Скачать или смотреть Large-scaled telematics analytics

The increasing availability of mobile phones with embedded GPS devices and sensors has spurred the use of vehicle telematics in recent years. Telematics provides detailed and continuous information of a vehicle such as the location, speed, and movement. Vehicle telematics can be further linked with other spatial data to provide context to understand driving behaviors at the detailed level. However, the collection of high-frequency telematics data results in huge volumes of data that must be processed efficiently. And the raw sensor and GPS data must be properly pre-processed and transformed to extract signal relevant to downstream processes. In addition, driving behavior often depends on the spatial context, and the analysis of telematics must be contextualized using spatial and real-time traffic data.

Our talk covers the promises and challenges of telematics data. We present a framework for large-scaled telematics data analysis using Apache big data tools (Hadoop, Hive, Spark, Kafka, etc). We discuss common techniques to load and transform telematics data. We then present how to use machine learning on telematics data to derive insights about driving safety.

Speakers
YANWEI ZHANG
Senior Data Scientist II
Uber

NEIL PARKER
Senior Software Engineer
Uber Technologies Inc
Neil Parker is a software engineer at Uber Technologies Inc. He has a Bachelor’s degree in information science and a Master’s degree in computer science from Cornell University. He has worked on projects ranging from creating visualizations to building efficient real-time systems. He has interests in distributed computing with a focus on driving safety.