Article
Computer Science, Information Systems
Xiyao Liu, Yayun Zhang, Jiayu Wang, Yuying Sun, Wei Zhang, Di Zhou, Gerald Schaefer, Hui Fang
Summary: This paper proposes a novel multiple-feature-based zero-watermarking scheme for copyright protection of DIBR 3D videos. The scheme integrates dual-tree complex wavelet transform, discrete cosine transform, and ring-partition statistical residual features, encrypts them with a chaotic system, and uses attention-based fusion for optimal copyright protection. Experimental results show that the proposed scheme has stronger robustness and discriminative capacity compared to state-of-the-art methods.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Wenzhong Shen, Ji Rong, Yingfeng Liu, Yan Zhao
Summary: This article proposes a novel digital watermarking method called IrisMarkNet, which embeds the copyright owner's iris features into the cover image based on deep neural networks, to protect image copyright. Experimental results demonstrate the superior performance of IrisMarkNet in terms of imperceptibility, robustness, and accuracy rate.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
A. Hernandez-Joaquin, G. Melendez-Melendez, R. Cumplido
Summary: This paper introduces a dual watermarking scheme for image authentication and copyright protection. Two watermarks, a fragile watermark and a robust watermark, are embedded into the host image using the discrete wavelet transform (DWT). The proposed scheme achieves satisfactory watermark imperceptibility levels and high watermark robustness against image processing attacks. It also achieves high authentication accuracy against tampering attacks, outperforming similar state-of-the-art dual watermarking methods in terms of watermark robustness and authentication accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Saad M. Darwish, Osama F. Hassan
Summary: This paper proposes a method for optimizing image multiple watermarking techniques using genetic algorithms to enhance watermark capacity and imperceptibility. By encoding watermarks using 2-D Walsh transform in color images, and utilizing Singular Value Decomposition to determine significant embedding locations, the proposed model demonstrates greater robustness against common image manipulation attacks in terms of PSNR and NCC.
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
MingQuan Fan
Summary: In this paper, a blind dual image watermarking scheme is proposed for copyright protection, tamper proofing and self-recovery. The scheme uses a binary handwritten signature as a robust watermark and embeds it into a hybrid domain constructed by dual tree complex wavelet transform (DT-CWT) and discrete cosine transform (DCT) for copyright protection. For tamper proofing and self-recovery, source encoding output bits generated by set partitioning in hierarchical trees (SPIHT) encoding are embedded into the image based on least significant bits (LSB) replacement. The proposed watermarking mechanism can withstand various image processing attacks, accurately locate and recover the tampered area of an image, and has the ability of tamper discrimination that other existing schemes do not have. It can be applied for joint ownership and content authentication synchronously.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
B. Sridhar, V. Syambabu
Summary: This paper presents a non-blind video watermarking technique that reshapes watermark images, decomposes and recombines the luminance band of frames to achieve copyright marking. The main objective is to design and develop gatefold-based video authentication approaches to increase robustness, payload, and minimize the bit error rate.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Iynkaran Natgunanathan, Purathani Praitheeshan, Longxiang Gao, Yong Xiang, Lei Pan
Summary: This article proposes a privacy protection mechanism for multimedia distribution networks (MDNs) by combining the advantages of blockchain and watermarking technologies. A specifically designed watermarking algorithm is used to link copyright information with audio files, while a blockchain-based smart contract mechanism is developed to ensure the proper functioning of entities in the distribution network. The proposed mechanism is computationally efficient and can be extended to other multimedia objects.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Younes Akbari, Omar Elharrouss, Somaya Al-Maadeed
Summary: Feature-level-based fusion has attracted much interest. In this paper, a fusion method using wavelet transform is proposed to improve classification accuracy by extracting common aspects of different views. The experimental results show competitive performance compared to existing methods.
PATTERN ANALYSIS AND APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Baowei Wang, Shi Jiawei, Weishen Wang, Peng Zhao
Summary: This paper studies image storage and authentication frameworks, utilizing the advantages of zero-watermarking algorithm and blockchain technology. It solves the data expansion problem by using the Inter-Planetary File System and avoids the drawbacks of zero-watermarking algorithm and blockchain. The feasibility of the proposed framework is demonstrated through experiments.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
L. Velazquez-Garcia, A. Cedillo-Hernandez, M. Cedillo-Hernandez, M. Nakano-Miyatake, H. Perez-Meana
Summary: This paper introduces a robust and imperceptible video watermarking method performed in the base-band domain. Two nonoverlapped watermarks, representing ownership and data sharing, are embedded in the host video frames. Experimental results show that this method has advantages such as simplicity, low computational complexity, and improved robustness and imperceptibility.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2022)
Article
Computer Science, Information Systems
Hazem Munawer Al-Otum
Summary: A novel dual color image watermarking technique for copyright protection, authentication, and recovery applications is proposed in this research. The scheme shows high imperceptibility performance, survivability against unintentional attacks, and high forgery detection accuracy and recovery performance against intentional attacks.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Engineering, Multidisciplinary
Mianjie Li, Yuan Liu, Zhihong Tian, Chun Shan
Summary: In this article, an information hiding method based on multidimensional feature fusion for privacy protection in 6G networks is proposed. The method is based on the strong attack resistance of carriers carrying private information, and it involves studying multidimensional feature fusion arbitration methods and constructing an efficient and accurate feature-based information hiding technology.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Hui Shi, Yanni Li, Baoyue Hu, Meihan Chen, Yonggong Ren
Summary: This paper proposes a zero-watermarking scheme that combines various techniques to address the weak robustness and security of existing schemes. Experimental results show that the proposed scheme has strong robustness and visibility against various attacks. The authors also provide theoretical and complexity analysis to demonstrate the comprehensive performance of the scheme.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Remote Sensing
Xianyue Wang, Longxia Qian, Jian Shi, Mei Hong, Jinde Cao
Summary: This article presents an efficient feature extraction framework, called the dual feature fusion model (DFFM), to address issues in hyperspectral image applications. The framework utilizes a novel two-order feature fusion and a valid three-order feature fusion method to maintain spatial structure integrity and save computing costs. It also automatically selects a suitable number of features and is robust to noise and training sets. Experimental results demonstrate that the framework outperforms state-of-the-art techniques in classification precision and execution time across various training sizes.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Deyang Wu, Li Li, Jiayan Wang, Penghui Ma, Zichi Wang, Hanzhou Wu
Summary: This article proposes a robust zero-watermarking scheme using DT CWT and improved differential entropy to protect the copyright and security of medical images. Experimental results show that the proposed scheme provides a high level of robustness.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Mathematics
Qasim M. Zainel, Saad M. Darwish, Murad B. Khorsheed
Summary: In this study, a quantum fruit fly optimization algorithm (QFOA) was proposed for parameter estimation in chaotic systems. Compared to other algorithms, QFOA showed significant improvement in accuracy and estimation power.
Article
Chemistry, Multidisciplinary
Saad M. M. Darwish, Mohamed A. A. Salah, Adel A. A. Elzoghabi
Summary: Indoor object detection is crucial for developing mobility-assistive technology for visually impaired people. The complexity of background, occlusions, and viewpoint shifts poses challenges in identifying interior objects in real indoor environments. Recent methods, including neural networks, probabilistic methods, and fuzzy logic, have been proposed to address these challenges. This study presents a method using a rotational ultrasonic array and neutrosophic logic to accurately detect indoor objects and guide visually impaired individuals. Experimental results demonstrate a high accuracy rate of 97.2+/-1%.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Jamal Khudair Madhloom, Hussein Najm Abd Ali, Haifaa Ahmed Hasan, Oday Ali Hassen, Saad Mohamed Darwish
Summary: This paper introduces a novel modified gateway discovery approach based on quantum swarm intelligence technique, which improves the processes of exploring new gateways, testing and maintaining existing paths to gateways, exploring different paths to existing gateways, detecting any connection failure in any route, and attempting to fix that failure by discovering an alternative optimal path. The experimental results show that this approach has 27% improvement in discovering new gateways, 70% improvement in the time taken by newly inserted node to discover all gateways on average, 53% improvement in routing overhead on average, and 60% improvement in gateway's overhead on average.
Article
Mathematics
Ramy A. Othman, Saad M. Darwish, Ibrahim A. Abd El-Moghith
Summary: The Internet of Things (IoT) covers various applications, such as smart cities, autonomous vehicles, surveillance, medical devices, and crop control. Virtualization in wireless sensor networks (WSNs) is considered to be a revolutionary technological technique used in these areas. However, previous research on virtual WSNs has overlooked the impact of communication latency. This study utilizes the Evolutionary Multi-Objective Crowding Algorithm (EMOCA) to optimize fault tolerance and communication delay for virtual network embedding in WSNs.
Article
Imaging Science & Photographic Technology
Ansam A. Abdulhussien, Mohammad F. Nasrudin, Saad M. Darwish, Zaid Abdi Alkareem Alyasseri
Summary: Recently, signature verification systems have been widely used for individual verification based on handwritten signatures. Feature extraction and classification greatly affect the accuracy of system authentication. The diversity of signatures and sample circumstances pose challenges for feature extraction in signature verification systems. The current techniques show promising results in identifying genuine and forged signatures, but skilled forgery detection remains a challenge. Additionally, most current techniques require a large number of learning samples, restricting the practical application of the system.
JOURNAL OF IMAGING
(2023)
Article
Engineering, Multidisciplinary
Saad M. Darwish, Dheyauldeen A. Farhan, Adel A. Elzoghabi
Summary: This paper presents a model for finding malicious domains by analyzing DNS data passively. The proposed model builds a real-time, accurate, middleweight, and fast classifier by combining a genetic algorithm for selecting DNS data features with a two-step quantum ant colony optimization (QABC) algorithm for classification. The use of the Hadoop framework and a hybrid machine learning approach to deal with large size of URL data is a major contribution of this paper. The results showed that the suggested model could work with more than 96.6% accuracy for more than 10 million query-answer pairs.
Article
Physics, Multidisciplinary
Saad M. Darwish, Ibrahim Abdullah Mhaimeed, Adel A. Elzoghabi
Summary: The majority of recent research in text similarity has focused on using machine learning strategies to address the problem in the educational environment. This article proposes a unified framework that combines semantic extraction and the quantum genetic algorithm (QGA) to identify idea plagiarism and improve the performance of existing methods in terms of detection accuracy and computational time. This approach utilizes semantic similarity measures and the QGA's ability to identify cohesive sentences to capture a document's idea and effectively convey the main idea of the source document.
Article
Chemistry, Multidisciplinary
Saad M. Darwish, Raad A. Ali, Adel A. Elzoghabi
Summary: Most educators agree that essays are the best way to evaluate students' understanding, guide their studies, and track their growth as learners. Manually grading student essays is a tedious but necessary part of the learning process. Automated Essay Scoring (AES) provides a feasible approach to completing this process.
APPLIED SCIENCES-BASEL
(2023)
Article
Biotechnology & Applied Microbiology
Saad M. Darwish, Lina J. Abu Shaheen, Adel A. Elzoghabi
Summary: Accurate segmentation of brain tumors in 3D-MRI is crucial for facilitating diagnosis and treatment. This article proposes a clustering method influenced by the Quantum Inspired Dragonfly Algorithm to extract initial contour points, and a level set segmentation technique to isolate tumor areas. The experimental results on the BraTS' 2019 dataset demonstrate that the proposed technique outperforms state-of-the-art approaches.
BIOENGINEERING-BASEL
(2023)
Article
Engineering, Electrical & Electronic
Hesham M. Elkady, Haythem H. Abdullah, Saad M. Darwish
Summary: A novel design of a high-frequency multiband circular polarisation antenna for CubeSat applications is presented. The antenna consists of a spiral antenna and four patch antennas, allowing it to cover multiple frequency bands. The measured results show good agreement with the simulated results.
IET MICROWAVES ANTENNAS & PROPAGATION
(2023)
Article
Computer Science, Information Systems
Marwan A. Hefnawy, Saad M. Darwish, Amr A. Elmasry
Summary: A Mobile Ad Hoc Network (MANET) is a communication network without permanent infrastructure, and utilizes Ant Colony Optimization (ACO) routing algorithms for balancing between exploring new routes and utilizing known ones. This research introduces a novel method to find an optimal balance for this tradeoff during the communication session, showing higher performance compared to traditional offline tuning algorithms.
Article
Computer Science, Information Systems
Mohammed S. Zalat, Saad M. Darwish, Magda M. Madbouly
Summary: The fast development of mobile applications has increased the need for more resources and processing power on mobile devices. Mobile Cloud Computing combines cloud computing with mobile devices to enable resource-intensive applications to run on mobile devices. Computation offloading is used to overcome the performance limits of mobile devices, allowing heavy tasks to be offloaded to servers. However, most existing techniques for offloading choices are based on profile data and do not support multi-site offloading. This research proposes a novel strategy that combines genetic algorithms and Markov Decision Process to enhance the multi-site offloading mechanism by optimizing the offloading location and transition probability.
Article
Computer Science, Information Systems
Saad M. Darwish, Reham M. Essa, Mohamed A. Osman, Ahmed A. Ismail
Summary: Protecting the privacy of healthcare data is crucial, and negative association rules in data mining may be more informative than positive ones in certain cases. Recent technological advancements have focused on disrupting data and reconstructing distributions to support research in data mining while ensuring patient privacy.
Article
Computer Science, Information Systems
Marwan H. Hassan, Saad M. Darwish, Saleh M. Elkaffas
Summary: This paper investigates the problem of uncertainty in distributed real-time deadlock-resolving systems and proposes a solution using neutrosophic logic. Experimental results show that this method can increase the detection rate, significantly reduce the rollback rate, and greatly improve database performance.
Article
Computer Science, Information Systems
Reem Essameldin, Ahmed A. Ismail, Saad M. Darwish
Summary: One main incentive for using opinion mining in social media is the inability to manually analyze a large number of opinions. This study proposes an opinion mining model for handling perspectivism and opinion ambiguity, using social network analysis to rank and weight users, and integrating users' influence levels with polarity scores using an uncertainty classifier to obtain a new polarity score that reflects real-world reasoning.