Human activity data discovery from triaxial accelerometer sensor: Non-supervised learning sensitivity to feature extraction parametrization

• Published in: Information processing & management Vol. 51; no. 2; pp. 204 - 214
• Main Authors: Machado, Inês P., Luísa Gomes, A., Gamboa, Hugo, Paixão, Vítor, Costa, Rui M.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.03.2015; Elsevier Science Ltd
• Subjects: Accelerometers; Algorithms; Classification; Clustering; Clustering algorithms; Dimensionality reduction; Feature extraction; Feature selection; Human activity recognition; Human motion; Information systems; Interactive knowledge discovery; Parametrization; Recognition; Sensors; Studies; Wearable computers; Dimensionality reduction; Feature extraction; Human activity recognition; Interactive knowledge discovery; Clustering algorithms
• ISSN: 0306-4573; 1873-5371
• DOI: 10.1016/j.ipm.2014.07.008

•The presented study performs two different tests in intra and inter subject context.•A set of 180 features is implemented to be selected based on clustering performance.•Our algorithm searches for the best feature extraction parameter.•A new clustering metric based on the construction of the confusion matrix is proposed.•A novel gesture recognition system based on data from a single 3 dimensional accelerometer. Background: Our methodology describes a human activity recognition framework based on feature extraction and feature selection techniques where a set of time, statistical and frequency domain features taken from 3-dimensional accelerometer sensors are extracted. This framework specifically focuses on activity recognition using on-body accelerometer sensors. We present a novel interactive knowledge discovery tool for accelerometry in human activity recognition and study the sensitivity to the feature extraction parametrization. Results: The implemented framework achieved encouraging results in human activity recognition. We have implemented a new set of features extracted from wearable sensors that are ambitious from a computational point of view and able to ensure high classification results comparable with the state of the art wearable systems (Mannini et al. 2013). A feature selection framework is developed in order to improve the clustering accuracy and reduce computational complexity.1The software OpenSignals (Gomes, Nunes, Sousa, & Gamboa, 2012) was used for signal acquisition and signal processing algorithms were developed in Python Programming Language (Rossum & de Boer, 1991) and Orange Software (Curk et al., 2005).1 Several clustering methods such as K-Means, Affinity Propagation, Mean Shift and Spectral Clustering were applied. The K-means methodology presented promising accuracy results for person-dependent and independent cases, with 99.29% and 88.57%, respectively. Conclusions: The presented study performs two different tests in intra and inter subject context and a set of 180 features is implemented which are easily selected to classify different activities. The implemented algorithm does not stipulate, a priori, any value for time window or its overlap percentage of the signal but performs a search to find the best parameters that define the specific data. A clustering metric based on the construction of the data confusion matrix is also proposed. The main contribution of this work is the design of a novel gesture recognition system based solely on data from a single 3-dimensional accelerometer.