Download Interactive Context-aware System for Energy Efficient Living (INCA)

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Electric machine wikipedia , lookup

Pulse-width modulation wikipedia , lookup

Power engineering wikipedia , lookup

Alternating current wikipedia , lookup

Negative feedback wikipedia , lookup

Artificial intelligence wikipedia , lookup

Control system wikipedia , lookup

Opto-isolator wikipedia , lookup

Distribution management system wikipedia , lookup

Anastasios Venetsanopoulos wikipedia , lookup

Hendrik Wade Bode wikipedia , lookup

Transcript
Interactive Context-aware System
for Energy Efficient Living (INCA)
• The aim of the project is to develop context-aware sensorbased feedback and control system to support energy
efficient living and housing
– self-motivate inhabitants to be aware of their energy consumption
habits
• Project team of ISG at University of Oulu (UO)
– Prof. Juha Röning (Principal investigator), Jaakko Suutala,
Tuomo Alasalmi, Ari Pitkänen (Researchers)
– Main research topics: low-level sensing systems, machine learning
and data mining, human context recognition
• Joint project with Assoc. Prof. Kaori Fujinami at Tokyo
University of Agriculture and Technology
– Main research topics: Persuasive feedback and control techniques,
activity recognition
Overview of INCA Project
• Novel techniques to detect water and electricity consumption
in relation to inhabitants acting in environment to control
devices and to give informative feedback
– easy to install, low-cost sensors approaches together with signal
processing and machine learning algorithms are developed
Current Activities at UO (1)
• Water flow and consumption estimation using
mechanical vibration of water pipe
– Embedded system to collect data
– Machine learning to estimate flow rate from sound
signal
Current Activities at UO (2)
• Non-intrusive load monitoring to measure per appliance
electricity consumption
– Single-point measurements of power, reactive power, cumulative
consumption, voltage, and current
– Signal processing and machine learning to detect and discriminate
individual appliances signatures (e.g., on-off events)