Get started
Work

Towards Synthetic Augmentation of Training Datasets Generated by Mobility-on-Demand Service Using Deep Variational Autoencoders

Year: 2025
Type: article
Abstract: The machine learning-based approaches for analysing the mobility needs of users are currently the most prevalent approach in the Mobility-on-Demand (MoD) analysis. Their efficiency relies on the comprehensiveness and consistency of training datasets. Here is also the biggest challenge as high-quality training data are often difficult to obtain. Thus, the Variational Autoencoders (VAE) are investigated as potential generators of synthetic samples for the augmentation of MoD-based datasets. This MoD-based dataset is created using real-world taxi trip data recorded in the Manhattan district of New York City, USA. This augmentation by synthetic samples can potentially enable larger, balanced, and more consistent datasets for machine learning analysis of MoD-based data. The proposed VAE approaches are compared with common dimensionality reduction techniques and standard Autoencoders concerning their efficiency in 2-dimensional clustering based on collected MoD-based data. The proposed 2-dimensional convolution VAE framework has achieved clustering results comparable with the other analysed approaches. Thus, it is used to generate synthetic samples, known as ”deep fakes”, in different percentages for existing MoD-based dataset augmentation. This creates various configurations of combined training datasets. The results of investigated models trained with different selected dataset configurations have shown that augmentation of the initial training dataset with synthetic samples can improve accuracy for most of them. Moreover, the accuracy of models is significantly increased if they are trained with a lower percentage of synthetic samples in combined training datasets.
DOI: 10.3390/app15094708
Language: English
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W4409772102
FWCI:
Cites: 27
Cited by:
Related to: 10