BLEMAT: Data Analytics and Machine Learning for Smart Building Occupancy Detection and Prediction

Saša Pešić, Milenko Tošić, Ognjen Iković, Miloš Radovanović, Mirjana Ivanović, Dragan Bošković

Research output: Contribution to journalArticle

Abstract

Running costs of buildings represent a significant outlay for all businesses, thus finding a way to run facilities as efficiently as possible is vital. IoT-enabled Building Management Systems provide means for process and resource usage automation leading to overall efficiency improvements. Inferring spatial and temporal occupancy in all its forms (binary, numerical or continuous) is one of the key contextual inputs required for smart building management systems. In this work, we showcase design, implementation and experimental validation of a smart building occupancy detection and forecasting solution. The presented solution comprises three main building blocks: (1) A fog computing indoor positioning system (BLEMAT-Bluetooth Low Energy Microlocation Asset Tracking) which, combined with wireless access network monitoring processes, produces indoor location information in a semi-unsupervised manner; (2) Data analysis and pattern searching pipelines responsible for fusing data coming from different smart building and networking systems and deriving information on temporal and spatial occupancy patterns; (3) Long short-term memory (LSTM) neural networks trained to predict occupancy patterns in different areas of a smart building. Data analysis and neural network training are conducted on real-world smart building dataset which authors provide in public online repository. Experimental validation confirms that the proposed solution can provide actionable occupancy detection and prediction information, required by smart building management systems.

Original languageEnglish (US)
Article number1960005
JournalInternational Journal on Artificial Intelligence Tools
Volume28
Issue number6
DOIs
StatePublished - Sep 1 2019
Externally publishedYes

Fingerprint

Intelligent buildings
Learning systems
Neural networks
Process monitoring
Bluetooth
Fog
Automation
Pipelines
Costs
Industry

Keywords

  • Bluetooth indoor positioning
  • LSTM neural networks
  • occupancy data analytics
  • occupancy prediction

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

BLEMAT : Data Analytics and Machine Learning for Smart Building Occupancy Detection and Prediction. / Pešić, Saša; Tošić, Milenko; Iković, Ognjen; Radovanović, Miloš; Ivanović, Mirjana; Bošković, Dragan.

In: International Journal on Artificial Intelligence Tools, Vol. 28, No. 6, 1960005, 01.09.2019.

Research output: Contribution to journalArticle

Pešić, Saša ; Tošić, Milenko ; Iković, Ognjen ; Radovanović, Miloš ; Ivanović, Mirjana ; Bošković, Dragan. / BLEMAT : Data Analytics and Machine Learning for Smart Building Occupancy Detection and Prediction. In: International Journal on Artificial Intelligence Tools. 2019 ; Vol. 28, No. 6.
@article{d14d6264efab414c8d477c6ac073331d,
title = "BLEMAT: Data Analytics and Machine Learning for Smart Building Occupancy Detection and Prediction",
abstract = "Running costs of buildings represent a significant outlay for all businesses, thus finding a way to run facilities as efficiently as possible is vital. IoT-enabled Building Management Systems provide means for process and resource usage automation leading to overall efficiency improvements. Inferring spatial and temporal occupancy in all its forms (binary, numerical or continuous) is one of the key contextual inputs required for smart building management systems. In this work, we showcase design, implementation and experimental validation of a smart building occupancy detection and forecasting solution. The presented solution comprises three main building blocks: (1) A fog computing indoor positioning system (BLEMAT-Bluetooth Low Energy Microlocation Asset Tracking) which, combined with wireless access network monitoring processes, produces indoor location information in a semi-unsupervised manner; (2) Data analysis and pattern searching pipelines responsible for fusing data coming from different smart building and networking systems and deriving information on temporal and spatial occupancy patterns; (3) Long short-term memory (LSTM) neural networks trained to predict occupancy patterns in different areas of a smart building. Data analysis and neural network training are conducted on real-world smart building dataset which authors provide in public online repository. Experimental validation confirms that the proposed solution can provide actionable occupancy detection and prediction information, required by smart building management systems.",
keywords = "Bluetooth indoor positioning, LSTM neural networks, occupancy data analytics, occupancy prediction",
author = "Saša Pešić and Milenko Tošić and Ognjen Iković and Miloš Radovanović and Mirjana Ivanović and Dragan Bošković",
year = "2019",
month = "9",
day = "1",
doi = "10.1142/S0218213019600054",
language = "English (US)",
volume = "28",
journal = "International Journal on Artificial Intelligence Tools",
issn = "0218-2130",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "6",

}

TY - JOUR

T1 - BLEMAT

T2 - Data Analytics and Machine Learning for Smart Building Occupancy Detection and Prediction

AU - Pešić, Saša

AU - Tošić, Milenko

AU - Iković, Ognjen

AU - Radovanović, Miloš

AU - Ivanović, Mirjana

AU - Bošković, Dragan

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Running costs of buildings represent a significant outlay for all businesses, thus finding a way to run facilities as efficiently as possible is vital. IoT-enabled Building Management Systems provide means for process and resource usage automation leading to overall efficiency improvements. Inferring spatial and temporal occupancy in all its forms (binary, numerical or continuous) is one of the key contextual inputs required for smart building management systems. In this work, we showcase design, implementation and experimental validation of a smart building occupancy detection and forecasting solution. The presented solution comprises three main building blocks: (1) A fog computing indoor positioning system (BLEMAT-Bluetooth Low Energy Microlocation Asset Tracking) which, combined with wireless access network monitoring processes, produces indoor location information in a semi-unsupervised manner; (2) Data analysis and pattern searching pipelines responsible for fusing data coming from different smart building and networking systems and deriving information on temporal and spatial occupancy patterns; (3) Long short-term memory (LSTM) neural networks trained to predict occupancy patterns in different areas of a smart building. Data analysis and neural network training are conducted on real-world smart building dataset which authors provide in public online repository. Experimental validation confirms that the proposed solution can provide actionable occupancy detection and prediction information, required by smart building management systems.

AB - Running costs of buildings represent a significant outlay for all businesses, thus finding a way to run facilities as efficiently as possible is vital. IoT-enabled Building Management Systems provide means for process and resource usage automation leading to overall efficiency improvements. Inferring spatial and temporal occupancy in all its forms (binary, numerical or continuous) is one of the key contextual inputs required for smart building management systems. In this work, we showcase design, implementation and experimental validation of a smart building occupancy detection and forecasting solution. The presented solution comprises three main building blocks: (1) A fog computing indoor positioning system (BLEMAT-Bluetooth Low Energy Microlocation Asset Tracking) which, combined with wireless access network monitoring processes, produces indoor location information in a semi-unsupervised manner; (2) Data analysis and pattern searching pipelines responsible for fusing data coming from different smart building and networking systems and deriving information on temporal and spatial occupancy patterns; (3) Long short-term memory (LSTM) neural networks trained to predict occupancy patterns in different areas of a smart building. Data analysis and neural network training are conducted on real-world smart building dataset which authors provide in public online repository. Experimental validation confirms that the proposed solution can provide actionable occupancy detection and prediction information, required by smart building management systems.

KW - Bluetooth indoor positioning

KW - LSTM neural networks

KW - occupancy data analytics

KW - occupancy prediction

UR - http://www.scopus.com/inward/record.url?scp=85072973448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072973448&partnerID=8YFLogxK

U2 - 10.1142/S0218213019600054

DO - 10.1142/S0218213019600054

M3 - Article

AN - SCOPUS:85072973448

VL - 28

JO - International Journal on Artificial Intelligence Tools

JF - International Journal on Artificial Intelligence Tools

SN - 0218-2130

IS - 6

M1 - 1960005

ER -