Practical occupancy detection for programmable and smart thermostats

Soltanaghaei, Elahe; Whitehouse, Kamin

doi:10.1016/j.apenergy.2017.11.024

Cited by 28 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the traditional technologies for human presence sensing, PIR [2,19,20], CO2 [27] and cameras [26] have been identified as commercial occupancy sensors. However, none of these sensors accurately measure occupancy.…”

Section: Human Presence Detectionmentioning

confidence: 99%

Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model

Soltanaghaei

Sharma

Wang

et al. 2020

Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Self Cite

View full text Add to dashboard Cite

The ubiquity of WiFi devices combined with the ability to cover large areas, pass through walls, and detect subtle motions makes WiFi signals an ideal medium for sensing occupancy. While extremely promising, existing WiFi sensing solutions have not been rigorously tested outside of lab environments and don't often consider real-world constraints associated with non-expert installers, cost-effective platforms and long-term changes in the environment. This paper presents M-WiFi, a user-in-the-loop self-tuning framework for WiFi-based human presence detection with on-device learning and domain adaption capabilities that operates entirely on an embedded platform. M-WiFi robustly detects human presence by separating human-specific disturbances on WiFi signals from those of static objects, moving furniture or even pets. The high-level features of human presence are captured in an initial generalized classification model which adapts over time to a new building by selectively asking users to annotate a small number of critical time periods. We evaluate M-WiFi in 7 different houses, for a total of 100 days, with a mixture of pets and including periods of sleep and stationary activities. We show that our domain adaptive model can detect the human presence with an average accuracy of 90% in a completely new house after only 3 days of self-tuning and rapidly reaches a steady-state performance of 98% in long-term operations. CCS Concepts • Human-centered computing → Ubiquitous and mobile computing design and evaluation methods.

show abstract

Section: Human Presence Detectionmentioning

confidence: 99%

Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model

Soltanaghaei

Sharma

Wang

et al. 2020

Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Li et al [1] found an average positioning accuracy of 88% for stationary occupants and 62% for mobile occupants when using active RFID systems, although the active network infrastructure is expensive [37]. Some researchers also investigated the application of motion sensors as walkaway sensing to track occupancy movement and behaviors, which achieves 96% and 95% average accuracies in offline and online modes [38]. At the computer science and artificial intelligence laboratory of Massachusetts Institute of Technology (MIT), Fadel Adib et al have researched how to Radio Frequency (RF)-capture and WiTrack to track an occupant through walls with Wi-Fi signals and via body radio reflections [39].…”

Section: Location Tracking and Activity Of Occupancy Studiesmentioning

confidence: 99%

Modeling occupancy distribution in large spaces with multi-feature classification algorithm

Wang

Chen

Hong

2018

Building and Environment

View full text Add to dashboard Cite

Occupancy information enables robust and flexible control of heating, ventilation, and airconditioning (HVAC) systems in buildings. In large-sized spaces, multiple HVAC terminals are usually installed to provide cooperative services for different thermal zones. Occupancy information for large spaces, such as people counts, determines the cooperation among terminals. However, a people count at room-level is not adequate to optimize HVAC system operation due to occupant movement within the room leading to uneven distribution of loads. Without an accurate knowledge of occupants' spatial distribution, uneven distribution of occupants often results in under-cooling/heating or over-cooling/heating in some thermal zones. Therefore, the lack of high-resolution occupancy distribution is often perceived as a bottleneck for future improvement in HVAC operation efficiency. To fill this gap, this study proposes a multi-feature based k-Nearest-Neighbors (k-NN) classification algorithm to extract occupancy distribution through reliable and low-cost Bluetooth Low Energy (BLE) networks. To demonstrate the proposed methods, an on-site experiment was conducted in a typical office of an institutional building. To validate the detection accuracy, the experiment outcomes were examined in three case studies, and one method based on City Block Distance (CBD) is used to measure the distance between detected occupancy distribution and ground truth and assess the results of occupancy distribution. The results show that the accuracy of CBD = 1 is over 71.4% and accuracy of CBD = 2 can reach 92.9%.

show abstract

“…In addition to smart meters and energy devices that have emerged on the market for saving energy in households and buildings, connected thermostats (CTs) have a significant impact on saving energy in HVAC systems. The fundamental goal of an HVAC control system is to keep temperature and air quality within a comfortable range while minimizing energy usage (Soltanaghaei and Whitehouse, 2018). In (Ponce et al, 2018a), a connected thermostat (CT) is defined as an electrical device that links smart homes with smart grids.…”

Section: Introductionmentioning

confidence: 99%

“…In (Ponce et al, 2018a), a connected thermostat (CT) is defined as an electrical device that links smart homes with smart grids. CTs are thus designed to automatically learn occupants' schedules and turn heating and cooling on or off on the users' behalf (Soltanaghaei and Whitehouse, 2018). The CTs' design makes it possible to consume low energy, increase consumer comfort, and inform users about the energy conditions of the thermostats through mobile device interfaces.…”

Section: Introductionmentioning

confidence: 99%

Tailored gamification and serious game framework based on fuzzy logic for saving energy in connected thermostats

Ponce

Meier

Méndez

et al. 2020

Journal of Cleaner Production

View full text Add to dashboard Cite

Connected thermostats (CTs) often save less energy than predicted because consumers may not know how to use them and may not be engaged in saving energy. Additionally, several models perform contrary to consumers' expectations and are thus not used the way they are intended to. As a result, CTs save less energy and are underused in households. This paper reviews aspects of gamification and serious games focused on engaging consumers. A gamification and serious games framework is proposed for saving energy that is tailored by a fuzzy logic system to motivate connected thermostat consumers. This intelligent gamification framework can be used to customize the gamification and serious game strategy to each consumer so that fuzzy logic systems can be adapted according to the requirements of each consumer. The framework is designed to teach, engage, and motivate consumers while helping them save electrical energy when using their thermostats. It is described the proposed framework as well as a mockup that can be run on a cellphone. Although this framework is designed to be implemented in CTs, it can be translated to their energy devices in smart homes.

show abstract

Practical occupancy detection for programmable and smart thermostats

Cited by 28 publications

References 21 publications

Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model

Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model

Modeling occupancy distribution in large spaces with multi-feature classification algorithm

Tailored gamification and serious game framework based on fuzzy logic for saving energy in connected thermostats

Contact Info

Product

Resources

About