检索结果-内蒙古大学图书馆

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kulkarni, Mayuri Shahade, Makarand Mahajan, Deep Nikam, Bhavesh Badgujar, Rushikesh Sharma, Piyush SVKM's Institute of Technology Department of Computer Engineering Dhule India

ISBN: (纸本)9798331300579

The Decentralized technology 'Blockchain' has some point Centralization in terms of Remote Procedure Call Mechanism. Relying on centralized RPC (Remote Procedure Call) is risky and running a node can be expensive, time consuming and more complex making it extremely inaccessible for most of the users. Web3 companies must spend huge expenses on maintaining their infrastructure and fault-tolerant operation. The Lightning Sidebridge is Based on the core Infrastructure of Blockchain & Decentralized RPC Load Balancing. Lightning Sidebridge (Load Balancer) is a decentralized RPC Gateway service that provides more secure and reliable access to the blockchain. Lightning Sidebridge is a decentralized network of nodes that are responsible for validating transactions and blocks. The network is secured using a various Consensus mechanism such as Proof of Stake and reputation systems. Lightning Sidebridge is designed to distribute requests across a network of Decentralized RPC nodes to avoid failure and errors. The system (Load Balancer) sits between Decentralized applications and Blockchain RPC Layer. It is designed to distribute the requests amongst a cluster of public RPC nodes. The Proposed system can reroute specific requests to another active RPC endpoint automatically if node that is currently in use goes down. Implemented nodes are hardened and secured for various attacks and continuously monitored for security vulnerabilities. as Current RPC Network is Centralized, the Proposed system is more focused on Decentralized RPC Gateway and enabling potential of decentralized node validation services in fortifying blockchain accessibility and security. © Grenze Scientific Society, 2024.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Key Management in Space Integrated Terrestrial Network: A Cybersecurity Perspective 2

Key Management in Space Integrated Terrestrial Network: A Cy...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Ahlawat, Priyanka National Institute of Technology Computer Engineering Department Haryana Kurukshetra India

ISBN: (纸本)9798350366570

Satellite networks comprise of large number of satellite constellations. It makes the management of keys used for different security mechanism a very important issue to be studied. Key management is set of procedure that creates, exchange, store, delete and refresh the keys. Ensuring secure key management across satellite-terrestrial integrated networks (STIN) is very challenging. It is one of the challenging area due to large number of keys and their frequent updating by satellite nodes. How often the key is to be updated also need to considered. It may depend on services of type of data communication. If keys are updated very frequently, it induces a large overhead on the system. This paper aims to focus on the role of key management in providing security in STIN. Different key management schemes are analyzed and various research gaps along with future research directions are given. It will serve as a foundation for future research in STIN security. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms in Fish Survival Prediction

Comparative Analysis of Machine Learning Algorithms in Fish ...

引用

2024 IEEE Bangalore Humanitarian technology Conference, B-HTC 2024

作者： Shirwaikar, Rudresh D. D'Souza, Lyzandra Bhangle, Anirudh Santosh Joshi, Sarang Deepak Jathar, Nupur Ajit Alvares, Jonathan Elroy Agnel Institute of Technology and Design Department of Computer Engineering Mapusa India

ISBN: (纸本)9798350344509

This research paper conducts an exploration of prevalent machine learning classification algorithms, emphasizing the refinement of Random Forest models to optimize performance. The initial phase involves a comparative analysis of Random Forest, k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Logistic Regression, and Naive Bayes Classification algorithms across the dataset, resulting in Random forest to be best performed among all with average accuracy of 61%. Subsequently, then we focus on enhancement of the Random Forest algorithm with random train-test split dataset, resulting in an enhanced average accuracy of 65% which is about 4% improvement to the previous accuracy and choosing the best traintest split dataset, along with fine tuning the model, improved the average accuracy to 73% which is about 12% improvement to previous accuracy which is significantly higher showcasing the significance of precise algorithmic tuning. The completion of our investigation lies in the creation of an integrated model which incorporates multiple Random Forest classifier models, each specifically trained for binary class classification, along with a comprehensive model designed for multiclass classification. This combined model excels with a peak accuracy of 82.75% for the best split, demonstrating its strong performance in classification tasks. This research not only contributes to the theoretical understanding of algorithm performance and optimization but also offers practical insights for the application of machine learning in challenging classification scenarios. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Advancing Data Sovereignty in Distributed Environments: An In-Depth Exploration of Data Localization Challenges

Advancing Data Sovereignty in Distributed Environments: An I...

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Kancharla, Jaganmohan Reddy Madhu Kumar, S.D. National Institute of Technology Department of Computer Science & Engineering Calicut India

ISBN: (纸本)9798350388534

Data localization in distributed computing has gotten a lot of attention because it has the potential to improve data sovereignty, make sure regulations are followed, and make data easier to access. However, this practice also brings forth a multitude of challenges and threats to cybersecurity, data privacy, and overall information security. In this comprehensive survey paper, we delve into the complex landscape of challenges and threats associated with data localization in distributed computing environments. We explore the intricate interplay between data localization, distributed infrastructure, cybersecurity, and privacy concerns. This paper provides an in-depth analysis of various challenges such as regulatory compliance, data integrity, authentication, and access control, along with potential threats like data breaches, insider attacks, and unauthorized access. Furthermore, we investigate the state-of-the-art security mechanisms, encryption techniques, privacy-preserving methods, and access control strategies that researchers and practitioners have developed to address these challenges. Through this survey, we aim to provide a comprehensive overview of the critical issues surrounding data localization within cloud computing and shed light on the emerging trends and potential solutions that can pave the way for secure and privacy-aware data localization practices. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Analysing for Impact of Neutral Sentiments for Enhancing Quality of Services 2

Analysing for Impact of Neutral Sentiments for Enhancing Qua...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Ranjan, Roop Singh, Ranjeet Shukla, Roshan Buddha Institute of Technology Department of Computer Science and Engineering Gorakhpur India

ISBN: (纸本)9798350368109

Sentiment analysis (SA) is an intellectual process of extracting a user's views. Social media is gaining prominence in public transit agencies for communication strategies and daily management. In recent years, web documents are identified as an important source of reviewing individual opinions. Researchers using these social networking platforms are producing a high rate of increase in interest in methods for automatically extracting and analysing opinions from web documents such as for weblogs, customer reviews, movies and public services etc. This paper is an attempt to perform an evaluation of public opinion for the Quality of Services of two very popular public transportations in North India. Opinions of public have been collected in form of tweets for a specific time. An approach based on fuzzy logic and machine learning is introduced to solve the tweets extraction that is used for classification. The impact of neutral tweets is discussed. Results show that the performance of road transport is better than the transport through railway services and neutral tweets play a significant role in emotion analysis of the system. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Customer Segmentation using Clustering Techniques: Data-Driven Approach to Enhance Marketing Strategy 5

Customer Segmentation using Clustering Techniques: Data-Driv...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Sakthi Priya, G. Vignesh Saravanan, K. Hemalatha, B. Karthika, R. Kavya Srinidhi, B. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

Customer segmentation is a vital strategy for businesses seeking to enhance their marketing efforts and optimize resource allocation. This research focuses on segmenting customers using the Mall Customer Segmentation dataset, which includes demographic and behavioral attributes such as age, gender, annual income, and spending score. The work begins with data preprocessing, involving the handling of missing values, encoding of categorical variables, and scaling of numerical features to prepare the data for analysis. Following preprocessing, exploratory data analysis (EDA) is conducted to visualize feature distributions and relationships, providing insights into the data's structure. The core of the research involves applying various clustering algorithms-K-Means, Hierarchical Clustering, and DBSCAN-to identify distinct customer segments. The optimal number of clusters is determined through methods like the Elbow Method and Silhouette Score. The clusters are then evaluated for quality, and their characteristics are analyzed to understand different customer segments. This segmentation enables businesses to their marketing strategies, enhance customer satisfaction, and make data-driven decisions based on customer behavior insights and demographics. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Remember This Event That Year? Assessing Temporal Information and Understanding in Large Language Models

Remember This Event That Year? Assessing Temporal Informatio...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Beniwal, Himanshu Patel, Dishant Kowsik Nandagopan, D. Ladia, Hritik Yadav, Ankit Singh, Mayank Department of Computer Science and Engineering Indian Institute of Technology Gandhinagar India

ISBN: (纸本)9798891761681

Large Language Models (LLMs) are increasingly ubiquitous, yet their ability to retain and reason about temporal information remains limited, hindering their application in real-world scenarios where understanding the sequential nature of events is crucial. Our study experiments with 12 state-of-the-art models (ranging from 2B to 70B+ parameters) on a novel numerical-temporal dataset, TempUN, spanning from 10,000 BCE to 2100 CE, to uncover significant temporal retention and comprehension limitations. We propose six metrics to assess three learning paradigms to enhance temporal knowledge acquisition. Our findings reveal that open-source models exhibit knowledge gaps more frequently, suggesting a trade-off between limited knowledge and incorrect responses. Additionally, various fine-tuning approaches significantly improved performance, reducing incorrect outputs and impacting the identification of 'information not available' in the generations. The associated dataset and code are available at https://***/lingoiitgn/TempUN. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Occluded Face Recognition Through Device-Edge Collaboration and Cross-Domain Feature Fusion with Heatmaps 3

Enhancing Occluded Face Recognition Through Device-Edge Coll...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Prasanth, Ashwin Annie Micheal, A. Department of Computer Science & Engineering Sathyabama Institute of Science & Technology Chennai India

ISBN: (纸本)9798331527549

Face recognition under occlusion presents a persistent challenge in computer vision, primarily due to difficulties in capturing and effectively integrating visible and obscured facial features. This paper introduces a novel device-edge collaborative framework that advances occluded face recognition through an innovative cross-domain feature fusion technique. Our method employs a software-generated, occlusion-aware heatmap created from standard visible-light images, which emphasizes key facial landmarks even when regions of the face are partially covered. This heatmap provides a complementary data layer that enhances traditional visible facial features, allowing the cross-domain feature fusion process to synthesize a more comprehensive set of features for reliable recognition under occlusion. The combined feature set leverages both visible and simulated heatmap information to improve model robustness, even in complex occlusion scenarios. Additionally, a delay-optimized task scheduling method is applied on the edge, ensuring efficient resource allocation, faster processing, and minimal latency. Although this project is ongoing, preliminary evaluations indicate the potential effectiveness of this approach, with expected outcomes to include high recognition accuracy and reduced latency. This framework provides a scalable solution for occluded face recognition by integrating complementary data sources without requiring specialized hardware. © 2025 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Detecting Fake Images Using Texture Variation Network

引用

Inteligencia Artificial 2023年第72期26卷 1-14页

作者： Haseena, S. Saroja, S. Shri Dharshini, D. Nivetha, A. Department of Information Technology Mepco Schlenk Engineering College India Department of Computer Applications National Institute of Technology Trichy India

Face manipulation technology is rapidly evolving, making it impossible for human eyes to recognize fake faces in photos. Convolutional Neural Network (CNN) discriminators, on the other hand, can quickly achieve high accuracy in distinguishing fake from real face photos. In this paper, we investigate how CNN models distinguish between fake and real faces. According to our findings, face forgery detection heavily relies on the variation in the texture of the images. As a result of the aforementioned discovery, we propose a deep texture variation network, a new model for robust face fraud detection based on convolution and pyramid pooling. Convolution combines pixel intensity and pixel gradient information to create a stationary representation of composition difference information. Simultaneously, multi-scale information fusion based on the pyramid pooling can prevent the texture features from being destroyed. The proposed deep texture variation network outperforms previous techniques on a variety of datasets, including Faceforensics++, DeeperForensics-1.0, Celeb-DF, and DFDC. The proposed model is less susceptible to image distortion, such as JPEG compression and blur, which is important in this field. © IBERAMIA and the authors.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Software Fault Localization using CNN-LSTM Model 15

Software Fault Localization using CNN-LSTM Model

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Singh, Vishwank Vikram Bisi, Manjubala National Institute of Technology Department of Computer Science and Engineering Warangal India

ISBN: (纸本)9798350370249

Software fault localization is a critical task which identify the faulty statements in a program. Traditional fault localization techniques are unable to capture complex relationships within program execution data. In recent years, Convolutional Neural Networks (CNNs) has shown promise in enhancing fault localization performance. In this paper, we propose a CNN-LSTM model for software fault localization. We perform extensive experiments on four programs and observe that proposed CNN-LSTM model consistently outperforms existing methods, achieving higher accuracy and reliability in localizing software faults. © 2024 IEEE.

关键词： CNN LSTM MBFL SBFL

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：