English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

The emergence of data-driven demand analysis has led to the increased use ofgenerative modelling to learn the probabilistic dependencies between randomvariables. Although their apparent use has mostly been limited to imagerecognition and classification in recent years, generative machine learningalgorithms can be a powerful tool for travel behaviour research by replicatingtravel behaviour by the underlying properties of data structures. In thispaper, we examine the use of generative machine learning approach for analyzingmultiple discrete-continuous (MDC) travel behaviour data. We provide aplausible perspective of how we can exploit the use of machine learningtechniques to interpret the underlying heterogeneities in the data. We showthat generative models are conceptually similar to the choice selectionbehaviour process through information entropy and variational Bayesianinference. Without loss of generality, we consider a restricted Boltzmannmachine (RBM) based algorithm with multiple discrete-continuous layers,formulated as a variational Bayesian inference optimization problem. Wesystematically describe the proposed machine learning algorithm and develop aprocess of analyzing travel behaviour data from a generative learningperspective. We show parameter stability from model analysis and simulationtests on an open dataset with multiple discrete-continuous dimensions from adata size of 293,330 observations. For interpretability, we derive theconditional probabilities, elasticities and perform statistical analysis on thelatent variables. We show that our model can generate statistically similardata distributions for travel forecasting and prediction and performs betterthan purely discriminative methods in validation. Our results indicate thatlatent constructs in generative models can accurately represent the jointdistribution consistently on MDC data.

A bi-partite generative model framework for analyzing and simulating large scale multiple discrete-continuous travel behaviour data