Transportation Mode Detection Using an Optimized Long Short-Term Memory Model on Multimodal Sensor Data

Paris Mastorocostas,Georgios Miaoulis,Athanasios Voulodimos,Djamchid Ghazanfarpour,Ifigenia Drosouli

doi:10.3390/e23111457

Paris Mastorocostas, Georgios Miaoulis + Show 3 more

Open Access

https://doi.org/10.3390/e23111457

Copy DOI

Journal: Entropy	Publication Date: Nov 3, 2021
Citations: 4	License type: CC BY 4.0

Affiliation: University of West Attica, University of Limoges

Abstract

The advancement of sensing technologies coupled with the rapid progress in big data analysis has ushered in a new era in intelligent transport and smart city applications. In this context, transportation mode detection (TMD) of mobile users is a field that has gained significant traction in recent years. In this paper, we present a deep learning approach for transportation mode detection using multimodal sensor data elicited from user smartphones. The approach is based on long short-term Memory networks and Bayesian optimization of their parameters. We conducted an extensive experimental evaluation of the proposed approach, which attains very high recognition rates, against a multitude of machine learning approaches, including state-of-the-art methods. We also discuss issues regarding feature correlation and the impact of dimensionality reduction.

Highlights

Memory Model on MultimodalAs urbanization and populations have increased in recent years, transportation has become a major factor that affects the experience of people living in big cities
We present a deep learning approach for transportation mode detection using multimodal sensor data elicited from user smartphones
The contributions of this work with respect to the state of the art are as follows: (1) the development of a probabilistic Bayesianoptimized long short-term memory (LSTM) framework, through which the model configuration parameters are optimally tuned, resulting in outperforming other state-of-the-art methods for identifying all eight transportation modes; (2) the scrutinization of the effectiveness of a large number of conventional machine learning and deep learning methods used for transportation mode detection based on multimodal smartphone sensor data; (3) a first attempt to explore techniques for understanding and visualizing feature maps for features’ correlation impact on the model performance; (4) time measurements may vary depending on the system and model architecture, numerous experiments were carried out to compare the impact of different features and algorithm parameters on process time

Summary

Introduction

As urbanization and populations have increased in recent years, transportation has become a major factor that affects the experience of people living in big cities. With the recent the growth of the Internet of Things (IoT), several attempts have been made in the development of new methods to observe urban mobility by using APC systems (APCSs). The operation of these systems is based on Wi-Fi access points (APs) [1], infrared sensors [2,3], video image sensors [4,5], etc. With the advent of modern mobile devices such as tablets, smartphones, and smartwatches, new efficient and user-centric ways have been discovered [6] to detect an individual citizen’s movements throughout the city and collect detailed data about their journey map

Objectives

Results

Conclusion