The Internet of Things domain bring a new challenge for handling large streams of data from multiple sources into some data store for persistence or later analysis. In the analytics case we would like run real time anomaly detection and alerting or detecting user activity such as walking, running or sleeping from raw accelerometer data, while in other cases the data requires to be transformed, cleaned or filtered before persisted.
In this talk we will describe the Intel Stream Analytics Engine via the Parkinson Disease research project. The research of Parkinson«™s disease is developed in a partnership between Intel and the Michael J. Fox foundation to enable breakthroughs in Parkinson’s disease (PD) research, by leveraging wearable sensors and smartphones to monitor PD patient«™s motor activity 24/7. We built a platform based on open source solutions to enable collection and processing of high data streams (up to 1 GB per patient per day, sensor sampling of up to 50hz) and different analytics services.
About the speaker
Assaf Araki is responsible for big data analytics path findings in Intel Advanced Analytics group within Intel Information Technology that delivers machine learning and big data solutions across Intel.
Assaf drives the overall work with the academy and industry for Big Data Analytics and merge new technologies inside Intel Information Technology.
Assaf has over 10 years of experience in Data Warehousing, Decision Support solutions and applied analytics within Intel.