Article
Transportation Science & Technology
Phat Thai, Sameer Alam, Nimrod Lilith, Binh T. Nguyen
Summary: This paper proposes a computer vision framework for airport-airside surveillance, which uses cameras to monitor ground movement objects and improve safety and operational efficiency. The framework achieves good detection and prediction results in video data from Houston Airport and Obihiro Airport.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Engineering, Electrical & Electronic
Lin Li, Xiaolei Yu, Zhenlu Liu, Zhimin Zhao, Ke Zhang, Shanhao Zhou
Summary: This article optimizes the reading performance of multitag through deep learning, improves the ability to detect small targets by enhanced features, achieves dynamic deblurring of multitag images, and ultimately enhances the reading performance of the RFID system.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Xueyan Zou, Fanyi Xiao, Zhiding Yu, Yuheng Li, Yong Jae Lee
Summary: Aliasing refers to the phenomenon where high frequency signals become completely different after sampling. In the context of deep learning, downsampling layers are commonly used, leading to the aliasing problem. To address this, the paper proposes an adaptive content-aware low-pass filtering layer that predicts separate filter weights for each spatial location and channel group.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Automation & Control Systems
Dunlu Peng, Yongsheng Zhang
Summary: This work proposes a new deep learning framework, Memory Augmented Graph Convolutional Network (MA-GCN), to address the challenges of accurately capturing the long time dependence of traffic data and the complex spatial dependence of road networks. The model combines graph convolutional network (GCN) to capture the spatial dependence and differential neural computer (DNC) to capture the long-term dynamic changes of traffic data. Experimental evaluation on two public datasets, PeMSD4 and PeMSD8, shows that the MA-GCN model outperforms comparative models on several evaluation metrics.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Maralbek Zeinullin, Marion Hersh
Summary: This article introduces a study aimed at helping people with visual impairments access information. The study developed a special system that utilizes tactile graphics and a mobile application to make educational materials more accessible. The results of the experiments showed that the application allows users to explore graphics more efficiently.
Article
Computer Science, Artificial Intelligence
Robin Kuok Cheong Chan, Joanne Mun-Yee Lim, Rajendran Parthiban
Summary: The study proposed three solutions including real-time traffic simulation, pheromone and neural network traffic prediction and rerouting system, and weighted historical data method. Benchmark tests were conducted using Google Maps system, showing significant improvements in traffic management efficiency with the proposed systems.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Fan Zhou, Qing Yang, Ting Zhong, Dajiang Chen, Ning Zhang
Summary: This article presents a novel Bayesian framework for traffic forecasting and demonstrates its superiority over traditional methods through extensive experiments.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Youcef Djenouri, Asma Belhadi, Hsing-Chung Chen, Jerry Chun-Wei Lin
Summary: This paper presents a novel deep learning architecture that uses a convolutional neural network and decomposition strategy to identify outliers in urban traffic data. The system trains different models on similar clusters of highly correlated data and merges the results to improve accuracy. Experimental results show that the proposed framework outperforms competitors.
COMPUTER COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Shiva Azimi, Rohan Wadhawan, Tapan K. Gandhi
Summary: In the past decade, high-throughput plant phenotyping techniques utilizing image analysis and machine learning have been successful in identifying and quantifying plant health and diseases. To address the issue of early detection and recovery, a deep learning pipeline for analyzing plant visual changes induced by stress has been proposed.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Automation & Control Systems
Pakize Erdogmus, Abdullah Talha Kabakus
Summary: Alzheimer's Disease is a devastating neurologic disorder with no cure, and its symptoms eventually interfere with daily tasks. We propose a novel Convolutional Neural Network as a cheap, fast, yet accurate solution for early diagnosis, achieving an accuracy of 90.4% which outperforms existing classifiers.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Optics
Jiahao Huang, Haiyang Zhang, Lin Wang, Zilong Zhang, Changming Zhao
Summary: The paper introduces an active laser detection system to address the abuse of miniature cameras in information security and privacy. By utilizing the improved YOLOv3-4L model, small targets can be accurately detected, with experimental results showing superior performance compared to traditional models like YOLOv3, Faster R-CNN, and Single Shot Multi-box Detector.
OPTICS AND LASER TECHNOLOGY
(2021)
Article
Engineering, Marine
Dmitry Nikushchenko, Andrey Maevskiy, Igor Kozhemyakin, Vladimir Ryzhov, Alexander Bondar, Artem Goreliy, Ivan Pechaiko, Ekaterina Nikitina
Summary: AI systems are widely used in various industries, including data processing and marine robotics. This article focuses on the development of an intelligent system for path planning for a group of marine robotic complexes. The system utilizes a cascade approach and includes functional modules for perception. It provides a detailed description of the development process, mathematical modeling of algorithms, and results of experiments.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Zaid Saeb Sabri, Zhiyong Li
Summary: The study investigates the design of low-cost multiunit surveillance systems using deep learning techniques to monitor and recognize suspicious and vital events in real time. The system ensures that relevant events are alarmed to officers, such as stranger intrusions, the presence of guns, suspicious movements, and identified fugitives.
PEERJ COMPUTER SCIENCE
(2021)
Article
Automation & Control Systems
Chao Ning, Hongping Gan, Minghe Shen, Tao Zhang
Summary: This paper proposes a method to calculate padding data using learning-based approaches to maintain the output size of convolutional neural networks (CNNs). By designing two different modules, learning-based padding by convolution (LPC) and learning-based padding by attention (LPA), padding data can be obtained from the connectivity of the input images. Extensive experiments show that the proposed padding schemes consistently achieve higher accuracy than standard padding schemes in various deep network backbones.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Xiaowei He, Rao Cheng, Zhonglong Zheng, Zeji Wang
Summary: An improved algorithm named YOLO-MXANet is proposed to enhance the detection accuracy of small objects in traffic scenes. By utilizing CIoU, a lightweight backbone network called SA-MobileNeXt, and other methods, the algorithm is able to improve object detection accuracy and reduce model complexity effectively.
Article
Computer Science, Artificial Intelligence
Mohamed Abd Elaziz, Laith Abualigah, Ahmed A. Ewees, Mohammed A. A. Al-qaness, Reham R. Mostafa, Dalia Yousri, Rehab Ali Ibrahim
Summary: In this paper, a modified version of Manta Ray Foraging Optimization (MRFO) called MRTMO is proposed to overcome the issue of trapping in local solutions in metaheuristic techniques. The proposed MRTMO integrates the triangular mutation operator and orthogonal learning strategy to achieve a balance between algorithm cores and guide the search agents effectively. Extensive experiments demonstrate the competitive performance of MRTMO in solving optimization and engineering problems.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Multidisciplinary
Mohammed A. A. Al-qaness, Ahmed A. Ewees, Hong Fan, Laith Abualigah, Ammar H. Elsheikh, Mohamed Abd Elaziz
Summary: Wind power is a crucial green energy source, and accurate prediction of wind power is essential for efficient power grid operations and increased market competitiveness. This paper presents an optimized RVFL network using the Capuchin search algorithm (CapSA), which improves the configuration and prediction capability of the RVFL model.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Mathematics
Mohammed A. A. Al-qaness, Abdelghani Dahou, Ahmed A. A. Ewees, Laith Abualigah, Jianzhu Huai, Mohamed Abd Elaziz, Ahmed M. M. Helmi
Summary: Many Chinese cities suffer from severe air pollution due to rapid economic development, urbanization, and industrialization. Particulate matter (PM2.5) is a major component of air pollutants and is associated with cardiopulmonary and other systemic diseases due to its ability to penetrate the human respiratory system. Forecasting PM2.5 concentration is vital for governments and local authorities to plan and take necessary actions.
Article
Engineering, Electrical & Electronic
Nabil Mohsen, Ammar Hawbani, Xingfu Wang, Monika Agrawal, Liang Zhao
Summary: This paper proposes two optimized sparse nested arrays, OSNA-I and OSNA-II, for the direction of arrival estimation of non-circular signals. These structures enhance the degrees of freedom and mitigate mutual coupling. The expressions for actual sensor locations, number of uniform degrees of freedom, and available degrees of freedom are derived. Simulation results demonstrate the superiority of the proposed structures in terms of robustness and estimation accuracy.
Article
Computer Science, Information Systems
Raushan Myrzashova, Saeed Hamood Alsamhi, Alexey V. Shvetsov, Ammar Hawbani, Xi Wei
Summary: Recently, innovations in the Internet of Medical Things (IoMT), information and communication technologies, and machine learning (ML) have enabled smart healthcare. Federated learning (FL) overcomes the challenges of centralized data storage and provides high-level security and privacy for smart healthcare. Combining blockchain and FL can further enhance the competency of healthcare by managing data in a decentralized manner and utilizing dispersed clinical data fully.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Saeed Hamood Alsamhi, Ammar Hawbani, Alexey V. Shvetsov, Santosh Kumar
Summary: The intersection of Federated Learning and Healthcare 5.0 plays a crucial role in pandemic preparedness, offering a more efficient and data-driven approach to healthcare delivery. It ensures privacy protection, enables decentralized decision-making, and enhances real-time surveillance.
ADVANCES IN HUMAN-COMPUTER INTERACTION
(2023)
Article
Ecology
Kanak Kumar, Navin Singh Rajput, Alexey V. Shvetsov, Abdu Saif, Radhya Sahal, Saeed Hamood Alsamhi
Summary: This paper proposes an Intelligent Decision Support System (ID2S4FH) to generate real-time fire maps of storage and distribution centres (SDCs) during a fire hazard. The system helps firefighters to extinguish the fire using the appropriate fire retardant.
Article
Engineering, Civil
Zhuhui Li, Liang Zhao, Geyong Min, Ahmed Y. Al-Dubai, Ammar Hawbani, Albert Y. Zomaya, Chunbo Luo
Summary: This paper proposes a novel GCN-based greedy routing algorithm (NGGRA) in the hybrid SDVN. The SDVN control plane trains the GCN decision model based on globally collected data, which vehicles can use to make routing decisions. Simulation results show that NiGCN outperforms popular GCN models in training efficiency and accuracy. NGGRA improves packet delivery ratio and reduces delay compared with its counterparts.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Adel R. Alharbi, Sajjad Shaukat Jamal, Muhammad Fahad Khan, Mohammad Asif Gondal, Aaqif Afzaal Abbasi
Summary: This paper proposes an innovative approach for constructing dynamic S-boxes using Gaussian distribution-based pseudo-random sequences. The proposed technique overcomes the weaknesses of existing chaos-based S-box techniques by leveraging the strength of pseudo-randomness sequences. The technique achieves a maximum nonlinearity of 112, which is comparable to the ASE algorithm.
Article
Computer Science, Information Systems
Iram Arshad, Saeed Hamood Alsamhi, Wasif Afzal
Summary: Big Data is transforming industries by providing decision support through analyzing large data volumes. Testing Big Data is challenging due to the diversity and complexity of data. This paper systematically reviews testing techniques, challenges, and future directions in Big Data testing from 2010 to 2021.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Computer Science, Information Systems
Xiguang Li, Baolu Feng, Yunhe Sun, Ammar Hawbani, Saeed Hammod Alsamhi, Liang Zhao
Summary: This paper proposes an enhanced scatter search strategy, using opposition-based learning, to solve the problem of automated test case generation based on path coverage (ATCG-PC). The proposed ESSENT algorithm selects the path with the lowest path entropy among the uncovered paths as the target path and generates new test cases to cover the target path by modifying the dimensions of existing test cases. Experimental results show that the ESSENT algorithm outperforms other state-of-the-art algorithms, achieving maximum path coverage with fewer test cases.
INFORMATION SCIENCES
(2024)
Review
Computer Science, Information Systems
Alexey V. Shvetsov, Saeed Hamood Alsamhi, Ammar Hawbani, Santosh Kumar, Sumit Srivastava, Sweta Agarwal, Navin Singh Rajput, Amr A. Alammari, Farhan M. A. Nashwan
Summary: The combination of drones and Intelligent Reflecting Surfaces (IRS) has the potential to improve the performance of 6G communication networks by modifying wireless communication through smart signal reflection. Integrating IRS with Federated Learning (FL) can further enhance the performance by enabling collaborative learning among drones. This integration offers advantages such as rapid deployment, improved coverage and quality of communication services, and increased accessibility to remote areas.
Article
Computer Science, Information Systems
Majjed Al-Qatf, Xingfu Wang, Ammar Hawbani, Amr Abdussalam, Saeed Hammod Alsamhi
Summary: Topic modelling has made significant progress in improving image captioning. To address challenges in existing models, we propose a novel method that predicts suitable topics and enhances explainability. Experiments demonstrate that our approach outperforms other methods in terms of performance and evaluation metrics.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Hardware & Architecture
Xiujun Wang, Zhi Liu, Alex X. Liu, Xiao Zheng, Hao Zhou, Ammar Hawbani, Zhe Dang
Summary: Continuous tag recognition is a critical problem in mobile RFID systems. This paper studies this problem and proposes a near-optimal protocol called OPT-L. Extensive simulation and experimental results demonstrate its superior performance over other existing protocols.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Information Systems
Muhammad Ilyas Khattak, Hui Yuan, Ayaz Ahmad, Ajmal Khan, Ammar Hawbani, Inamullah
Summary: The increasing usage of distributed computing has led designers and entrepreneurs to utilize these solutions for diverse purposes. Vehicular fog computing (VFC) is an innovative paradigm that has been developed using AI-based advanced optimization procedures. However, many of these strategies have not been adapted for specific application data and types, resulting in poor performance.
INTERNET OF THINGS
(2023)