BOUCHUT, Quentin, APPIAH, Kofi, LOTFI, Ahmad and DICKINSON, Patrick (2019). Ensemble One-vs-One SVM Classifier for Smartphone Accelerometer Activity Recognition. In: 2018 IEEE 20th International Conferences on High Performance Computing and Communications (HPCC). IEEE. [Book Section]
Documents
21751:499237
PDF
quentinCR.pdf - Accepted Version
Available under License All rights reserved.
quentinCR.pdf - Accepted Version
Available under License All rights reserved.
Download (282kB) | Preview
Abstract
A recognition framework to identify six full body motion from smartphone sensory data is proposed. The proposed system relies on accelerometer, gyroscope and magnetometer data to classify user activities into six groups (sitting, standing, lying down, walking, walking up stairs and walking downstairs). The proposed solution is an improvement of a one-verse-one SVM classifier with an ensemble of different learning methods each trained to discriminate a single activity against another. The improvement presented here doesn't only focus on accuracy but also potential embedded implementation capable of performing real-time classification with mobile data from the cloud. The presented one-versus-one approach, based on a linear kernel achieved 97.50 percent accuracy on a public dataset; second best to 98.57 percent reported in literature which uses a polynomial kernel.
More Information
Statistics
Downloads
Downloads per month over past year
Metrics
Altmetric Badge
Dimensions Badge
Share
Actions (login required)
View Item |