
Abstract: The smartphone is perhaps the most powerful machine in human history. People take it with them everywhere they go, and it provides essentially limitless entertainment, knowledge, and utility. Smartphones are also one of the richest sources of data today. Almost every phone comes equipped with sensors that passively generate enormous amounts of data, such as the GPS, IMU, magnetometer and barometer. Companies are using this data to design machine learning systems that can predict the weather, forecast stock prices, build behavior profiles and detect dangerous driving. In this talk we will discuss how to harness the power of smartphone sensor data, including how to: Best utilize each smartphone sensor, Understand the fundamental problems with sensor data and the algorithms we use to combat them, Win the battle against battery usage, Deal with the limitations of data collection, Make the most of classical ML and Deep Learning algorithms for sensor data analysis
Bio: Dan is a Data Scientist at TrueMotion, where he develops machine learning algorithms that use smartphone sensors to understand and score driving behaviors. Dan leads TrueMotion's efforts on developing smartphone IMU algorithms to detect hard brakes and distracted driving. In his spare time, Dan volunteers as a Deep Learning Researcher at Brown University and as a guest speaker at the NYC Data Science Academy.

Dan Shiebler
Title
Senior Data Scientist at TrueMotion
