Impact of Sliding Window Length in Indoor Human Motion Modes and Pose Pattern Recognition Based on Smartphone Sensors
Autor: | Lei Wang, Mengqi Wu, Tao Liu, Qingquan Li, Wei Wang, Gaojing Wang |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2018 |
Předmět: |
Support Vector Machine
Boosting (machine learning) Movement Posture Decision tree window length 02 engineering and technology lcsh:Chemical technology 01 natural sciences Biochemistry Article Pattern Recognition Automated Analytical Chemistry Machine Learning Activity recognition smartphone sensors Sliding window protocol human motion mode 0202 electrical engineering electronic engineering information engineering Humans lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation business.industry 010401 analytical chemistry machine-learning method Window (computing) Bayes Theorem Pattern recognition Data segment Atomic and Molecular Physics and Optics 0104 chemical sciences Support vector machine Pattern recognition (psychology) human pose pattern 020201 artificial intelligence & image processing Smartphone Artificial intelligence business |
Zdroj: | Sensors Volume 18 Issue 6 Sensors, Vol 18, Iss 6, p 1965 (2018) Sensors (Basel, Switzerland) |
ISSN: | 1424-8220 |
DOI: | 10.3390/s18061965 |
Popis: | Human activity recognition (HAR) is essential for understanding people&rsquo s habits and behaviors, providing an important data source for precise marketing and research in psychology and sociology. Different approaches have been proposed and applied to HAR. Data segmentation using a sliding window is a basic step during the HAR procedure, wherein the window length directly affects recognition performance. However, the window length is generally randomly selected without systematic study. In this study, we examined the impact of window length on smartphone sensor-based human motion and pose pattern recognition. With data collected from smartphone sensors, we tested a range of window lengths on five popular machine-learning methods: decision tree, support vector machine, K-nearest neighbor, Gaussian naï ve Bayesian, and adaptive boosting. From the results, we provide recommendations for choosing the appropriate window length. Results corroborate that the influence of window length on the recognition of motion modes is significant but largely limited to pose pattern recognition. For motion mode recognition, a window length between 2.5&ndash 3.5 s can provide an optimal tradeoff between recognition performance and speed. Adaptive boosting outperformed the other methods. For pose pattern recognition, 0.5 s was enough to obtain a satisfactory result. In addition, all of the tested methods performed well. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |