检索结果-内蒙古大学图书馆

Advances in Data engineering and Intelligent Computing Systems (ADICS), International Conference on

作者： Mohammed Sameer K Sudharsan A Benazir Begum Dept.of Computer Science & Engineering Hindustan Institute of Technology and Science Chennai India

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

In response to the challenges posed by complex and hard-to-remember passwords in traditional authentication systems, this research introduces an innovative approach leveraging Low Rank Adaption (LoRA) fine-tuned Large Language Models (LLMs) to generate natural language-like strong passwords. Focused on striking a balance between usability and security, proposed system methodology employs smaller-sized pre-trained LLMs, adapted using LoRA fine-tuning, to produce passwords that are both strong and memorable. By addressing the limitations of current password generation practices, proposed system framework aims to encourage user adoption of secure practices, contributing to a positive societal impact through improved cybersecurity hygiene. The proposed solution involves deploying a fine-tuned LLM and serving them through an frontend web UI which emphasizes resource efficiency scalability of deployment of such model, and ease of using the generated passwords in real life authentication purposes fostering good cybersecurity practices among non-technical users.

关键词： Computational modeling Scalability Authentication Passwords Data engineering Data models Usability

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Leap Motion Controller-Based Hand Gesture Datasets

A Comprehensive Review of Leap Motion Controller-Based Hand ...

引用

2023 IEEE International Conference on Next Generation Electronics, NEleX 2023

作者： Chakravarthi, Bharatesh Prabhu Prasad, B.M. Imandi, Raju Pavan Kumar, B.N. School of Computing and Augmented Intelligence Arizona State University TempeAZ United States Indian Institute of Information Technology Dept. of Computer Science and Engineering Dharwad India Indian Institute of Information Technology Sri City Dept. of Computer Science and Engineering Chittoor India

ISBN: (纸本)9798350319088

This paper comprehensively reviews hand gesture datasets based on Ultraleap's leap motion controller, a popular device for capturing and tracking hand gestures in real-time. The aim is to offer researchers and practitioners a valuable resource for developing and evaluating gesture recognition algorithms. The review compares various datasets found in the literature, considering factors such as target domain, dataset size, gesture diversity, subject numbers, and data modality. The strengths and limitations of each dataset are discussed, along with the applications and research areas in which they have been utilized. An experimental evaluation of the leap motion controller 2 device is conducted to assess its capabilities in generating gesture data for various applications, specifically focusing on touchless interactive systems and virtual reality. This review serves as a roadmap for researchers, aiding them in selecting appropriate datasets for their specific gesture recognition tasks and advancing the field of hand gesture recognition using leap motion controller technology. © 2023 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Design and Characterization of a Ka-Band Parasitic Patch Antenna for 5G Applications 9

Design and Characterization of a Ka-Band Parasitic Patch Ant...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Kouser, Kahkashan Hannan, Mohammad Shafi, Faizan Aknan, Mohammad Dept. of Computer Science & Engineering Bihar Motihari India Rajiv Gandhi Institute of Petroleum Technology Dept. of Electrical and Electronics Engineering Uttar Pradesh Amethi India Indian Institute of Technology Dept. of Electrical Electronics and Communication Engineering Dharwad India

ISBN: (纸本)9798350377972

He design of parasitic patch antennas for high-frequency applications, such as 5G millimeter-wave (mm-wave) communication, presents several challenges, including achieving high gain, wide bandwidth, and efficient impedance matching within a compact structure. Recent techniques, such as the use of parasitic elements and stepped impedance feedlines, have shown promise in enhancing antenna performance. However, these methods still face limitations related to fabrication complexity, signal degradation, and reliability under varying conditions. This work introduces a circular patch antenna with a parasitic reflector element specifically designed for Ka-band applications at 28 GHz. The proposed design addresses these challenges by optimizing the placement of parasitic elements to achieve high gain, a wide bandwidth of 2 GHz, and stable VSWR performance across the operating range. The single-layer, single-side etching structure further simplifies fabrication, making it suitable for compact wireless *** design of parasitic patch antennas for high-frequency applications, such as 5G millimeter-wave (mm-wave) communication, presents several challenges, including achieving high gain, wide bandwidth, and efficient impedance matching within a compact structure. Recent techniques, such as the use of parasitic elements and stepped impedance feedlines, have shown promise in enhancing antenna performance. However, these methods still face limitations related to fabrication complexity, signal degradation, and reliability under varying conditions. This work introduces a circular patch antenna with a parasitic reflector element specifically designed for Ka-band applications at 28 GHz. The proposed design addresses these challenges by optimizing the placement of parasitic elements to achieve high gain, a wide bandwidth of 2 GHz, and stable VSWR performance across the operating range. The single-layer, single-side etching structure further simplifies fabrication, making it suitable

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

Attention-Based AdaptSepCX Network for Effective Student Action Recognition in Online Learning

引用

Procedia computer science 2024年 233卷 164-174页

作者： Arnab Dey Anubhav Anand Subhajit Samanta Bijay Kumar Sah Samit Biswas Dept. of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur Howrah 711103 India

In the realm of online learning and distance education, the issue of inadequate supervision looms large, posing a significant obstacle. This paper delves into the challenges posed by the lack of supervision in online learning environments and proposes an innovative solution to understand and recognize students’ behaviors. This study's primary objective is to detect and recognize students’ actions in images captured through webcam. This task distinguishes itself from the well-established video-based student action recognition domain, which relies on temporal cues. Recognizing student actions from images intensifies the complexity of the problem. To meet this challenge, a novel deep learning model named AdaptSepCX Attention, specifically designed for student action recognition in online learning environments, is introduced. The proposed method exhibits exceptional performance with 92.73% validation accuracy on the Student Online Action Image dataset (SOAId), a carefully curated collection comprising 2029 student-centric images. The proposed model outperforms well-established models such as DenseNet121, NASNet Mobile, Con-vXNet, DELVS1 and MobileNetV2 in student action recognition. Action recognition for students has broader implications beyond the online classroom. It has the potential to revolutionize educational technology, making online learning more interactive and engaging. Enabling machines to understand and respond to student actions enhances education, personalizes learning, and supports students’ academic success and well-being. This research enhances the understanding of student involvement in online learning and offers an effective solution for recognizing actions from images.

关键词： Students Action Recognition Action Recognition Online Learning Attention Adaptive Seperable Convolution Network

来源：评论

学校读者我要写书评

暂无评论

Block-Hash Signature (BHS) for Transaction Validation in Smart Contracts for Security and Privacy using Blockchain

引用

Journal of Mobile Multimedia 2023年第4期19卷 935-962页

作者： Bhatnagar, Sonika Dayal, Mohit Singh, Deepti Upreti, Shitiz Upreti, Kamal Kumar, Jitender Dept. of Computer Science & Engineering Government Polytechnic Baheri Bareilly India Dept. of Applied Science Bharati Vidyapeeth’s College of Engineering New Delhi India Dept. of Information Technology ABES Institute of Technology Ghaziabad India Dept.of Information Technology Asian Education Group (AEG) Noida India Dept. of Computer Science & Engineering Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India Dept. of Computer Science & Engineering J.C Bose University of Science & Technology YMCA Haryana Faridabad India

Some of the well-known signature techniques like Winternitz and Lamport are not considered to be very appropriate for the usage of hashing or smart contracts in Blockchains security because of their size O(n²), which is prominently too high. Although in Blockchain, the security concern is on the top priority because of its distributed P2P design still, the security enhancement is required to sign and verify the documents forwarded to the peers, especially in Hyperledger Fabric. Here, this paper presents a new signature technique “Block-Hash” to enhance Blockchain security by using it in smart contracts as well as hashing with size 3Xn bits (n = 256, generally for SHA-256 Hashing) and which can score 112 bits security. The proposed signature can be used appropriately for signing a smart contract by the endorser or committer node. Also, it can be used with a hash algorithm in forming a Merkle tree. Apart from the description and implementation of Block-Hash Signature, this paper has covered the analysis of its security and correctness measures with a table for result comparison. © 2023 River Publishers.

关键词： blockchain security Digital signature hyperledger fabric smart contract

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of ML Algorithms for Load Redistribution Attack Detection 1

Comparative Study of ML Algorithms for Load Redistribution A...

引用

1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

作者： Verma, Praveen Dasgupta, Pallab Chakraborty, Chandan School of Energy Science & Engineering Indian Institute of Technology Kharagpur India Indian Institute of Technology Dept. of Computer Science & Engineering Kharagpur India Indian Institute of Technology Dept. of Electrical Engineering Kharagpur India

ISBN: (纸本)9798350398069

A Load Redistribution (LR) attack is a special type of False Data Injection (FDI) attack on the power grid in which the attacker manipulates the load request. This manipulation results in false dispatch decisions by the grid operator, which causes congestion/overflow in the lines and uneconomic operation of the grid. The drawbacks of conventional detection mechanisms have motivated researchers to explore data-driven mechanisms employing Machine Learning (ML) techniques. This paper presents a comparative study of the performance of 6 different ML algorithms for detecting LR attacks on the IEEE 30 bus test system. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Critical Load Identification for Load Redistribution Attacks 11

Critical Load Identification for Load Redistribution Attacks

引用

11th International Conference on Innovative Smart Grid Technologies - Asia, ISGT-Asia 2022

作者： Verma, Praveen Gupta, Sagar Dasgupta, Pallab Chakraborty, Chandan School of Energy Science & Engineering Indian Institute of Technology Kharagpur India Indian Institute of Technology Dept. of Computer Science & Engineering Kharagpur India Indian Institute of Technology Dept. of Electrical Engineering Kharagpur India

ISBN: (纸本)9798350399660

The smart integration of communication and information technology into electrical power grids has significantly benefited the monitoring and operations of the grid, but it has also made it vulnerable to cyber attacks. A Load Redistribution (LR) attack is a type of attack in which the attacker manipulates one or more load requests to create an overflow (congestion) in a transmission line. The cost and limitations of conventional detectors have motivated researchers to explore Machine Learning (ML) and data driven mechanisms for detecting potential LR attacks. The expanding nature of the grid and the rapidly increasing number of loads on a grid necessitates the monitoring of a huge number of points and creates a data deluge for the ML-based detectors, thereby adversely affecting their performance. This paper provides an approach for identifying a subset of loads, namely critical loads, that needs to be monitored for detecting LR attacks. This helps the grid operator to monitor fewer loads thereby reducing the cost of monitoring the loads, the detection time, and the computational burden. The proposed approach is implemented on the IEEE 30 bus system. The results validate the fact that LR attacks can be detected by monitoring only the identified critical loads, without adversely affecting the performance of the ML detectors. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT: Communication protocols and security threats

引用

Internet of Things and Cyber-Physical Systems 2023年第1期3卷 1-13页

作者： Gerodimos, Apostolos Maglaras, Leandros Ferrag, Mohamed Amine Ayres, Nick Kantzavelou, Ioanna School of Computer Science and Informatics University of Thessaly Lamia Greece School of Computing at Edinburgh Napier University Edinburgh United Kingdom Technology Innovation Institute Abu Dhabi United Arab Emirates School of Computer Science and Informatics De Montfort University Leicester United Kingdom School of Engineering Dept.of Informatics and Computer Engineering University of West Attica Athens Greece

In this study, we review the fundamentals of IoT architecture and we thoroughly present the communication protocols that have been invented especially for IoT technology. Moreover, we analyze security threats, and general implementation problems, presenting several sectors that can benefit the most from IoT development. Discussion over the findings of this review reveals open issues and challenges and specifies the next steps required to expand and support IoT systems in a secure framework. © 2023 The Authors

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Creation of a Digital Rig Vedic Index (Anukramani) for Computational Linguistic Tasks 18

Creation of a Digital Rig Vedic Index (Anukramani) for Compu...

引用

18th World Sanskrit Conference

作者： Mahesh, A.V.S.D.S. Bhattacharya, Arnab Dept. of Computer Science and Engineering Indian Institute of Technology Kanpur India

ISBN: (纸本)9781950737710

Rig Veda, the oldest text in Vedic Sanskrit, is a collection of hymns addressed to various devatas. We present an index of Rig Vedic verses along with the respective devata, rsi and chandas which is, in short, a digitized form of the well known Rig Vedic Anukramani. We then build several deep learning based language models from the corpus. The models are tested on a downstream classification task that predicts the devata associated with a given verse. The six classifiers we test are based on FastText, ELMo, ALBERT, Word2Vec, GloVe and RoBERTa language models pretrained on the GRETIL data. We find that RoBERTa outperforms the other models on this task and achieves an accuracy of 77.3%. © 2022 Proceedings of the Computational Sanskrit and Digital Humanities at the 18th World Sanskrit Conference. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A technique for optimum distribution of watermark in a document image 4

A technique for optimum distribution of watermark in a docum...

引用

4th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2022

作者： Das, Nandini Pal, Tamal Indian Institute of Engineering Science and Technology Dept. of Computer Science and Technology Shibpur Howrah India

ISBN: (纸本)9781665402392

Watermarking is a very useful technique to ensure the integrity of a document image. But when too many bits are embedded into image, it reduces quality of the document. When limited number of watermark bits are used, these should not be concentrated in background or few parts of the image. As very few existing techniques address this issue, in this paper, we propose a watermark distribution scheme, which divides image into optimum number of segments and distributes watermark based on information content such that watermark is well spread across the document. After embedding, on average the proposed scheme achieves 31.79% more area with ensuring 38.59% better quality in terms of PSNR compared to state-of-the-art schemes. © 2022 IEEE.

关键词： Signal to noise ratio

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：