辦公室 : 地理系館608室
My research explored artificial intelligence tools within the geographic domain, adapting state-of-the-art artificial neural network architectures into the context of geospatial analysis. It primarily involved human mobility processing (time-series-based formats) and remote sensing applications (image-based formats), targeting an automatic extraction and use of space-time information without any human knowledge assistance.
Feb 2018 – May 2021:
•PhD in Applied Geoinformatics, University of Salzburg (Salzburg, Austria).
PhD Thesis: Artificial neural networks for human mobility analysis and spatial-temporal activity modeling.
(Supervisors: Prof. Euro Beinat, Dr. Pavlos Kazakopoulos).
• Oct 2015 – Dec 2017:
MSc in Biomedical Engineering, Politecnico di Milano (Milan, Italy).
Master Thesis: Identification of atrial fibrillation from RR intervals: a feasibility study on Long Short-Term Memory neural networks.
(Supervisors: Prof. Manuela Ferrario, Prof. Joseph Randall Moorman).
• Sep 2011 – Feb 2015:
BSc in Biomedical Engineering, Politecnico di Milano (Milan, Italy).
Bachelor Thesis: Biomedical sensor system for physical activity monitoring.
(Supervisor: Prof. Giambattista Gruosso).
WORK AND RESEARCH EXPERIENCE
•Aug 2021 – July 2023:
Postdoctoral Research Fellow in Artificial Intelligence at the Department of Computer Science and Engineering, Southern University of Science and Technology (Shenzhen, China).
Research topic: GeoAI – Artificial Intelligence for geospatial applications.
• Feb 2018 – May 2021:
PhD researcher in Applied Geoinformatics at the Doctoral College “GIScience”, Department of Geoinformatics - Z_GIS, University of Salzburg (Salzburg, Austria).
Fully-funded position by the Austrian Science Fund (FWF).
Research topic: Artificial neural networks for human mobility analysis and spatial-temporal activity modeling.
•Mar 2020 – Jul 2020:
Research intern in Naspers and Prosus AI team (Amsterdam, The Netherlands), and collaborations with iFood AI team (Sao Paulo, Brazil) on behalf of Prosus.
Paid internship position by Prosus, within the context of PhD research stay abroad.
Research topic: Predicting urban distribution of short-term food delivery demand (side works also comprise restaurant churn forecasting, demand shaping strategies
and customer recommendations).
• Mar 2017 – Sep 2017:
Visiting researcher at the University of Virginia Health System (Charlottesville, VA, USA).
Invited research guest for developing the experimental part of the Master Thesis.
Research topic: Deep learning for automatic cardiac arrhythmias detection
GeoAI / Geospatial Data Science (Geoinformatics)
Introduction to Data Science and Machine Learning
Crivellari, A., Beinat, E., Caetano, S., Seydoux, A., & Cardoso, T. (2022). Multi-target CNN-LSTM regressor for predicting urban distribution of short-term food delivery demand. Journal of Business Research, 144, 844-853.
Crivellari, A., & Resch, B. (2022). Investigating functional consistency of mobility-related urban zones via motion-driven embedding vectors and local POI-type distributions. Computational Urban Science, 2(1), 1-15.
Crivellari, A., Resch, B., & Shi, Y. (2022). TraceBERT — A feasibility study on reconstructing spatial–temporal gaps from incomplete motion trajectories via BERT training process on discrete location sequences. Sensors, 22(4), 1682.
Ghorbanzadeh, O., Shahabi, H., Crivellari, A., Homayouni, S., Blaschke, T., & Ghamisi, P. (2022). Landslide detection using deep learning and object-based image analysis. Landslides, 1-11.
Ghorbanzadeh, O., Crivellari, A., Ghamisi, P., Shahabi, H., & Blaschke, T. (2021). A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan). Scientific Reports, 11(1), 1-20.
Crivellari, A., & Ristea, A. (2021). CrimeVec — Exploring spatial-temporal based vector representations of urban crime types and crime-related urban regions. ISPRS International Journal of Geo-Information, 10(4), 210.
Crivellari, A., & Beinat, E. (2020). LSTM-based deep learning model for predicting individual mobility traces of short-term foreign tourists. Sustainability, 12(1), 349.
Crivellari, A., & Beinat, E. (2020). Trace2trace — A feasibility study on neural machine translation applied to human motion trajectories. Sensors, 20(12), 3503.
Crivellari, A., & Beinat, E. (2020). Forecasting spatially-distributed urban traffic volumes via multi-target LSTM-based neural network regressor. Mathematics, 8(12), 2233.
Crivellari, A., & Beinat, E. (2019). From motion activity to geo-embeddings: Generating and exploring vector representations of locations, traces and visitors through large-scale mobility data. ISPRS International Journal of Geo-Information, 8(3), 134.
Crivellari, A., & Beinat, E. (2019). Identifying foreign tourists’ nationality from mobility traces via LSTM neural network and location embeddings. Applied Sciences, 9(14), 2861.
Kovacs-Györi, A., Ristea, A., Kolcsar, R., Resch, B., Crivellari, A., & Blaschke, T. (2018). Beyond spatial proximity — Classifying parks and their visitors in London based on spatiotemporal and sentiment analysis of Twitter data. ISPRS International Journal of Geo-Information, 7(9), 378.
• 2nd prize at the Young Investigator Award 2020 (University of Salzburg)
• 2nd prize at the Mouse Behavior Challenge 2020 (Hiroshima University)
• 3rd prize at the Basketball Behavior Challenge 2020 (Hiroshima University)