检索结果-内蒙古大学图书馆

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Rahul Priyadarshi Jayant Kumar Rout Anish Kumar Vishwakarma Nikhil Dhengre Rakesh Ranjan Amit Verma Faculty of Engineering and Technology ITER SOA Bhubaneswar India School of Computer Application KIIT Bhubaneswar India School of Computer Science UPES Dehradun Uttarakhand India Department of ECE IIIT Nagpur Maharashtra India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Wireless Sensor Networks (WSNs) require efficient node deployment strategies to optimize network longevity, energy consumption, and coverage. This paper introduces a novel approach for strategic node deployment in WSNs using Bayesian Optimization (BO). A BO-based framework that iteratively modifies node positions to maximize network performance metrics, such as energy efficiency and coverage ratio, while minimizing execution time is proposed. Through extensive simulations across diverse deployment scenarios, the proposed method is evaluated and demonstrates superior performance compared to both traditional and machine learning (ML)-based techniques. The results indicate significant improvements in coverage and energy efficiency, alongside competitive execution times. These findings highlight the potential of BO to enhance WSN deployment strategies, offering a scalable and adaptive solution for real-world applications. Future research will focus on integrating BO with other optimization techniques and extending the approach to dynamic environments and varied network configurations.

关键词： Learning systems Wireless sensor networks Energy consumption Adaptive systems Machine learning Energy efficiency Real-time systems Bayes methods Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

Optical polarized orthogonal matrix

引用

Photonics Research 2025年第2期13卷 373-381页

作者： SHUJUN ZHENG JIAREN TAN XIANMIAO XU HONGJIE LIU YI YANG XIAO LIN XIAODI TAN Information Photonics Research Center College of Photonic and Electronic EngineeringFujian Normal University Department of Electrical and Computer Engineering Duke University College of Photonic and Electronic Engineering Key Laboratory of Opto-Electronic Science and for Medicine of Ministry of EducationFujian Provincial Key Laboratory of Photonics TechnologyFujian Provincial Engineering Technology Research Center of Photoelectric Sensing ApplicationFujian Normal University

Multiplexing technology serves as an effective approach to increase both information storage and transmission capability. However, when exploring multiplexing methods across various dimensions, the polarization dimension encounters limitations stemming from the finite orthogonal combinations. Given that only two mutually orthogonal polarizations are identifiable on the basic Poincaré sphere, this poses a hindrance to polarization modulation. To overcome this challenge, we propose a construction method for the optical polarized orthogonal matrix(OPOM), which is not constrained by the number of orthogonal combinations. Furthermore, we experimentally validate its application in high-dimensional multiplexing of polarization holography. We explore polarization holography technology, capable of recording amplitude, phase, and polarization, for the purpose of recording and selective reconstruction of polarization multi-channels. Our research reveals that, despite identical polarization states, multiple images can be independently manipulated within distinct polarization channels through orthogonal polarization combinations, owing to the orthogonal selectivity among information.

关键词： Multiplex holography Optical data storage Optical encryption Orbital angular momentum multiplexing Signal transmission Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Innovative anti-phishing framework using machine learning approach with evolutionary optimization to secure multimedia applications

引用

Multimedia Tools and applications 2025年 1-28页

作者： Sharma, Bhawna Khurana, Savita Sharma, Gaurav Rani, Sunita Nandal, Sudesh Kumari Chandi, Pragya Rastogi, Rashi Castilla, Ángel Kuc Goyal, Nitin Department of Computer Science & Engineering JMIT Radaur India Department of Information Technology JMIT Radaur India Department of Computer Science & Engineering and Information Technology BPS Mahila Vishwavidalaya Sonipat India Department of Electronics and Communication Engineering BPS Mahila Vishwavidalaya Sonipat India Department of Computer Science & Engineering University Institute of Engineering and Technology Kurukshetra University Haryana India Department of Computer Application Sir Chhotu Ram Institute of Engineering and Technology CCS University Meerut India Engineering Research & Innovation Group Universidad Europea del Atlántico Santander Spain Department of Project Management Universidad Internacional Iberoamericana Campeche México Department of Project Management Universidad Internacional Iberoamericana Arecibo USA Department of Computer Science & Engineering School of Engineering and Technology Central University of Haryana Mahendergarh India

The transmission of users’ personal data via networks poses an increased risk of being exposed to phishing threats. Phishing URLs hiding malicious web addresses have become a widespread means of compromising user privacy. This paper is to improve the accuracy and efficiency of detecting and defending against phishing attacks in multimedia applications, aiming to safeguard users'personal data from exposure via phishing URLs. The proposed approach can be summarized in three phases. In the first phase, cosine and Jaccard similarities between training and test datasets are calculated to obtain a comprehensive understanding of the similarities of data points. A hybrid similarity score is built by combining these two measures in the second phase of the experiment to effectively blend content-related and quantity-related similarities. The third and final phase involves training a model on XGBoost that uses a hybrid similarity score as an input and then tunning up its hyperparameters using a genetic algorithm with the optimization of classification performance. Finally, the created powerful classifiers are merged to form a stacked ensemble model, increasing the overall accuracy of the classification. The strenuous test evaluation of 11,429 rows, 88 columns, through key metrics, such as Precision, Recall, F-Score, and Accuracy show that the proposed anti-phishing model has outperformance parameters in other models. With this lean approach, accuracy in classification can be improved by the incorporation of similarity-based techniques and machine learning and evolutionary optimization, in which defense can be performed against phishing threats in multimedia environments. The new innovation involved in the proposed work is based on stacking an ensemble of similarity-based techniques with a learning and optimization framework of machines, ensuring robustness toward phishing threat defense.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain technology for digital twin security in smart grids using interpretable generalized additive neural networks

引用

Peer-to-Peer Networking and applications 2025年第4期18卷 1-17页

作者： Suggala, Ravi Kumar Kumar, Jaydip Jain, Prateek Kumar, Boddepalli Kiran Department of Information Technology Shri Vishnu Engineering College for Women Bhimavaram India Department of Computer Science and Application COER University 7th km on Roorkee – Haridwar Road Vardhmanpuram Uttarakhand Roorkee247 667 India Department of Computer Science School of Engineering and Sciences GD Goenka University Sohna Gurugram India Department of Computer Science and Engineering Aditya University Surampalem Kakinada533437 India

The Smart Grid (SG), as the next generation of efficient and intelligent electric power transmission networks, is driven by the Internet of Things (IoT). However, Smart Meters (SMs) within the SG environment often rely on unsecured public channels to exchange data and services, posing significant security risks. This manuscript proposes Blockchain technology for Digital Twin Security in Smart Grids using Interpretable Generalized Additive Neural Networks (BDTS-SG-IGANN) to address these challenges. The methodology begins with data collection from the N-BaIoT dataset, followed by pre-processing using the Constrained Normalized Subband Adaptive Filter (CNSAF) to enhance data quality and normalization. The pre-processed data is then secured through blockchain technology utilizing the Proof-of-Monitoring (PoM) consensus mechanism for authenticating data sources. Subsequently, secured data is analyzed using an Interpretable Generalized Additive Neural Network (IGANN) for intrusion detection. To optimize IGANN weight parameters, the Leaf-in-Wind Optimization (LWO) algorithm is employed. The proposed BDTS-SG-IGANN technique is put into practice using Python and evaluated using performance metrics like Precision, Recall, Accuracy, F1 Score, Mean Square Error (MSE), and Specificity. Experimental results demonstrate that BDTS-SG-IGANN outperforms existing methods, achieving 29.36%, 26.42%, and 23.27% higher accuracy and 18.36%, 14.42% and 12.27% lower compared to digital twin-based reinforcement learning for extracting network structures and load patterns in planning and operation of distribution systems (DTRL-ENS-CNN), Digital twin-driven SDN for smart grid: A deep learning integrated blockchain for cyber security (DTD-IBCS-SGN) and Blockchain-Based Cyber-Physical Security for Electrical Vehicle Aided Smart Grid Ecosystem (BCPS-EVSGE-SDN). This study establishes BDTS-SG-IGANN as an innovative and effective framework for securing digital twins in SG environments. © The Author

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction

Augmenting Short Enrollment Speech via Synthesis for Target ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Zikang Lin, Jingru Ge, Meng Jiang, Yu Wang, Xiaobao Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen China Department of Electrical and Computer and Engineering National University of Singapore Singapore Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798350368741

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, that provides limited cues. To address this issue, we propose an enrollment augmentation strategy that allows us to enrich the limited enrollment speech with massive text data through speech synthesis. By doing so, the extended enrollment speech contains enhanced speaker timbre and phonetic content which leads to better extraction quality. Furthermore, we propose a training data augmentation strategy to improve the model's robustness and generalization in short enrollment speech scenarios. Experiments on Libri2Mix demonstrate that our proposed strategies bring a significant improvement in extreme scenarios where only 0.5s and 1-word enrollment speech is provided. We also release our code at https://***/HuangZikang-TJU/Aug4TSE. © 2025 IEEE.

关键词： continue speaking data augmentation short enrollment speech synthesis Target speaker extraction

来源：评论

学校读者我要写书评

暂无评论

Optimal Dispatch Strategy for Roof Top Solar PV-Based EV Charging Stations

Optimal Dispatch Strategy for Roof Top Solar PV-Based EV Cha...

引用

International Conference on Signal Processing and Communication (ICSC)

作者： Rishabh Mishra Mohammed Aslam Husain Yudhishthir Pandey Asif Khan Alka Agrawal Shivam Mishra Department of Electrical Engineering Rajkiya Engineering College Ambedkar Nagar UP India Department of Computer Application Integral University Lucknow UP India Department of Information Technology Babasaheb Bhimrao Ambedkar University Lucknow UP India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

Electric vehicles (EV) are exciting alternatives to conventional vehicles (CV) which have zero carbon emission during operation. The electric vehicle's ability is to reduce total climate effect & pollutant emission significantly. In This paper present a comparative analysis study of an optimization dispatch strategy for electric vehicles (ODSEV) charging station by using general algebraic modelling system (GAMS) to solve optimization dispatch equation. In the current distributed electricity generation scenario, a reliable, economical energy distribution plan is required. The problem of pollutant emissions from fossil fuels and their finite supply have forced researchers to concentrate on the future of renewable energy production. The output of this paper is to optimization dispatch strategy for electric vehicles (ODSEV) which includes four thermal & one solar power plant. This paper aims to introduce a cost-effective and environmentally conscious algorithm that integrates both thermal and solar power plants. Additionally, the algorithm accounts for the uncertainties associated with varying climatic conditions, ensuring a more practical and adaptable solution.

关键词： Renewable energy sources Costs Uncertainty Biological system modeling Signal processing algorithms Charging stations Electric vehicles Mathematical models Power generation Optimization

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare Record Management: Secure Documentation Storage and Access through Advanced Blockchain Solutions

arXiv

引用

arXiv 2025年

作者： Brijwani, Geeta N. Ajmire, Prafulla E. Junaid, Mohammad Atique Mohammad Charasia, Suhashini Awadhesh Bhende, Deepali O. Computer Science Dept. Sant Gadge Baba Amravati University Amravati India Department of Computer Science Faculty of Engineering & Technology Sant Gadge Baba Amravati University India Department of Computer Science Rashtrasant Tukadoji Maharaj Nagpur University Nagpur India Department of Master of Computer Application Rashtrasant Tukadoji Maharaj Nagpur University Nagpur India

Integrating blockchain technology into healthcare systems presents a transformative approach to documenting, storing, and accessing electronic health records (EHRs). This research introduces a novel blockchain-based EHR system designed to significantly enhance security, scalability, and accessibility compared to existing solutions. Current systems primarily utilize SHA-256 for security and either IPFS or centralized storage, which, while effective, have limitations in providing comprehensive data integrity and security. The proposed system leverages a hybrid security algorithm combining Argon2 and AES and integrates a hybrid storage and consensus mechanism utilizing IPFS and PBFT. This multifaceted approach ensures robust encryption, efficient consensus, and high fault tolerance. Furthermore, the system incorporates Multi-Factor Authentication (MFA) to safeguard against unauthorized access. It utilizes advanced blockchain tools like MetaMask, Ganache, and Truffle to facilitate seamless interaction with the decentralized network. Simulation results demonstrate that this system offers superior protection against data breaches and enhances operational efficiency. Specifically, the proposed hybrid model substantially improves data integrity, consensus efficiency, fault tolerance, data availability, latency, bandwidth utilization, throughput, memory usage, and CPU usage across various healthcare applications. To validate the performance and security of the proposed system, comprehensive analyses were conducted using real-world healthcare scenarios. The findings highlight the significant advantages of the blockchain-based EHR system, emphasizing its potential to revolutionize healthcare data management by ensuring secure, reliable, and efficient handling of sensitive medical information. © 2025, CC0.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Prediction Using Machine Learning

Breast Cancer Prediction Using Machine Learning

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Shiv Ashish Dhondiyal Pooja Luthra Bhupender Sharma Rajni Rajni Ishita Uniyal Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Science & Engineering Chandigarh University Mohali Punjab Department of Computer Science and Application Coer University Roorkee Uttarakhand Department Of Computer Science & Engineering Guru Jambheshwar University of Science and Technology Hisar Haryana India Department of Electrical Engineering Graphic Era Hill University

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

The number of newly diagnosed cases of breast cancer exceeds 2.3 million annually worldwide. There is a severe lack of valid prognostic and predictive indicators for the clinical treatment of breast cancer patients at the present time. In order to decrease the mortality rate and increase the survival time of breast cancer patients, early detection of this deadly disease is crucial. Improving breast cancer prognosis relies on the analysis and processing of mammography data, the gold standard for screening and early detection. In order to detect breast cancer in mammograms, the Fuzzy C-means algorithm is employed for image segmentation. Next, we train it to identify the characteristics of the segmented regions, and then we use an effective classifier to categorise the trained pictures into their respective mammography classes. This research used the Breast Cancer Wisconsin Diagnostic dataset and two ML algorithms: K-Nearest Neighbours (KNN) and Random Forest. After getting the results, we compared and evaluated the performance of these two classifiers. Potentially useful tools for both early diagnosis and treatment planning include breast cancer prediction models that account for a wide range of risk factors. Effective disease management involves the collection, storage, and administration of many data sets, as well as intelligent systems based on several aspects for the prediction of breast cancer.

关键词： Image segmentation Accuracy Machine learning algorithms Sensitivity Databases Nearest neighbor methods Prediction algorithms Breast cancer Classification algorithms Random forests

来源：评论

学校读者我要写书评

暂无评论

Construction of PCOS Prediction Model Based on BP Neural Network

Construction of PCOS Prediction Model Based on BP Neural Net...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Xianqing Hu Amit Yadav Asif Khan Abhishek Pratap Sah Sami Azam School of Computer and Software Chengdu Neusoft University Chengdu China Faculty of Science and Technology Charles Darwin University NT Australia Department of Computer Application Integral University Lucknow India School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Polycystic ovary syndrome (PCOS), a common endocrine-metabolic disorder affecting about 10-13% of women during reproductive age worldwide, often leads to irregular menstruation, infertility, obesity, and long-term health risks such as diabetes and cardiovascular disease. In this paper, clinical data from PCOS patients and healthy control group were collected from ten hospitals containing 37 key indicators such as age, weight, BMI, menstrual cycle, etc. BP (Back Propagation) Neural Network prediction models were constructed and compared using the collected data and the cross-validation method was used for parameter tuning. It was found that BP N eural Network performed particularly well on the test set, and both demonstrated high prediction accuracy and generalization ability which provided strong evidence for the early identification and early valuable intervention opportunities for PCOS patients.

关键词： Training Adaptation models Accuracy Biological system modeling Computational modeling Neural networks Predictive models Data models Robustness Tuning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Infrastructure Security with GraphSAGE-Based Intrusion Detection Systems

Enhancing Cloud Infrastructure Security with GraphSAGE-Based...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： G. Nanda Kishor Kumar Shakir Syed Amit Karbhari Mogal Tahera Abid Anvesh Perada Sampathirao Suneetha University of South Florida USA Department of Computer Science and Engineering Malla Reddy University Hyderabad India Corporate Partners Bargersville IN USA Department of Computer Science and Application MVP Samaj’s CMCS College Nashik India Department of Information Technology Nawab Shah Alam Khan College of Engineering and Technology Hyderabad India Department of Electrical and Computer Engineering Drexel University Philadelphia USA Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Cloud computing provides scalable and adaptable infrastructure however is significantly susceptible to cyber-attacks. This work presents a hybrid methodology that integrates the GOA and GA for feature selection, alongside the Residual GraphSAGE model for intrusion detection. The hybrid GOA-GA method enhances feature selection by optimizing the balance between exploration and exploitation, mitigating overfitting, and augmenting classification performance. The Residual GraphSAGE model alleviates over smoothing while effectively capturing node and edge interactions for precise intrusion classification. Assessment on a benchmark dataset reveals exceptional performance, attaining an accuracy of 91.74%, surpassing established models such as GCN and ResNet. This study emphasizes the need of hybrid optimization and sophisticated graph-based learning in improving cloud infrastructure security.

关键词： Training Cloud computing Accuracy Smoothing methods Computational modeling Organizations Feature extraction Optimization Genetic algorithms Overfitting

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：