Chikaraishi, M., Garg, P., Varghese, V., Yoshizoe, K., Urata, J., Shiomi, Y., Watanabe, R. (2020) On the possibility of short-term traffic prediction during disaster with machine learning approaches: An exploratory analysis, Transport Policy (Accepted).
Abstract: Since the cost and time required to finetune parameters in traditional short-term traffic prediction models such as traffic simulators are very high, the prediction models have been developed mainly for managing recurrent congestion, rather than non-recurrent congestion caused, for example, by disaster. Machine learning models are promising candidates for traffic prediction during non-recurrent congestion due to their ability to tune parameters without a-priori knowledge, while their applicability to non-recurrent conditions has rarely been explored. To fill in this gap, this study conducts an exploratory analysis on the applicability of various machine learning models during a transportation network disruption with particular focuses on their ability to predict traffic states and the interpretability of the results. The analysis is conducted by using data obtained during the massive transport network disruption which occurred in Hiroshima in July 2018 due to heavy rain and subsequent landslides. The models tested include random forest, support vector machine, XGBoost, shallow feed-forward neural network, and deep feed-forward neural network. The results indicate that random forest and XGBoost methods produced the best results in terms of prediction accuracy. On the other hand, deep neural network models produce better results in terms of the interpretability of the results, i.e., the results can be logically explained from the perspective of existing traffic flow theory. These findings indicate that the 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.
Chikaraishi, M., Khan, D., Yasuda, B., Fujiwara, A. (2020) Risk Perception and Social Acceptability of Autonomous Vehicles: A Case Study in Hiroshima, Japan, Transport Policy (In Press).
Given the impending introduction of self-driving cars to Japan within the next several years, gaining a better understanding of public opinion and risk perception of autonomous vehicles (AVs) is crucial. Though AVs have numerous potential social and economic benefits, including reduced travel time and environmental impacts, their implementation will depend on public acceptance. This study expanded on existing work by directly examining which aspects of AV use and function most affect risk perception. Participants were shown short animated video clips depicting the introduction of AVs into society at large, as well as three specific possible risk factors: system error, external interference with car controls (i.e., hacking), and the inability of the car to cope with unexpected events. Participants were then surveyed about their attitudes toward AVs and other potentially risky activities and technologies. The study established that the perceived advantages of all AV types (cars and buses, different automation levels) outweighed their perceived risks. Consistent with prior research, the two major aspects of perceived risk were dread and unfamiliarity. The results showed compared with other technologies, AV scores were neutral for dread risk but higher for unfamiliarity risk. The finding of high unfamiliarity indicates that public acceptance and perceived risks are likely to change as the public’s knowledge increases. We also found that receiving information about a potential system error indirectly reduced AV acceptability, where dread and unfamiliarity to the AV risks served as mediators. The results suggest that proper management on the diffusion of information, which includes public information campaigns, test-ride events and transparency about safety options, will likely influence the ultimate social acceptability of AVs and will be crucial towards its successful introduction on the market.
We had an intensive seminar on discrete choice models. We originally planned to visit Kurashiki for the seminar, but we decided to have it on our campus due to COVID-19.
Day 1 (March 19)
13:00- Discrete choice models (logit, nested logit, and mixed logit)
13:00-15:00: Linking theory with programming code (MNL by Varun, NL by Johan, and ML by Monir, and Hybrid choice model by Haewon)
15:00-15:10: Data introduction by Monir
17:00-18:00: Presentations and Discussions
Day 2 (March 20)
9:00- Recursive logit models
9:00-10:30: Linking theory with code (by Ota)
10:30-11:30: Review on existing works (by Diana, Silvia, and Maya)
11:30-12:00: Data introduction by Ota
15:00-16:00: Presentations and Discussions
Mr. Arpit Jain from Indian Institute of Technology, Delhi (IIT-D) had joined our group for a month as an intern, and he did an excellent job during his stay on the application of transfer learning for short term prediction of non-recurrent traffic congestion. We really appreciate his hard work and contribution!
Dr. Prawira Fajarindra Belgiawan (Lecturer at Institut Teknologi Bandung, School of Business and Management) introduces their study on Online Transportation in Indonesia, entitled “To compete or not compete: exploring the relationships between motorcycle‑based ride‑sourcing, motorcycle taxis, and public transport in the Jakarta metropolitan area”.
Thank you very much, Dr. Fajar!
Two lab members just finished their master thesis presentations today.
Tigulo April Ann Demetrio
“Slum relocation or in-situ redevelopment: What are the impacts of displacement?”
“GIS-based multi-criteria decision-making approach for site selection of cross-docking facility in a retail supply chain”
They are the very first students of our lab, and did excellent job. I’m very happy that both of them got the Excellent Master Thesis Awards (April san got the First Place of Excellence, and Nita san got the Second Place of Excellence). Congratulations and best wishes for your continued success in the future.
Seven members from our lab participated in the 8th Civil Engineering Conference in the Asian Region (CECAR8) held in Ikebukuro, Tokyo last April 16 to 19. The said event had the theme “Resilient Infrastructures in Seamless Asia.”
The CECAR was organized by The Asian Civil Engineering Coordinating Council (ACECC) which was first held in 1998.
During the plenary sessions, speakers talked about the future of civil engineering in the face of changing climate and globalization. The buzzword for this event is “resiliency” and how the civil engineering profession could address the needs of humankind through innovations along climate change and disaster planning and management, coastal management, infrastructure development, and forensic engineering.
The conference opened doors of opportunities especially among us students and provided inspiration for us to do our best in our research and respective jobs in government.
East Hokkaido offers postcard-worthy sceneries like this snow-capped mountains. This photo was taken along the Kushiro Shitsugen-Akan-Mashu Scenic Byway while the participants are aboard a rented vehicle.
Towards the end of March 2019, JDS fellows under the supervision of Makoto Chikaraishi were fortunate enough to explore the lesser known side of Hokkaido prefecture. All throughout the 3-day tour, students were able to bear witness to the pre-launching of autonomous bus experiment, got acquainted with few roadside stations along the scenic byway of East Hokkaido and discovered the infamous city in Hokkaido – Yubari City.
Cosmall Taiki is one of the 122 roadside stations located in Hokkaido prefecture. Aside from serving as a rest stop for travelers, roadside stations also offer information, guides and exhibit local products and foods in the area.
Despite the chilly and windy weather on the first day of the tour, Chikaraishi-sensei and the JDS fellows were warmly welcomed by representatives from the Advanced Smart Mobility Co., Ltd, Docon Co., Ltd and Hokkaido Regional Development Bureau under the Ministry of Land, Infrastructure and Tourism. A brief overview of the autonomous experiment was provided on one of the michi no eki 道の駅 (roadside station) in Tokachi area called Cosmall Taiki. The visiting crew was also given the opportunity to experience autonomous ride aboard the bus along the experiment route. Key features of the autonomous bus were explained and questions from the fellows regarding safety, technology and cost-effectiveness of the autonomous vehicle experiment were graciously received and answered.
The autonomous vehicle experiment briefing was started by meishi koukan (名刺交換), a japanese etiquette involving the formal exchange of business cards.
The brief overview of the autonomous vehicle experiment was held in Cosmall Taiki. Photo credits to Jack Mai.
The autonomous bus that will be used in the 1-month long experiment featuring key improvements from the previous pilot experiment. Photo credits to Jack Mai and JS.
Meanwhile, the second day of the tour was dedicated to the exploration of the Kushiro Shitsugen-Akan-Mashu Scenic Byway. This scenic route is part of the Scenic Byway HOKKAIDO Program which features 6 routes showcasing the different and distinct landscapes, sceneries, recreation, culture and history of Hokkaido. This program that was started on 2005 was designed to encourage local and international tourists to discover Hokkaido on a different light through the comfort of their owned or rented vehicles (http://www.scenicbyway.jp/english/theaters.html#5). The participants made their way thru Akan Lake, visited the Lake Akan Eco Museum Center and drove atop the Kushiro-shitsugen National Park to view the marshlands. On the way back, the team have encountered hilly roads that remain unpaved that might pose inconvenience to visiting excursionists.
(Above) The view of Mount Oakan from the frozen Lake Akan. (Below) The Mashu onsen roadside station offers feet-onsen (hotspring) that motorists can enjoy free of charge. Photo credits to JS.
The last day of the tour revolved around knowing about the bankrupt city of Yubari. The first stop to the city was another roadside station called “Meroad”, a word play for “melon” which the city is now known for producing expensive melons, and road station. Meroad offers a mini grocery, souvenir items and a small exhibit about melon cultivation and the coal mining industry that visitors could check out while enjoying their delightful melon-flavored ice cream. Afterward, the fellows headed to visit the Coal Mining Museum of Yubari to know what lead to the downfall of the city. Interestingly, the museum was situated on an actual mining site utilized previously. Although the exhibit doesn’t have English translation and audio narration, the interactive displays and life-sized diorama have compensated for such and the participants were able to grasp the story behind the coal mining town. As the team headed its way to the airport, they were taken aback by the crowds of photographers that await beside the railway tracks. Fortunately, the fellows were able to see the glimpse of a passing train unknowingly that on that particular day, March 31, 2019, marks the final journey of the 127-year operation of JR Hokkaido’s Yubari Line (http://www.asahi.com/ajw/articles/AJ201904010029.html).
“Meroad”, a word play for “melon” which the city is now known for producing expensive melons, and “road” station.
Meroad, the roadside station of Yubari city – home of Japan’s renowned expensive melons. Photo courtesy of JS.
A preview inside the Coal Mining Museum of Yubari which is situated on actual mining site previously used. Photo credits to JS.
Wrapping up the tour as the team head their way back to Hiroshima, one may ask if autonomous vehicle can be the possible future solution to the declining population and booming tourism industry in East Hokkaido. As another JR train line closes in Yubari City while a growing need for mobility increases as thousands of tourist flocks Hokkaido, the potential realization for the demand and usage of autonomous vehicle as a mode for public transportation looms around the horizon.
JR Hokkaido Yubari line’s final run ending its 127-year train operation on the 31st of March 2019. Photo courtesy of JS.