检索结果-内蒙古大学图书馆

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

作者： Mishra, Suraj Garg, Animesh Batra, Vansh Saxena, Devansh Om Gouthaman, P. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Networking and Communications 603203 India School of Computing SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications India

ISBN: (纸本)9798331530013

The Cricket Performance Analysis System based on big data tools, like Hadoop and Apache Spark, gives realtime deep insights into performances from players and teams and conditions in matches based on large-scale cricket match data. It scales up speedily and finds patterns using distributed computing capabilities of Spark, which makes it possible to take decisions around performance improvements and strategies. The system applies a set of machine learning techniques including K-means clustering, Logistic Regression, and Random Forest classifiers to be used for the analysis of player performance metrics and match outcomes. Thus, through the conversion of raw data into actionable insights, teams can improve their strategies, make better improvements in performance, and thus gain an upper hand against other competing professional cricket teams. As a result, teams are best positioned to make adjustments in good time and direct finer tactics toward further enhancement of overall performance. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Markov enhanced I-LSTM approach for effective anomaly detection for time series sensor data

引用

International Journal of Intelligent Networks 2024年第1期5卷 154-160页

作者： Shanmuganathan, V. Suresh, A. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur ChengalpattuTamil Nadu603203 India

Users could engage and interact with their immediate surroundings without effort in smart settings. The emergence of intelligent technologies along with software-based services has made this possible. It is clear that technical advancements have ushered in a new era for both computer processing and sensor technology, facilitating the concept of smart surroundings. Even though their implementation faces a number of obstacles, numerous expansive projects are working to advance their adoption. The problem of anomalies in the sensor data could result inappropriate decisions and could lead unamicable situations to the users. Many such algorithms are already there, which does not provide satisfactory predictions for the sensor data for the time series data. Time series anomaly detection problems are typically stated as finding outlier data points in comparison to some norm or typical signal. Better anomaly detection in time series data is provided by the proposed Markov and enhanced LSTM technique. The Markov model and the enhanced LSTM offer accurate predictions for extra- and short-term data, which is highly useful in situations involving intelligent environments. When compared to the KNN algorithm, the technique offers reduced MAE, RMSE, MSE and MAPE errors. The algorithm also performs better than other LSTM and RNN methods. The proposed algorithm provides 0.00047 reduced error in humidity data, 0.00416 reduced error in temperature and 0.01771 reduced MAE value in case of light intensity when comparing with the KNN algorithm. © 2024 The Authors

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Editing Memories Through Few Targeted Neurons 39

Editing Memories Through Few Targeted Neurons

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Wei Wei, Wei Cao, Guibang Wang, Fei Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China China Ping An Property & Casualty Insurance Company of China Ltd China Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)157735897X

Model editing is a novel research topic in large language models (LLMs), aimed at efficiently handling various knowledge editing tasks. Since irrelevant knowledge is difficult to measure, existing editing methods often lack explicit ways to preserve it, especially for editing methods based on the fine-tuning paradigm. They generally control the locality performance of model editing by constraining the range of changes in model parameters. However, their performance improvements are not always ideal, and may even lead to a decrease in the editing reliability. In this paper, we try to explore effective editing locality control methods based on the relationship between the stored knowledge and the strongly associated model components. Based on the discovery of "knowledge neurons" and enough experimental results, we further explore the potential characteristics between knowledge and model components, confirm and point out: (1) only 1% neurons have significant contributions to specific knowledge storage, and (2) these targeted neurons often have a high overlap for knowledge with similar relational descriptions, which means that knowledge with similar relationships may be severely affected when these targeted neurons are modified. Based on these findings, we propose Targeted Neurons Fine-tuning with Data Augmentation (TNF-DA), which performs data augmentation based on the relational representation of edited knowledge to improve editing locality. By freezing most of the model parameters and only fine-tuning the highly contributing neurons corresponding to the edited knowledge, we obtain desirable results in terms of generalization and specificity compared with previous fine-tuning-based methods. Extensive experiments have demonstrated the superior editing performance achieved by our proposed method. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Secure SSI framework using the optimized Orkey identity schema

引用

International Journal of Information technology (Singapore) 2024年第6期16卷 4007-4014页

作者： Pandu N, K. Kumar, A. Sasi Department of Computer Science and Engineering Srinivas University Institute of Engineering and Technology Srinivas University Department of Computer Science amd Engineering Yenepoya Institute of Technology VTU

In the era of digital transformation and increasing concerns regarding data privacy, the concept of Self-Sovereign Identity (SSI) has attained substantial recognization. SSI offers individuals greater control over their personal information and reduces reliance on centralized authorities for identity verification. However, existing SSI frameworks face challenges in terms of scalability, privacy, and competence. This paper introduces a noivel Secure SSI Framework based on the Optimized OrKey Identity Schema (OIS) for Inter-organizational business processes (IOBP). The Optimized OrKey Identity Schema optimizes data storage and retrieval, reducing the computational overhead associated with identity verification. The pigeon's communicative and mimicry behavior of pigeon-inspired optimization (PIO) as well as the flamingo's foraging and migratory patterns of the Flamingo Search Algorithm (FSA) served as the basis for the proposed Flamieon-inspired optimization method. A Verifiable Data Credential is introduced to combine the elements of verifiable credentials and the Blockchain method to improve the security and trustworthiness of sharing data and verification in a decentralized manner. The proposed OIS methods achieve a value of 4.00% for Anonymization, 9989.57 for Gas ratio, 7445.70 KB for Memory usage, 17.32% for Network hash rate, 5.07 ms for Transaction latency, and 41,234.82 ms for Transaction Time. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： BC technology Flamieon-inspired optimization OrKey identity schema Self-sovereign identity Verifiable data credential

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dataset Quantization 39

Adaptive Dataset Quantization

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Muquan Zhang, Dongyang Dong, Qiang Xie, Xiurui Qin, Ke Institute of Intelligent Computing University of Electronic Science and Technology of China China

ISBN: (纸本)157735897X

Contemporary deep learning, characterized by the training of cumbersome neural networks on massive datasets, confronts substantial computational hurdles. To alleviate heavy data storage burdens on limited hardware resources, numerous dataset compression methods such as dataset distillation (DD) and coreset selection have emerged to obtain a compact but informative dataset through synthesis or selection for efficient training. However, DD involves an expensive optimization procedure and exhibits limited generalization across unseen architectures, while coreset selection is limited by its low data keep ratio and reliance on heuristics, hindering its practicality and feasibility. To address these limitations, we introduce a newly versatile framework for dataset compression, namely Adaptive Dataset Quantization (ADQ). Specifically, we first identify the sub-optimal performance of naive Dataset Quantization (DQ), which relies on uniform sampling and overlooks the varying importance of each generated bin. Subsequently, we propose a novel adaptive sampling strategy through the evaluation of generated bins' representativeness score, diversity score and importance score, where the former two scores are quantified by the texture level and contrastive learning-based techniques, respectively. Extensive experiments demonstrate that our method not only exhibits superior generalization capability across different architectures, but also attains state-of-the-art results. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Cloud Secure Storage based AES Method of Dispersion 5

A Cloud Secure Storage based AES Method of Dispersion

引用

5th IEEE Global Conference for Advancement in technology, GCAT 2024

作者： Ajitha Lokesh, N. Kumaran, B. Sivasangari, A. Gomathi, R.M. Roobini, M.S. Sathyabama Institute of Science and Technology School of Computing Chennai India

ISBN: (纸本)9798350376685

The popularity of cloud storage services is due to their convenience and fast access to data. However, security incidents like data leakage continue to occur, often caused by negligence or malicious attacks. To address this problem, a Cloud Secure Storage Mechanism (CSSM) has been proposed. The main objective of CSSM is to safeguard the confidentiality of cloud data by utilizing data dispersion and distributed storage. This approach involves encrypting, breaking down, and distributing data, which helps reduce the likelihood of data breaches at the storage *** utilizes a hierarchical management approach that combines user passwords with secret sharing to ensure the security of cryptographic materials. This method helps prevent the leakage of cryptographic materials and enhances the overall security of the cloud storage system. Experimental results have demonstrated the effectiveness of CSSM in safeguarding data security CSSM is a reliable and efficient solution for maintaining cloud data confidentiality and preventing data leakage at the storage layer. It can store a large amount of data in the cloud without significant time overhead. For instance, uploading or downloading a 5GB file with CSSM takes only 646 and 269 seconds, respectively, which is acceptable for users. Overall, CSSM offers a dependable and efficient method for securing cloud data. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Web-Based Framework for Evaluating Clustering Algorithms Across Multiple Datasets

Web-Based Framework for Evaluating Clustering Algorithms Acr...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Tiwari, Gyanendar Kumar Singh, Kshitij Dorathi Jayaseeli, J.D. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331509828

This research study develops a web-based framework to compare clustering algorithms based on multiple datasets, assess the performance of algorithmic based on dataset characteristics and clustering objectives. The framework designed to support such widely used algorithms such as KM, DBSCAN and Hierarchical Clustering, offers visual and quantitative analysis for performance comparison. This platform was designed to make it easier for users to try out various algorithms and different parameter settings and thus, help them to choose the best clustering methods for a range of data types. This work impacts that greater understanding of how effective clustering is based on different data structures and application contexts by providing a useful framework for data driven research and analysis. © 2025 IEEE.

关键词： clustering algorithms DBSCAN Hierarchical Clustering K-Means Web-based framework

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Handwritten Digit Recognition using MLP, CNN, LeNet-5 Model's

Comparative Analysis of Handwritten Digit Recognition using ...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Mughesh Kumar, N.R. Joshi, Siddharth Chanduri, Pranava Preethivardhan Sivakumar, S. Srm Institute of Science and Technology School of Computing Tiruchirappalli India

ISBN: (纸本)9798350375442

The analysis of three distinct neural network architectures for Handwritten Digit Recognition (HDR): Multi-Layer Perceptron (MLP), Simple Convolutional Neural Network (CNN), and LeNet-5. The MNIST dataset, an internationally renowned benchmark made up of 70,000 grayscale photos of handwritten numbers, is used to assess the models. To alleviate overfitting and improve model resilience, the data is pre-processed and split into training and validation sets using K-Fold cross-validation. The MLP architecture employs a fully connected layer (FCL) structure with three layers, achieving a training accuracy of 87.12% and a validation accuracy of 95.78% in 115 seconds of training time. The Simple CNN consists of two convolutional layers (CL) and two fully connected layers, yielding, after 395 seconds of training, a validation accuracy of 99.06% and a training accuracy of 99.76%. LeNet-5, with two convolutional layers and three fully connected layers, takes 168 seconds to train and achieves 99.38% training accuracy and 98.89% validation accuracy. Performance evaluation reveals that while the Simple CNN exhibits the highest accuracy (99.15%) on the test set, LeNet-5 offers a more balanced trade-off between training time and accuracy. This work underscores the varying capabilities of MLP, Simple CNN, and LeNet-5 architectures in HDR tasks, providing insights for selecting the appropriate model based on specific application requirements. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Survey of Non-Volatile Main Memory File Systems

引用

Journal of computer science & technology 2023年第2期38卷 348-372页

作者：王盈贾文庆蒋德钧熊劲 State Key Laboratory of Processors Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China Research Center for Advanced Computer Systems Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Non-volatile memories(NVMs)provide lower latency and higher bandwidth than block ***,NVMs are byte-addressable and provide persistence that can be used as memory-level storage devices(non-volatile main memory,NVMM).These features change storage hierarchy and allow CPU to access persistent data using load/store ***,we can directly build a file system on ***,traditional file systems are designed based on slow block *** use a deep and complex software stack to optimize file system *** design results in software overhead being the dominant factor affecting NVMM file ***,scalability,crash consistency,data protection,and cross-media storage should be reconsidered in NVMM file *** survey existing work on optimizing NVMM file ***,we analyze the problems when directly using traditional file systems on NVMM,including heavy software overhead,limited scalability,inappropriate consistency guarantee techniques,***,we summarize the technique of 30 typical NVMM file systems and analyze their advantages and ***,we provide a few suggestions for designing a high-performance NVMM file system based on real hardware Optane DC persistent memory ***,we suggest applying various techniques to reduce software overheads,improving the scalability of virtual file system(VFS),adopting highly-concurrent data structures(e.g.,lock and index),using memory protection keys(MPK)for data protection,and carefully designing data placement/migration for cross-media file system.

关键词： non-volatile main memory(NVMM) file system performance scalability crash consistency data protection crossmeida

来源：评论

学校读者我要写书评

暂无评论

Interactive tool for visualizing the comprehensive performance of evolutionary multi-objective algorithms applied to problems with two or three objectives

Interactive tool for visualizing the comprehensive performan...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Tomczyk, Michal Kadziński, Milosz Poznan University of Technology Institute of Computing Science Poznań Poland

ISBN: (纸本)9798400704956

The performance of evolutionary algorithms for multi-objective optimization is typically assessed by considering only the final populations. This is troublesome for the following reasons. First, it ignores most solutions constructed throughout the evolution, thus not portraying overall progression. Second, evolutionary methods are susceptible to randomness. Therefore, the results obtained from a single test run are unreliable. Third, these methods are complex algorithms that can be evaluated from many perspectives, not just by assessing the qualities of the final solutions they present. Overcoming these issues motivated the development of our novel visualization tool that accounts for robustness in assessment. It supports both 2D and 3D visualization, and, in the case of the latter, it introduces interactivity, allowing the inspection of presented results in a manner most suited to the user. The developed software is an inherent part of this paper and can be downloaded and re-used by researchers to foster their research. © 2024 held by the owner/author(s).

关键词： evolutionary multi-objective optimization

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：