Occupancy detection in commercial buildings using opportunistic context sources

J Ambient Intell Human Comput

2014

This paper presents a dynamically adaptive proximity controller (APC) to balance energy consumption and user comfort of computer screens in office environments. Our APC system detects desk activities, such as working with the computer screen (screen on) and being away (screen off) and controls screens accordingly. Ultrasound range (USR) sensors were used to measure user proximity. To compensate for USR measurement errors, APC timing parameters were dynamically adapted and previous screen switch-off operations corrected using implicit user feedback. The feedback was obtained from proximity variance increases due to user movement following erroneous control operations. System performance and user comfort were evaluated in a real-life intervention study with 12 participants during 19 days. Detection accuracy was up to 98 %. Energy savings of up to 21 % were obtained by comparing intervention and baseline measurements. User responses showed that the APC system could yield energy savings, while maintaining user comfort when assessed using pre-and post-intervention questionnaires. The implicit feedback control is suitable to reduce system commissioning effort.

Section: Related Workmentioning

confidence: 99%

Using implicit user feedback to balance energy consumption and user comfort of proximity-controlled computer screens

Garcia

Gonzalez

J Ambient Intell Human Comput

2014

“…In [10] and [22] authors used user access badges, identification via Wi-Fi points, user calendars, Instant Messaging clients, and computer system activity, in order to track users and recognize their activities. With this rich information about users, these opportunistic approaches showed good recognition accuracies and potential for energy saving.…”

Section: Related Workmentioning

confidence: 99%

An opportunistic activity-sensing approach to save energy in office buildings

Milenkovic

Proceedings of the Fourth International Conference on Future Energy Systems

2013

In this work, we recognised office worker activities that are relevant for energy-related control of appliances and building systems using sensors that are commonly installed in new or refurbished office buildings. We considered desk-related activities and people count in office rooms, structured into desk-and room-cells. Recognition was performed using finite state machines (FSMs) and probabilistic layered hidden Markov models (LHMMs).We evaluated our approach in a real living-lab office, including three private and multi-person office rooms. As example devices, we used different ceiling-mounted PIR sensors based on the EnOcean platform and plug-in power meters. In at least five days of study data per office room, including reference sensor data and occupant annotations, we confirmed that activities can be recognised using these sensors. For computer and desk work, an overall recognition accuracy of 95% was achieved. People count was estimated at 87% and 78% for the best-performing two office rooms. We furthermore present building simulation results that compare different control strategies. Compared to modern BEMS, our results show that 21.9% and 19.5% of electrical energy can be saved for controls based on recognised desk activity and estimated people count, respectively. These results confirm the relevance of building energy management based on activity sensing.

“…The authors modelled rhythm patterns from data obtained through computer-mediated communication technologies, to share availability in remote working scenarios. Similarly, a soft sensing approach based on Wi-Fi access points, user calendar, system activity monitor, instant messaging clients and time-of-day was used, achieving recognition accuracies of 90% [8]. Conversely, commodity computer hardware, including computer microphones and speakers was used to recognise user activities from ultrasonic signals achieving a performance accuracy of up to 96% [9].…”

Section: Related Workmentioning

confidence: 99%

Improving energy efficiency through activity-aware control of office appliances using proximity sensing - A real-life study

Jaramillo

2013 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops)

2013

Energy efficiency is a key operational characteristic of today's office environments. In this paper, we present a system architecture to control desk appliances such as computer screens based on recognised desk and computer work activities. In a real-life intervention study at seven desks, we use screen-attached ultrasound sensors and explore a proximitybased activity recognition approach for saving energy by automatically turing computer screens off when not using them. We analyse online performance of our approach regarding recognition rate and screen resume delay. Furthermore, we present a comparative analysis of our proximity-controlled approach against the computer-controlled power management and a non-controlled baseline to quantify energy saving benefits. Our results show energy savings of up to 43% and 55% for proximity-controlled computer screens compared to computercontrolled and non-controlled scenarios respectively.