检索结果-内蒙古大学图书馆

A hybrid gazelle optimization and reptile search algorithm for optimal clustering in wireless sensor networks

Scientific Reports 2025年第1期15卷 1-33页

作者： Elashry, Soha S. Abohamama, A.S. Abdul-Kader, Hatem Mohamed Rashad, M.Z. Ali, Ahmed F. Department of Computer Science Faculty of Computers and Information Mansoura University Mansoura Egypt Department of Information System Faculty of Computers and Information Menofia University Shebien El Koum Egypt Faculty of Information Technology and Computer Science Sinai University Kantara Egypt Department of Computer Science Arab East Colleges Riyadh Saudi Arabia Department of Computer Science Faculty of Computers and Informatics Suez Canal University Ismailia Egypt

In our modern societies, the wireless sensor network (WSN) is categorized as a smart motivated technology that can be utilized in many work environments and activities to enhance daily life. However, several challenging concerns have been assigned to WSN. The clustering process is a main complex concern and still an open problem in WSN. To support an efficient clustering process, two crucial requirements must be considered, energy management and network lifetime extension, especially in the development of large-scale WSN. The primary objective of this article is to introduce a new meta-heuristic algorithm, denoted as the hybrid gazelle optimization and reptile search algorithm (HGORSA), which optimizes cluster head selection in WSNs. In the proposed algorithm, the mathematical models for the exploration and exploitation phases of the traditional gazelle optimization algorithm (GOA) are enhanced by integrating the hunting operator, reduction function, and predator cumulative effect operators from the traditional RSA. These modifications improve the balance between diversification and intensification processes, effectively addressing two key clustering requirements mentioned above. At the same time, they also positively impact the overall performance evaluation of the WSN. Various simulation scenarios are designed to evaluate the performance of the proposed HGORSA in different network configurations. First, the main experiment was conducted with 300 sensor nodes (SNs). The experimental results then analyzed to assess the effectiveness of the proposed algorithm under different conditions against six state-of-the-art meta-heuristic algorithms. Based on simulation outputs, HGORSA demonstrated superior performance compared to particle swarm optimization, grey Wolf optimizer, sperm swarm optimization, chernobyl disaster optimizer, gazelle optimization algorithm and reptile search algorithm. Specifically, HGORSA achieved percentage improvements in terms of stability period

关键词： Clustering Energy consumption Gazelle Optimization Algorithm (GOA) Meta-heuristics Network lifetime Reptile Search Algorithm (RSA) Wireless sensor network (WSN)

来源：评论

学校读者我要写书评

暂无评论

Nafion edge passivation and nitrogen annealing treatment to improve solar cell reliability under light and elevated temperature induced degradation (LeTID) investigation

引用

Current Applied Physics 2025年 75卷 1-7页

作者： Jony, Jaljalalul Abedin Yousuf, Hasnain Khokhar, Muhammad Quddamah Zahid, Muhammad Aleem Madara, Polgampola Chamani Rahman, Rafi Ur Alamgeer Chu, Mengmeng Sanyal, Simpy Wang, Fucheng Kim, Youngkuk Kim, Kyesoo Dhungel, Suresh Kumar Park, Sangheon Yi, Junsin Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Gyeonggi-do Suwon16419 Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Gyeonggi-do Suwon16419 Korea Republic of University Tamilnadu 600124 India Research Institute for Clean Energy College of Information and Communication Engineering Sungkyunkwan University Gyeonggi-do Suwon16419 Korea Republic of Faculty of Technology Nepal Academy of Science and Technology 3323 Khumaltar Lalitpur Nepal

This research examines the effectiveness of nitrogen annealing and Nafion treatment in mitigating Light and Elevated Temperature Induced Degradation (LeTID) in Passivated Emitter and Rear Contact (PERC) solar cells, employing a 30-kW photovoltaic (PV) system for evaluation. As a photosensitive device, solar cells are susceptible to damage from laser irradiation, leading to reduced photoelectric conversion efficiency, structural damage, and functional loss. To minimize this loss, nitrogen annealing and Nafion treatments were applied, followed by the analysis of LeTID effects on untreated, Nafion-treated, and combined nitrogen-annealed and Nafion-treated PERC cells. Untreated cells showed an 8 % fall in open-circuit voltage (Voc) and a 7 % fill factor (FF) loss. The combined treatment (Combination of Nitrogen & Nafion Treatment) improved stability, reducing losses to 6 % in Voc and 5 % in FF. The Nafion treatment yielded the best results, limiting deterioration to 4 % in Voc and 3 % in FF. PVsyst simulations, incorporating real-world data, confirmed enhanced stability and efficiency, aiding in optimizing PV system design and maintenance. © 2025 Korean Physical Society

关键词： Annealing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Stroke Prediction in Smart Healthcare:Integrating Fuzzy K-Nearest Neighbor and Artificial Neural Networks with Feature Selection Techniques

引用

computers, Materials & Continua 2025年第3期82卷 5115-5134页

作者： Abdul Ahad Ira Puspitasari Jiangbin Zheng Shamsher Ullah Farhan Ullah Sheikh Tahir Bakhsh Ivan Miguel Pires Department Information System Study Program Faculty of Science and TechnologyUniversitas AirlanggaSurabaya60286Indonesia School of Software Northwestern Polytechnical UniversityXi’an710072China Research Center for Quantum Engineering Design Faculty of Science and TechnologyUniversitas AirlanggaSurabaya60286Indonesia School of Computer Science and Software Engineering Shenzhen UniversityShenzhen518061China Cybersecurity Center Prince Mohammad Bin Fahd University617Al JawharahKhobarDhahran34754Saudi Arabia Cardiff School of Technologies Cardiff Metropolitan UniversityWestern AvenueCardiffCF52YBUK Instituto de Telecomunicacoes Escola Superior de Tecnologia e Gestao de AguedaUniversidade de Aveiroágueda3750-127Portugal

This research explores the use of Fuzzy K-Nearest Neighbor(F-KNN)and Artificial Neural Networks(ANN)for predicting heart stroke incidents,focusing on the impact of feature selection methods,specifically Chi-Square and Best First Search(BFS).The study demonstrates that BFS significantly enhances the performance of both *** BFS preprocessing,the ANN model achieved an impressive accuracy of 97.5%,precision and recall of 97.5%,and an Receiver Operating Characteristics(ROC)area of 97.9%,outperforming the Chi-Square-based ANN,which recorded an accuracy of 91.4%.Similarly,the F-KNN model with BFS achieved an accuracy of 96.3%,precision and recall of 96.3%,and a Receiver Operating Characteristics(ROC)area of 96.2%,surpassing the performance of the Chi-Square F-KNN model,which showed an accuracy of 95%.These results highlight that BFS improves the ability to select the most relevant features,contributing to more reliable and accurate stroke *** findings underscore the importance of using advanced feature selection methods like BFS to enhance the performance of machine learning models in healthcare applications,leading to better stroke risk management and improved patient outcomes.

关键词： Fuzzy K-nearest neighbor artificial neural network accuracy precision recall F-measure Chi-Square best search first heart stroke

来源：评论

学校读者我要写书评

暂无评论

A q-learning approach for enhanced routing in dynamic LEO satellite networks

引用

Egyptian Journal of Remote Sensing and Space science 2025年第2期28卷 272-279页

作者： Riyad, Ahmed E. Mokhtar, Medhat Belal, Mohamed A. Bahloul, Mahmoud Mohamed Department of Information System El-Obour Institutes Egypt National Authority for Remote Sensing and Space Sciences Egypt Computer Science Faculty of Computing & Artificial Intelligence Helwan University 6 October Technology University Cairo Egypt Business Information Systems Business Information Systems Department Faculty of Commerce and Business Administration Helwan University Cairo Egypt

As global communication demand rises, Low Earth Orbit (LEO) satellite systems offer high-speed data transmission and extensive coverage options but face routing challenges due to dynamic topologies. This paper introduces a Q-Learning-based routing approach that converts dynamic networks into virtually static topologies at different snapshot intervals. Simulation results on a 66-satellite Starlink constellation demonstrate that Q-Learning outperforms Dijkstra's algorithm, achieving faster convergence and reduced latency. These findings highlight the potential for Q-Learning in enhancing efficient, cost-effective satellite communications. © 2025 The Authors

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology SydneyNSW2007 Australia Institute of Software Chinese Academy of Sciences Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 1982-2012 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

HYBRID FIREFLY ALGORITHM AND SPERM SWARM OPTIMIZATION ALGORITHM USING NEWTON-RAPHSON METHOD (HFASSON) AND ITS APPLICATION IN CR-VANET

arXiv

引用

arXiv 2025年

作者： Rehannara Beegum, T. Idris, Mohd Yamani Idna Ayub, Mohamad Nizam Bin Shehadeh, Hisham A. Ali, Usman Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia Department of Information Technology Al-Huson University College Al-Balqa Applied University Al-Huson Jordan Department of Computer and Software Technology University of Swat KPK Pakistan

This paper proposes a new hybrid algorithm, combining FA, SSO, and the N-R method to accelerate convergence towards global optima, named the Hybrid Firefly Algorithm and Sperm Swarm Optimization with Newton-Raphson (HFASSON). The performance of HFASSON is evaluated using 23 benchmark functions from the CEC 2017 suite, tested in 30, 50, and 100 dimensions. A statistical comparison is performed to assess the effectiveness of HFASSON against FA, SSO, HFASSO, and five hybrid algorithms: Water Cycle Moth Flame Optimization (WCMFO), Hybrid Particle Swarm Optimization and Genetic Algorithm (HPSOGA), Hybrid Sperm Swarm Optimization and Gravitational Search Algorithm (HSSOGSA), Grey Wolf and Cuckoo Search Algorithm (GWOCS), and Hybrid Firefly Genetic Algorithm (FAGA). Results from the Friedman rank test show the superior performance of HFASSON. Additionally, HFASSON is applied to Cognitive Radio Vehicular Ad-hoc Networks (CR-VANET), outperforming basic CR-VANET in spectrum utilization. These findings demonstrate HFASSON’s efficiency in wireless network applications. © 2025, CC BY.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Mapping Shallot in Lowland Areas Through Sentinel-2 Imagery and Machine Learning Approach 10th

Mapping Shallot in Lowland Areas Through Sentinel-2 Imagery ...

引用

10th International Seminar of Aerospace science and Technology, ISAST 2024

作者： Arifandri, Robby Karolinoerita, Vicca Ramadhani, Fadhlullah Dirgahayu, Dede Devy, Lukita Habibie, Muhammad Iqbal Fanggidae, Yudi Riadi Dharmayanti Harahap, Robby Kurniawan Pratiwi, Swelandiah Endah Widiastuti Research Center for Artificial Intelligence and Cyber Security BRIN Bandung Indonesia Research Center for Geoinformatics BRIN Bandung Indonesia Research Center for Horticulture BRIN Cibinong Indonesia Research Center for Environmental and Clean Technology BRIN Tangerang Selatan Indonesia Research Center for Climate and Atmosphere BRIN Bandung Indonesia Faculty of Industrial Technology Gunadarma University Depok Indonesia Faculty of Computer Science and Information System Gunadarma University Depok Indonesia

ISBN: (纸本)9789819613434

As one of the staple horticultural crops, Shallot requires accurate monitoring to understand its cultivation better and to face environmental challenges in lowland regions. Nevertheless, there are still limited studies on mapping shallot agriculture using remote sensing data. In this study, we aimed to enhance the accuracy and efficiency of mapping shallot cultivation in lowland areas by leveraging high-resolution Sentinel-2 imagery combined with machine-learning techniques, specifically Random Forest, to classify the cultivation areas accurately. Preprocessed Sentinel-2 data using Google Earth Engine and validation data from field surveys and high-resolution satellite imagery inspection are utilized to create training and testing datasets for the machine learning model. Our findings reveal that the Random Forest model resulted in an Overall Accuracy of 88% and a total area of 12,121 hectares in July 2023. The proposed method can be used to estimate the planting and harvested area regularly to support smart-climate agriculture. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Guardian-AI: A novel deep learning based deepfake detection model in images

引用

Alexandria Engineering Journal 2025年 126卷 507-514页

作者： Alsolai, Hadeel Mahmood, Khalid Alshuhail, Asma Ben Miled, Achraf Alqahtani, Mohammed Alshareef, Abdulrhman Alallah, Fouad Shoie Alghamdi, Bandar M. Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University PO Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Department of Computer Science College of Science Northern Border University Arar73213 Saudi Arabia Department of Information System and Cyber Security College of Computing and Information Technology University of Bisha Bisha61922 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

The rapid advancement of deepfake technology has introduced significant challenges and opportunities across various domains. This article proposes a robust deepfake detection pipeline utilising a combination of attention mechanisms, pre-trained Vision Transformers (ViTs), and Long Short-Term Memory (LSTM) networks. The initial phase of the pipeline involves preparing photos and videos, potentially using optional facial detection to enhance accuracy. Vision Transformers derive features by capturing the global dependencies of input data. Long short-term memory (LSTM) networks address inter-frame temporal dependencies, whereas multi-head and traditional attention processes focus on essential elements. Ultimately, fully connected layers are employed for classification within the ensemble architecture, which consolidates the outcomes of several models. To ensure generalisability, assessment and regularisation approaches are employed to train the model using labelled datasets. Given the escalating threat of deepfakes, the findings indicate that the pipeline can consistently distinguish between genuine and fabricated information. © 2025 The Authors

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A novel Facial Recognition technique with Focusing on Masked Faces

arXiv

引用

arXiv 2025年

作者： Abdullah, Dana A. Hamad, Dana Rasul Beitollahi, Hakem Maolood, Ismail Y. Abdullah, Abdulhady Abas Ameen, Aso Khaleel - System Information Ministry of Higher Education and Scientific Research Department of Computer Science College of Science Knowledge University Erbil44001 Iraq Computer Science Department Faculty of Science Soran University Erbil Soran Iraq Artificial Intelligence and Innovation Centre University of Kurdistan Hewlêr Erbil Iraq

Recognizing the same faces with and without masks is important for ensuring consistent identification in security, access control, and public safety. This capability is crucial in scenarios like law enforcement, healthcare, and surveillance, where accurate recognition must be maintained despite facial occlusion. This research focuses on the challenge of recognizing the same faces with and without masks by employing cosine similarity as the primary technique. With the increased use of masks, traditional facial recognition systems face significant accuracy issues, making it crucial to develop methods that can reliably identify individuals in masked conditions. For that reason, this study proposed Masked-Unmasked Face Matching Model (MUFM). This model employs transfer learning using the Visual Geometry Group (VGG16) model to extract significant facial features, which are subsequently classified utilizing the K-Nearest Neighbors (K-NN) algorithm. The cosine similarity metric is employed to compare masked and unmasked faces of the same individuals. This approach represents a novel contribution, as the task of recognizing the same individual with and without a mask using cosine similarity has not been previously addressed. By integrating these advanced methodologies, the research demonstrates effective identification of individuals despite the presence of masks, addressing a significant limitation in traditional systems. Using data is another essential part of this work, by collecting and preparing an image dataset from three different sources especially some of those data are real provided a comprehensive power of this research. The image dataset used were already collected in three different datasets of masked and unmasked for the same faces. The current study provided %95 results of the used image dataset face recognition between masked and unmasked images. The results highlight the potential of this approach for enhancing accuracy in security and other applications wh

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Hybridization of deep learning models with crested porcupine optimizer algorithm-based cybersecurity detection on industrial IoT for smart city environments

引用

Alexandria Engineering Journal 2025年 127卷 239-250页

作者： Sarah A. Alzakari Mohammed Aljebreen Mashael M. Asiri Wahida MANSOURI Sultan Alahmari Mohammed Alqahtani Shaymaa Sorour Wafi Bedewi Department of Computer Sciences College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia Department of Computer Science Community College King Saud University P.O. Box 28095 Riyadh 11437 Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science and Information Technology Faculty of Sciences and arts Turaif Northern Border University Arar 91431 Saudi Arabia King Abdul Aziz City for Science and Technology (KACST) Cybersecurity Institute Riyadh Saudi Arabia Department of Information System and Cyber Security College of Computing and Information Technology University of Bisha Bisha 61922 Saudi Arabia Department of Management Information Systems School of Business King Faisal University Al-Ahsa 31982 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Smart cities have attracted extensive coverage from multidisciplinary studies, and many artificial intelligence (AI) solutions have been designed. Conversely, cybersecurity has constantly been a crucial issue and is becoming gradually dangerous in smart cities. The attack defence models are inappropriate for perceiving multistep assaults as the recognition rules are restricted, and efficacy is partial due to many false security alarms. Therefore, an innovative solution is immediately required to progress cybersecurity defence ability. Machine learning (ML) methods are commonly employed to recognize numerous attacks because they could help network administrators grab analogous initials to avert intrusion. This study presents Cybersecurity using a Crested Porcupine Optimizer Algorithm with Hybrid Deep Learning Models (CCPOA-HDLM). The foremost intention of this study is to improve cybersecurity detection and classification in smart city environments. To accomplish that, the CCPOA-HDLM method comprises distinct processes such as min-max normalization, improved Salp swarm algorithm (ISSA)-based feature selection, Multi-Channel Convolutional Neural Network - Recurrent Neural Network (MCNN-RNN)-based cybersecurity detection, and crested porcupine optimizer (CPO)-based parameter selection process. Primarily, data normalization utilizing min-max normalization is implemented. Next, the CCPOA-HDLM method utilizes ISSA based feature selection method to select optimum features. The CCPOA-HDLM technique employs a hybrid of the MCNN-RNN model for the cybersecurity detection and classification process. Moreover, the hyperparameter range of the hybrid of DL techniques occurs using the CPO technique. The experimental validation of the CCPOA-HDLM approach is performed on the UNSW-NB15 dataset, and the outcome portrayed a superior accuracy value of 99.04 % over other recent approaches under various measures.

关键词： Crested porcupine optimizer Hybrid deep learning Smart city Cybersecurity Improved salp swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：