Harutoshi Yamada

The University of Tokyo

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Yoshihide Sekimoto

The University of Tokyo

Ryosuke Shibasaki

The University of Tokyo

Yutaka Matsubayashi

Hiroshi Makino

Kagoshima University

Satoru Nakajo

Setsuo Hirai

National Institute for Land and Infrastructure Management

Yoshitaka Minami

Aichi Medical University

Osamu Shinohara

Japan Society of Civil Engineers

Quanjun Chen

The University of Tokyo

Xuan Song

Jilin University

Cooperative Institutions

The University of Tokyo

Tokyo University of Science

Tokyo University of Information Sciences

National Institute for Land and Infrastructure Management

Tokyo Metropolitan Komaba High School

Japan Society of Civil Engineers

Ministry of Land, Infrastructure, Transport and Tourism

Southern University of Science and Technology

Kansai University

Advanced Institute of Industrial Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

A study on the quality of CAD drawings of expressways and addition of lane marking data

Harutoshi Yamada Yoshihide Sekimoto Yutaka Matsubayashi

Source

Cite

Citations (2)

DEVELOPMENT OF THE CRUISE-ASSIST SYSTEM AND ITS EFFECTS ON THE IMPROVEMENT OF TRAFFIC SAFETY

Doboku Gakkai Ronbunshuu D (2007)

Harutoshi Yamada Setsuo Hirai Hiroshi Makino Tsutomu Yamazaki Hiroyuki Mizutani

交通の安全性の向上は,高度道路交通システムの重要な目標のひとつである.走行支援道路システムの開発の一環として,前方障害物衝突防止支援システムの研究開発が実施されてきた.開発されたシステムの性能をドライビングシミュレーター,試験走行路等で検証したうえで,2005(平成17)年から社会実験が開始された.本論文では,こうしたシステムの要素技術に必要な機能とその実現方法について述べ,さらに首都高速道路参宮橋地区における社会実験で交通事故が大幅に減少したことを示し,導入された前方障害物衝突防止支援システムが事故の減少にどの程度寄与したのかを分析した.路側表示板による前方障害物の警告表示は舗装の打ち替え以上の減少効果があり,VICSを用いた情報提供はこれらに次ぐ効果をもつことを見いだした.

10.2208/jscejd.63.360

Cite

Citations (1)

Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference

Proceedings of the AAAI Conference on Artificial Intelligence (2016)

Quanjun Chen Xuan Song Harutoshi Yamada Ryosuke Shibasaki

With the rapid development of urbanization and public transportation system, the number of traffic accidents have significantly increased globally over the past decades and become a big problem for human society. Facing these possible and unexpected traffic accidents, understanding what causes traffic accident and early alarms for some possible ones will play a critical role on planning effective traffic management. However, due to the lack of supported sensing data, research is very limited on the field of updating traffic accident risk in real-time. Therefore, in this paper, we collect big and heterogeneous data (7 months traffic accident data and 1.6 million users' GPS records) to understand how human mobility will affect traffic accident risk. By mining these data, we develop a deep model of Stack denoise Autoencoder to learn hierarchical feature representation of human mobility. And these features are used for efficient prediction of traffic accident risk level. Once the model has been trained, our model can simulate corresponding traffic accident risk map with given real-time input of human mobility. The experimental results demonstrate the efficiency of our model and suggest that traffic accident risk can be significantly more predictable through human mobility.

Autoencoder

10.1609/aaai.v30i1.10011

Cite

Citations (198)

Evaluation of the Effects of a Forward Obstacle/Congestion Warning Service on Traffic Accidents

16th ITS World Congress and Exhibition on Intelligent Transport Systems and ServicesITS AmericaERTICOITS Japan (2009)

Harutoshi Yamada

A forward obstacle/congestion warning system was installed at a black spot on the Metropolitan Expressway in Tokyo. After the warning service began, the number of accidents decreased considerably. However, other countermeasures were implemented around the same time as the warning service. Therefore, the effects of the warning service on traffic accidents should be analyzed separately. A change-point model is adopted to analyze the effects and estimated using MCMC. The effect of repavement is proved to be most important and that of warning service using dedicated short range communication (DSRC) is secondary. These results are compared with those of the preceding analysis.

Black spot

Source

Cite

Citations (0)

A Context-Aware Nonnegative Matrix Factorization Framework for Traffic Accident Risk Estimation via Heterogeneous Data

2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) (2018)

Quanjun Chen Xuan Song Zipei Fan Tianqi Xia Harutoshi Yamada

Traffic accidents have significantly globally increased over the past decades. The safety of transportation system has become an important issue for human society. Efficiently estimating accident risk will help for alleviating these safety issues and improving safety investment. As accidents are always caused by complex factors, heterogeneous data and a suitable model to combine these data information are needed in accident risk analysis. In this paper, we proposed a framework which utilizes matrix factorization method to estimate accident risk. First, we collect heterogeneous data and extract features from them so that we can get feature matrices to describe the background when accidents happened. Furthermore, we utilize context-aware non-negative matrix factorization method to model accident risk in a citywide scale. The results validate the efficiency of our model, and suggest that accident risk estimation can be significantly more accurate with heterogeneous data even accident data is missing or environment changes.

Accident (philosophy)

Non-negative Matrix Factorization

10.1109/mipr.2018.00077

Cite

Citations (21)

NEW URBAN FREIGHT TRANSPORT SYSTEM.

M Koshi Harutoshi Yamada Eiichi Taniguchi

Transport system

Source

Cite

Citations (0)

Framework of Road-update Information and its Collection from Road Managers

19th ITS World CongressERTICO - ITS EuropeEuropean CommissionITS AmericaITS Asia-Pacific (2012)

Yoshihide Sekimoto Satoru Nakajo Harutoshi Yamada Ryosuke Shibasaki

While one hand some forms of mobility support, including safe-driving support systems, have been diversifying rapidly in recent years, the importance of digital roadmaps is increasing more and more as an element of the social infrastructure. These roadmaps show information on local sites to provide support for mobility-support controls and decision making. A database of road-related information, which was established through the initiatives of agencies in both the public and private sectors, has been enhanced and is expected to continue to include more accurate and up-to-date data. In this research, therefore, a definition of ―road-update information‖ is provided, systemized, and arranged, including for existing measures. In addition, a summary is provided on what is required of road-update information and what is the actual nature of the information provided by road administrators. Finally, the paper summarizes the way information should be provided by road administrators.

Source

Cite

Citations (1)

DEMAND FORECAST AND FINANCIAL FEASIBILITY OF NEW FREIGHT TRANSPORT SYSTEMS

Harutoshi Yamada

In this paper, two proposed freight systems were compared in relation to their performance, and their financial feasibility and effects on road traffic and environment. The network of the new freight transport systems will run underground around 100 km, and have 50 or so depots if the new system is implemented in the Tokyo metropolitan area. Future freight demand was distributed to the minimum-cost path. It was found that subsidies are necessary that cover the construction cost of the infrastructure of the new freight transport system for the managing body to repay the loan. However, it was proved that the new system has a great effect on traffic flow and the environment; that is, it will mitigate the severe traffic congestion in Tokyo and NOx emission will be significantly reduced.

Traffic Management

Source

Cite

Citations (2)

Getting Broad Overview of Road Update from Procurement Notices of Road Constructions

16th ITS World Congress and Exhibition on Intelligent Transport Systems and ServicesITS AmericaERTICOITS Japan (2009)

Satoru Nakajo Yoshihide Sekimoto Yoshitaka Minami Harutoshi Yamada Ryosuke Shibasaki

This paper describes how it is necessary to collect and disseminate updated road information as soon as possible for wide intelligent transportation system (ITS) applications such as navigation. This paper shows the result of a trial of getting road update information from procurement notices of road authorities. First, the circumstances of collecting road update information are summarized. Next, the information included in a procurement notice of road authorities is described and the potential of the use of this information for collecting road updating is evaluated. It was found out that it is possible to use the procurement notices of road construction works for collecting road update information.

Road Construction

Source

Cite

Citations (2)

TIME TO UNBLOCK JAPAN'S URBAN TRAFFIC CONGESTION

Harutoshi Yamada

This article examines suburban traffic congestion in Japan and explains why the current urban transport situation is unsatisfactory. The following factors are why Japan's urban traffic is unsatisfactory: urban road development is insufficient; population increase in the outer areas of cities has increased transport demand for railways; buses have failed to compete with private cars; environmental impact of traffic is increasing.

Source

Cite

Citations (0)