An improved model for predicting trip mode distribution using convolution deep learning
- PDF / 739,381 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 11 Downloads / 283 Views
An improved model for predicting trip mode distribution using convolution deep learning Amin Nezarat1 · N. Seifadini2
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Trip mode selection is a behavioral characteristic of passengers with immense importance for travel demand analysis, transportation planning, and traffic management. Identification of trip mode distribution will allow transportation authorities to adopt appropriate strategies to reduce travel time, traffic, and air pollution. The majority of existing trip mode inference models operate based on human-selected features and traditional machine learning algorithms. However, human-selected features are sensitive to changes in traffic and environmental conditions and susceptible to personal biases, which can make them inefficient. One way to overcome these problems is to use neural networks capable of extracting high-level features from raw input. In this study, the convolutional neural network (CNN) architecture is used to predict the trip mode distribution based on raw GPS trajectory data. The key innovation of this paper is the design of the layout of the input layer of CNN as well as normalization operation, in a way that is not only compatible with the CNN architecture but can also represent the fundamental features of motion including speed, acceleration, jerk, and bearing rate. The highest prediction accuracy achieved with the proposed configuration for the convolutional neural network with batch normalization is 85.26%. Keywords Deep learning · Convolutional neural network · Trip prediction
1 Introduction Transportation is an essential part of living in the modern world, particularly in urban areas. As cities grow, so does their need for public services and facilities, and meeting this need, in turn, creates new challenges for urban management, especially * Amin Nezarat [email protected] 1
Institute of Computer Science, Masaryk University, Botanick´a 68a, 60200 Brno, Czech Republic
2
Yazd Branch, Islamic Azad University, Yazd, Iran
13
Vol.:(0123456789)
A. Nezarat, N. Seifadini
regarding transportation. Transportation also plays a key role in the economic development of all communities around the world. The adverse effects of neglecting transportation issues on social and economic activities and vitality of a region are very well understood, and so is the need for sensible vision and planning to build sufficient capacity for a sustainable urban transport network. Today, the policies of transportation management authorities are focused not on expanding and building up transportation networks but rather on traffic management solutions such as demand reduction, traffic control and taking a systematic approach to this issue. Meanwhile, the advances in information technology (IT) have transformed traffic management practices across the board, so much so that many traffic management entities are now dependent on IT-based techniques to gather and analyze traffic data and deliver their services to people. Wit
Data Loading...
