Abstract
Smartphone-based activity recognition (SP-AR) recognizes users' activities using the embedded accelerometer sensor. Only a small number of previous works can be classified as online systems, i.e., the whole process (pre-processing, feature extraction, and classification) is performed on the device. Most of these online systems use either a high sampling rate (SR) or long data-window (DW) to achieve high accuracy, resulting in short battery life or delayed system response, respectively. This paper introduces a real-time/online SP-AR system that solves this problem. Exploratory data analysis was performed on acceleration signals of 6 activities, collected from 30 subjects, to show that these signals are generated by an autoregressive (AR) process, and an accurate AR-model in this case can be built using a low SR (20 Hz) and a small DW (3 s). The high within class variance resulting from placing the phone at different positions was reduced using kernel discriminant analysis to achieve position-independent recognition. Neural networks were used as classifiers. Unlike previous works, true subject-independent evaluation was performed, where 10 new subjects evaluated the system at their homes for 1 week. The results show that our features outperformed three commonly used features by 40% in terms of accuracy for the given SR and DW.
Highlights
Context-awareness is an essential part of ubiquitous computing, and human activity recognition (HAR) has emerged as an important tool to identify the user’s context for automatic service delivery in ubiquitous application
This research work was carried out as following: (1) Activity acceleration data were collected from subjects using 6 different sampling rates, and 3 different phone positions; (2) Exploratory data analysis was performed on this data to find features that are both lightweight and efficient to ensure long battery-life, fast response, and high recognition accuracy; (3) An accelerometer’s output can vary for the same activity when carried in different positions, resulting in high within-class variance; to enable activity recognition for different positions, a method was needed after feature extraction that would suppress this variance
Several methods were studied for this purpose before selecting the Kernel discriminant analysis (KDA); (4) All the algorithms were implemented in Java; (5) Classifiers were trained offline, and transferred to smartphones; (6) Lastly, real-time evaluations were performed on phones using 10 new subjects
Summary
Context-awareness is an essential part of ubiquitous computing, and human activity recognition (HAR) has emerged as an important tool to identify the user’s context for automatic service delivery in ubiquitous application. The main problem with an external approach is its lack of pervasiveness, i.e., it forces the user to stay within a perimeter defined by the position and capabilities of the sensors. As for a wearable approach, a range of wearable sensors has been used to capture and analyze human movement in free-living subjects [6]. Of these sensors, accelerometers are becoming widely accepted as useful tools for the assessment of human motion in clinical settings and free-living environments [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
