Article
Chemistry, Multidisciplinary
Mesfer Al Duhayyim, Eatedal Alabdulkreem, Khaled Tarmissi, Mohammed Aljebreen, Bothaina Samih Ismail Abou El Khier, Abu Sarwar Zamani, Ishfaq Yaseen, Mohamed Eldesouki
Summary: Video surveillance in smart cities provides efficient city operations, safer communities, and improved municipal services. This study introduces Aquila Optimization with Transfer Learning based Crowd Density Analysis for Sustainable Smart Cities (AOTL-CDA3S) technique, which aims to identify different kinds of crowd densities in smart cities.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Civil
Xiao Xiao, Ziyan Peng, Yunqing Lin, Zhiling Jin, Wei Shao, Rui Chen, Nan Cheng, Guoqiang Mao
Summary: With the increasing number of cars in cities, smart parking has become a strategic issue in building a smart city. Accurate parking prediction can reduce the time drivers spend searching for parking spaces and alleviate traffic congestion, but various methods are proposed for parking prediction. In this survey, we provide a comprehensive review of existing methods and classify different parking problems. This survey will be of interest to researchers and practitioners in intelligent transportation systems and smart cities.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Ambreen Sabha, Arvind Selwal
Summary: The growth of multifarious video contents generated by various applications is resulting in huge volumes and manual analysis of these contents is a challenging task. Video analysis plays a vital role in various real-time applications in smart cities, such as security surveillance, traffic monitoring, entertainment, and medicine. This study aims to investigate computer vision-based video analysis approaches and present a generic video analysis layered architecture for smart cities. The analysis demonstrates the pertinency of video analysis in smart city infrastructure and identifies future research challenges.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Asma Belhadi, Youcef Djenouri, Gautam Srivastava, Djamel Djenouri, Jerry Chun-Wei Lin, Giancarlo Fortino
Summary: This paper presents a new model for identifying collective abnormal human behaviors in smart cities through data mining and deep learning algorithms. Experimental results demonstrate that the deep learning solution outperforms other algorithms in terms of accuracy and runtime.
INFORMATION FUSION
(2021)
Article
Computer Science, Artificial Intelligence
Gen Chen, Jiawan Zhang
Summary: This study discusses the feasibility and efficiency of adopting Artificial Intelligence (AI) Deep Learning in smart city scenarios. A traffic flow prediction model based on the Deep Belief Network (DBN) algorithm is constructed and compared with other models. The results show that the proposed algorithm has higher prediction accuracy and better performance in traffic congestion evacuation, providing experimental references for the construction of smart cities.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Qiuying Lv, Nannan Yang, Adam Slowik, Jianhui Lv, Amin Yousefpour
Summary: The construction of Smart Cities is closely related to the healthy operation of markets. Reasonable data analysis plays a crucial role in market behavior development, considering the vast amount of data generated by a market economy. We propose enhanced cluster generative adversarial networks (eClusterGAN) for latent space clustering and suggest a GAN-based network intrusion detection system (GAN-NIDS) that uses adversarial learning to learn the spatial distribution of normal network flows. Simulation results demonstrate that the proposed eClusterGAN and GAN-NIDS outperform benchmarks in terms of clustering accuracy, running time, precision, recall, and F1, supporting researchers in studying economic data trends. The construction of Smart Cities can effectively ensure healthy market development by discovering and disseminating the potential value of market economic data.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Fatma M. Talaat, Hanaa ZainEldin
Summary: This paper introduces a smart fire detection system (SFDS) based on the YOLOv8 algorithm, which can detect fires in real time, improve accuracy, reduce false alarms, and be cost-effective compared to traditional methods. The SFDS can also be extended to detect other objects of interest in smart cities, such as gas leaks or flooding.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Chemistry, Analytical
Rabiah Al-Qudah, Yaser Khamayseh, Monther Aldwairi, Sarfraz Khan
Summary: The need for a smart city has become more urgent in recent years due to various factors such as pandemics, lockdowns, climate change, population growth, and limitations on natural resources. This article proposes a general framework for designing a smart city and introduces a technology-driven model to support it. By designing and implementing a smart image handling system and a generalized image processing model using deep learning, the importance and practicality of this framework are highlighted.
Review
Construction & Building Technology
Dongliang Chen, Pawel Wawrzynski, Zhihan Lv
Summary: Smart cities bring about changes in people's lives, while also posing hidden cyber security risks. The current development of cyber security is unable to keep pace with global smart city technologies, making correct design based on deep learning methods essential for protecting smart city networks. This paper summarizes concepts of Smart Cities, Cyber Security, and Deep Learning, as well as discusses related work on IoT security in smart cities, deep learning models, cyber security applications, and future trends in smart city cyber security.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Computer Science, Information Systems
Rajdeep Chatterjee, Ankita Chatterjee, Manas Ranjan Pradhan, Biswaranjan Acharya, Tanupriya Choudhury
Summary: Violence, especially involving firearms, is a shameful part of our society and results in the loss of innocent lives. This paper focuses on utilizing deep learning techniques to detect guns and human faces, providing law enforcement with quick intelligence and preventive measures. By employing various detection techniques and ensemble schemes, it achieves the best performance in identifying firearms and human faces, with promising applicability in social media content detection. The rigorous testing and comparative results demonstrate the effectiveness and reliability of the proposed model.
Article
Computer Science, Hardware & Architecture
Yuxi Hu, Taimeng Fu, Guanchong Niu, Zixiao Liu, Man-On Pun
Summary: Large-scale high-resolution three-dimensional (3D) maps are crucial for the development of smart cities. This study proposes a novel deep learning-based multi-view-stereo method that reconstructs 3D maps in large-scale urban environments using a monocular camera. The proposed method performs 3D depth estimation more efficiently in terms of computational complexity and graphics processing unit memory usage, enabling depth estimation for each pixel before generating 3D maps for even large-scale scenes. Extensive experiments confirm the good performance of the proposed method using the well-known DTU dataset and real-life data collected on our campus.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Engineering, Civil
Antonio Greco, Alessia Saggese, Mario Vento, Vincenzo Vigilante
Summary: The translated text discusses the profitable adoption of video analytics in smart road environments and the importance of accurate vehicle detection. It also highlights the preference for performing video analysis directly on smart surveillance cameras to reduce bandwidth usage and the challenge of limited resources for processing on embedded devices. The text raises the question of the best method for vehicle detection in smart camera systems, taking into account accuracy, computational burden, and hardware limitations.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Khosro Rezaee, Mohammad R. Khosravi, Hani Attar, Varun G. Menon, Mohammad Ayoub Khan, Haitham Issa, Lianyong Qi
Summary: This study investigates the use of UAV video frames to analyze the most efficient route for emergency medical vehicles in smart cities, considering overcrowding and abnormal situations. Utilizing IoMT and public safety video surveillance systems can help determine the optimal routes and improve rescue speed and traffic flow.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Construction & Building Technology
Mostafa Mohammadpourfard, Abdullah Khalili, Istemihan Genc, Charalambos Konstantinou
Summary: Future cities face a challenge in achieving environmental sustainability while also defending against cyber threats. Ensuring the cybersecurity of smart grids is crucial, especially with growing uncertainties and the impact of renewable energy resources. The development of LSTM-based attack detection models shows promise in accurately capturing the dynamic behaviors of modern power grids and outperforming traditional methods in detecting real-time attacks.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Computer Science, Artificial Intelligence
Qi Chen, Wei Wang, Kaizhu Huang, Suparna De, Frans Coenen
Summary: Advancements in the Internet of Things have enabled the development of smart city applications and expert systems, utilizing deep learning techniques to analyze big data from the Cyber, Physical, and Social worlds to enhance city resource planning and utilization, particularly in the field of traffic event detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Ahsan Shahzad, Seunguk Ko, Samgyu Lee, Jeong-A Lee, Kiseon Kim
IEEE SENSORS JOURNAL
(2017)
Article
Automation & Control Systems
Ahsan Shahzad, Kiseon Kim
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2019)
Article
Computer Science, Information Systems
Ahsan Shahzad, Aresh Dadlani, Hyeonil Lee, Kiseon Kim
Summary: This paper investigates gait biomarkers for Mild Cognitive Impairment (MCI) and shows that dual-task walking provides better distinction between MCI and cognitively normal (CN) subjects. The machine learning model achieves high accuracy and sensitivity for MCI pre-screening.