On the possibility of short-term traffic prediction during disaster with machine learning approaches: An exploratory analysis

Chikaraishi, Makoto; Garg, Prateek; Varghese, Varun; Yoshizoe, Kazuki; Urata, Junji; Shiomi, Yasuhiro; Watanabe, Ryuki

doi:10.1016/j.tranpol.2020.05.023

Cited by 43 publications

(20 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Improving accuracy cannot be the lone goal of such models and in principle, these models should be rooted in existing theories. For example, Chikaraishi et al (2020) argued that, in short-term traffic state prediction, a machine learning model which produces the best prediction accuracy is not always the best for practical use since it does not mimic the mechanisms of congestion occurrence. Second, these methods are cost and resource intensive, with a set of influences from external factors such as type of data and sample size.…”

Section: Challenges In Applying Deep Learning Methodsmentioning

confidence: 99%

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Varghese

Chikaraishi

Urata

2020

J. Big Data Anal. Transp.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Challenges In Applying Deep Learning Methodsmentioning

confidence: 99%

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Varghese

Chikaraishi

Urata

2020

J. Big Data Anal. Transp.

Self Cite

View full text Add to dashboard Cite

show abstract

“…A more recent study in [ 47 ] reported that RF achieved the lowest average errors compared to other regression models for predicting travel times across an urban road network. An empirical analysis in [ 48 ] acknowledged the limitation that fine-tuning is a time-consuming procedure. In addition, a previous study in [ 49 ] showed that RF requires little time for tuning, favorable for real-time applications.…”

Section: Related Workmentioning

confidence: 99%

Towards an End-to-End Framework of CCTV-Based Urban Traffic Volume Detection and Prediction

Peppa

Komar

Xiao

et al. 2021

Sensors

View full text Add to dashboard Cite

Near real-time urban traffic analysis and prediction are paramount for effective intelligent transport systems. Whilst there is a plethora of research on advanced approaches to study traffic recently, only one-third of them has focused on urban arterials. A ready-to-use framework to support decision making in local traffic bureaus using largely available IoT sensors, especially CCTV, is yet to be developed. This study presents an end-to-end urban traffic volume detection and prediction framework using CCTV image series. The framework incorporates a novel Faster R-CNN to generate vehicle counts and quantify traffic conditions. Then it investigates the performance of a statistical-based model (SARIMAX), a machine learning (random forest; RF) and a deep learning (LSTM) model to predict traffic volume 30 min in the future. Tests at six locations with varying traffic conditions under different lengths of past time series are used to train the prediction models. RF and LSTM provided the most accurate predictions, with RF being faster than LSTM. The developed framework has been successfully applied to fill data gaps under adverse weather conditions when data are missing. It can be potentially implemented in near real time at any CCTV location and integrated into an online visualization platform.

show abstract

“…Moreover, it stopped people from going to work and participating in other economic activities. The impact of the incident was seen over the next three months as heavy congestion on its remaining roads continued (Chikaraishi et al., 2020). Similarly, the road networks of other Japanese cities have also been severely affected due to disasters in the recent past.…”

Section: Introductionmentioning

confidence: 99%

Road network vulnerability and city-level characteristics: A nationwide comparative analysis of Japanese cities

Santos

Safitri

Safira

et al. 2021

Environment and Planning B: Urban Analytics and City Science

Self Cite

View full text Add to dashboard Cite

Climate change is making our cities more vulnerable, increasing the needs for further policy actions to make them more resilient. In particular, the transport network is critical in the first phase of disaster response. This study presents the epirical findings of a large scale, nationwide analysis of the road network vulnerability in 69 Japanese cities. We (1) identify the level of network efficiency using topological elements in its undisturbed normal state; (2) evaluate the level of network robustness under different random and targeted attack scenarios; and (3) analyze the relationship of the identified network efficiency and robustness indicators with city-level characteristics. The main findings include: (1) cities with a higher population and a higher infrastructure investment tend to be more robust under random attacks; (2) larger cities tend to be less robust to targeted attacks, presumably due to their high agglomeration of urban functions; (3) car dependency tends to make cities more vulnerable toward random attacks and less vulnerable toward targeted attacks as it indicates a weaker concentration in urban functions; and (4) a high modal share for trains tends to make cities less vulnerable toward random events as it indicates a high agglomeration of urban functions. These findings will help policymakers to prioritize their budget allocations to improve nationwide disaster resilience.

show abstract

On the possibility of short-term traffic prediction during disaster with machine learning approaches: An exploratory analysis

Cited by 43 publications

References 34 publications

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Towards an End-to-End Framework of CCTV-Based Urban Traffic Volume Detection and Prediction

Road network vulnerability and city-level characteristics: A nationwide comparative analysis of Japanese cities

Contact Info

Product

Resources

About