New Publication in the International Journal of Disaster Risk Reduction

The following paper is now available online!

Wu, L., Chikaraishi, M., Nguyen, T.A.H., Fujiwara, A. (2021) Analysis of post-disaster population movement by using mobile spatial statistics, International Journal of Disaster Risk Reduction, 54, 102047.

Abstract: Understanding and predicting post-disaster human movements is critical for evaluating a population’s vulnerability and resilience and developing plans for disaster evacuation, response and recovery. In this study, we attempt to analyze population movement by using mobile spatial statistics. In order to extract behavior patterns from the aggregated data, we use four different Latent Variable Analysis (LVA) methods – Independent Component Analysis (including FastICA and Spatial colored ICA), Non-negative Matrix Factorization (NMF), and Sparse Principal Component Analysis (SPCA) to analyze mobile statistics data of the disaster-affected area. The results indicate that each LVA methods has its pros and cons in extracting behavior patterns from the aggregated population. We conclude that, using multiple LVA methods and finding out the common patterns would be a robust way to understand and explain population dynamics. Finally, we argue that using mobile spatial statistics would be a feasible and practical option to estimate the dynamic change of human population after the occurrence of disasters.

New Publication in the Journal of Big Data Analytics in Transportation

The following paper is now available online!

Varghese, V. Chikaraishi, M., Urata, J. (2020) Deep Learning in Transport Studies: A Meta-Analysis on the Prediction Accuracy, Journal of Big Data Analytics in Transportation, Vol. 2, 199–220.

Deep learning methods are being increasingly applied in transport studies, while the methods require modellers to go through a try-and-error model tuning process particularly on choosing neural network structure. Moreover, the accuracy level also depends on other factors such as the type of data, sample size, region of data collection, and time of prediction. To efficiently facilitate such a model tuning process, this study attempts to summarize the relationship between the prediction accuracy of deep learning models and the factors which influence it. We conducted a comprehensive review of the literature by adopting a detailed search strategy, followed by a meta-analysis on prediction accuracy. Four separate linear mixed effects models, taking into account unobserved heterogeneities in prediction accuracy across studies, were developed to statistically test the impacts of influential factors on prediction accuracy for (a) all observations (136 studies; 2314 cases), (b) studies with MAPE, MRE, and average accuracy indicators (86 studies; 1,878 cases), (c) classification-based studies with accuracy indicator (29 studies; 220 cases), and (d) traffic forecasting studies with MAPE, MRE, and average accuracy indicators (36 studies, 991 cases). The final model includes additional factors to test the influence of sample size and time horizon of prediction variables. The findings showed that, as expected, deep learning models, particularly ones that consider spatiotemporal dependencies of transport phenomena, show better prediction accuracies compared to conventional machine learning models. We also found that, on average, the prediction accuracy is improved by 5.90% with 100 million additional data, while the accuracy is reduced by 5.28% with 100 min increase in time horizon of prediction in traffic forecasting studies. We concluded this paper with a comprehensive summary of the existing findings on the applications of deep learning to transport studies.