Abstract
Given the importance of recognizing indoor occupant’s location and activity intensity to the control of intelligent homes, exploring approaches that can detect occupants’ location and activity types while protecting occupants’ privacy is helpful. In this study, occupants’ zonal location and activity intensity recognition models were developed using passive infrared (PIR) sensors and machine learning algorithms. A PIR sensor array with 15 nodes was employed to monitor indoor occupant’s and cat’s behavior in a case residential building for 71 days. The output signals of PIR sensors varied with different locations and activity intensities. By analyzing the PIR data feature, models were established using six machine learning algorithms and two sets of data. After comparing model performance, the support vector machine (SVM) algorithm was selected to establish the final models. The model input was optimized by accumulating the PIR data. Taking PIR original counting values in 1-minute and 30-minute accumulated data as input features, the optimized SVM model can achieve 99.7% accuracy under the 10-fold cross-validation for the training data set, and 90.9% accuracy for the test data set. The cat’s activity intensity is much weaker than that of occupant, yielding much smaller PIR output, which helped the SVM model to distinguish cat’s activity from occupant’s with >90% accuracy. The model’s recognition accuracy decreases with the decrease of sensor numbers and nine sensors were necessary. The findings obtained in this study support the promising future of applying PIR sensors in smart homes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Al-jabery KK, Obafemi-Ajayi T, Olbricht GR, et al. (2020). Data analysis and machine learning tools in MATLAB and Python. In: Al-jabery KK, Obafemi-Ajayi T, Olbricht GR, et al. (Eds.), Computational Learning Approaches to Data Analytics in Biomedical Applications. Cambridge, MA, USA: Academic Press.
Al-Naimi I, Wong CB, Moore P, et al. (2014). Advanced approach for indoor identification and tracking using smart floor and pyroelectric infrared sensors. In: Proceedings of the 5th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan.
ASHRAE (2017). ASHRAE Handbook: Fundamentals. Atlanta, Ga, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers
Bahadori S, Cesta A, Iocchi L, et al. (2005). Towards ambient intelligence for the domestic care of the elderly. In: Remagnino P, Foresti GL, Ellis T (Eds.), Ambient Intelligence. New York: Springer.
Belafi Z, Hong T, Reith A (2017). Smart building management vs. intuitive human control—Lessons learnt from an office building in Hungary. Building Simulation, 10: 811–828.
Belmonte-Fernández Ó, Puertas-Cabedo A, Torres-Sospedra J, et al. (2017). An indoor positioning system based on wearables for ambient-assisted living. Sensors, 17: 36.
Benya J (2001). Advanced Lighting Guidelines. White Salmon, WA, USA: New Buildings Institute.
Carlucci S, de Simone M, Firth SK, et al. (2020). Modeling occupant behavior in buildings. Building and Environment, 174: 106768.
Chen Y, Liang X, Hong T, et al. (2017). Simulation and visualization of energy-related occupant behavior in office buildings. Building Simulation, 10: 785–798.
Chen Z, Jiang C, Xie L (2018). Building occupancy estimation and detection: A review. Energy and Buildings, 169: 260–270.
Chen S, Zhang H, Guan J, et al. (2020). Agent-based modeling and simulation of stochastic heat pump usage behavior in residential communities. Building Simulation, 13: 803–821.
Dai X, Liu J, Zhang X (2020). A review of studies applying machine learning models to predict occupancy and window-opening behaviours in smart buildings. Energy and Buildings, 223: 110159.
Dong B, Yan D, Li Z, et al. (2018). Modeling occupancy and behavior for better building design and operation—A critical review. Building Simulation, 11: 899–921.
Dua N, Singh SN, Semwal VB (2021). Multi-input CNN-GRU based human activity recognition using wearable sensors. Computing, 103: 1461–1478
Fan C, Yan D, Xiao F, et al. (2021). Advanced data analytics for enhancing building performances: From data-driven to big data-driven approaches. Building Simulation, 14: 3–24.
Hao Q, Brady DJ, Guenther BD, et al. (2006). Human tracking with wireless distributed pyroelectric sensors. IEEE Sensors Journal, 6: 1683–1696.
Hao Q, Hu F, Xiao Y (2009). Multiple human tracking and identification with wireless distributed pyroelectric sensor systems. IEEE Systems Journal, 3: 428–439.
Hu S, Yan D, Azar E, et al. (2020). A systematic review of occupant behavior in building energy policy. Building and Environment, 175: 106807.
Jin W, Ma J, Bi C, et al. (2020). Dynamic variation in dew-point temperature of attached air layer of radiant ceiling cooling panels. Building Simulation, 13: 1281–1290.
Jin Y, Yan D, Chong A, et al. (2021a). Building occupancy forecasting: A systematical and critical review. Energy and Buildings, 251: 111345.
Jin Y, Yan D, Zhang X, et al. (2021b). A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development. Building Simulation, 14: 219–235.
Kang X, Yan D, An J, et al. (2021). Typical weekly occupancy profiles in non-residential buildings based on mobile positioning data. Energy and Buildings, 250: 111264.
Kim HH, Ha KN, Lee S, et al. (2009). Resident location-recognition algorithm using a Bayesian classifier in the PIR sensor-based indoor location-aware system. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 39: 240–245.
Lai KC, Ku B, Wen CY (2018). Using cooperative PIR sensing for human indoor localization. In: Proceedings of 27th Wireless and Optical Communication Conference (WOCC).
Li H, Hong T, Sofos M (2019). An inverse approach to solving zone air infiltration rate and people count using indoor environmental sensor data. Energy and Buildings, 198: 228–242.
Li A, Xiao F, Fan C, Hu M (2021). Development of an ANN-based building energy model for information-poor buildings using transfer learning. Building Simulation, 14: 89–101.
Lin Y, Yang L, Luo M (2021). Physiological and subjective thermal responses to heat exposure in northern and southern Chinese people. Building Simulation, 14: 1619–1631.
Lu X, Feng F, Pang Z, et al. (2021). Extracting typical occupancy schedules from social media (TOSSM) and its integration with building energy modeling. Building Simulation, 14: 25–41.
Luo M, Zhou X, Zhu Y, et al. (2016a). Revisiting an overlooked parameter in thermal comfort studies, the metabolic rate. Energy and Buildings, 118: 152–159.
Luo X, Liu T, Shen B, et al. (2016b). Human indoor localization based on ceiling mounted PIR sensor nodes. In: Proceedings of the 13th IEEE Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA.
Ma R, Hu F, Hao Q (2017). Active compressive sensing via pyroelectric infrared sensor for human situation recognition. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47: 3340–3350.
Muroni A, Gaetani I, Hoes P-J, et al. (2019). Occupant behavior in identical residential buildings: A case study for occupancy profiles extraction and application to building performance simulation. Building Simulation, 12: 1047–1061.
Ouf MM, Park JY, Gunay HB (2021). A simulation-based method to investigate occupant-centric controls. Building Simulation, 14: 1017–1030.
Peng Y, Rysanek A, Nagy Z, et al. (2018). Using machine learning techniques for occupancy-prediction-based cooling control in office buildings. Applied Energy, 211: 1343–1358.
Ruano A, Hernandez A, Ureña J, et al. (2019). NILM techniques for intelligent home energy management and ambient assisted living: A review. Energies, 12: 2203.
Tang R, Wang S, Sun S (2021). Impacts of technology-guided occupant behavior on air-conditioning system control and building energy use. Building Simulation, 14: 209–217.
Wang C, Yan D, Jiang Y (2011). A novel approach for building occupancy simulation. Building Simulation, 4: 149–167.
Wang W, Hong T, Li N, et al. (2019). Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification. Applied Energy, 236: 55–69.
Xiong J, Li F, Liu J (2016). Fusion of different height pyroelectric infrared sensors for person identification. IEEE Sensors Journal, 16: 436–446.
Yang B, Li X, Luo J (2015). A novel multi-human location method for distributed binary pyroelectric infrared sensor tracking system: Region partition using PNN and bearing-crossing location. Infrared Physics & Technology, 68: 35–43.
Yang D, Xu B, Rao K, et al. (2018). Passive infrared (PIR)-based indoor position tracking for smart homes using accessibility maps and A-star algorithm. Sensors, 18: 332.
Yang B, Li X, Hou Y, et al. (2020). Non-invasive (non-contact) measurements of human thermal physiology signals and thermal comfort/discomfort poses—A review. Energy and Buildings, 224: 110261.
Yeo C, Ahammad P, Ramchandran K, et al. (2008). High-speed action recognition and localization in compressed domain videos. IEEE Transactions on Circuits and Systems for Video Technology, 18: 1006–1015.
Zhang J, Zhou X, Lei S, et al. (2021a). Energy and comfort performance of occupant-centric air conditioning strategy in office buildings with personal comfort devices. Building Simulation, https://doi.org/10.1007/s12273-021-0852-1
Zhang Y, Hu S, Yan D, et al. (2021b). Exploring cooling pattern of low-income households in urban China based on a large-scale questionnaire survey: A case study in Beijing. Energy and Buildings, 236: 110783.
Zhou X, Liu T, Yan D, et al. (2021a). An action-based Markov chain modeling approach for predicting the window operating behavior in office spaces. Building Simulation, 14: 301–315.
Zhou X, Ren J, An J, et al. (2021b). Predicting open-plan office window operating behavior using the random forest algorithm. Journal of Building Engineering, 42: 102514.
Zhou X, Tian S, An J, et al. (2021c). Comparison of different machine learning algorithms for predicting air-conditioning operating behavior in open-plan offices. Energy and Buildings, 251: 111347.
Acknowledgements
This research has been supported by the National Natural Science Foundation of China (No. 51908414), and China National Key R&D Program during the 13th Five-year Plan Period (No. 2017YFC0702200). The authors would like to express appreciation to the little cat, Plan Zhang.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, J., Zhao, T., Zhou, X. et al. Room zonal location and activity intensity recognition model for residential occupant using passive-infrared sensors and machine learning. Build. Simul. 15, 1133–1144 (2022). https://doi.org/10.1007/s12273-021-0870-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12273-021-0870-z