Real-time room occupancy estimation with Bayesian machine learning using a single PIR sensor and microcontroller

Abstract

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 highperformance 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.

Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab

“…However, the switching AR model can be seen as an extension of the infinite HMM. Therefore, in order to perform real-time inference of the model on smartphone or wearable devices, we can use the computational optimisation proposed in Raykov et al [ 48 ] and Leech et al [ 64 ], which enables the inference of an infinite HMM on a highly resource-constrained microcontroller.…”

Literature Review for Sensor Impact Evaluation and Verification Use Cases - Building Controls and Fault Detection and Diagnosis (FDD)

“…The occupancy sensing and estimation methods can also be categorized with sensors or measures used. Motion sensors-such as passive infrared (PIR), ultrasonic, and microwave sensors-have been widely employed because of their low cost and power consumption, small form factor, and the fact that they are nonintrusive and privacy-preserving [26,36,[47][48][49][50][51][52][53]. Especially, PIR sensors are popular for real applications as they are robust to interference caused by environmental variances [54].…”

Otomasi sistem kelistrikan menggunakan algoritma a-star berbasis internet of things

“…Wibisono dan Bayhaki [1] membahas pendekatan otomasi lampu jalan menggunakan adhoc network berbasis wireless connectivity; Leech et al [2] menekankan pendekatan optimisasi memory sistem pemantauan kondisi ruangan yang bekerja menggunakan algoritma Bayesian; Cynthia et al [3] membahas sistem otomasi perangkat listrik kelas menggunakan mikrokontroler Arduino tanpa adanya algoritma tertentu, menekankan pada ketiadaan aktivitas selama 10 menit didalam kelas sebagai sebagai penentu keputusan; dan Lee et al [4] membahas sistem tracking kendaraan berbasis mikrokontroler yang dipasang pada mesin kendaraan dengan mengirimkan data posisi perangkat GPS/GSM/GPRS yang terhubung dengan mikrokontroler ke database sistem monitoring.…”