Name: Sobhan Moosavi
Type: User
Company: Lyft
Bio: I'm a Scientist at Lyft (mapping team). Prior to that, I was a PhD student at Ohio State, working on driving risk prediction and traffic data modeling.
Twitter: sobmoosavi
Location: San Francisco, CA
Blog: https://smoosavi.org/
Sobhan Moosavi's Projects
This is a tensorflow implementation of "Autoencoder Regularized Network For Driving Style Representation Learning"
This is a tensorflow implementation of "Characterizing Driving Styles with Deep Learning".
This repo contains all the codes and sample files for the DCRNN paper
An abstraction layer for distributed computing and machine learning. Fugue ports SQL, Python, and Pandas code to run on Spark and Dask.
Code for "How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks"
Map Matching based on GraphHopper
This is a simplified version of progressive neural networks (https://arxiv.org/abs/1606.04671)
This repo contains all the codes and sample files for the "Short and Long-term Pattern Discovery Over Large-Scale Geo-Spatiotemporal Data" paper
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
This repository contains all the code related to Telematics Research
This repo contains the code and sample data for "Discovery of Driving Patterns by Trajectory Segmentation" paper.