检索结果-内蒙古大学图书馆

Disruptive technologies (ICDT), International Conference on

作者： Kiran Kumar C B. Aruna Devi Lakshmana Phaneendra Maguluri Mahaveer Singh Naruka Data Science Codecraft Technologies Bangalore Karnataka India Department of Electronics and Communication Engineering Dr.NGP Institute of Technology Coimbatore Tamil Nadu India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur AP India GL Bajaj Institute of Technology and Management Greater Noida India

The classification of real time images from the fast data capturing devices in Internet of Things (IoT) environment is a critical task. It requires suitable processing and development of a model for increased accuracy in classifying the objects in real-time. Therefore, the necessity in improving the accuracy of classifying the instances is needed post performing the modelling, building and development of a model. In this paper, a three-dimensional (3D) Convolutional Neural Network (CNN) is developed to increase the process of classification for the objects in the real-time environment. The objects needed to train the classifier is supplied and the model is built in python environment. The results show an increased classification accuracy in detecting multi-objectives than the state-of-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING APPLICATION for IMAGE ENHANCEMENT 9

DEEP LEARNING APPLICATION for IMAGE ENHANCEMENT

引用

9th International Conference "Distributed Computing and Grid technologies in science and education", GRID 2021

作者： Elaraby, Ahmed Elansary, Ismail Nechaevskiy, Andrey Department of Computer Science Faculty of Computers and Information South Valley University Qena83523 Egypt Modern Academy for Computer Science and Management Technology Cairo Egypt Meshcheryakov Laboratory of Information Technologies Joint Institute for Nuclear Research Joliot-Curie 6 Dubna 141980 Russia

Recently, deep learning has obtained a central position toward our daily life automation and delivered considerable improvements as compared to traditional algorithms of machine learning. Enhancing of image quality is a fundamental image processing task and. A high-quality image is always expected in several tasks of vision, and degradations like noise, blur, and low-resolution, are required to be removed. The deep techniques approaches can significantly and substantially boost performance compared with classical ones. One of the main research areas where deep learning can make a major impact is imaging. This work presents a survey of deep learning on image enhancement and describes its potential for future research. Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

arXiv

引用

arXiv 2024年

作者： Liang, Weixin Izzo, Zachary Zhang, Yaohui Lepp, Haley Cao, Hancheng Zhao, Xuandong Chen, Lingjiao Ye, Haotian Liu, Sheng Huang, Zhi McFarland, Daniel A. Zou, James Y. Department of Computer Science Stanford University United States Machine Learning Department NEC Labs America United States Department of Electrical Engineering Stanford University United States Graduate School of Education Stanford University United States Department of Management Science and Engineering Stanford University United States Department of Computer Science UC Santa Barbara United States Department of Biomedical Data Science Stanford University United States Department of Sociology Stanford University United States Graduate School of Business Stanford University United States

We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Building Device Models Using LLMs for Requirements Simulation in Smart Homes

Building Device Models Using LLMs for Requirements Simulatio...

引用

IEEE International Requirements Engineering Conference Workshops (REW)

作者： Shi Chen Xiaohong Chen Zhi Jin Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Key Laboratory of High-Confidence Software Technologies Peking University Ministry of Education China Department of Computer Science and Technology Peking University Beijing China

ISBN: (数字)9798350395518

ISBN: (纸本)9798350395525

The implementation of model-based requirements simulations in smart homes is an effective strategy that allows users to comprehend the execution impact of their personalized needs before deployment. This necessitates the use of device models in advance. In this paper, we propose an automatic modeling method for smart home devices that utilizes a Large Language Model (LLM) to assist end users in modeling their devices. The method involves extracting information directly from device manuals using the extraction capabilities of the LLM, deducing the automata models using the reasoning capabilities of the LLM, and verifying the model quality through the properties of valid device models. Our evaluation has demonstrated that our method can generate high-quality device models. The resultant model can be utilized for smart home scenario simulations, assisting users in validating their requirements. Thus, this provides a cost-effective and scalable solution for offering device models to simulate user requirements in smart homes.

关键词： Large language models Conferences Automata Smart homes Manuals Information retrieval Cognition

来源：评论

学校读者我要写书评

暂无评论

EtherClue:Digital investigation of attacks on Ethereum smart contracts

引用

Blockchain(Research and Applications) 2021年第4期2卷 12-29页

作者： Simon Joseph Aquilina Fran Casino Mark Vella Joshua Ellul Constantinos Patsakis Department of Computer Science University of MaltaMsidaMSD 2080Malta Department of Informatics University of PiraeusPiraeus18534Greece Information Management Systems Institute Athena Research CenterMarousi15125Greece Centre for Distributed Ledger Technologies University of MaltaMsidaMSD 2080Malta

Programming errors in Ethereum smart contracts can result in catastrophic financial losses from stolen *** vulnerability detectors can prevent vulnerable contracts from being deployed,this does not mean that such contracts will not be *** a vulnerable contract is instantiated on the blockchain and becomes the target of attacks,the identification of exploit transactions becomes indispensable in assessing whether it has been actually exploited and identifying which malicious or subverted accounts were *** this work,we study the problem of post-factum investigation of Ethereum attacks using Indicators of Compromise(IoC)specially crafted for use in the *** definitions need to capture the side-effects of successful exploitation in the context of the Ethereum ***,we define a model for smart contract execution,comprising multiple abstraction levels that mirror the multiple views of code execution on a ***,we compare IoCs defined across the different levels in terms of their effectiveness and practicality through EtherClue,a prototype tool for investigating Ethereum security *** results illustrate that coarse-grained IoCs defined over blocks of transactions can detect exploit transactions with less ***,they are contract-specific and suffer from false *** the other hand,fine-grained IoCs defined over virtual machine instructions can avoid these pitfalls at the expense of increased computation,which is nevertheless applicable for practical use.

关键词： Blockchain forensics Ethereum attacks Indicators of compromise Ethereum operational semantics

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Key management for Intrusion Detection In Cloud Storage Based On PLS And SVM Model

A Secure and Efficient Key Management for Intrusion Detectio...

引用

2024 International Conference on Integration of Emerging technologies for the Digital World, ICIETDW 2024

作者： Suresh Kumar, A. Rajesh Kumar, A. Manoranjithem, V. Ramakrishna, B. Gottumukkala, Prasanthi Thulasimani, T. Rathinam Technical Campus Department of Computer Science and Engineering Coimbatore India N.S.N. College of Engineering and Technology Department of CSE Tamil Nadu India Kalasalingam Academy of Research and Education India CVR College of Engineering Department of Emerging Technologies (CSE-DS) Telangana India Gokaraju Rangaraju Institute of Engineering and Technology Department of Information Technology Hyderabad India Bannari Amman Institute of Technology Department of Mathematics Erode India

ISBN: (纸本)9798331541170

Cloud computing, a novel way of storing and processing data, has become an essential tool for many individuals very soon. With the proliferation of AI and big data, it is now standard practice in manufacturing to employ these technologies to discover novel approaches to enhancing decision-making or to accelerate production. This proposed method consists of three phases: preprocessing, feature extraction, and model training. The goal of text preprocessing is to enhance the quality and utility of the text data so that it is better suited for additional analysis or modeling. Equations such as symmetric uncertainty, gain ratio, IG, chi-squared, and other filter-based feature selection approaches are employed for feature selection. We used a PLS-SVM to train the model. The proposed methodology outshines more traditional methods. After using the strategy, the accuracy was enhanced by 95.43%. © 2024 IEEE.

关键词： Cloud Computing Intrusion Detection System Partial Least Square Model (PLS)

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Image Hiding Algorithm Transform Using Wavelet and SHA-512

A Discrete-Time Image Hiding Algorithm Transform Using Wavel...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Santosh Kumar Savya Sachi Neetu Avnish Kumar Abhishek Jain M.S.R. Prasad CSE-IOT Noida Institute of Engineering and Technology Greater Noida Department of Information Technology Lalit Narayan Mishra College of Business Management Muzaffarpur Bihar India College of Smart Computing COER University Roorkee U.K. India Department of Computer Science and Engineering Glocal University Saharanpur Department of Computer Science and Engineering Uttranchal University Dehradun U.K. India Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation Guntur AP India

Steganography is an ancient technique used to conceal information within another medium, enhancing security alongside cryptographic methods. This paper's steganography approach revolves around concealing data within the skin region of a cover image converted from RGB to YCbCr colour space. The YCbCr colour model facilitates skin tone detection, employing its components Yellow, Chromatic Blue, and Chromatic Red. The secret information is first encrypted using the SHA-512 algorithm for robust data hiding. Next, a frequency domain approach, specifically the Discrete Wavelet Transform (DWT), is employed for embedding, proving more effective than the Discrete Cosine Transform (DCT). The key idea is to use an object-oriented steganography mechanism that focuses on tracking skin tone objects within the image, thereby enhancing security. The secret encrypted data is embedded in one of the high-frequency sub-bands of DWT, specifically within skin pixels in that sub-band. This approach demonstrates higher security levels through experimentation while maintaining satisfactory PSNR (Peak Signal-to-Noise Ratio) values. By adopting this technique, the paper highlights an efficient and secure way to achieve hidden communication without compromising the cover image's visual quality.”

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized and Lightweight Cross-Chain Transaction Scheme Based on Proxy Re-signature 23

Decentralized and Lightweight Cross-Chain Transaction Scheme...

引用

23rd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2024

作者： Zou, Huiying Duan, Jia Liu, Xi Ren, Wei Li, Tao Zheng, Xianghan Choo, Kim-Kwang Raymond Hunan Engineering Research Center of Geographic Information Security and Application The Third Surveying and Mapping Institute of Hunan Province Hunan China China University of Geosciences School of Computer Science Wuhan China Sichuan University Ministry of Education Key Laboratory of Data Protection and Intelligent Management China Casm State Key Laboratory of Geo-Information Engineering Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of Mnr Beijing China Fuzhou University College of Computer and Big Data China Sanya College School of Information and Intelligent Engineering China University of Texas at San Antonio Department of Information Systems and Cyber Security San Antonio United States

With the widespread application of digital assets and the rapid development of blockchain technology, achieving secure and efficient transactions between different blockchain networks has become an urgent challenge. Existing cross-chain methods impose limitations, e.g., hash lock technology exhibits low scalability, side-chain technology is overly complex, and notary schemes pose centralization risks. In order to address these issues, we propose a cross-chain transaction solution based on proxy re-signature technology. To tackle the centralization concerns, we employ proxy re-signature technology to decentralize the authority of notaries among transaction participants, minimizing the potential for centralization at a low cost. We further present an extended scheme that can guarantee more requirements such as higher transaction amount and shorter transaction time. Furthermore, we analyze and compare the signature technologies used in the proposed solution and provide a systematic proof of our approach's security. © 2024 IEEE.

关键词： blockchain transaction cross-chain technology notary schemes proxy re-signature

来源：评论

学校读者我要写书评

暂无评论

Novel Enthusiasm Evaluating Method for Code Programming Curriculum

Novel Enthusiasm Evaluating Method for Code Programming Curr...

引用

7th International Conference on Applied System Innovation, ICASI 2021

作者： Wu, JainShing Chien, Ting-Hsuan Yang, Chin-Yi Chien, Li-Ren Department of Computer Science and Information Management Providence University Taichung City Taiwan 18 DICE Education Technology Co. Ltd Taichung City Taiwan National Chung Cheng University Department of Computer Science and Information Engineering Taichung City Taiwan

ISBN: (纸本)9781665441438

In order to improve the logical ability of all youths, the governments of different countries have set the code programming curriculum in high school as one of their education policies. Hence, some programming aid software are developed for student trying to learn how to program, taking exams on the system, and evaluating the students according to the codes of students. However, it is hard to know the enthusiasm from learning of the students which directly impact the following learning status of students. Hence, observing the enthusiasm from learning of the students is important for teachers. In our previous work, we used the Fuzzy Logic to evaluate the enthusiasm of the students from the log files in the DICE system. However, it only observes the login frequency and during time. In this paper, we provide a novel way to improve the evaluating the enthusiasm of the students. First, we analyze the all the information from the log files. And then, we store all behaviors with time stamp of one student into one special tensor. After all tensors of all students ready, we send input them to the Convolution Neural Network (CNN) to classify the students to three categories 'passion', 'normal' and 'apathetic.' We used log files with the number of over 206. We separate the dataset into training and testing datasets 20 times randomly. The accuracy of training dataset is 100%, and the accuracy of average testing dataset is 93.01%. The experimental results show that we can separate the students into the three categories. Hence, for our new method can significantly measure the learning enthusiasm of the students. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Intelligent and Sustainable Smart Healthcare Application in Cloud-Centric IoT

引用

computers, Materials & Continua 2021年第2期66卷 1987-2003页

作者： K.V.Praveen P.M.Joe Prathap S.Dhanasekaran I.S.Hephzi Punithavathi P.Duraipandy Irina V.Pustokhina Denis A.Pustokhin Department of Information Technology St.Peters College of Engineering and TechnologyChennai600054India Department of Information Technology RMD Engineering CollegeChennai601206India Department of Computer Science and Engineering Kalasalingam Academy of Research and EducationKrishnankoil626128India Department of Computer Science and Engineering Sphoorthy Engineering CollegeHyderabad501510India Department of Electrical and Electronics Engineering J B Institute of Engineering and TechnologyHyderabad500075India Department of Entrepreneurship and Logistics Plekhanov Russian University of EconomicsMoscow117997Russia Department of Logistics State University of ManagementMoscow109542Russia

Recent developments in information technology can be attributed to the development of smart cities which act as a key enabler for next-generation intelligent systems to improve security,reliability,and *** healthcare sector becomes advantageous and offers different ways to manage patient information in order to improve healthcare service *** futuristic sustainable computing solutions in e-healthcare applications depend upon Internet of Things(IoT)in cloud computing *** energy consumed during data communication from IoT devices to cloud server is significantly high and it needs to be reduced with the help of clustering *** current research article presents a new Oppositional Glowworm Swarm Optimization(OGSO)algorithmbased clustering with Deep Neural Network(DNN)called OGSO-DNN model for distributed healthcare *** OGSO algorithm was applied in this study to select the Cluster Heads(CHs)from the available IoT *** selected CHs transmit the data to cloud server,which then executes DNN-based classification process for healthcare *** extensive simulation analysis was carried out utilizing a student perspective healthcare data generated from UCI repository and IoT devices to forecast the severity level of the disease among *** proposed OGSO-DNN model outperformed previous methods by attaining the maximum average sensitivity of 96.956%,specificity of 95.076%,the accuracy of 95.764%and F-score value of 96.888%.

关键词： IoT devices healthcare deep learning energy efficiency glowworm swarm 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：