sensors-logo

Journal Browser

Journal Browser

Sensing in Smart Buildings

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: closed (30 September 2023) | Viewed by 5888

Special Issue Editors


E-Mail Website
Guest Editor
School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Singapore
Interests: sensors; sensor networks; sensor fusion; signal processing; nonlinear dynamics and complexity; decentralized optimization; machine learning; smart buildings; energy efficiency

E-Mail Website
Guest Editor
Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis Way, Singapore 138632, Singapore
Interests: data analytics; deep learning; domain adaptation; self-supervised learning and related applications
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100811, China
Interests: localization and control for connected vehicles; SLAM; localization for unmanned systems; information fusion for smart city

Special Issue Information

Dear Colleagues,

In the modern era, people spend some 90% of their time inside buildings for living, working, shopping, recreation, etc. To provide thermal comfort and good indoor environment quality (IEQ), modern buildings account for about 40% of total energy consumption. To ensure the efficient use of energy in the building sectors for sustainable development, there has been a lot of R&D on developing smart buildings. A smart building consists of the physical building, its environment, information systems, and occupants. The intelligence of a building is based on its ability to know its operating status, environment, and occupants through intelligent sensing and information processing systems so that it can provide the essential intelligence, safety, good air quality, thermal comfort, and efficient energy consumption required of the modern building.

This Special Issue of Sensors, entitled Sensing in Smart Buildings, will focus on intelligent sensing and information processing techniques for smart buildings. There are a large number of challenges associated with intelligent sensing and information processing, including cost, energy efficiency, integration, low-impact spaces, easy setup, and user-friendliness. The intelligent system is the main reason why it is called a ‘smart’ building, be it a ‘smart home’, a ‘smart office’, a ‘smart mall’, or a ‘smart service’. These smart systems usually include a heating, ventilation, and air-conditioning (HVAC) system, a lighting system, a smart grid, an indoor robotic system, etc., and their associated sensors. Since occupants are important service objects, the occupant information, including the number of occupants, locations, and activities, is another critical factor for sensing in smart buildings.

Intelligent sensing and information processing capabilities of a ‘smart’ building will determine its abilities to sense and monitor the interacting environment so as to provide optimal and efficient services to its users. The sensing building environment includes observations of building indoor/outdoor temperature, humidity, radiant temperature, air velocity, pollution density, occupants and their localization, localization of pollution sources, localization of wall cracks and abnormalities, impacts on the health and wellness of occupants, etc. The environment sensing of a smart building presents a number of academic and practical challenges, which include (but are not limited to) the following issues:

  • Sensor selection and placement: A smart building requires a large amount of various types of sensors. To guarantee good sensing of the building, there will be redundant sensors. How to select the right sensors and find suitable locations to place them to guarantee sensing quality and reduce the amount of sensors is a big challenge in this area.
  • Occupancy estimation: The number of indoor occupants will impact the services required of the building and its intelligent systems. How to achieve a good estimation of the number of indoor occupants in a low-cost, nonintrusive way is a hot research area.
  • Localization: Accurate positioning of indoor pollution sources, occupants, and indoor robotics are important factors in providing building safety and comfort, as well as services. How to localize them in a low-cost and user-friendly manner is quite challenging and has attracted increasing attention in recent years.
  • Human activity estimation: The activity information can be used for intelligent control, as different activities may have different thermal preferences. Many sensors can be used for activity recognition. The biggest problems are how to select the best sensing techniques and how to design activity estimation approaches.
  • Thermal comfort sensing: Human thermal comfort plays a critical role in determining the productivities of indoor occupants and in the control of HVACs. It is related to both the environmental condition and the individual features, and it is still a big challenge to estimate each individual’s (localised) thermal comfort level and the mean thermal comfort in a user-friendly way.
  • Environment sensing: Indoor temperature, humidity, air velocity, and many other environmental factors are inhomogeneous and are all involved in air quality monitoring. How to estimate the full information of the indoor environment from sparse sensors is not just an academic but a useful practical issue.
  • Impact on health and wellbeing: As people are living, working and spending their leisure time indoors, the building’s impacts on the physical and mental wellbeing of occupants is of great concern. How to implement intelligent sensing to aid/complement optimal building design and to monitor wellness of occupants will be highly valued in our modern society.
  • Multi-agent sensing: A room or an indoor robot will have a group of sensors. A smart building includes many rooms and robots, which constitute a multi-agent system. How to apply the multi-agent systems for better sensing is an interesting problem worth pursuing.
  • Fault diagnosis: Fault detection and diagnosis is of great importance for the reliability of systems in smart buildings. As the systems in smart buildings are quite complex, it is challenging to design diagnosis systems that are both accurate and robust.  

Prof. Dr. Yeng Chai Soh
Dr. Zhenghua Chen
Dr. Chaoyang Jiang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • sensor selection and placement
  • occupancy estimation
  • localization
  • human activity estimation
  • thermal comfort sensing
  • environment sensing
  • impact on health and wellbeing
  • multi-agent sensing
  • fault diagnosis

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

16 pages, 2301 KiB  
Article
Improving the Efficiency of Fan Coil Units in Hotel Buildings through Deep-Learning-Based Fault Detection
by Iva Matetić, Ivan Štajduhar, Igor Wolf and Sandi Ljubic
Sensors 2023, 23(15), 6717; https://0-doi-org.brum.beds.ac.uk/10.3390/s23156717 - 27 Jul 2023
Cited by 5 | Viewed by 1110
Abstract
Optimizing the performance of heating, ventilation, and air-conditioning (HVAC) systems is critical in today’s energy-conscious world. Fan coil units (FCUs) play a critical role in providing comfort in various environments as an important component of HVAC systems. However, FCUs often experience failures that [...] Read more.
Optimizing the performance of heating, ventilation, and air-conditioning (HVAC) systems is critical in today’s energy-conscious world. Fan coil units (FCUs) play a critical role in providing comfort in various environments as an important component of HVAC systems. However, FCUs often experience failures that affect their efficiency and increase their energy consumption. In this context, deep learning (DL)-based fault detection offers a promising solution. By detecting faults early and preventing system failures, the efficiency of FCUs can be improved. This paper explores DL models as fault detectors for FCUs to enable smarter and more energy-efficient hotel buildings. We tested three contemporary DL modeling approaches: convolutional neural network (CNN), long short-term memory network (LSTM), and a combination of CNN and gated recurrent unit (GRU). The random forest model (RF) was additionally developed as a baseline benchmark. The fault detectors were tested on a real-world dataset obtained from the sensory measurement system installed in a hotel and additionally supplemented with simulated data via a physical model developed in TRNSYS. Three representative FCU faults, namely, a stuck valve, a reduction in airflow, and an FCU outage, were simulated with a much larger dataset than is typically utilized in similar studies. The results showed that the hybrid model, integrating CNN and GRU, performed best for all three observed faults. DL-based fault detectors outperformed the baseline RF model, confirming these solutions as viable components for energy-efficient hotels. Full article
(This article belongs to the Special Issue Sensing in Smart Buildings)
Show Figures

Figure 1

17 pages, 2849 KiB  
Article
A Fault Tolerant Surveillance System for Fire Detection and Prevention Using LoRaWAN in Smart Buildings
by Abdullah Safi, Zulfiqar Ahmad, Ali Imran Jehangiri, Rohaya Latip, Sardar Khaliq uz Zaman, Muhammad Amir Khan and Rania M. Ghoniem
Sensors 2022, 22(21), 8411; https://0-doi-org.brum.beds.ac.uk/10.3390/s22218411 - 01 Nov 2022
Cited by 17 | Viewed by 3912
Abstract
In recent years, fire detection technologies have helped safeguard lives and property from hazards. Early fire warning methods, such as smoke or gas sensors, are ineffectual. Many fires have caused deaths and property damage. IoT is a fast-growing technology. It contains equipment, buildings, [...] Read more.
In recent years, fire detection technologies have helped safeguard lives and property from hazards. Early fire warning methods, such as smoke or gas sensors, are ineffectual. Many fires have caused deaths and property damage. IoT is a fast-growing technology. It contains equipment, buildings, electrical systems, vehicles, and everyday things with computing and sensing capabilities. These objects can be managed and monitored remotely as they are connected to the Internet. In the Internet of Things concept, low-power devices like sensors and controllers are linked together using the concept of Low Power Wide Area Network (LPWAN). Long Range Wide Area Network (LoRaWAN) is an LPWAN product used on the Internet of Things (IoT). It is well suited for networks of things connected to the Internet, where terminals send a minute amount of sensor data over large distances, providing the end terminals with battery lifetimes of years. In this article, we design and implement a LoRaWAN-based system for smart building fire detection and prevention, not reliant upon Wireless Fidelity (Wi-Fi) connection. A LoRa node with a combination of sensors can detect smoke, gas, Liquefied Petroleum Gas (LPG), propane, methane, hydrogen, alcohol, temperature, and humidity. We developed the system in a real-world environment utilizing Wi-Fi Lora 32 boards. The performance is evaluated considering the response time and overall network delay. The tests are carried out in different lengths (0–600 m) and heights above the ground (0–2 m) in an open environment and indoor (1st Floor–3rd floor) environment. We observed that the proposed system outperformed in sensing and data transfer from sensing nodes to the controller boards. Full article
(This article belongs to the Special Issue Sensing in Smart Buildings)
Show Figures

Figure 1

Back to TopTop