Real-time room occupancy estimation with Bayesian machine learning using a single PIR sensor and microcontroller. Leech, C., Raykov, Y. P., Ozer, E., & Merrett, G. V. In 2017 IEEE Sensors Applications Symposium (SAS), pages 1–6, March, 2017. ![Real-time room occupancy estimation with Bayesian machine learning using a single PIR sensor and microcontroller [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex This paper presents the implementation and deployment of a compute/memory intensive non-parametric Bayesian machine learning algorithm on a microcontroller unit (MCU) to estimate room occupancy in a Smart Room using a single analogue PIR sensor. We envisage an IoT device consisting of a resource-constrained MCU, PIR sensor and a battery running the occupancy estimation algorithm and operating over days or months without recharging or replacing the battery. Both hardware-independent and hardware-dependent optimizations are performed to reduce memory footprint and yet provide acceptable real-time performance while consuming less energy. We show a significant reduction in the on-chip memory usage in the MCUs by the algorithm through optimisation of the machine learning models and of the static memory footprint and dynamic memory usage. We also show that a low-end MCU does not meet the real-time requirements of the application without causing high average power consumption. However, a moderately high-performance MCU with a higher clock frequency and hardware floating-point unit provides 19x improvement in the execution time of the algorithm, better meeting the real-time specification of the application and reducing power consumption. Further, we estimate the battery lifetime of the IoT device if it operates continuously in a Smart Room. With a typical size battery, an IoT device consisting of a Cortex-M4F MCU and PIR sensor can operate for more than a month without replacement or recharging of the battery while running the compute-intensive Bayesian machine learning algorithm.
@inproceedings{leech_real-time_2017,
title = {Real-time room occupancy estimation with {Bayesian} machine learning using a single {PIR} sensor and microcontroller},
url = {https://ieeexplore.ieee.org/document/7894091},
doi = {10.1109/SAS.2017.7894091},
abstract = {This paper presents the implementation and deployment of a compute/memory intensive non-parametric Bayesian machine learning algorithm on a microcontroller unit (MCU) to estimate room occupancy in a Smart Room using a single analogue PIR sensor. We envisage an IoT device consisting of a resource-constrained MCU, PIR sensor and a battery running the occupancy estimation algorithm and operating over days or months without recharging or replacing the battery. Both hardware-independent and hardware-dependent optimizations are performed to reduce memory footprint and yet provide acceptable real-time performance while consuming less energy. We show a significant reduction in the on-chip memory usage in the MCUs by the algorithm through optimisation of the machine learning models and of the static memory footprint and dynamic memory usage. We also show that a low-end MCU does not meet the real-time requirements of the application without causing high average power consumption. However, a moderately high-performance MCU with a higher clock frequency and hardware floating-point unit provides 19x improvement in the execution time of the algorithm, better meeting the real-time specification of the application and reducing power consumption. Further, we estimate the battery lifetime of the IoT device if it operates continuously in a Smart Room. With a typical size battery, an IoT device consisting of a Cortex-M4F MCU and PIR sensor can operate for more than a month without replacement or recharging of the battery while running the compute-intensive Bayesian machine learning algorithm.},
urldate = {2024-05-06},
booktitle = {2017 {IEEE} {Sensors} {Applications} {Symposium} ({SAS})},
author = {Leech, Charles and Raykov, Yordan P. and Ozer, Emre and Merrett, Geoff V.},
month = mar,
year = {2017},
keywords = {Batteries, Bayes methods, Estimation, Hidden Markov models, MATLAB, Optimization, Standards},
pages = {1--6},
}
Downloads: 0
{"_id":"o2QCEAwMCbdZwyTQ9","bibbaseid":"leech-raykov-ozer-merrett-realtimeroomoccupancyestimationwithbayesianmachinelearningusingasinglepirsensorandmicrocontroller-2017","author_short":["Leech, C.","Raykov, Y. P.","Ozer, E.","Merrett, G. V."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Real-time room occupancy estimation with Bayesian machine learning using a single PIR sensor and microcontroller","url":"https://ieeexplore.ieee.org/document/7894091","doi":"10.1109/SAS.2017.7894091","abstract":"This paper presents the implementation and deployment of a compute/memory intensive non-parametric Bayesian machine learning algorithm on a microcontroller unit (MCU) to estimate room occupancy in a Smart Room using a single analogue PIR sensor. We envisage an IoT device consisting of a resource-constrained MCU, PIR sensor and a battery running the occupancy estimation algorithm and operating over days or months without recharging or replacing the battery. Both hardware-independent and hardware-dependent optimizations are performed to reduce memory footprint and yet provide acceptable real-time performance while consuming less energy. We show a significant reduction in the on-chip memory usage in the MCUs by the algorithm through optimisation of the machine learning models and of the static memory footprint and dynamic memory usage. We also show that a low-end MCU does not meet the real-time requirements of the application without causing high average power consumption. However, a moderately high-performance MCU with a higher clock frequency and hardware floating-point unit provides 19x improvement in the execution time of the algorithm, better meeting the real-time specification of the application and reducing power consumption. Further, we estimate the battery lifetime of the IoT device if it operates continuously in a Smart Room. With a typical size battery, an IoT device consisting of a Cortex-M4F MCU and PIR sensor can operate for more than a month without replacement or recharging of the battery while running the compute-intensive Bayesian machine learning algorithm.","urldate":"2024-05-06","booktitle":"2017 IEEE Sensors Applications Symposium (SAS)","author":[{"propositions":[],"lastnames":["Leech"],"firstnames":["Charles"],"suffixes":[]},{"propositions":[],"lastnames":["Raykov"],"firstnames":["Yordan","P."],"suffixes":[]},{"propositions":[],"lastnames":["Ozer"],"firstnames":["Emre"],"suffixes":[]},{"propositions":[],"lastnames":["Merrett"],"firstnames":["Geoff","V."],"suffixes":[]}],"month":"March","year":"2017","keywords":"Batteries, Bayes methods, Estimation, Hidden Markov models, MATLAB, Optimization, Standards","pages":"1–6","bibtex":"@inproceedings{leech_real-time_2017,\n\ttitle = {Real-time room occupancy estimation with {Bayesian} machine learning using a single {PIR} sensor and microcontroller},\n\turl = {https://ieeexplore.ieee.org/document/7894091},\n\tdoi = {10.1109/SAS.2017.7894091},\n\tabstract = {This paper presents the implementation and deployment of a compute/memory intensive non-parametric Bayesian machine learning algorithm on a microcontroller unit (MCU) to estimate room occupancy in a Smart Room using a single analogue PIR sensor. We envisage an IoT device consisting of a resource-constrained MCU, PIR sensor and a battery running the occupancy estimation algorithm and operating over days or months without recharging or replacing the battery. Both hardware-independent and hardware-dependent optimizations are performed to reduce memory footprint and yet provide acceptable real-time performance while consuming less energy. We show a significant reduction in the on-chip memory usage in the MCUs by the algorithm through optimisation of the machine learning models and of the static memory footprint and dynamic memory usage. We also show that a low-end MCU does not meet the real-time requirements of the application without causing high average power consumption. However, a moderately high-performance MCU with a higher clock frequency and hardware floating-point unit provides 19x improvement in the execution time of the algorithm, better meeting the real-time specification of the application and reducing power consumption. Further, we estimate the battery lifetime of the IoT device if it operates continuously in a Smart Room. With a typical size battery, an IoT device consisting of a Cortex-M4F MCU and PIR sensor can operate for more than a month without replacement or recharging of the battery while running the compute-intensive Bayesian machine learning algorithm.},\n\turldate = {2024-05-06},\n\tbooktitle = {2017 {IEEE} {Sensors} {Applications} {Symposium} ({SAS})},\n\tauthor = {Leech, Charles and Raykov, Yordan P. and Ozer, Emre and Merrett, Geoff V.},\n\tmonth = mar,\n\tyear = {2017},\n\tkeywords = {Batteries, Bayes methods, Estimation, Hidden Markov models, MATLAB, Optimization, Standards},\n\tpages = {1--6},\n}\n\n\n\n\n\n\n\n","author_short":["Leech, C.","Raykov, Y. P.","Ozer, E.","Merrett, G. V."],"key":"leech_real-time_2017","id":"leech_real-time_2017","bibbaseid":"leech-raykov-ozer-merrett-realtimeroomoccupancyestimationwithbayesianmachinelearningusingasinglepirsensorandmicrocontroller-2017","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/7894091"},"keyword":["Batteries","Bayes methods","Estimation","Hidden Markov models","MATLAB","Optimization","Standards"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/qiuyuanwang","dataSources":["wWPhSRj9hrZuqsm9D"],"keywords":["batteries","bayes methods","estimation","hidden markov models","matlab","optimization","standards"],"search_terms":["real","time","room","occupancy","estimation","bayesian","machine","learning","using","single","pir","sensor","microcontroller","leech","raykov","ozer","merrett"],"title":"Real-time room occupancy estimation with Bayesian machine learning using a single PIR sensor and microcontroller","year":2017}