https://orcid.org/0000-0003-1327-1283
https://orcid.org/0000-0002-4812-346X
https://orcid.org/0000-0003-1327-1283
https://orcid.org/0000-0002-4812-346X
Transportation mode detection from smartphone data is investigated as a relevant problem in the multi-modal transportation systems context. Neural networks are chosen as a timely and viable solution. The goal of this paper is to solve such a problem with a combination model of Convolutional Neural Network (CNN) and Bidirectional-Long short-term memory (BiLSTM) only processing accelerometer and magnetometer data. The performance in terms of accuracy and F1 score on the Sussex-Huawei Locomotion-Transportation (SHL) challenge 2018 dataset is comparable to methods that require the processing of a wider range of sensors. The uniqueness of our work is the light architecture requiring less computational resources for training and consequently a shorter inference time.
Deep CNN-BiLSTM Model for Transportation Mode Detection Using Smartphone Accelerometer and Magnetometer
2022-06-01
Conference paper
Electronic Resource
English
A Fiber Optic Accelerometer—Magnetometer
| British Library Online Contents | 2017
Speed Estimation using Smartphone Accelerometer Data
| Transportation Research Record | 2019
Transportation mode recognition using GPS and accelerometer data
| Online Contents | 2013