Article
Computer Science, Artificial Intelligence
Hongying Yang, Shuren Qi, Jialin Tian, Panpan Niu, Xiangyang Wang
Summary: This paper proposes a method to address the contradiction between robustness and discriminability in moment-based image representation by introducing Fractional-order Jacobi-Fourier Moments (FJFM) and developing a new framework Mixed Low-order Moment Feature (MLMF). Experimental results demonstrate the superior performance of the proposed method in terms of robustness and discriminability.
PATTERN RECOGNITION
(2021)
Article
Chemistry, Analytical
Chunpeng Wang, Hongling Gao, Meihong Yang, Jian Li, Bin Ma, Qixian Hao
Summary: This study proposes fractional-order polar harmonic Fourier moments (FrPHFMs) by extending integer-only PHFMs to improve image reconstruction and object recognition performance. Experimental results demonstrate that FrPHFMs outperform integer-order PHFMs and other fractional-order continuous orthogonal moments in terms of performance, showing strong image description ability and stability.
Article
Computer Science, Artificial Intelligence
Xiangyang Wang, Yuyang Zhang, Jialin Tian, Panpan Niu, Hongying Yang
Summary: This paper presents a new set of quaternion fractional-order orthogonal moments for color images, along with improved computation methods and image representation. The experimental results demonstrate the effectiveness and superiority of the proposed scheme.
PATTERN ANALYSIS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Rachid Benouini, Imad Batioua, Khalid Zenkouar, Said Najah
Summary: The introduced fractional-order generalized Laguerre moments can extract both global and local features, and derive a new set of rotation, scale, and translation invariants for image classification and invariant pattern recognition. The systematic parameter selection method and recursive methods for reducing computation time are also provided, showcasing their usefulness in image analysis.
IET IMAGE PROCESSING
(2021)
Article
Mathematics, Applied
Chunpeng Wang, Qixian Hao, Bin Ma, Jian Li, Hongling Gao
Summary: Fractional-order quaternion exponential moments (FrQEMs) are proposed for color images in this paper, which outperform QEMs in image reconstruction, noise resistance, and object recognition while also demonstrating rotation invariance.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
Article
Computer Science, Information Systems
Khalid M. Hosny, Mohamed M. Darwish, Mostafa M. Fouda
Summary: This paper introduces a new robust watermarking algorithm for color images using fractional-order multi-channel orthogonal exponent moments. The algorithm consists of three phases: scrambling the watermark, calculating fractional-order moments, and quantization. Experimental results show that the proposed algorithm outperforms existing algorithms in terms of visual imperceptibility and resistance to attacks.
Article
Computer Science, Artificial Intelligence
Horlando Vargas-Vargas, Cesar Camacho-Bello, Jose S. Rivera-Lopez, Alicia Noriega-Escamilla
Summary: This paper briefly reviews fractional-order circular moments and proposes an alpha procedure to find the optimal parameter for image feature extraction. The method is validated through experiments using MNIST and MNIST-R datasets, demonstrating the effectiveness of searching for the best rotation-invariant features.
PATTERN RECOGNITION LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Achraf Daoui, Hicham Karmouni, Mohamed Yamni, Mhamed Sayyouri, Hassan Qjidaa
Summary: This paper presents two new algorithms for the fast and stable computation of high-order discrete orthogonal dual Hahn polynomials (DHPs). It also proposes a new method for ensuring the numerical stability of high-order DHPs. The results of simulations and comparisons demonstrate the effectiveness and superiority of these algorithms.
PATTERN RECOGNITION
(2022)
Article
Engineering, Electrical & Electronic
Chunpeng Wang, Bin Ma, Zhiqiu Xia, Jian Li, Qi Li, Yun-Qing Shi
Summary: In the past two years, some research progress has been made on fractional-order continuous orthogonal moments (FrCOMs). Compared to integer-order continuous orthogonal moments (InCOMs), FrCOMs increase the number of affine invariants and improve numerical stability. This study deduces FrCOMs corresponding to various types of InCOMs and combines them with trinion theory to construct trinion FrCOMs (TFrCOMs) applicable to stereoscopic images. The reconstruction performance and geometric invariance of TFrCOMs are analyzed theoretically and experimentally. The superior performance of TFrCOMs is verified through an application in the stereoscopic image zero-watermarking algorithm.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Xiangyang Wang, Maoying Deng, Panpan Niu, Hongying Yang
Summary: This paper proposes a zero-watermarking algorithm for color images based on accurate quaternion fractional-order pseudo-Jacobi-Fourier moments with time-frequency analysis capability. By defining a new set of orthogonal moments and providing an accurate computation scheme, the algorithm achieves a balance between robustness and discriminability for image zero-watermarking. The algorithm demonstrates good effectiveness and superiority, with improved legibility and robustness in image representation.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2023)
Article
Computer Science, Artificial Intelligence
Amal Hjouji
Summary: This paper presents new sets of discrete orthogonal moments and their invariants to translation, scaling, and rotation for image representation and recognition. Through comparative experiments, the proposed orthogonal moments show great potential in pattern recognition and image analysis.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Mathematics
Doaa Sami Khafaga, Amel Ali Alhussan, Mohamed M. Darwish, Khalid M. Hosny
Summary: This study introduces a new mathematical method for representing volumetric images and demonstrates through experiments that this method outperforms existing algorithms in 3D image reconstruction, invariance, noise resistance, and computational time.
Article
Computer Science, Information Systems
Achraf Daoui, Hicham Karmouni, Mhamed Sayyouri, Hassan Qjidaa
Summary: This article introduces new algorithms for fast and stable computation of high-order discrete orthogonal Hahn polynomials and moment invariants, showcasing their efficiency through signal and image reconstruction with low errors. The proposed methods offer significant improvement in computational stability and accuracy, especially demonstrated in medical imaging applications. Comparisons with recent literature further validate the effectiveness of the proposed algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Mathematics
Tieyu Zhao, Yingying Chi
Summary: The research in this paper focused on the definition of linear summation of fractional-order matrices and its application in image encryption. A reformulation of the definitions and theoretical analysis were proposed. The study found that many weighted terms are invalid and showed that effective weighted terms depend on the period of the matrix. The research also demonstrated that image encryption methods based on weighted fractional-order transform may pose security risks due to key invalidation.
Article
Computer Science, Artificial Intelligence
Omar El Ogri, Hicham Karmouni, Mohamed Yamni, Mhamed Sayyouri, Hassan Qjidaa, Mustapha Maaroufi, Badreeddine Alami
Summary: This paper introduces a new set of fractional-order continuous orthogonal moments called FrJMs and provides a fast and precise calculation method. The invariants of FrJMs with respect to RST are derived, and a parameter selection method is proposed. Experimental results demonstrate that FrJMs outperform recent orthogonal moments in various aspects.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Khalid M. Hosny, Asmaa M. Khalid, Hanaa M. Hamza, Seyedali Mirjalili
Summary: This paper presents a modified Coronavirus Optimization algorithm for image segmentation. The algorithm increases the diversity of solutions by incorporating the concept of chaotic maps in the initialization step. A hybrid of two commonly used methods is applied as the fitness function to determine the optimal threshold values. Evaluation using different datasets demonstrates the superiority of the proposed algorithm in image segmentation.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mohamed A. A. Kassem, Soaad M. M. Naguib, Hanaa M. M. Hamza, Mostafa M. M. Fouda, Mohamed K. K. Saleh, Khalid M. M. Hosny
Summary: This study presents an accurate computer-aided-diagnosing system based on deep learning for detecting pelvis fractures. An explainable artificial intelligence (XAI) framework was constructed for pelvis fracture classification. The model was trained using a dataset of 876 X-ray images, achieving 98.5% accuracy, sensitivity, specificity, and precision.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Information Systems
Khalid M. Hosny, Ahmed I. Awad, Marwa M. Khashaba, Ehab R. Mohamed
Summary: Computational offloading allows lightweight battery-operated devices to send computation tasks to nearby edge servers. This paper proposes an improved Gorilla Troops Algorithm (IGTA) to offload dependent tasks in the multi-access edge computing (MEC) environments. IGTA aims to minimize execution latency, energy consumption, and cost usage. It outperforms other optimizers by reducing latency by 33%, energy consumption by 93%, and cost usage by 34.5%.
JOURNAL OF GRID COMPUTING
(2023)
Article
Computer Science, Information Systems
Sondos Fadl, Khalid M. Hosny, Mohamed Hammad
Summary: This paper proposes a novel method for automatically detecting altered handwritten documents and locating the fake part. It uses a digitally scanned version of the document to identify the forged document, and applies color histograms and structural similarity index (SSIM) to detect the forged parts. The experimental results demonstrate its high performance in identifying and localizing foreign ink in handwritten documents.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2023)
Article
Computer Science, Artificial Intelligence
Asmaa M. M. Khalid, Hanaa M. M. Hamza, Seyedali Mirjalili, Khaid M. M. Hosny
Summary: A new multi-objective Coronavirus disease optimization algorithm (MOCOVIDOA) is proposed for solving global optimization problems with up to three objective functions. The algorithm uses an archive to store non-dominated POSs during the optimization process. A roulette wheel selection mechanism is utilized to select effective archived solutions by simulating the frameshifting technique Coronavirus particles use for replication. The efficiency is evaluated by solving twenty-seven multi-objective problems and comparing the results with five common multi-objective metaheuristics using six evaluation metrics. The obtained results and the Wilcoxon rank-sum test demonstrate the superiority of this novel algorithm and its applicability in solving multi-objective problems.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Ahmed A. Akl, Khalid M. Hosny, Mostafa M. Fouda, Ahmad Salah
Summary: COVID-19 is a highly infectious disease that can be detected using machine learning and deep learning models from computerized chest CT scans. Deep learning models outperform machine learning models in this task. The performance of the models is evaluated based on the quality of feature extraction and classification accuracy. This work includes four contributions: comparing end-to-end deep learning models with using deep learning for feature extraction and machine learning for classification, studying the fusion of features from image descriptors with features from deep learning models, training a new convolutional neural network from scratch and comparing it with deep transfer learning, and studying the performance gap between classic machine learning models and ensemble learning models. The proposed framework is evaluated using a CT dataset and achieves a best accuracy rate of 99.39%.
Article
Medicine, General & Internal
Soaad M. Naguib, Hanaa M. Hamza, Khalid M. Hosny, Mohammad K. Saleh, Mohamed A. Kassem
Summary: Cervical spine fractures or dislocations are serious medical emergencies with potential severe consequences. This paper proposes a deep learning-based computer-aided-diagnosis system for classifying these injuries. The system aims to support physicians in diagnosing cervical spine injuries, especially in emergency services. The results show high accuracy, sensitivity, specificity, and precision. The work targets both research and clinical purposes, with the designed software being potentially useful in emergency situations.
Article
Computer Science, Hardware & Architecture
Khalid M. Hosny, Ahmed I. Awad, Marwa M. Khashaba, Mostafa M. Fouda, Mohsen Guizani, Ehab R. Mohamed
Summary: This research paper investigates Mobile Edge Computing (MEC) networks and aims to determine whether to process each user task locally on the device or to offload and process it on one of the nearby MEC servers or the central cloud server. The paper proposes an enhanced multi-objective version of the Gorilla Algorithm (EMGA) for offloading interdependent tasks in edge-cloud environments, with objectives of reducing execution latency, lowering energy consumption, and minimizing cost.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2023)
Article
Chemistry, Analytical
Asmaa M. Khalid, Doaa Sami Khafaga, Eman Abdullah Aldakheel, Khalid M. Hosny
Summary: This paper proposes an algorithm based on COVIDOA and SA for feature selection in the HAR process. Through comparison with other feature selection algorithms, the results show that the proposed method performs well in accuracy and feature selection.
Article
Engineering, Multidisciplinary
Mohamed Meselhy Eltoukhy, Ayman E. Khedr, Mostafa M. Abdel-Aziz, Khalid M. Hosny
Summary: This paper proposes a new robust watermarking method that combines Slant, Singular Value Decomposition (SVD), and quaternion Fourier-Transform (QFT) for securing color medical images. The method involves splitting the input image into four parts, encrypting them using OTP encryption, applying Slant transform for compaction, applying SVD for quality preservation, and applying QFT for imperceptibility. The proposed method achieves a good tradeoff between invisibility and robustness compared to existing schemes, and attains high visual imperceptibility.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Computer Science, Information Systems
Mohamed Gabr, Rimon Elias, Khalid M. Hosny, George A. Papakostas, Wassim Alexan
Summary: This research work proposes a new symmetric, secure and robust image encryption method by hybridizing chaotic functions and a Memristor circuit to generate pseudo-random numbers for encryption keys and substitution boxes. Different logical and arithmetic operations are used for data diffusion, and multiple S-boxes of varying base-n are generated and utilized for data confusion in a parallel fashion. The computed results demonstrate the superior capabilities of the proposed image encryption technique against various attacks.
Review
Computer Science, Information Systems
Khalid M. M. Hosny, Doaa Elshoura, Ehab R. R. Mohamed, Eleni Vrochidou, George A. A. Papakostas
Summary: Skin cancer, a major public health issue, can benefit from computer-aided diagnosis to reduce the burden of this common disease. Researchers are motivated to develop computer-aided diagnosis systems due to the time-consuming nature of visual examination. Skin lesion segmentation is crucial in the analysis process, but it is a challenging task due to color similarities and unclear borders. Various studies have tackled this issue, but there is a need for new methodologies to enhance efficiency.
Article
Computer Science, Information Systems
Khalid M. Hosny, Mohamed A. Zaki, Nabil A. Lashin, Mostafa M. Fouda, Hanaa M. Hamza
Summary: Considering the reliance on digital technology in modern society, protecting multimedia through encryption is crucial. Multimedia encryption-based security techniques are increasingly important for secure sharing of multimedia content on digital platforms. This survey aims to review the current state of encryption schemes applicable to digital multimedia, such as images, videos, and audio, in order to understand their effectiveness and contribute to future development of efficient and secure encryption schemes.
Article
Computer Science, Information Systems
Khalid. M. M. Hosny, Walaa. M. M. El-Hady, Farid. M. M. Samy, Eleni Vrochidou, George. A. A. Papakostas
Summary: Plant diseases are a major cause of reduced agricultural production quantity and quality. This study proposes a lightweight deep convolutional neural network model for accurate classification and detection of plant leaf diseases. The model combines deep features and traditional handcrafted local binary pattern features to capture local texture information in plant leaf images. Experimental results on three datasets show high validation and test accuracies, indicating the effectiveness of the proposed approach in providing better control solutions for plant diseases.
Article
Mathematics, Interdisciplinary Applications
Eman Abdullah Aldakheel, Doaa Sami Khafaga, Islam S. Fathi, Khalid M. Hosny, Gaber Hassan
Summary: The paper introduces a new method for calculating FrGLMs, reducing computational time and replacing the QR decomposition technique with the Schwarz-Rutishauser algorithm. The proposed method is accurate, simple, and fast for processing large signals and shows significant superiority in experiments.
FRACTAL AND FRACTIONAL
(2023)
Article
Engineering, Electrical & Electronic
Alam Abbas Syed, Hassan Foroosh
Summary: This paper presents effective methods using spherical polar Fourier transform data for two different applications: 3D volumetric registration and machine learning classification network. The proposed method for registration offers unique and effective techniques, handling arbitrary large rotation angles and showing robustness. The modified classification network achieves robust classification results in processing spherical data.
Article
Engineering, Electrical & Electronic
Ruibo Fan, Mingli Jing, Jingang Shi, Lan Li, Zizhao Wang
Summary: In this study, a new low-rank sparse decomposition algorithm named TVRPCA+ is proposed for foreground-background separation. The algorithm combines spectral norm, structured sparse norm, and total variation regularization to suppress noise and obtain cleaner foregrounds. Experimental results demonstrate that TVRPCA+ achieves high performance in complex backgrounds and noise scenarios.
Article
Engineering, Electrical & Electronic
Omair Aldimashki, Ahmet Serbes
Summary: This paper proposes a coarse-to-fine FrFT-based algorithm for chirp-rate estimation of multi-component LFM signals, which achieves improved performance and a reduced signal-to-noise breakdown threshold by utilizing mathematical models for coarse estimation and a refined estimate-and-subtract strategy. Extensive simulation results demonstrate that the proposed algorithm performs very close to the Cramer-Rao lower bound, with the advantages of eliminating leakage effect, avoiding error propagation, and maintaining acceptable computational cost compared to other state-of-the-art methods.
Article
Engineering, Electrical & Electronic
Xinlei Shi, Xiaofei Zhang, Yuxin Sun, Yang Qian, Jinke Cao
Summary: In this paper, a low-complexity localization approach for multiple sources using two-dimensional discrete Fourier transform (2D-DFT) is proposed. The method computes the cross-covariance and utilizes phase offset method and total least square solution to obtain accurate position estimates.
Article
Engineering, Electrical & Electronic
Prabhanjan Mannari, Ratnasingham Tharmarasa, Thiagalingam Kirubarajan
Summary: This paper discusses the problem of extended target tracking for a single 2D extended target with a known convex polytope shape and dynamics. It proposes a framework based on the existing point multitarget tracking framework to address the challenges of uncertainty in shape and kinematics, as well as self-occlusion. The algorithm developed using this framework is capable of dynamically changing the number of parameters used to describe the shape and estimating the whole target shape even when different parts of the target are visible at different frames.
Article
Engineering, Electrical & Electronic
Yongsong Li, Zhengzhou Li, Jie Li, Junchao Yang, Abubakar Siddique
Summary: This paper proposes a weighted adaptive ring top-hat transformation (WARTH) for extracting infrared small targets in complex backgrounds. The WARTH method effectively measures local and global feature information using an adaptive ring-shaped structural element and a target awareness indicator, resulting in accurate detection of small targets with minimized false alarms.
Article
Engineering, Electrical & Electronic
Yu Wang, Zhen Qin, Jun Tao, Yili Xia
Summary: In this paper, an enhanced sparsity-aware recursive least squares (RLS) algorithm is proposed, which combines the proportionate updating (PU) and zero-attracting (ZA) mechanisms, and introduces a general convex regularization (CR) function and variable step-size (VSS) technique to improve performance.
Article
Engineering, Electrical & Electronic
Neil J. Bershad, Jose C. M. Bermudez
Summary: This paper analyzes the impact of processing delay on the Least Mean Squares (LMS) algorithm in system identification, highlighting bias issues in the resulting weight vector.
Article
Engineering, Electrical & Electronic
Kanghui Jiang, Defu Jiang, Mingxing Fu, Yan Han, Song Wang, Chao Zhang, Jingyu Shi
Summary: In this paper, a novel method for velocity estimation using multicarrier signals in a single dwell is proposed, which effectively addresses the issue of Doppler ambiguity in pulse Doppler radars.
Article
Engineering, Electrical & Electronic
Xiao-Jun Zhang, Peng-Lang Shui, Yu-Fan Xue
Summary: This paper proposes a method for low-velocity small target detection in maritime surveillance radars. It models sea clutter sequences using the spherical invariant random vector (SIRV) model with block tridiagonal speckle covariance matrix and inverse Gamma distributed texture. The proposed detector, which is a long-time adaptive generalized likelihood ratio test with linear threshold detector (GLRT-LTD), shows competitive detection performance in experiments.
Article
Engineering, Electrical & Electronic
Aiyi Zhang, Fulai Liu, Ruiyan Du
Summary: This paper proposes an adaptive weighted robust data recovery method with total variation regularization for hyperspectral image. The method models the HSI recovery problem as a tensor robust principal component analysis optimization problem, decomposing the data into low-rank HSI data, outliers, and noise component. An adaptive weighted strategy is then defined to impose on the tensor nuclear norm and outliers, using the priori information of singular values and strengthening the sparsity of outliers.
Article
Engineering, Electrical & Electronic
Hamid Asadi, Babak Seyfe
Summary: This paper presents a novel approach for estimating the model order in the presence of observation errors. The proposed method is based on correntropy estimation of eigenvalues in the observation space, which is further enhanced by resampling the observations using the bootstrap method. The algorithm partitions the observation space into signal and noise subspaces using the covariance matrix of mixtures, and determines the model order based on a correntropy estimator with kernel functions. Theoretical analysis and comparative evaluations demonstrate the superiority of this information-theoretic approach.
Article
Engineering, Electrical & Electronic
Buket colak Guvenc, Engin Cemal Menguc
Summary: In this paper, a novel family of online censoring based complex-valued least mean kurtosis (CLMK) algorithms is proposed. The algorithms censor less informative complex-valued data streams and reduce the costs of data processing without affecting accuracy. Robust algorithms are also developed to handle outliers. The simulation results confirm the attractive features of the proposed algorithms in large-scale system identification and regression scenarios.
Article
Engineering, Electrical & Electronic
Yun Su, Weixian Tan, Yifan Dong, Wei Xu, Pingping Huang, Jianxin Zhang, Diankun Zhang
Summary: In this study, a novel method for detecting low-resolution and small targets in millimeter wave radar images is proposed. The Wavelet-Conv structure and Wavelet-Attention mechanism are introduced to overcome the limitations of existing detectors. Experimental results demonstrate that the proposed method improves recall and mean average precision while maintaining competitive inference speed.
Article
Engineering, Electrical & Electronic
Xin Wang, Xingxing Jiang, Qiuyu Song, Jie Liu, Jianfeng Guo, Zhongkui Zhu
Summary: This study proposes a variational mode extraction (VME) method for extracting specific modes from complicated signals. By exploring the convergence property of VME, strategies for identifying ICF and determining the balance parameter are designed, and a bandwidth estimation strategy is constructed. The effectiveness of the proposed method for bearings fault diagnosis is verified and compared with other methods.