Wang, Lin, Gjoreski, Hristijan, Ciliberto, Mathias, Mekki, Sami, Stefan, Valentin and Roggen, Daniel (2018) Benchmarking the SHL Recognition Challenge with classical and deep-learning pipelines. HASCA Workshop at Ubicomp 2018, Singapore, 8-12 October 2018. Published in: Murao, Kazuya, Enokibori, Yu, Gjoreski, Hristijan, Lago, Paula, Okita, Tsuyoshi, Siirtola, Pekka, Hiroi, Kei and Scholl, Philipp, (eds.) Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. 1626-1635. Association for Computing Machinery ISBN 9781450359665

PDF - Accepted Version Download (484kB)

Abstract

In this paper we, as part of the Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenge organizing team, present reference recognition performance obtained by applying various classical and deep-learning classifiers to the testing dataset. We aim to recognize eight modes of transportation (Still, Walk, Run, Bike, Bus, Car, Train, Subway) from smartphone inertial sensors: accelerometer, gyroscope and magnetometer. The classical classifiers include naive Bayesian, decision tree, random forest, K-nearest neighbour and support vector machine, while the deep-learning classifiers include fully-connected and convolutional deep neural networks. We feed different types of input to the classifier, including hand-crafted features, raw sensor data in the time domain, and in the frequency domain. We employ a post-processing scheme to improve the recognition performance. Results show that convolutional neural network operating on frequency domain raw data achieves the best performance among all the classifiers.

Item Type:	Conference Proceedings
Keywords:	Activity recognition; Dataset; Deep learning; Machine learning; Transportation mode recognition
Schools and Departments:	School of Engineering and Informatics > Engineering and Design School of Engineering and Informatics > Informatics
Research Centres and Groups:	Sensor Technology Research Centre
Subjects:	Q Science > Q Science (General) > Q0300 Cybernetics Q Science > QA Mathematics > QA0276 Mathematical statistics Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Related URLs:	http://ubicomp.org/ubicomp2018/
Depositing User:	Daniel Roggen
Date Deposited:	05 Sep 2018 10:40
Last Modified:	15 Nov 2018 12:31
URI:	http://srodev.sussex.ac.uk/id/eprint/78510

View download statistics for this item

📧 Request an update