检索结果-内蒙古大学图书馆

An enhanced Walrus Optimizer with opposition-based learning and mutation strategy for data clustering

学校读者我要写书评

暂无评论

Array 2025年 26卷

作者： Abualigah, Laith Alomari, Saleh Ali Almomani, Mohammad H. Zitar, Raed Abu Migdady, Hazem Saleem, Kashif Smerat, Aseel Snasel, Vaclav Ezugwu, Absalom E. Computer Science Department Al al-Bayt University Mafraq25113 Jordan Faculty of Science and Information Technology Jadara University Irbid21110 Jordan Department of Mathematics Facility of Science The Hashemite University P.O box 330127 Zarqa13133 Jordan Faculty of Engineering and Computing Liwa College Abu Dhabi United Arab Emirates CSMIS Department Oman College of Management and Technology Barka320 Oman Department of Computer Science & Engineering College of Applied Studies & Community Service King Saud University Riyadh11362 Saudi Arabia Faculty of Educational Sciences Al-Ahliyya Amman University Amman19328 Jordan Computer Technologies Engineering Mazaya University College Nasiriyah Iraq Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Poruba-Ostrava 70800 Czech Republic Unit for Data Science and Computing North-West University 11 Hofman Street Potchefstroom2520 South Africa

data clustering plays a crucial role in various domains, such as image processing, pattern recognition, and data mining. Traditional clustering techniques often suffer from limitations like sensitivity to initialization, poor convergence, and entrapment in local optima. To address these challenges, this paper proposes an Enhanced Walrus Optimizer (IWO) tailored for clustering tasks. The proposed IWO integrates two powerful strategies–Opposition-Based Learning (OBL) and Mutation Search Strategy (MSS)–to improve population diversity and prevent premature convergence, thereby enhancing both exploration and exploitation capabilities. These enhancements enable more accurate and stable identification of cluster centers. The effectiveness of IWO is validated through extensive experiments on multiple benchmark clustering datasets and compared against several state-of-the-art metaheuristic algorithms, including PSO, GWO, AOA, and others. The results demonstrate that IWO achieves better results, indicating improved compactness and separation of clusters. Statistical validation using p-values and ranking scores further confirms the superiority of the proposed method. These findings suggest that IWO offers a robust and flexible framework for solving complex clustering problems. Future work will explore hybrid deep learning-integrated models and parallel implementations to enhance scalability. © 2025

关键词： Swarm intelligence

Future of Cybersecurity

学校读者我要写书评

暂无评论

Future of Cybersecurity

Recent Trends in Information Technology (CSCTIT), College of science International Conference of

作者： Yasamin Alagrash Senior lecturer in the computer science department college of science Mustansiriyah University Baghdad Iraq Department of computer science Ph.D. in computer science and informatics college of engineering Oakland university MI USA Computer science department MSC in data security university of technology Baghdad Iraq

Cybersecurity is critical to the digital world's ongoing progress. Whether you are a company owner or a customer, you must be prepared to adapt to new technology, policies, and methods that will aid in the creation of a safer and more secure online environment. As a result, the frequency of exposed network surfaces compels us to invest in more advanced protection measures.

关键词：

VULSEYE: Detect Smart Contract Vulnerabilities via Stateful Directed Graybox Fuzzing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liang, Ruichao Chen, Jing Wu, Cong He, Kun Wu, Yueming Cao, Ruochen Du, Ruiying Liu, Yang Zhao, Ziming Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan430072 China Cyber Security Lab College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science and Engineering University at Buffalo New York United States

Smart contracts, the cornerstone of decentralized applications, have become increasingly prominent in revolutionizing the digital landscape. However, vulnerabilities in smart contracts pose great risks to user assets and undermine overall trust in decentralized systems. Fuzzing, a prominent security testing technique, is extensively explored to detect vulnerabilities. But current smart contract fuzzers fall short of expectations in testing efficiency for two primary reasons. Firstly, smart contracts are stateful programs, and existing approaches, primarily coverage-guided, lack effective feedback from the contract state. Consequently, they struggle to effectively explore the contract state space. Secondly, coverage-guided fuzzers, aiming for comprehensive program coverage, may lead to a wastage of testing resources on benign code areas. This wastage worsens in smart contract testing, as the mix of code and state spaces further complicates comprehensive testing. To address these challenges, we propose VULSEYE, a stateful directed graybox fuzzer for smart contracts guided by vulnerabilities. Different from prior works, VULSEYE achieves stateful directed fuzzing by prioritizing testing resources to code areas and contract states that are more prone to vulnerabilities. We introduce Code Targets and State Targets into fuzzing loops as the testing targets of VULSEYE. We use static analysis and pattern matching to pinpoint Code Targets, and propose a scalable backward analysis algorithm to specify State Targets. We design a novel fitness metric that leverages feedback from both the contract code space and state space, directing fuzzing toward these targets. With the guidance of code and state targets, VULSEYE alleviates the wastage of testing resources on benign code areas and achieves effective stateful fuzzing. In comparison with state-of-the-art fuzzers, VULSEYE demonstrated superior effectiveness and efficiency. Notably, it uncovered 4,845 vulnerabilities in 42,738 rea

关键词： Software testing

Robust MIMO-OFDM Channel Estimation for 5G Networks Using Conditional Self-Attention GANs

学校读者我要写书评

暂无评论

Robust MIMO-OFDM Channel Estimation for 5G Networks Using Co...

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： K. Aravinda Tejaswini Rangaraju Atul Singla Ashish Parmar Ali Abdulhussein Hameed Electronics and Communication Engineering New Horizon College of Engineering Bangalore India Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering Hyderabad India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Greater Noida Uttar Pradesh Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Due to the rapid increase in Mobile networks data traffic, there is a need to improve on channel estimation methods for Multiple Input Multiple Output (MIMO) system that combined with the Orthogonal Frequency Division Multiplexing (OFDM) relevant to 5G and future generations. The papers introduced in this research present a novel method that is based on the use of Conditional Self-Attention Generative Adversarial Networks (CSAGANs) to improve the channel estimation. CSAGANs combine the generative adversarial network (GAN) that has the function of generating high quality synthetic image with long-range dependencies and self-attention mechanisms that enable Identify the dependencies of MIMO-OFDM channels. The conditioned aspect maintains that the estimated sources satisfy realistic conditions in the channels, which enhances the solutions' accuracy and robustness. Experimental outcomes also prove that in terms of MSE and BER, proposed methodology exhibits better performance as compared to conventional techniques like LS and MMSE. This means that the proposed method provides higher efficiency in cases where there are mobile nodes and constantly changing SNR as in the case of 5G technology. Moreover, it is revealed that the CSAGAN framework can effectively decrease computational costs which is why it can be applicable for real-time tasks. This work opens up avenues for developing more robust and accurate channel estimation schemes, which are required for the evolution of the forth coming wireless communication systems.

关键词： Accuracy 5G mobile communication OFDM Channel estimation Estimation Generative adversarial networks MIMO Mathematical models Computational complexity Signal to noise ratio

Generating CGAN-based Synthetic Dermoscopy Images and Classifying with Deep Lightweight CNN

学校读者我要写书评

暂无评论

Generating CGAN-based Synthetic Dermoscopy Images and Classi...

Computing, Networking, Telecommunications & engineering sciences Applications (CoNTESA), International Conference on

作者： Suriya Sultana Israt Yasmin Muhammed J. A. Patwary Mohammad Arif Sobhan Bhuiyan Iftekhar Salam Mahdi H. Miraz Department of Computer Science and Engineering International Islamic University Chittagong School of Electrical and Electronic Engineering Xiamen University Malaysia Sepang Malaysia School of Computing and Data Science (SCDS) Xiamen University Malaysia Sepang Malaysia

Effective dermatological diagnosis and treatments significantly depend on the accurate categorisation of the skin lesions. It is difficult to classify skin lesions using automated diagnostic techniques due to class-imbalance datasets and the absence of labelled data. The applications of various deep learning methods have demonstrated superior performance in medical diagnosis in the recent past. Unfortunately, training these models requires a substantial quantity of labelled instances. A novel approach, combining Deep Learning convolutional neural networks (CNNs) as well as conditional generative adversarial networks (CGANs), for classifying skin lesion images, has been presented in this study. CGAN is an enhanced version of the GAN, in which the generator takes input images with specific class labels. Applying conditions for minority classes can help to equalise the dataset by increasing the sample size for those minority classes. In this research, CGANs were used to produce synthetic images of minority classes for a skin lesion dataset named PAD UFES-20. The images generated from CGANS were added then to the original dataset to train a lightweight deep-learning CNN network named MobileNetv2. The analysis of the results shows an improvement of 6% average accuracy and 5% recall value, when the synthetic data augmentation was added to the original dataset. This synthetic data augmentation approach can also widely be used in various medical classification applications to reduce the imbalance problems, resulting in enhanced diagnosis.

关键词：

Regularized Newton Methods for Monotone Variational Inequalities with Hölder Continuous Jacobians

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Chengchang Luo, Luo Department of Computer Science and Engineering The Chinese Unversity of Hong Kong Hong Kong School of Data Science Fudan University China

This paper considers the problems of solving monotone variational inequalities with Hölder continuous Jacobians. By employing the knowledge of Hölder parameter ν, we propose the ν-regularized extra-Newton method within at most O(ǫ−2/(2+ν)) iterations to obtain an ǫ-accurate solution. In the case of ν is unknown, we propose the universal regularized extra-Newton method within O(ǫ−4/(3(1+ν))) iteration complexity. © 2022, CC BY.

关键词： Newton-Raphson method

Unsupervised Cardiac Segmentation Utilizing Synthesized Images from Anatomical Labels

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Sihan Wu, Fuping Li, Lei Gao, Zheyao Hong, Byung-Woo Zhuang, Xiahai School of Data Science Fudan University Shanghai China Institute of Biomedical Engineering University of Oxford Oxford United Kingdom Computer Science Department Chung-Ang University Seoul Korea Republic of

Cardiac segmentation is in great demand for clinical practice. Due to the enormous labor of manual delineation, unsupervised segmentation is desired. The ill-posed optimization problem of this task is inherently challenging, requiring well-designed constraints. In this work, we propose an unsupervised framework for multi-class segmentation with both intensity and shape constraints. Firstly, we extend a conventional non-convex energy function as an intensity constraint and implement it with U-Net. For shape constraint, synthetic images are generated from anatomical labels via image-to-image translation, as shape supervision for the segmentation network. Moreover, augmentation invariance is applied to facilitate the segmentation network to learn the latent features in terms of shape. We evaluated the proposed framework using the public datasets from MICCAI2019 MSCMR Challenge, and achieved promising results on cardiac MRIs with Dice scores of 0.5737, 0.7796, and 0.6287 in Myo, LV, and RV, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Heart

Deep Perspective Transformation Based Vehicle Localization on Bird’s Eye View

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mahyar, Abtin Motamednia, Hossein Rahmati, Dara Department of Computer and Data Sciences Shahid Beheshti University Tehran Iran High Performance Computing Laboratory School of Computer Science Institute for Research in Fundamental Sciences Tehran Iran Faculty of Computer Science and engineering Shahid Beheshti University Tehran Iran

An accurate understanding of a self-driving vehicle’s surrounding environment is crucial for its navigation system. To enhance the effectiveness of existing algorithms and facilitate further research, it is essential to provide comprehensive data to the routing system. Traditional approaches rely on installing multiple sensors to simulate the environment, leading to high costs and complexity. In this paper, we propose an alternative solution by generating a top-down representation of the scene, enabling the extraction of distances and directions of other cars relative to the ego vehicle. We introduce a new synthesized dataset that offers extensive information about the ego vehicle and its environment in each frame, providing valuable resources for similar downstream tasks. Additionally, we present an architecture that transforms perspective view RGB images into bird’s-eye-view maps with segmented surrounding vehicles. This approach offers an efficient and cost-effective method for capturing crucial environmental information for self-driving cars. 1 © 2023, CC BY.

关键词： Birds

Semi-Supervised Video Inpainting with Cycle Consistency Constraints

学校读者我要写书评

暂无评论

Semi-Supervised Video Inpainting with Cycle Consistency Cons...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhiliang Wu Hanyu Xuan Changchang Sun Weili Guan Kang Zhang Yan Yan School of Computer Science and Engineering Nanjing University of Science and Technology China School of Big Data and Statistics Anhui University China Department of Computer Science Illinois Institute of Technology USA School of Information Technology Monash University Australia Peng Cheng Laboratory China

Deep learning-based video inpainting has yielded promising results and gained increasing attention from re-searchers. Generally, these methods assume that the cor-rupted region masks of each frame are known and easily ob-tained. However, the annotation of these masks are labor-intensive and expensive, which limits the practical application of current methods. Therefore, we expect to relax this assumption by defining a new semi-supervised inpainting setting, making the networks have the ability of completing the corrupted regions of the whole video using the anno-tated mask of only one frame. Specifically, in this work, we propose an end-to-end trainable framework consisting of completion network and mask prediction network, which are designed to generate corrupted contents of the current frame using the known mask and decide the regions to be filled of the next frame, respectively. Besides, we introduce a cycle consistency loss to regularize the training parameters of these two networks. In this way, the completion network and the mask prediction network can constrain each other, and hence the overall performance of the trained model can be maximized. Furthermore, due to the natural existence of prior knowledge (e.g., corrupted contents and clear bor-ders), current video inpainting datasets are not suitable in the context of semi-supervised video inpainting. Thus, we create a new dataset by simulating the corrupted video of real-world scenarios. Extensive experimental results are reported to demonstrate the superiority of our model in the video inpainting task. Remarkably, although our model is trained in a semi-supervised manner, it can achieve compa-rable performance as fully-supervised methods.

关键词：