segmentation of real-time sensor data stream for complex activity recognition

“…This section presents some state-of-the-art studies that have been used for real-time sensor data segmentation (i.e., in knowledge-driven [7,24], data-driven [1,17], or hybrid [8,38] approaches) and highlight some literature in activity learning so that the inferred knowledge can also be considered during the segmentation stage. The common characteristics that are used to separate the data stream are time, location, sensor type (i.e., temperature, humidity, touch), and value (binary, float, decimal, string) [5].…”

Adaptive HAR System to Improve Recognition Accuracy

“…Based on the study [3], it can be concluded that certain statistical features give an insight regarding the data pattern of an activity. The data pattern analysis is an approach that can be used to divide the activities into various groups.…”

“…A similar kind of study to compare statistical features that are typically extracted from the sensors' raw data, and on classification algorithms, which are used to construct classification models, was done in [3], to examine the data behavior. Based on the study [3], it can be concluded that certain statistical features give an insight regarding the data pattern of an activity.…”