Published in The 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL 2019). (Chicago, IL), 2019
This paper is a new solution for real-time accident prediction based on heterogeneous data such as traffic, weather, and points-of-interest.
Download here
Published in The 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD 2019). (Anchorage, AK), 2019
This paper is a new framework to discovery short and long-term patterns over geo-spatiotemporal data (e.g. traffic, weather, etc.). Short-term patterns show propagation of geo-spatiotemporal entities which cause other entities to happen (e.g. rain –> accident –> traffic jam). Long-term patterns show the influence of a temporally long-term entity on its spatiotemporal neighborhood (e.g. major construction –> more traffic issue).
Download here
Published in 12th International AAAI Conference on Web and Social Media (ICWSM 2018). (Stanford, CA), 2018
This paper is a new framework to estimate question dificulty and exprtise of users in community question anwering systems such as Stack Overflow. The outcome can be used for effective question routing and increasing collaborations in such environments.
Download here
Published in Proceedings of the 3rd ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, 2017
A new geo-sptial annotation framework and a dataset to be used as ground-truth data for trajectory segmentation.
Download here
Published in 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (Los Angeles, CA), 2017
A new framework to characterize driving context based on driving behavior as prerequisite for driving risk prediction.
Download here
Published in arxiv preprint, 2017
A new geo-sptial annotation framework and a dataset to be used as ground-truth data for trajectory segmentation (technical report).
Download here
Published in 3rd ACM SIGSPATIAL PhD Symposium (San Francisco, CA), 2016
A novel approach to perform trajectory segmentation based on driving behavior using Markov Model and Dynamic Programing solution.
Download here
Published in 2nd InternationalWorkshop on Parallelism in Bioinformatics (PBio), IEEE Cluster (Madrid, Spain), 2014
A novel framework to perform protein interaction prediction on proterin-protein interaction netwrosk, based on rotations of proteins in 3D space.
Download here
Published in 18th National CSI Computer Conference (Tehran, Iran), 2013
This paper provides a comprehensive framework to compare web search engines on Farsi web based on several factors, including relevance, retrieval, crawling, etc.
Published in Journal of Computational Biology and Chemistry, 2013
This paper provides a new framework to leverage structural properties of protein-protein interaction networks to perform protein function prediction.
Download here
Published in 19th International Conference on Neural Information Processing (Doha, Qatar), 2012
A novel framework to perform protein function prediction using structure of protein-protein interaction network.