Article
Computer Science, Artificial Intelligence
Will Serrano
Summary: This article introduces iBuilding, a concept of distributed artificial intelligence embedded into intelligent buildings for Industry 4.0 applications, enabling adaptation to external environment and different building users. Through neural networks and deep learning structure, it monitors and predicts building variables for energy efficiency and increased functionality.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Giuseppe Starace, Amber Tiwari, Gianpiero Colangelo, Alessandro Massaro
Summary: This work discusses the applications of the Internet of Things (IoT) in smart buildings, specifically focusing on energy consumption monitoring and forecasting systems, as well as indoor air quality (IAQ) control. The implementation involves low-cost hardware integrated with sensors and open source platforms for cloud data transmission, storage, and processing. Advanced data analytics techniques, such as SARIMA and LSTM, are used for accurate energy predictions. The results are developed within the framework of the D-SySCOM project, aiming to provide modular and cost-effective solutions for energy efficiency and wellness in public indoor environments.
Article
Computer Science, Theory & Methods
Kanika Saini, Sheetal Kalra, Sandeep K. Sood
Summary: In this study, an intelligent evacuation system is proposed that integrates IoT, fog layer, and cloud layer to efficiently and accurately guide evacuees to safer locations while significantly reducing direct fire exposure.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Information Systems
Liangtian Wan, Mingyue Zhang, Lu Sun, Xianpeng Wang
Summary: This article discusses the importance of vehicle localization in Intelligent Transportation Systems (ITS), as well as the proposed methods and technologies, including vehicle number estimation methods for non-circular signals and DOA estimation methods based on IoT. Through the application of machine learning techniques, the vehicle localization system demonstrates excellent performance and high estimation accuracy in smart cities.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Abdelfettah Maatoug, Ghalem Belalem, Said Mahmoudi
Summary: Nowadays, smart buildings utilize IoT technology from cloud and fog computing paradigms for coordination and collaboration between connected objects. Fog computing provides low latency, wider spread, and geographically distributed nodes to support mobility, real-time interaction, and location-based services. This study uses the DEVS formalism to accurately design and integrate sub-models of connected objects in a building, resulting in improved energy efficiency and reduced latency. The flexibility of DEVS allows for easy addition or removal of sub-models, enabling continuous design improvement.
FRONTIERS OF COMPUTER SCIENCE
(2023)
Article
Green & Sustainable Science & Technology
Enrique Cano-Sunen, Ignacio Martinez, Angel Fernandez, Belen Zalba, Roberto Casas
Summary: Advancements in smart ecosystems demonstrate IoT as a strategic approach to enhance energy efficiency, indoor air quality, and building knowledge. However, a significant number of buildings lack integrated HVAC systems and smart sensors. This study aims to bridge the gap between theoretical simulations and real measurements by using IoT ecosystems, and highlights the cost-effectiveness of IoT-based solutions for data acquisition and analysis. The paper outlines a three-level methodology for identifying buildings, monitoring behavior, and deploying wireless sensors, and provides insights on building complexity, energy consumption, and IAQ improvement. The study also proposes a proof of concept for predictive building performance using neural networks. Overall, IoT strategies offer a modular and interoperable approach to improve energy efficiency and environmental quality at low cost and quick implementation. Challenges remain for IoT growth and interconnection, particularly in the face of climate change and sustainability. Rating: 8/10.
Article
Computer Science, Information Systems
Tao Han, Khan Muhammad, Tanveer Hussain, Jaime Lloret, Sung Wook Baik
Summary: The article emphasizes on an intelligent energy management framework based on deep learning, focusing on efficient communication between edge devices and smart grids for short-term energy consumption prediction. By applying various data preprocessing techniques and decision-making algorithms, the mean-square error and root mean-square error of residential and commercial datasets were significantly reduced.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Chemistry, Analytical
Brena Santos, Andre Soares, Tuan-Anh Nguyen, Dug-Ki Min, Jae-Woo Lee, Francisco-Airton Silva
Summary: Smart buildings in big cities are now equipped with an IoT infrastructure to monitor different aspects of people's daily lives. This study proposes a queuing network based message exchange architecture to evaluate the performance of an intelligent building infrastructure, identifying bottlenecks through sensitivity analysis using the DoE method. The number of cores was found to have a greater impact on response time than the number of nodes.
Article
Computer Science, Artificial Intelligence
Ashutosh Bhoi, Rajendra Prasad Nayak, Sourav Kumar Bhoi, Srinivas Sethi, Sanjaya Kumar Panda, Kshira Sagar Sahoo, Anand Nayyar
Summary: This study proposes an IoT-enabled ML-trained recommendation system for efficient water usage with minimal farmer intervention. By deploying IoT devices in crop fields to collect data and analyzing it using ML approaches, the system shows promising results in improving water resource utilization.
PEERJ COMPUTER SCIENCE
(2021)
Review
Chemistry, Multidisciplinary
Syed Faisal Abbas Shah, Muhammad Iqbal, Zeeshan Aziz, Toqir A. Rana, Adnan Khalid, Yu-N Cheah, Muhammad Arif
Summary: This article focuses on the role of IoT devices in smart buildings, highlighting the IoT devices platform and its components. It also discusses security challenges related to IoT and smart buildings, as well as describing the main factors and different methods of using machine learning with IoT technologies to improve the efficiency of smart buildings.
APPLIED SCIENCES-BASEL
(2022)
Article
Construction & Building Technology
Haithem Chaouch, Celal Ceken, Seckin Ari
Summary: A new smart approach is presented in this study to reduce the energy consumption of an HVAC system while maintaining the thermal comfort of occupants by considering the heat loads of a building and implementing machine-to-machine communication. The proposed system has successfully reduced annual energy consumption by an average of 16%.
JOURNAL OF BUILDING ENGINEERING
(2021)
Review
Chemistry, Analytical
Muhammad Umair, Muhammad Aamir Cheema, Omer Cheema, Huan Li, Hua Lu
Summary: The COVID-19 pandemic has had a positive impact on the adoption of IoT in various industries, promoting the development of technology and innovation. Through research and expert interviews, the paper explores the influence of the pandemic on sectors such as healthcare, smart homes, and smart cities, and summarizes research directions and challenges that will accelerate IoT adoption.
Article
Engineering, Aerospace
Yong Sun, Wenan Tan, Li Huang, Na Xie, Ling Ruan, Li Da Xu
Summary: In this study, we propose an innovative integrated collaborative filtering framework that incorporates location-aware quality into a graph embedding model for reliable IoT service discovery. A privacy protection mechanism is also introduced to safeguard sensitive location information. Experimental results demonstrate the significant efficacy and reliability of our framework in large-scale IoT service discovery scenarios.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2022)
Article
Chemistry, Multidisciplinary
Chun-Te Lee, Liang-Bi Chen, Huan-Mei Chu, Che-Jen Hsieh, Wei-Chieh Liang
Summary: This article introduces an IoT-based master-slave intelligent LED light-controlling system that can be applied to various large-scale public areas to achieve energy savings. The system is easy to install, low-cost, and has several advantages, such as no need to replace the original lamp holder, no wiring required, and no need for server setup.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
Mohsen Khorasany, Ali Dorri, Reza Razzaghi, Raja Jurdak
Summary: P2P energy trading in smart grids presents challenges in decentralized management, market settlement, and grid constraints. This paper proposes a blockchain-enabled framework for energy trading among agents, considering reputation factors and electrical distance.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2021)
Article
Telecommunications
Weitao Wang, Yuebin Bai, Peng Feng, Jun Huang, Mo Sha, Jianpei Tantai
Summary: The paper presents a new DTN routing algorithm called DTN-Balance, which takes into account the forwarding capacity and queue of relay nodes for better load distribution in the network. By defining a message forwarding utility metric and incorporating small world theory, the algorithm significantly increases routing efficiency. Simulation results on real DTN traces show that the algorithm offers excellent forwarding efficiency despite a slight decrease in throughput.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Article
Construction & Building Technology
Mariam Elnour, Nader Meskin, Khaled Khan, Raj Jain
Summary: This paper presents an analysis of the security of the HVAC system using a TRNSYS model and a data-driven attack detection strategy. Three schemes were investigated, including PCA feature extraction and 1D CNN-based encoder for temporal feature extraction, showing promising capabilities in attack detection with high reliability and low computational cost compared to standard machine-learning approaches.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Computer Science, Information Systems
Zebo Yang, Ali Ghubaish, Devrim Unal, Raj Jain
Summary: This study explores the impact of real-world environments on wireless network performance, finding that factors related to path and weather have the greatest influence. A comprehensive checklist of these factors is provided, which is believed to be beneficial for both academics and industrial practitioners in the field of wireless IoT systems.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2021)
Review
Computer Science, Information Systems
Ali Ghubaish, Tara Salman, Maede Zolanvari, Devrim Unal, Abdulla Al-Ali, Raj Jain
Summary: The advancements in Internet of Things (IoT) technologies have transformed the healthcare industry through remote patient monitoring, enhancing patient care efficiency. Yet, the security of these systems remains a major challenge, requiring robust measures to safeguard data.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Multidisciplinary Sciences
Mariam Elnour, Nader Meskin, Khaled Khan, Raj Jain
Summary: This paper presents a dataset of a 12-zone HVAC system collected from a simulation model to support research in the cybersecurity of HVAC systems in smart buildings. It aims to facilitate the validation of attack detection and mitigation strategies, benchmark different data-driven algorithms, and study the impact of attacks on HVAC systems.
Article
Computer Science, Information Systems
Junyang Shi, Di Mu, Mo Sha
Summary: Low-power wireless mesh networks (LPWMNs) are widely used in wireless monitoring and control applications. Recent studies show that adding low-power wide-area network radios such as LoRa effectively overcomes the limitations of LPWMNs. However, users are reluctant to embrace this new communication approach due to the cost of hardware modification.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2022)
Article
Computer Science, Information Systems
Maede Zolanvari, Zebo Yang, Khaled Khan, Raj Jain, Nader Meskin
Summary: Despite the challenges in generating trust, explainable AI (XAI) has emerged to address the black box nature of artificial intelligence (AI). In this study, a universal XAI model called TRUST was proposed, which is model-agnostic, high performing, and suitable for numerical applications. The TRUST model utilizes statistical theory to model the AI's outputs and provides explanations by ranking influential variables and determining the likelihood of new samples belonging to each class using multimodal Gaussian distributions (MMG). Results from a case study on IIoT cybersecurity demonstrate TRUST's effectiveness with an average success rate of 98% and superiority over the popular XAI model LIME in terms of performance, speed, and explainability.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Junyang Shi, Xingjian Chen, Mo Sha
Summary: IEEE 802.15.4-based wireless sensor-actuator networks play a significant role in improving industrial efficiency, but managing large and complex networks is difficult. This article presents a solution for enabling cross-technology communication from LoRa to ZigBee, providing reliable communication with high throughput and low bit error rate.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2022)
Article
Computer Science, Artificial Intelligence
Lav Gupta, Tara Salman, Ali Ghubaish, Devrim Unal, Abdulla Khalid Al-Ali, Raj Jain
Summary: This paper presents MUSE, a system of deep hierarchical stacked neural networks for timely and accurate detection of malicious activity in healthcare networks. By merging and aggregating trained edge cloud models, a partly pre-trained core cloud model can be constructed, leading to faster training times and high accuracy in detecting attacks on dataflows.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Xia Cheng, Junyang Shi, Mo Sha, Linke Guo
Summary: This paper presents a new threat to WirelessHART networks, smart selective jamming attacks, which can greatly reduce network reliability without being easily detected.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Information Systems
Mariam Elnour, Mohammad Noorizadeh, Mohammad Shakerpour, Nader Meskin, Khaled Khan, Raj Jain
Summary: This work presents a distributed, machine learning based attack detection and mitigation framework for sensor false data injection cyber-physical attacks in industrial control systems. The framework is developed using the system's standard operational data and validated using a hybrid testbed of a reverse osmosis plant. The proposed solution can be adopted in the existing industrial control systems and demonstrated effective performance in real-time detection and mitigation of actual cyber-physical attacks.
Article
Computer Science, Information Systems
Zebo Yang, Maede Zolanvari, Raj Jain
Summary: Driven by rapid progress in quantum hardware, academia and industry have engaged in a fierce race for quantum technologies. Quantum computers have achieved hundreds of qubits and quantum annealers have reached thousands of qubits. This article provides an introduction to quantum computing and communications from a computer science perspective, reviewing key milestones and recent advances. It categorizes the key elements of a quantum Internet into four important issues: quantum computers, quantum networks, quantum cryptography, and quantum machine learning. Additionally, the article discusses barriers, research directions, and trends.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Proceedings Paper
Computer Science, Information Systems
Qi Li, Keyang Yu, Dong Chen, Mo Sha, Long Cheng
Summary: As more and more people use IoT devices to monitor and control their environments, the security and privacy of these devices become a growing concern. One recent research reveals that VPN-encrypted IoT network traffic is not anonymous and can be disaggregated into individual device traffic, potentially exposing sensitive user information. To investigate this privacy threat, researchers develop a new smart home traffic disaggregator called TrafficSpy, which accurately disaggregates VPN traffic into device-level data. However, this disaggregated data is susceptible to further attacks that can reveal user sensitive information. TrafficSpy represents both a serious privacy threat and a potentially valuable tool for smart home monitoring and automation.
2022 IEEE CONFERENCE ON COMMUNICATIONS AND NETWORK SECURITY (CNS)
(2022)
Proceedings Paper
Computer Science, Hardware & Architecture
Junyang Shi, Mo Sha
Summary: This paper presents a novel approach to localize a campus shuttle using the LoRa link characteristics measured by a single base station and deep learning. Experimental results demonstrate that the proposed solution achieves high accuracy without requiring new hardware and introducing additional communication overhead.
2022 31ST INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATIONS AND NETWORKS (ICCCN 2022)
(2022)
Article
Computer Science, Information Systems
Marcio Andrey Teixeira, Maede Zolanvari, Khaled M. Khan, Raj Jain, Nader Meskin
Summary: Intrusion detection in SCADA systems is crucial, but current approaches lack representative datasets and real-time adaptability. This study presents a flow-based dataset and a deep learning-based IDS for SCADA systems. Experimental results show the model can detect cyberattacks in real time.
IET CYBER-PHYSICAL SYSTEMS: THEORY & APPLICATIONS
(2021)