Ensemble of One-Class Classifiers for Personal Risk Detection Based on Wearable Sensor Data

• Published in: Sensors (Basel, Switzerland) Vol. 16; no. 10; p. 1619
• Main Authors: Rodríguez, Jorge, Barrera-Animas, Ari, Trejo, Luis, Medina-Pérez, Miguel, Monroy, Raúl
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 29.09.2016; MDPI
• Subjects: Accuracy; Algorithms; behavior analysis; classifier ensemble; Classifiers; Datasets; Feature selection; one-class classification; personal risk detection; Projection; Risk; Sensors; Support vector machines; Wearable; wearable sensor; one-class classification; personal risk detection; wearable sensor; classifier ensemble; behavior analysis
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s16101619

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users.