Abstract
Objectives: This study is an endeavor to provide quick, on-the-go classification of a human activity dataset with an aim to improve on the classification time of a machine learning algorithm for Human Activity Recognition (HAR) datasets. Methods/Statistical analysis: It proposes the use of a customized sampler called the Normal On-The-Go (Normal OTG) sampler to reduce the classification time. Concocted using a combination of stratified, random and normal sampling, the Normal OTG sampler was tested on HAR datasets and was found to significantly reduce the training time of the most commonly used machine learning algorithms. Three datasets, ShoaibSA, ShoaibPA and USC-HAD were used to conduct the experiments. Findings: It was found that using as little as 5% samples from the training dataset sampled by the Normal OTG sampler, sufficiently reliable accuracy was obtained from most of the 9 classifiers that were used. The results indicated that almost 96% of time was saved in the training process in the case of USC-HAD, and 62% and 83% time was saved in the case of ShoaibPA and ShoaibSA respectively. It was also found that the results were consistent among the three datasets. Application/Improvements: The study helps training of data in human activity recognition a faster process and thereof, making algorithm selection a less tedious procedure Keywords: Classification Time, Human Activity Recognition, Robust, Sampling Technique
Highlights
Human activity recognition has been an essential part of contemporary research owing to its importance in assisted living and ubiquitous computing
Datasets, 2) a comparison of classifier results of the sampled datasets and 3) the impact of Normal OTG sampling on classification time
The accuracy of 87% received from 5% samples in the ShoaibPA dataset was representative of accuracy results from unsampled dataset
Summary
Human activity recognition has been an essential part of contemporary research owing to its importance in assisted living and ubiquitous computing. With its promising applications in the Internet of Things paradigm[1] and its public acceptability, it has been approached with statistical, probabilistic, logical reasoning and machine learning where the state-of-the-art activity recognition techniques have largely been attributed to machine learning techniques with continuous streaming as its target. The process of machine learning activity recognition involves five steps as mentioned by[1]: Data Acquisition, Preprocessing, Feature Selection and Extraction, Training and Testing. State-of-the-art uses continuous streams of data for acquisition; creation of features based on discriminative models; training the models with adaptive and personalized approaches; and testing with hybrid classifiers. Author[3] provides an in-depth survey on the preprocessing, adaptive sensor selection and resource consumption of smartphone based activity recognition. Author[4] provides a detailed survey on feature selection and classifier evaluation of these sensors. Author[6] provides a comprehensive survey on challenges faced by live data streams
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have