Novel Methods for Activity Classification and Occupany Prediction Enabling Fine-grained HVAC Control

TL;DR

This paper introduces novel sensor fusion and activity classification methods using smartphones to accurately estimate occupancy and activity, enabling more energy-efficient HVAC control without requiring additional infrastructure.

Contribution

It presents a sensor fusion approach for occupancy estimation with near-perfect accuracy and an activity classification algorithm that reduces processing by half while maintaining high accuracy.

Findings

Sensor fusion achieves nearly 100% occupancy estimation accuracy.

Activity classification matches state-of-the-art accuracy with 50% less processing.

Methods enable cost-effective, smartphone-based HVAC optimization.

Abstract

Much of the energy consumption in buildings is due to HVAC systems, which has motivated several recent studies on making these systems more energy- efficient. Occupancy and activity are two important aspects, which need to be correctly estimated for optimal HVAC control. However, state-of-the-art methods to estimate occupancy and classify activity require infrastructure and/or wearable sensors which suffers from lower acceptability due to higher cost. Encouragingly, with the advancement of the smartphones, these are becoming more achievable. Most of the existing occupancy estimation tech- niques have the underlying assumption that the phone is always carried by its user. However, phones are often left at desk while attending meeting or other events, which generates estimation error for the existing phone based occupancy algorithms. Similarly, in the recent days the emerging theory of Sparse Random Classifier (SRC) has been applied for activity classification on smartphone, however, there are rooms to improve the on-phone process- ing. We propose a novel sensor fusion method which offers almost 100% accuracy for occupancy estimation. We also propose an activity classifica- tion algorithm, which offers similar accuracy as of the state-of-the-art SRC algorithms while offering 50% reduction in processing.