Scholar
Ye Hong
Google Scholar ID: dnaRSnwAAAAJ
ETH Zurich
Citations & Impact
Citations
1,450
H-index
17
i10-index
22
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- May 2025, gave a talk at STRC '25 titled 'Causal Inference for interpretable and robust deep learning in mobility analysis'.
- May 2025, published 'A causal intervention framework for synthesizing mobility data and evaluating predictive neural networks' in TRIP.
- May 2024, gave a talk at STRC '24 titled 'Towards realistic individual activity location demand synthesis using deep generative networks'.
- April 2024, published 'Is a 15-Minute City Within Reach? Measuring Multimodal Accessibility and Carbon Footprint in 12 Major American Cities' in Land Use Policy.
- November 2023, published 'Evaluating geospatial context information for travel mode detection' in JTRG.
- August 2023, published 'Context-aware multi-head self-attentional neural network model for next location prediction' in TRC.
- July 2023, published 'Influence of tracking duration on the privacy of individual mobility graphs' in Journal of Location Based Services.
- July 2023, published 'Predicting mobile users’ next location using the semantically enriched geo-embedding model and the multilayer attention mechanism' in CEUS.
- July 2023, accepted 'Predicting visit frequencies to new places' at GIScience '23.
- July 2023, published 'Trackintel: An open-source Python library for human mobility analysis' in CEUS.
- December 2022, published 'Conserved quantities in human mobility: from locations to trips' in TRC.
Research Experience
- Postdoctoral Researcher at the Mobility Information Engineering (MIE) Lab, ETH Zurich, and a joint appointment at the Urban Analytics Group, Department of Geography, University of Zurich.
Education
- PhD: ETH Zurich, supervised by Prof. Martin Raubal and Prof. Konrad Schindler; MSc: ETH Zurich, Geomatics; BSc: Sun Yat-sen University, Geographic Information Science and Remote Sensing.
Background
- Research interests: human mobility, urban computing, and network science. The work focuses on applying machine learning and deep learning techniques to understand, predict, and model individual mobility behavior, aiming to develop computational frameworks that enable personalized travel solutions and facilitate the transition toward sustainable and intelligent transportation systems.
Co-authors