Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier (2017-2018 à 2018-2019).

Per Statistics Canada, households continued to be the largest users of energy accounting for 24.0% of nationalx000D
energy use. Heating, ventilation, and air-conditioning (HVAC) has been singled out as the most importantx000D
contributor to gas emissions. This project aims at enhancing residential HVAC systems to optimize energyx000D
consumption based on intelligent occupancy detection/identification. While several technologies/sensors havex000D
been proposed to address this challenge, the cost, accuracy, and the seamless integration with existing buildingx000D
automation infrastructures remain major challenges especially for homes where cost and complexity are keyx000D
factors. Recently, there is a noticeable increase in number and types of affordable sensors in modern homes.x000D
For example, solar radiation sensors are used to detect room lightening condition. Infrared and ultrasoundx000D
sensors are used as proximity and motion sensors. Weight sensors are becoming common in several houses.x000D
Some advanced HVAC systems provides level of carbon dioxide. The availability of these sensors creates anx000D
opportunity to develop cost-effective advanced occupancy detection and identification technology to enablex000D
optimized adaptive residential HVAC systems. The proposed project will adopt a sensor fusion approach tox000D
tackle the problem. In one possible scenario, radar and silicon MEMS-based microphone sensors may be usedx000D
to develop occupancy maps. Radar and silicon MEMS-based microphone sensors provide far field soundx000D
waves capture by audio beam-forming combined with radar target presence detection. With the increasingx000D
number of other available sensors, artificial intelligence and machine learning can be used to apply sensorx000D
fusion. The proposed system will have two phases; training phase and identification phase. In training phase,x000D
occupancy and identity data will be collected along with available sensor measurements. Data will be modeledx000D
using a Hidden Markov Model. In identification phase, first, the available sensor measurements will be used tox000D
detect occupancy. Then, the radar/MEMS-based microphone can be will be used to identify the occupantsx000D
using voice recognition.