arrow_back Knowledge Inference: Estimating how much the student knows
Sensor Analytics for IoT and Embedded Systems
Submitted by Amit Doshi (@amitdoshi) on Saturday, 30 April 2016
Section: Crisp talk Technical level: Intermediate
Analytics-driven embedded systems are here!
We’ll show this in action by classifying human activity in real-time using sensor data from a smartphone accelerometer. The demo will show a complete workflow:
– pre-processing with digital filtering and frequency analysis, – exploring different classification algorithms (such as decision trees, support vector machines, or neural networks), and – automatically generating C/C++ from MATLAB to deploy a streaming classification algorithm for embedded sensor analytics.
The ability to create analytics that process massive amounts of business and engineering data is enabling designers in many industries to develop intelligent products and services. We’ll show you how to use analytics to describe and predict a system’s behavior, and further combine analytics with embedded control systems to automate actions and decisions.
MATLAB for analytics-driven embedded systems and an end-to-end workflow:
1. Data access from sensors and historical data
2. Pre-processing, including filtering and feature selection
3. Predictive modeling with machine learning
4. Integrating with enterprise IT and embedded systems
5. Scaling the solution with Big Data
Amit Doshi, MathWorks India
Amit Doshi is an application engineer at MathWorks in the area of technical computing. He focuses on data acquisition, data presentation, statistical analysis, and parallel computing. Amit has over 9 years of experience in experimental test setup development, testing and validation, workflow automation, and system simulations. He previously worked at Suzlon Energy Limited in Pune and Germany, Texas Instruments in Germany, and IIT Bombay. Amit holds a bachelor’s degree in mechanical engineering and a master’s degree in mechatronics.