检索结果-内蒙古大学图书馆

4th International Conference on Computational Methods in Science and technology, ICCMST 2024

作者： Dhiman, Pummy Kaur, Amandeep Sharma, Dilip Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Engineering and Application GLA University Mathura India

ISBN: (纸本)9781032911571

In today’s digital age, technology has advanced to the point where it is difficult to distinguish be-tween genuine and forged media content. It was intended to be used for entertainment, but it is now being used to deceive people and create biasness, which can lead to disastrous situations. The goal of this bibliometric study is to provide scientific mapping on the role of deep learning in deepfake detection published online. Scopus and VOSviewer are used to create a concept map of 128 articles. Additionally, future directions for research are suggested. © 2025 the Author(s).

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

DYTC:Dynamic Graph Triangle Counting on GPU 24

DYTC:Dynamic Graph Triangle Counting on GPU

引用

8th International Conference on Algorithms, Computing and Systems, ICACS 2024

作者： Wang, Zhuo Li, Zhixiong Tu, Jinxing Huang, Jianqiang Department of Computer Technology and Applications Qinghai University Xining China Intelligent Computing and Application Laboratory of Qinghai Province Qinghai University Xining China

ISBN: (纸本)9798400718304

Triangle counting is a critical problem in graph theory and network analysis, with widespread applications in social network analysis, network science, and bioinformatics. Dynamic graphs are extensively utilized in various domains and are prevalent in real-world scenarios. Over time, dynamic graphs necessitate frequent updates, where vertices and edges are inserted, deleted, or modified. However, existing dynamic graph analysis methods often focus solely on the data structure of dynamic graphs, neglecting the algorithms for dynamic graph processing. Current triangle counting methods are typically designed for static graphs and are not suited for continuously updated dynamic graphs. In this paper, we propose an incremental triangle counting algorithm tailored for dynamic graphs, which only requires recomputing the affected subgraph caused by updated edges, rather than the entire graph. Consequently, in comparison to the previous algorithm, our algorithm is capable of attaining a maximum speedup of . © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Forensic handwriting analysis: a hybrid classification framework for writer identification in Devanagari script

引用

Multimedia Tools and applications 2025年 1-12页

作者： Sethi, Monika Kumar, Munish Jindal, M.K. Department of Computer Science and Application Panjab University Chandigarh India P.G. Department of Information Technology Goswami Ganesh Dutta Sanatan Dharma College Chandigarh India Department of Computational Sciences Maharaja Ranjit Singh Punjab Technical University Punjab Bathinda India Department of Computer Science and Applications Panjab University Regional Centre Muktsar India

In a period marked by swift technological progress, the task of identifying writers through handwriting holds significant importance across various domains, including forensic investigation, plagiarism detection, and historical research. The importance of this endeavor has been further magnified by the widespread influence of digitalization. This study employs a hybrid approach that integrates cutting-edge deep learning techniques, specifically Convolutional Neural Networks (CNNs), with traditional machine learning methodologies, such as Support Vector Machines (SVM) and Random Forest (RF). Deep learning techniques are particularly valuable for analyzing extensive handwriting samples because they can automatically discern complex features and patterns from large datasets. In this research, we synthesize predictions from deep learning models and employ machine learning classification for writer identification based on handwriting analysis. Central to our study is a comprehensive dataset of Devanagari characters, collected from 220 unique writers. This dataset has been thoughtfully curated to validate the methodology we have employed. Our hybrid classification approach, combining CNN with SVM and CNN with RF, achieves remarkable accuracy rates of 91.49% and 88.78%, respectively—significantly surpassing the performance of standalone SVM and RF models, which achieved accuracies of 59.52% and 59%, respectively. Through a series of comprehensive experiments, we demonstrate the enhanced effectiveness and precision of our proposed methodology in the domain of Devanagari script writer identification. The findings of this study not only underscore the potential of our methodology but also represent a substantial advancement in the fields of pattern recognition and machine learning technology. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Decision-Based Clustering for Efficient Data Aggregation in Mobile UWSNs

引用

computers, Materials & Continua 2025年第4期83卷 259-279页

作者： Aadil Mushtaq Pandith Manni Kumar Naveen Kumar Nitin Goyal Sachin Ahuja Yonis Gulzar Rashi Rastogi Rupesh Gupta Department of Computer Science and Engineering Lovely Professional UniversityJalandhar144402PunjabIndia Department of Computer Science and Engineering Chandigarh UniversityMohali140413PunjabIndia Salesforce Inc. DallasTX 75201USA Department of Computer Science and Engineering School of Engineering and TechnologyCentral University of HaryanaMahendragarh123031HaryanaIndia Department of Management Information Systems College of Business AdministrationKing Faisal UniversityAl-Ahsa31982Saudi Arabia Department of Computer Application Sir Chhotu Ram Institute of Engineering and TechnologyCh.Charan Singh UniversityMeerut250001Uttar PradeshIndia Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpura140401PunjabIndia

Underwater wireless sensor networks(UWSNs)rely on data aggregation to streamline routing operations by merging information at intermediate nodes before transmitting it to the ***,many existing data aggregation techniques are designed exclusively for static networks and fail to reflect the dynamic nature of underwater ***,conventional multi-hop data gathering techniques often lead to energy depletion problems near the sink,commonly known as the energy hole ***,cluster-based aggregation methods face significant challenges such as cluster head(CH)failures and collisions within clusters that degrade overall network *** address these limitations,this paper introduces an innovative framework,the Cluster-based Data Aggregation using Fuzzy Decision Model(CDAFDM),tailored for mobile *** proposed method has four main phases:clustering,CH selection,data aggregation,and *** CH selection,a fuzzy decision model is utilized to ensure efficient cluster head selection based on parameters such as residual energy,distance to the sink,and data delivery likelihood,enhancing network stability and energy *** the aggregation phase,CHs transmit a single,consolidated set of non-redundant data to the base station(BS),thereby reducing data duplication and saving *** adapt to the changing network topology,the re-clustering phase periodically updates cluster formations and reselects *** results show that CDAFDM outperforms current protocols such as CAPTAIN(Collection Algorithm for underwater oPTical-AcoustIc sensor Networks),EDDG(Event-Driven Data Gathering),and DCBMEC(Data Collection Based on Mobile Edge Computing)with a packet delivery ratio increase of up to 4%,an energy consumption reduction of 18%,and a data collection latency reduction of 52%.These findings highlight the framework’s potential for reliable and energy-efficient data aggregation mobile UWSNs.

关键词： Clustering data aggregation data collection fuzzy model monitoring UWSN

来源：评论

学校读者我要写书评

暂无评论

Comparative study of IoT- and AI-based computing disease detection approaches

引用

Data Science and Management 2025年第1期8卷 94-106页

作者： Rhmann, Wasiur Khan, Jalaluddin Khan, Ghufran Ahmad Ashraf, Zubair Pandey, Babita Khan, Mohammad Ahmar Ali, Ashraf Ishrat, Amaan Alghamdi, Abdulrahman Abdullah Ahamad, Bilal Shaik, Mohammad Khaja Department of Computer Application Lovely Professional University Punjab Phagwara144411 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur522502 India School of Computing Science and Engineering VIT Bhopal University Kothrikalan MP Sehore466114 India Babasaheb Bhimrao Ambedkar University Lucknow226025 India College of Commerce and Business Administration Dhofar University Salalah211 Oman Faculty of Computer Studies Arab Open University 18211 Bahrain Department of Computer Application Shri Ramswaroop Memorial University Lucknow225003 India College of Computing and Information Technology Shaqra University Shaqra11961 Saudi Arabia

The emergence of different computing methods such as cloud-, fog-, and edge-based Internet of Things (IoT) systems has provided the opportunity to develop intelligent systems for disease detection. Compared to other machine learning models, deep learning models have gained more attention from the research community, as they have shown better results with a large volume of data compared to shallow learning. However, no comprehensive survey has been conducted on integrated IoT- and computing-based systems that deploy deep learning for disease detection. This study evaluated different machine learning and deep learning algorithms and their hybrid and optimized algorithms for IoT-based disease detection, using the most recent papers on IoT-based disease detection systems that include computing approaches, such as cloud, edge, and fog. Their analysis focused on an IoT deep learning architecture suitable for disease detection. It also recognizes the different factors that require the attention of researchers to develop better IoT disease detection systems. This study can be helpful to researchers interested in developing better IoT-based disease detection and prediction systems based on deep learning using hybrid algorithms. © 2024 Xi'an Jiaotong University

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Social Media Counterfeit Using Deep Learning Algorithm

Detecting Social Media Counterfeit Using Deep Learning Algor...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Mervin A Shanthi H J Department of computer Application Hindustan institute of technology and Science Chennai Tamilnadu India Department of computer Application Hindustan institute of technology and Science Chennai India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The rapid dissemination of fake news via traditional and digital platforms has emerged as one of the most critical challenges of today's information-driven society. Fake news, which is also known as deliberately false or misleading information, has always been generated to manipulate public opinion and damage reputations or even exploit by sensationalism for profit. Twitter and Facebook have become some of the most prominent social media channels through which such types of false information flow. Studies show that false information travels much faster than true factual information. Thus, to overcome all these types of issues, this project aims to present a fake newsdetecting model based on advanced machine learning and Natural Language Processing (NLP) techniques that would automatically identify misleading content. The model also uses text mining algorithms to extract the meaningful pattern and linguistic features of news articles by NLP techniques such as tokenization, stemming, lemmatization, and named entity recognition (NER). The features thus extracted are then analyzed using classification algorithms such as Naive Bayes, Gradient Boosting, and Random Forest, in order to classify the authenticity of the content. Model evaluations are done using a performance metric such as accuracy and a confusion matrix with initial expectations favoring the higher accuracy of the Naive Bayes classifier. Word embedding and sentiment analysis are also added to represent the model's ability to distinguish between real and fake news. The proposed framework is intended to contribute to the implementation of a successful scalable solution for real-time detection of fake news.

关键词： Text mining Sentiment analysis Accuracy Social networking (online) Feature extraction Real-time systems Tokenization Classification algorithms Fake news Random forests

来源：评论

学校读者我要写书评

暂无评论

Investigating the Impact of Public-Key Infrastructure in Information Security Models for Networked applications 5th

Investigating the Impact of Public-Key Infrastructure in Inf...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Shree, Ritu Saxena, Kumud Mehta, Deepak Pandeya, Megha Department of Computer Science and Application Vivekananda Global University Jaipur India Department of Computer Science Engineering Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Public-key infrastructure (PKI) is poised to play a crucial function in the use of secure data technology systems. With the increasing complexity of these dais’s networks and packages, PKI gives a reliable way to electronically affirm and securely exchange critical records. This paper investigates the effect of PKI on modern-day facts security models for networked applications. An assessment of the literature is conducted to discover the limitations of various PKI‐enabled architectures and packages. The research seems at the usage of cryptography and digital certificates inside the implementation of PKI, and evaluates the different varieties of authentication, authorization, and encryption strategies in shielding networked structures. Furthermore, the paper discusses the advantages and demanding situations associated with the deployment of PKI for distinctive use instances. The findings exhibit that during order for PKI to efficiently defend networked structures, a sound authentication system need to be blended with sturdy and consumer-friendly encryption strategies. Moreover, the paper shows strategies for overcoming the demanding situations related to enforcing PKI in a relaxed and efficient way. Public-key infrastructure (PKI) is an important device in data security fashions for networked packages. PKI is a security architecture that entails the use of public and private interchangeable cryptographic keys to ensure authenticated and comfortable verbal exchange among entities. Through developing a hierarchical accept as true with device, virtual certificate are used to cozy communications and the sender and authenticity and integrity of records. This architecture gives a at ease foundation for at ease dispensed computing across multiple sites located in numerous geographical places, as it enhances confidentiality, integrity, and authentication of exchanged information. In addition, PKI can facilitate cozy statistics sharing, alleviate potential privateness issues,

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

ColorVein: Colorful Cancelable Vein Biometrics

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4943-4955页

作者： Wang, Yifan Gui, Jie Shi, Xinli Gui, Linqing Tang, Yuan Yan Kwok, James Tin-Yau Southeast University School of Cyber Science and Engineering Nanjing210000 China Ministry of Education Purple Mountain Laboratories Engineering Research Center of Blockchain Application Nanjing210000 China Nanjing University of Posts and Telecommunications College of Computer Nanjing210003 China University of Macao Department of Computer and Information Science 999078 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering 999077 Hong Kong

Vein recognition technologies have become one of the primary solutions for high-security identification systems. However, the issue of biometric information leakage can still pose a serious threat to user privacy and anonymity. Currently, there is no cancelable biometric template generation scheme specifically designed for vein biometrics. Therefore, this paper proposes an innovative cancelable vein biometric generation scheme: ColorVein. Unlike previous cancelable template generation schemes, ColorVein does not destroy the original biometric features and introduces additional color information to grayscale vein images. This method significantly enhances the information density of vein images by transforming static grayscale information into dynamically controllable color representations through interactive colorization. ColorVein allows users/administrators to define a controllable pseudo-random color space for grayscale vein images by editing the position, number, and color of hint points, thereby generating protected cancelable templates. Additionally, we propose a new secure center loss to optimize the training process of the protected feature extraction model, effectively increasing the feature distance between enrolled users and any potential impostors. Finally, we evaluate ColorVein’s performance on all types of vein biometrics, including recognition performance, unlinkability, irreversibility, and revocability, and conduct security and privacy analyses. ColorVein achieves competitive performance compared with state-of-the-art methods. © 2005-2012 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Balancing data imbalance in biomedical datasets using a stacked augmentation approach with STDA, DAGAN, and pufferfish optimization to reveal AI's transformative impact

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 455-480页

作者： Veedhi, Bhaskar Kumar Das, Kaberi Mishra, Debahuti Mishra, Sashikala Behera, Mandakini Priyadarshani Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to Be) University Odisha Bhubaneswar India Department of Computer Application Siksha ‘O’ Anusandhan (Deemed to Be) University Odisha Bhubaneswar India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed to Be) University Maharashtra Pune India School of Computer Engineering KIIT (Deemed to Be) University Odisha Bhubaneswar India

This study systematically assesses the effectiveness of data augmentation techniques, focusing particularly on the stacked approach, across a diverse range of biomedical datasets. Advanced data augmentation methods, including style transfer data augmentation (STDA) and data augmentation generative adversarial network (DAGAN), offer promising solutions in this context. STDA leverages style transfer techniques from computer vision to create varied and realistic synthetic samples while preserving semantic content, thereby enhancing dataset variability and improving model generalization. Conversely, DAGAN utilizes generative adversarial networks (GANs) to learn the underlying data distribution, resulting in the generation of high-quality synthetic samples. Subsequently, STDA and DAGAN techniques are applied to the selected data, followed by convolution and pooling operations on the augmented samples. The pooled samples are then stacked, and the Cosine similarity is calculated to measure the resemblance to the original dataset. Parameters of STDA and DAGAN are fine-tuned to maximize the Cosine similarity. Additionally, a metaheuristic optimization algorithm called Pufferfish optimization algorithm (POA) is employed to optimize decision variables—learning rate, number of hidden units (common for both STDA and DAGAN), number of attention heads for STDA, and latent space dimensionality of DAGAN. The classification performance of the proposed POA-stacked STDA-DAGAN data augmentation methodology, along with variants using genetic algorithm (GA) and particle swarm optimization (PSO), is compared with original datasets and SMOTE balanced datasets using various classifiers and the observed accuracies, sensitivity, specificity and F-score are ranging from 91.83% to 99.11%, 91.38% to100%, 92.50% to 100% and 92.95% to 98.32% respective for all ten biomedical datasets used in this research. Additionally, the class distribution graphs, learning curves, statistical validation, and exe

关键词： Biomedical data Data augmentation Data augmentation generative adversarial network (DAGAN) Pufferfish optimization algorithm (POA) Style transfer data augmentation (STDA)

来源：评论

学校读者我要写书评

暂无评论

EPRFL:An Efficient Privacy-Preserving and Robust Federated Learning Scheme for Fog Computing

引用

China Communications 2025年第4期22卷 202-222页

作者： Ke Zhijie Xie Yong Syed Hamad Shirazi Li Haifeng School of Computer Technology and Application Qinghai UniversityXining 810016China School of Computer and Information Science Qinghai Institute of TechnologyXining 810016China Guangdong Key Laboratory of Blockchain Security Guangzhou UniversityGuangzhou 510006China Department of Information Technology Hazara UniversityBaffa 21110Pakistan Qinghai Provincial Key Laboratory of Big Data in Finance and Artificial Intelligence Application Technology Xining 810016China

Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple *** combined with Fog Computing,FL offers enhanced capabilities for machine learning applications in the Internet of Things(IoT).However,implementing FL across large-scale distributed fog networks presents significant challenges in maintaining privacy,preventing collusion attacks,and ensuring robust data *** address these challenges,we propose an Efficient Privacy-preserving and Robust Federated Learning(EPRFL)scheme for fog computing ***,we first propose an efficient secure aggregation strategy based on the improved threshold homomorphic encryption algorithm,which is not only resistant to model inference and collusion attacks,but also robust to fog node ***,we design a dynamic gradient filtering method based on cosine similarity to further reduce the communication *** minimize training delays,we develop a dynamic task scheduling strategy based on comprehensive *** analysis demonstrates that EPRFL offers robust security and low *** experimental results indicate that EPRFL outperforms similar strategies in terms of privacy preserving,model performance,and resource efficiency.

关键词： federated learning fog computing internet of things privacy-preserving robustness

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：