Developing Service Architecture of Sensor Data Analysis on Cloud Platforms (Half day, 3-Hour Tutorial)
Speaker: Yan Liu, Concordia University, Montreal, Canada
Big sensor data consists of data streams with large number of feature information constantly generated from geographically distributed sources. The processing capability becomes a data service that handles data records in parallel as they arrive and correlates across multiple records overtime to gain insights and values of data patterns. Thus the service architecture for processing high-speed data streams should scale on distributed platforms. The goal of this tutorial is to provide a practical view of the architecture challenges and techniques of building service architecture to parallelizing sensor data processing. This tutorial covers the following topics: (1) the discovery algorithms to identify the trends in time-series data streams; (2) the parallel programming frameworks for both batch and streaming implementation; (3) the ensemble of analysis models; and (4) a service architecture on a cloud cluster. This tutorial demonstrates case studies with public open dataset and a set of open source software frameworks on a fully integrated cluster environment on AWS cloud.
Dr. Yan Liu is Associate Professor at the Electrical and Computer Engineering Department, Concordia University, Canada. Her research interests are big data stream processing, cloud software architecture, distributed computing, software performance engineering, and adaptive systems. She was a senior scientist at the Pacific Northwest National Laboratory in Washington State where she led R&D projects on data intensive computing for a wide range of domains including smart grid, building energy optimization, chemical imaging, system biology knowledgebase, and climate modeling. She was a senior researcher at National ICT Australia after PhD graduation from The University of Sydney, Australia . She is a member of the IEEE and ACM. She has been actively serving international conference organizations as tool/demo chairs and workshop organizers in the past 10 years.