Learning-based occupancy behavior detection for smart buildings

Zhao, Haisen; Qi, Zhongdong; Wang, Shujuan; Vafai, Kambiz; Wang, Hai; Chen, Hai-Bao; Tan, Sheldon X.-D.

doi:10.1109/iscas.2016.7527400

Cited by 11 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19 The sensing infrastructure detects the occupied area, communicates this information to a control unit and the controller makes a decision according to the application of the received data. 60,63 The limitations of this approach are:…”

Section: General Approaches For Occupancy Detectionmentioning

confidence: 99%

“…Occupancy detection systems are widely used to monitor and detect events for building management purposes. [60][61][62][63] Over the past decade of research, fine-grained occupancy information has been a fundamental input for building simulation tools such as EnergyPlus, 64 ESP-r, DeSt and TRNSYS. 65 Among the several studies covering the various aspects of occupancy detection system, Labeodan et al 66 classified an occupancy detection system based on method (terminal and non-terminal), function (individualized and non-individualized) and infrastructure (implicit and explicit).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Occupancy detection systems for indoor environments: A survey of approaches and methods

Trivedi

Badarla

2019

Indoor and Built Environment

View full text Add to dashboard Cite

Utilization of smart services for indoor environments has gained extensive interest in the past decade due to the resulting increases in energy savings, user comfort and degree of automation. Occupancy detection is a critical element in automation systems due to its potential use in controlling electrical systems and devices such as lighting, air-conditioning and ventilation. It also has a high potential for improving the performance of demand-driven applications which require fine-grained occupancy information to optimize the trade-off between energy consumption and user comfort. Occupancy detection has been researched using different estimation methods and communication technologies. However, it remains challenging to procure sensory data and to model the occupancy information accurately due to the limitations of hardware deployment and underlying cost. This paper reviews existing occupancy methods and applications, along with their underlying issues. It provides a comparative analysis of the strategies from the perspectives of cost, intrusiveness and accuracy. Additionally, a new taxonomy which classifies the occupancy sensing techniques as being conventional or as alternate sensing has been proposed.

show abstract

Section: General Approaches For Occupancy Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Occupancy detection systems for indoor environments: A survey of approaches and methods

Trivedi

Badarla

2019

Indoor and Built Environment

View full text Add to dashboard Cite

show abstract

“…The potential of deep learning methods for energy consumption related OB modeling has already been researched by a number of studies [15], [34], [35], [36] [37], [38]. Coelho et al [34] designed a graphics processing unit (GPU)-based parallel strategy for timeseries learning of energy consumption.…”

Section: Deep Learning For Ob Modelingmentioning

confidence: 99%

Window opening model using deep learning methods

Markovic

Grintal

Wölki

et al. 2018

Building and Environment

View full text Add to dashboard Cite

Occupant behavior (OB) and in particular window openings need to be considered in building performance simulation (BPS), in order to realistically model the indoor climate and energy consumption for heating ventilation and air conditioning (HVAC). However, the proposed OB window opening models are often biased towards the over-represented class where windows remained closed. In addition, they require tuning for each occupant which can not be efficiently scaled to the increased number of occupants. This paper presents a window opening model for commercial buildings using deep learning methods. The model is trained using data from occupants from an office building in Germany.In total, the model is evaluated using almost 20 mio. data points from 3 independent buildings, located in Aachen, Frankfurt and Philadelphia. Eventually, the results of 3100 core hours of model development are summarized, which makes this study the largest of its kind in window states modeling. Additionally, the practical potential of the proposed model was tested by incorporating it in the Modelica-based thermal building simulation. The resulting evaluation accuracy and F1 scores on the office buildings ranged between 86-89 % and 0.53-0.65 respectively. The performance dropped around 15 % points in case of sparse input data, while the F1 score remained high.

show abstract

“…Monitored noise levels have also been used as an indication of occupied periods and used to train ANN models [35]. Other work in this field has used inter-related variables such as internal and external temperatures, HVAC demand and lighting consumption as source training data for ANN models [36][37][38].…”

Section: Collection Of Occupancy Schedule Datamentioning

confidence: 99%