Paper Info
Title
Benchmarking the SHL Recognition Challenge with Classical and Deep-Learning Pipelines.
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.
Year
DOI
Venue
2018
10.1145/3267305.3267531
UbiComp '18: The 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing Singapore Singapore October, 2018
Keywords
Field
DocType
Activity recognition, Dataset, Deep learning, Machine learning, Transportation mode recognition
Decision tree,Activity recognition,Naive Bayes classifier,Computer science,Convolutional neural network,Support vector machine,Human–computer interaction,Artificial intelligence,Deep learning,Classifier (linguistics),Random forest,Machine learning
Conference
ISBN
Citations 
PageRank 
978-1-4503-5966-5
1
0.39
References 
Authors
8
6
Name
Order
Citations
PageRank
Lin Wang117715.50
Hristijan Gjoreski226829.81
Mathias Ciliberto3336.12
Sami Mekki410.72
Stefan Valentin513014.09
Daniel Roggen61851137.05