Exploratory Data Analysis of Acceleration Signals to Select Light-Weight and Accurate Features for Real-Time Activity Recognition on Smartphones

• Published in: Sensors (Basel, Switzerland) Vol. 13; no. 10; pp. 13099 - 13122
• Main Authors: Khan, Adil, Siddiqi, Muhammad, Lee, Seok-Won
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 27.09.2013; Molecular Diversity Preservation International (MDPI)
• Subjects: accelerometer sensor; Accelerometers; Accelerometry - instrumentation; Accelerometry - methods; Accuracy; Actigraphy - instrumentation; Actigraphy - methods; activity recognition; Algorithms; Cell Phone; Computer engineering; Computer Systems; Computers, Handheld; context-awareness; Data analysis; Discriminant analysis; Equipment Design; Equipment Failure Analysis; expolatory data analysis; feature extraction; Fourier transforms; Humans; Miniaturization; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; Neural networks; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Sensors; smartphone; Smartphones; Transducers
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s131013099

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.