Call for Papers: Special Issue on Deep Modeling and Understanding of Big Human Mobility Data
- Renhe Jiang, The University of Tokyo, Japan
- Ryosuke Shibasaki, The University of Tokyo, Japan
- Kota Tsubouchi, Yahoo! Japan Research, Japan
- Peng Han, Aalborg University, Denmark
Thanks to the continuing development of IoT (Internet of Things) and CPS (Cyber-Physical Systems) technologies, massive human mobility data are collected from various sources such as connected cars, traffic sensors, mobile phones, location-based social networks, and Wi-Fi logs. With such data, understanding and predicting human mobility at different scales (district, city, state, country, worldwide) will be of great significance for transportation operations, disaster response, post-pandemic recovery, city management, public health, social economics, urban planning, and environmental sustainability. However, big human mobility at different scales and scenarios is highly complex, thus difficult to be modeled by traditional methodologies. Encouraged by the huge success of deep learning technologies in the main AI communities such as Computer Vision and Natural Language Processing, researchers in Geographic Information Science (GIS) and Data Science (DS) community also show that the state-of-the-art Deep Learning (DL) technologies help us better model and understand the big human mobility data.
But still, we have the following open challenges that need to be addressed. (1) Beyond human mobility, how could we semantically understand human behavior? Spatiotemporal patterns of human mobility can be easily discovered from the data but inferring and analyzing the underlying behavior in the data is more significant but challenging. (2) Beyond single-modal data, how could we better model and understand human mobility from multi-modal data? The additional data could be weather or event information, image and text on social media, and searching or shopping logs. (3) Beyond normal scenarios, how could we effectively model and understand human mobility under anomalous scenarios such as big events, disasters, and pandemics? Because human mobility under those situations will deviate from the routines to a large degree, which challenges the existing models and algorithms. (4) Beyond time and space, how could we understand long-term and large-scale human mobility in an efficient way? How could we transfer human mobility knowledge over time and space? If we are mobility-data rich, the former question matters, while the latter is particularly significant if we are data-poor. We believe these open challenges could be further explored or solved by DL technologies including advanced neural networks (e.g., graph neural networks, recurrent neural networks, convolutional neural networks, transformers) and learning paradigms (e.g., representation learning, contrastive learning, transfer learning, multitask learning, adversarial learning).
Thus, in this special issue, we encourage researchers to address the aforementioned open challenges or revisit the existing important research topics about human mobility modeling and understanding by leveraging state-of-the-art DL technologies. Moreover, to better facilitate whole community engagement, we particularly welcome studies that are conducted based on publicly available human mobility data including but not limited to:
- Taxi data in New York and Chicago
- Bike data in New York and Chicago
- Porto taxi dataset
- Foursquare check-in data
- Gowalla check-in data
- Brightkite check-in Data
- T-Drive trajectory data
- Geolife trajectory data
- SafeGraph POI visit data
- Yelp dataset
- Yahoo Bousai Crowd data
The research topics include, not limited to:
- Understanding human behavior from multimodal mobility data
- Modeling human mobility at big events/disasters
- Analyzing pre/post-pandemic human mobility/behavior
- Modeling human mobility at a large spatiotemporal scale
- Recommendation system on human mobility
- Human (Crowd/Traffic) mobility forecasting
- Natural language processing techniques for human mobility modeling
- Computer vision techniques for human mobility modeling
- Epidemic modeling with human mobility
- Understanding human mobility and environmental sustainability
- Understanding human mobility and urban resilience
- Understanding human mobility and transportation
- Understanding human mobility and social economics
- Paper submission deadline: July 31, 2023
- First notification: September 31, 2023
- Revision: November 30, 2023
- Final decision: January 31, 2024
How to Submit
- Choose "Submit Manuscript" on the right-hand side of the GeoInformatica site to access SNAPP, our article processing platform.
- Choose "Research" as your article type; you will be asked about the collection you wish to submit to later in the process.
- On the "Details" page in the "Collections" drop down choose "Special Issue on Deep Modeling and Understanding of Big Human Mobility Data."
Authors are encouraged to submit high-quality, original work that has neither appeared in, nor is under consideration by other journals. All papers will be reviewed following standard reviewing procedures for the Journal. Papers must be prepared in accordance with the Journal guidelines: http://www.springer.com/10707
Springer provides a host of information about publishing in a Springer Journal on our Journal Author Resources page, including FAQs, Tutorials along with Help and Support.
Other links include:
For authorsSubmit manuscript
Working on a manuscript?
Avoid the most common mistakes and prepare your manuscript for journal editors.Learn more