Transportation Research Part C: Emerging Technologies
Call for Papers on the Special issue: Emerging Methods for Data-driven Urban Transportation and Mobility Modeling: Machine Learning and Complexity Approaches
摘要截稿:
全文截稿: 2019-04-30
影响因子: 6.077
期刊难度:
CCF分类: 无
中科院JCR分区:
• 大类 : 工程技术 - 1区
• 小类 : 运输科技 - 1区
Overview
The advances in ICT and passive data collection techniques are generating large quantities of individual movement and travel activity trajectory data on a continuous basis, such as call detailed records, smartphone GPS observations, social media posts (e.g., Twitter), transit smart card transactions, license plate recognition records, and shared mobility data. These data sets have allowed us to observe and model individual mobility pattern and travel behavior with unprecedented spatiotemporal resolution, shifting our understanding on urban transportation and mobility from random to predictable. With the emergence of these large-scale data sets, the field of transportation research is also calling for new models, methodologies, and analytical frameworks for researchers and practitioners to better understand complex interactions between transportation networks and urban mobility, and build smart transportation systems of the future.
The models and tools from machine learning and complexity research have shown great potential to deal with and get insights from individual-based trajectory data sets in a variety of fields and applications, such as trip/route recommendation systems, spatiotemporal traffic prediction, and agent-based epidemic spreading and social diffusion analysis. In travel behavior research, machine learning and complexity approaches have also demonstrated a great potential in depicting the underlying patterns of human mobility from individual/collective traces. Developing these new tools and models for urban traffic and mobility has become an excited interdisciplinary research direction beyond transportation, attracting researchers from computer science, statistical physics, urban planning, public health, and also social sciences.
The focus of this special issue is to integrate the emerging individual-based `big-data' with the recent advances in machine learning and complexity research to build new frameworks for urban traffic/mobility modeling and prediction. Potential topics of interest include, but are not limited to:
- Recognizing patterns in aggregate and individual mobility and activity choices.
- Generative and predictive models for individual mobility and activity behaviors.
- Mobility synthesis algorithms for agent-based simulations.
- Large-scale spatiotemporal trajectory data set network modeling and analysis.
- Smart routing/trip planning and recommendation algorithms learned from collective travel data.
- Network-scale travel demand and road traffic forecasting.
- Social and physical diffusion processes resulted from urban mobility.
- Complexity of urban transportation network morphology and urban growth.
- Spatial interactions in cities as a complex system.