检索结果-内蒙古大学图书馆

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Kumar, Kotyada Mohan Kiran Ullas, Karthik Reddy, Vivek Srikar Snehitha, Munaga Sai Malkhed, Mahadevi E. Kumar, K. Dinesh Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India Amrita School of Engineering Amrita Vishwa Vidyapeetham Dept. of Electronics and Computer Engineering Bengaluru India

ISBN: (纸本)9798331504403

With the dawn of the new age of communication, i.e., social media, the world has come into the palms of every individual at every corner of the world. However, easier access to messaging implies easier forms of abuse. As the usage of social media increases, the other side of communication, bullying, also increases. Cyberbullying refers to the concept of harassing individuals or groups through means of the internet with the help of messages or multimedia. Cyberbullying has a huge impact on mental health and research is ongoing in this area to accurately detect bullying text. Existing models are embedded into social media platforms to either ban or apply sanctions on the users involved in the passage of such materials. The proposed study aims to develop a model with a similar approach to detect cyberbullying in comment text. Also, sentiment analysis is performed on the comment text to get an idea of the message's context, thus improving the chances of bullying detection. The work is divided into two stages. In the first stage, the text and the sentiment score are directly passed to the machine learning models. Later, during the second stage word embedding using Word2Vec, a natural language processing technique, is performed on the comment text to obtain vectorized features which are then given to the machine learning models along with sentiment features. It was observed that the latter model shows high levels of success and that it can be deployed in real-world applications. © 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

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Multi-DNN Inference 30

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Mul...

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Kang, Woosung Lee, Jinkyu Lee, Youngmoon Oh, Sangeun Lee, Kilho Chwa, Hoon Sung DGIST Dept. of Electrical Engineering and Computer Science Korea Republic of Dept. of Computer Science and Engineering Korea Republic of Hanyang University Dept. of Robotics Korea Republic of Ajou University Department of Software and Computer Engineering Korea Republic of School of AI Convergence Soongsil University Korea Republic of

ISBN: (纸本)9798350358414

The increasing complexity and memory demands of Deep Neural Networks (DNNs) for real-Time systems pose new significant challenges, one of which is the GPU memory capacity bottleneck, where the limited physical memory inside GPUs impedes the deployment of sophisticated DNN models. This paper presents, to the best of our knowledge, the first study of addressing the GPU memory bottleneck issues, while simultaneously ensuring the timely inference of multiple DNN tasks. We propose RT-Swap, a real-Time memory management framework, that enables transparent and efficient swap scheduling of memory objects, employing the relatively larger CPU memory to extend the available GPU memory capacity, without compromising timing guarantees. We have implemented RT-Swap on top of representative machine-learning frameworks, demonstrating its effectiveness in making significantly more DNN task sets schedulable at least 72% over existing approaches even when the task sets demand up to 96.2% more memory than the GPU's physical capacity. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying wireless IOT ICU traffic with machine learning models 19

Classifying wireless IOT ICU traffic with machine learning m...

引用

19th International Conference on Future Networks and Communications, FNC 2024 / 21st International Conference on Mobile systems and Pervasive Computing, MobiSPC 2024 / 14th International Conference on Sustainable Energy Information Technology, SEIT 2024

作者： Sibai, Fadi N. Sibai, Ahmad Electrical & Computer Engineering Dept. Gulf University for Science and Technology Mishref Kuwait Computer Science & Engineering Dept. University of South Florida TampaFL33620 United States

In this work, we classified the wireless internet of things (IoT) traffic of the IoT Health intensive care unit (IHI) dataset which belongs to three general classes: patient monitoring, environment monitoring, and network attack. We trained and tested 7 machine learning (ML) models with Orange 3 including kNN, Decision Tree (tree), SVM, Random Forest (RF), Neural Network (NN), Gradient Boosting (GB), and AdaBoost (AB). With the original dataset, 5 ML models performed perfect classification. After pruning the dataset columns by keeping the features with the highest correlations with the label in the dataset, good classifications were obtained with only 4 TCP/IP features by the Gradient Boosting, kNN, and RF models with MSEs in the range 0.008-0.011, and R2s in the range 0.978-0.984. With only 6 MQTT features, Gradient Boosting, RF, Tree, and NN were the top classifiers with MSEs in the range 0.073-0.074, and R2s in the range 0.856-0.859. This work demonstrates the effectiveness of guiding the feature pruning process by the values of the correlation coefficients in order to minimize the long training times of ML models while achieving good accuracies. © 2024 The Authors. Published by Elsevier B.V.

关键词： correlation coefficient feature pruning Internet of things IOT health intensive care unit dataset machine learning network security

来源：评论

学校读者我要写书评

暂无评论

Multispectral Satellite Data Classification Using Rank Correlation Similarity Index and Automatic Labeling Technique

引用

SN computer Science 2024年第8期5卷 1073页

作者： Ain, Arindom Gogoi, Minakshi Chutia, Dibyajyoti Dept. of Computer Science and Engineering GIMT Under Assam Science and Technology University Assam Guwahati India Dept. of Computer Science and Engineering Girijananda Chowdhury University Assam Guwahati India NESAC Umium Shillong India

Multispectral satellite image classification is crucial in remote sensing and image analysis, serving various applications like water area extraction, urban region classification, and vegetation monitoring. Model-based classification, particularly supervised learning approaches, heavily relies on manually annotated training samples, which are labor-intensive and subject to human bias. However, solely depending on features derived from individual pixels may fail to capture spatial contextual information effectively and manage mixed pixels and various types of noise, resulting in classification inaccuracies. To address these challenges, this research proposes a novel unsupervised learning approach and automatic labeling technique (ALT). This approach utilizes collective information from groups of pixels instead of relying solely on individual pixels for identification and extraction of meaningful unique patterns which serves as the most significant factor for satellite image classification. A new similarity index, the patch similarity index (PSI), is generated by incorporating the rank correlation similarity index (RCSI). The PSI is used to determine the similarity factor both between the patches and within the patch. Subsequently, a clustering algorithm is employed to group pixels into four distinct classes: vegetation, water, built-ups, and open land. Additionally, ALT streamlines the post-classification process by reducing the need for manual intervention in mapping clusters to the actual class label. The proposed method offers a more accurate and reliable unsupervised classification for multispectral satellite imagery, promising enhanced efficiency and reduced manual labor. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automatic labeling technique Frequent masking Multispectral Patch similarity index Rank Correlation

来源：评论

学校读者我要写书评

暂无评论

Multi-label Bengali Abusive Comments Classification using Problem Transformation Method 20

Multi-label Bengali Abusive Comments Classification using Pr...

引用

20th International Conference on Electrical engineering, Computing Science and Automatic Control, CCE 2023

作者： Khan, Tahsin Tasnia Hassan, Abid Ahamed, Md Faysal Islam, Samiul Rajshahi University of Engineering & Technology Dept. of Electrical & Computer Engineering Rajshahi Bangladesh North South University Dept. of Electrical & Computer Engineering Dhaka Bangladesh International Standard University Dept. of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350306767

Sentiment analysis on the Bengali language is limited to binary and multi-class classifications. This paper focuses on the multi-label classification of the Bengali abusive social media comments dataset having 10220 rows of different social media negative comments using the problem transformation method. The texts are categorized into five labels: toxic, threat, obscene, insult, and racism. Three different multi-label approaches: Binary Relevance, Label Powerset, and Classifier Chain combined with three popular machine learning algorithms: Multinomial Naive Bayes, Random Forest, and Logistic Regression are implemented in this research. This study evaluates the performance of these models by applying them to various classification scenarios, considering five-label, four-label, three-label, and two-label classifications independently. Our research outcomes are evaluated with some performance indicators: Accuracy, Precision, Recall, F1-Scores, Confusion matrix, Macro-average, and Hamming score. The combination of Label Powerset and Logistic Regression outperformed the other two classifier-model combinations because of their quick adaptation to the dataset with an accuracy of 88.07% for five label classifications, 90.12% for four label classifications, 90.56% considering three label classifications and 92.67% for two label classification individually. With 88.07% accuracy, the Label Powerset with Logistic Regression approach can be applied to classify five types of sentiment in a single text. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Digital Forensic Data for Unbreakable Trust and Security

Blockchain Based Digital Forensic Data for Unbreakable Trust...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Imrankhan, M. Viji, M. Sathishkumar, R. Gnanaprakash, T. Roshan, R. Karthik Saravanan, G. Manakula Vinayagar Institute of Technology Dept. of Cse Puducherry India Sri Manakula Vinayagar Engineering College Dept. of Computer Science and Business Systems Puducherry India

ISBN: (纸本)9798331510022

This can be one of the most magnificent advantages realized from applying blockchain technology in a forensic investigation context, namely, a transformative approach to address challenges embedded within legal and criminal justice systems. For example, smart contracts, being self-executing agreements with the automated inclusion of predefined rules, may even automate and secure the process of tracking evidence, managing chain of custody, and access control. This smart contract will ensure that forensic operations are transparent and of sound integrity. Every transaction and action performed on the blockchain is recorded there, instantaneously bringing down tampering to the lowest possibility and any chance for human mistakes. Regarding decentralized nature and cryptography-based security combined with immutability, blockchain is a technology known to have safeguards over sensitive data. Once recorded on the blockchain, the information thereupon becomes completely un-changeable, assuring the reliability and authenticity of evidence. This will be especially important in the management of an unforgeable chain of custody and in ensuring that forensic evidence remains unchanged and can be relied on with integrity throughout the court process.[6] Critical data can then be maintained tamper-proof for management and storage by developing Ethereum-based smart contracts on Remix IDE using Solidity.[15]Each transaction will be time-stamped and safely logged on the Ethereum blockchain, thus developing an unchallenged ledger that makes any investigation that much more trustworthy. In a nutshell, the application of blockchain in forensic activities builds greater control and efficiencies, reduces possible errors and conflicts, and provides transparency, integrity, and an unchangeable, permanent record for forensic processes. The invention thereby significantly upgrades the general integrity and confidence in legal and criminal justice inquiries. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Re-Cognition I: An Inspection of Learner's Cognitive Well-Being, Pursuant to Contemporary Period, Facilitates the Academic Life Cycle 6

Re-Cognition I: An Inspection of Learner's Cognitive Well-Be...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Ganguly, Souvik Pati Mandal, Kailash Guha, Debasis Dr. B.C. Roy Engineering College Dept. of Computer Application Durgapur India National Institute of Technology Dept. of Computer Science and Engineering Durgapur India

ISBN: (纸本)9798350306613

Recommender systems enhance the user experience by integrating factual and behavioral practices, enhancing learning strategies, and granting academic opportunities based on learners subjective interests. Cognitive intelligence, a learner's capability to interpret and synthesize cognitive abilities, is crucial to assemble effective recommendations. However, a student encounters diverse adversities in his or her academic life, whether it is his or her academic pacers or outward circumstances. As a result, a learner consequently experienced severe academic setbacks. Thus, this paper proposes a novel approach to identify cognitive deficits of learners in a school or college before recommending any scholastic content or pertaining in any academic activity. We have employed a modified Bi-directional Gated Recurrent Unit (Bi-GRU) method in conjunction with Shuffled Frog Leaping Algorithm (SFLA). Our approach overcomes some of the shortcomings of conventional Bi-GRU method in choosing the right scaling parameters during training. Bi-GRU method is opted for detecting the cognitive deficits of a learner and SFLA is applied over Bi-GRU in order to hyper-Tune the parameters. The proposed method is compared with a few cutting-edge methods, and the experimental result outperforms the other methods in training, validation, and testing accuracies, achieving 99.34%, 98.98%, and 99.19% respectively. © 2024 IEEE.

关键词： Bi-directional GRU Cognitive Deficits Cognitive Equilibrium Learner's Mental State Meta-heuristic Optimization SFLA

来源：评论

学校读者我要写书评

暂无评论

Multi-Layered Security Techniques for Protecting Cooperative Relay Networks from Eavesdropping

Multi-Layered Security Techniques for Protecting Cooperative...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Upadhyay, Abhay Gupta, Mridul Dhondiyal, Shiv Ashish Asudani, Deepak Suresh Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Dept. of Computer Science and Engineering Dehradun India Pune India

ISBN: (纸本)9798331542344

In this paper, we study the multi-layered security approaches for cooperative relay networks against passive eavesdropping adversaries. Specifically, we investigated physical layer approaches (i.e., beamformed and artificial noise injections) to improve the signal defence ability at a much lower eavesdropping capacity. Trade-offs in these cryptographic methods were studied in terms of encryption strength vs. decryption time under different loads on the network. The security of the network layer was assessed by measuring packet delivery ratios and data integrity violations under malicious nodes. Results show that multi-layer security is performed at the cost of performance, but much better network defence mechanisms are proposed overall. While this end-To-end approach strikes a reasonable balance between security and real-world performance considerations, it presents itself as a sensible solution for securing network communications against eavesdropping threats. © 2024 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

YOLOv3 based Reinforcement learning for mobile game playing policy

引用

Transactions of the Korean Institute of Electrical Engineers 2022年第1期71卷 233-238页

作者： Lee, Taehak Cho, Youngwan Dept. of Computer Engineering SeoKyeong University Korea Republic of

This paper proposes a reinforcement learning model that constructs a sequential behavioral decision policy for playing a game by extracting feature points in an environment in which a game image is given. In this paper, we propose a method of optimizing performance through state domain reduction, transfer learning, and multi-agent-based modeling to obtain the maximum score available for game environments that must continue their actions and have time limitations in decision making. These methods were implemented for the 'Timberman' game environment and experimented with learning performance by applying them as a player's behavioral policy to evaluate the trained model. © 2022 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Using Multi-Modal Fusion Combined with Attention Mechanism 4

Deepfake Detection Using Multi-Modal Fusion Combined with At...

引用

4th International Conference on Sustainable Expert systems, ICSES 2024

作者： Shirley, C.P. Berin Jeba Jingle, I. Abisha, M.B. Venkatesan, R. Yashvanth Ram, R.V. Elango, Elakkiya Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India Government Arts College for Woman Dept. of computer Science Sivaganga India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540364

The proliferation of deepfake technology poses a significant challenge to the authenticity of digital content. This research explores the application of multimodal fusion techniques to enhance deepfake detection accuracy. By combining visual and audio features, the proposed method leverages the complementary nature of different data types to detect discrepancies introduced by deepfake manipulation. An attention mechanism is incorporated to focus on salient regions within each modality, further improving detection accuracy. Convolutional Neural Networks (CNNs) and Mel-Frequency Cepstral Coefficients (MFCCs) are employed for feature extraction, followed by feature fusion for deepfake detection. This approach demonstrates the effectiveness of multimodal fusion in combating the evolving threat of deepfake technology. By advancing deepfake detection techniques, this research contributes to safeguarding the integrity of digital content and preserving trust in media. © 2024 IEEE.

关键词： Convolutional neural networks

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：