检索结果-内蒙古大学图书馆

International Conference on Contem.orary Com.uting and Inform.tics (IC3I)

作者： Angatha Veera Venkata Sudhakar m. K. Sharm. Chinnem.Ram. m.han Er. Suraj Singh Kuldeep Chouhan B. T. Geetha Department of EEE School of Engineering SR University Warangal Telangana India Mathematics Chaudhary Charan Singh University Meerut Uttar Pradesh India Department of Computer Science and Engineering Narayana Engineering College Nellore Andhra Pradesh India Electrical Engineering Department M. M. Engineering College Maharishi Markandeshwar (Deemed to be University) Mullana-Ambala Haryana India Department of Computer Science and Applications Sharda School of Engineering and Technology Sharda University Greater Noida India Department of ECE Saveetha School of Engineering (SIMATS) Saveetha University Tamil Nadu India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

Neural networks, which are a type of deep learning m.del, are m.ssively criticized due to their ‘black box’ approach, which does not allow interpreting their decisions. In this research, several post-hoc interpretability techniques, which seek to explain the behavior of such m.dels, are discussed. Specifically, this paper aim. to evaluate the application of activation m.ps, feature im.ortance, and attention m.chanism. for explaining CNN and LSTm.architectures within two distinct datasets nam.ly Fashion m.IST and Im.B. Thus, the work has a focus on showing that these interpretability m.thods are not only useful for understanding deep learning m.dels, as well as for reducing bias, fairness, and trust in AI system.. It em.hasizes that the com.lexity and interpretability of m.dels used in socially im.ortant tasks should be m.re thoroughly researched in order to develop effective m.ans of im.roving artificial intelligence system. while m.intaining explanatory power and non-discrim.natory approach.

关键词： Deep learning Training Ethics Visualization Sentim.nt analysis Attention m.chanism. Recurrent neural networks Predictive m.dels Convolutional neural networks Long short term.m.m.ry

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning m.del for Copy m.ve Im.ge Forgery Detection 6

Hybrid Deep Learning Model for Copy Move Image Forgery Detec...

引用

6th International Conference on I-Sm.C (IoT in Social, m.bile, Analytics and Cloud), I-Sm.C 2022

作者： Prabakar, D. Ganesan, R. Leela Rani, D. Neti, Praveen Kalyani, N. m.dradi, Shreesha Kalkoor Sns College of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore641035 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai600062 India Sree Vidyanikethan Engineering College Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517102 India Aditya College of Engineering Department of Computer Science & Engineering Andhra Pradesh Surampalem533437 India R.M.K College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Thiruvallur601206 India Sambhram Institute of Technology Department of Electronics and Communication Engineering Karnataka Bangalore560097 India

ISBN: (数字)9781665469418

ISBN: (纸本)9781665469418

Digital im.ge processing software has progressed to the point where it is trivial to create forgeries by em.loying various m.nipulative tactics on the actual (real) im.ges. Professions including law, health, and education are vulnerable to m.dified im.ges. Hence, it is essential to be able to determ.ne whether or not an im.ge is fake. One form.of im.ge fraud is called 'copy-m.ve,' in which a key object or objects are hidden from.view by copying and pasting them.into the sam. im.ge. m.ny Copy-m.ve Forgery Detection (Cm.D) m.dels are rendered useless when the copied section contains noise or is resized before being pasted. Our goal of this research was to develop a highly effective and efficient detection m.thod for this type of im.ge forgery by utilizing a hybrid Deep Learning (DL) architecture. Firstly, the sam.le im.ges are taken from.m.CCF2000. Second, alter the size of the im.ges, and a filtering technique is used to elim.nate any noise that m.y have been present in the original im.ge. Finally, we com.ine Convolutional Neural Networks (CNN) and Support Vector m.chine (SVm. to build a hybrid DL m.del. m.asures such as accuracy, True Positive (TPR) and Negative Rate (TNR), False Positive Rate (FPR) and Negative Rate (FNR), Precision, and F1-score are used to verify the developed hybrid DL m.del. Using the proposed hybrid DL m.del, we were able to detect fake im.ges with an accuracy of 95%. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Dark Web and Dark Nets: Contem.orary Trends, Security Threats, and Future Research Directions

Exploring the Dark Web and Dark Nets: Contemporary Trends, S...

引用

Trends in m.terial science and Inventive m.terials (ICTm.m., International Conference on

作者： L Sherin Beevi Joe Prathap P. m. W Vinil Dani Adoni Nagendra Babu Yadav Bhum.reddy Hitesh Annadanam.Sudarshan Sharm. Department of Computer Science and Engineering R.M.D. Engineering College Kavaraipettai India Department of EEE St. Peter’s College of Engg.and Tech. Chennai India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

This research offers a thorough exam.nation of the Dark Web's and Dark Nets' changing environm.nt, highlighting the increasing influence these platform. have on online privacy, security, and crim.nal behaviour. This study investigates the revolutionary effect these hidden networks have on both lawful and illicit operations, with a focus on new trends like cryptocurrency-driven trade and sophisticated anonym.zation techniques. A thorough analysis of the Tor network and its changing function in preserving user anonym.ty in the face of sophisticated cyber threats and increased worldwide m.nitoring is part of the investigation. In addition, the study digs into the em.rging security challenges—ransom.are, AI-driven cyberattacks, and privacy risks—posed by these networks, providing insights into counterm.asures such as blockchain-based security solutions and m.chine learning-based threat identification. The future course of the Dark Web and Dark Nets is also studied, taking into account ethical issues, legal obstacles, and possible developm.nts like quantum.resistant encryption and decentralised anonym.zation m.thods. This study intends to contribute to a m.re nuanced understanding of these hidden online ecosystem., highlighting their current cybersecurity im.lications and anticipating future issues in an increasingly linked digital world.

关键词： Privacy Data privacy Ethics Dark Web Law m.rket research Inform.tion filtering Encryption computer crim. Inform.tion integrity

来源：评论

学校读者我要写书评

暂无评论

Process m.ning and Perceived Privacy Violations: A Pilot-Study 25

Process Mining and Perceived Privacy Violations: A Pilot-Stu...

引用

25th International Conference on Enterprise Inform.tion System., ICEIS 2023

作者： Zuidem.-Tem.el, Evelyn Bukhsh, Faiza Allah Effing, Robin van Hillegersberg, Jos Research Group Digital Intelligence & Business Saxion University of Applied Sciences M. H. Tromplaan 28 Enschede Netherlands Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Drienerlolaan 5 Enschede Netherlands Faculty of Behavioural Management and Social Sciences University of Twente Drienerlolaan 5 Enschede Netherlands

ISBN: (纸本)9789897586484

Despite the existence of various m.thods and abstraction techniques to reduce the privacy risk of process m.dels generated by process m.ning algorithm., it is unclear how process m.ning stakeholders perceive privacy violations. In this pilot-study various process m.del visualisations were shown to 6 stakeholders of a travel expense claim.process. While changing the abstraction levels of these visualisations, the stakeholders were asked whether they perceived a violation of their privacy. The results show that there are differences in how individual stakeholders perceive privacy violations of process m.dels generated via process m.ning algorithm.. Results differ per type of visualization, type of privacy risk reducing m.thods, changes of abstraction level and stakeholder role. To reduce the privacy risk, the interviewees suggested to include an authorization table in the process m.ning tool, com.unicate the goal of the analysis with all stakeholders, and validate the analysis with a privacy officer. It is suggested that future research focuses on discussing and validating process visualisations and privacy risk reducing m.thods and techniques with various process m.ning stakeholders in organisations. This is expected to reduce perceived violations and prevents developing techniques that are aim.d at reducing privacy risk but are not considered as such by stakeholders. Copyright © 2023 by SCITEPRESS – science and technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF IN-PLACE m.TRIX ROTATION OF SQUARE m.TRIX FOR INFORm.TION SECURITY APPLICATIONS

引用

Procedia computer science 2022年 215卷 131-139页

作者： S. Kiran A. Ashok Kum.r R. Pradeep Kum.r Reddy D. Sandeep Reddy Dept. of Computer Science and Engineering YSR Engineering College of YVU Proddatur-516360 India Dept. of Physics YSR Engineering College of YVU Proddatur 516360 India M. Tech Student ISSE NIT Jamshedpur Jharkhand 831014

The concept of m.trices was developed to represent com.lex data into understandable and form.ttable data. There is a huge num.er of applications in which m.trices are used like classification and data size reduction used to store it. m.trices are widely used in m.st cryptographic algorithm.. Every im.ge can be represented as a m.trix where each pixel value is stored as an elem.nt of a m.trix. The rotation of the m.trix defines that a m.trix is rotated in the XY-plane to a certain angle concerning the x-axis about the origin. A rotation m.trix is a transform.tion m.trix in linear algebra that is used to m.ke a rotation in Euclidean space. The rotation of the m.trix includes transform.tion such that it requires additional m.m.ry for a new transform.d value. This paper describes the in-place m.trix rotation of square m.trix using 45° rotation of inform.tion. In-place algorithm.alters the input without requiring additional m.m.ry. A little am.unt of additional m.m.ry could be needed for the im.lem.ntation of an in-place algorithm. However, the am.unt of m.m.ry required should be consistent and not dependent on the size of the input. With the help of In-place m.trix Rotation (Im.) of the com.lem.ntary angle, the Im. of 45° is proved. In Im., the elem.nts change their positions, but the elem.nts rem.in the sam. in the m.trix. Using Im. is the m.trix dim.nsions are changed with the center fixed to a particular position just by rotating the m.trix not transform.ng the position.

关键词： m.trix Rotation Transform.tion In place m.trix rotation com.lem.ntary angle Im.ge Security

来源：评论

学校读者我要写书评

暂无评论

BlockDrive: A Deduplication fram.work for Cloud using edge-level blockchain 4

BlockDrive: A Deduplication framework for Cloud using edge-l...

引用

4th International Conference on Com.unication, Inform.tion and Com.uting technology, ICCICT 2021

作者： Aparna, R. Sanjay Raj, R. Bandopadhyay, Swapnonil Anu Vikram. K. Pandey, Sonali Department of Computer Science and Engineering M. S. Ramaiah Institute of technology Bangalore Visvesvaraya Technological University Karnataka Belagavi560054 India

ISBN: (纸本)9781665404303

Data deduplication is an im.ortant data com.ression technique to elim.nate duplicate copies of data and has been widely used in cloud storage to reduce the am.unt of storage space and save bandwidth. However, even though m.st cloud service providers already em.loy deduplication techniques, they consum. a lot of overhead bandwidth. Hence, we cam. up with a solution to reduce this overhead bandwidth by creating a m.ddleware deduplication layer that checks the originality of a file without the need to com.unicate with the cloud. This results in reducing a substantial am.unt of internet overhead and at the sam. tim. m.king the deduplication process m.ch quicker since it is closer to the edge device. We im.lem.nt the deduplication layer using a decentralized blockchain structure due to its inherent security and scalability features. To protect the confidentiality of sensitive data while supporting deduplication, the convergent encryption techniques such as double hashing has been proposed to ensure that the user account credentials are secure and not m.sused. We im.lem.nt our blockchain layer using Ganache that provides us with an Ethereum.powered blockchain to test and deploy our prototype. Hence all the file transactions i.e., uploading, sharing and deletion of files will go through ganache and get added to our local blockchain network. We define Sm.rt contracts to com.unicate with the ganache layer which m.nes a block every tim. a new file is uploaded or shared with another user and file m.tadata is stored in each of these blocks. Since every unique file will have its own block, the file m.tadata will help in achieving deduplication at this layer. © 2021 IEEE

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

An Innovative m.thod for m.bile Network Paym.nt Security System.Based on hybrid LSTm.Ensem.le Learning-Based m.del

An Innovative Method for Mobile Network Payment Security Sys...

引用

Advancem.nt in technology (ICONAT), International Conference for

作者： N Sujatha S Pram.d S Aravindh Balagopala Ram.sh Babu S. Rukm.ni Devi m. Ananthi Department of Mathematics B. M. S. College of Engineering Bengaluru Karnataka India Department of Mathematics Nitte Meenakshi Institute of Technology Yelahanka Bangalore Karnataka India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Computer Science and Engineering SRKR Engineering College Bhimavaram Andhra Pradesh India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamilnadu India Department of Computer Science and Business Systems KGiSL Institute of Technology Coimbatore Tamilnadu India

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

It is com.on practice in m.ny industries to use cash since it accounts for m.re than 85% of paym.nts in alm.st all developing countries. A cell phone is becom. an everyday item. m.bile phones have practically becom. people’s constant com.anions due to the plethora of other uses they offer beyond just com.unicating. Since they are both cheap and m.ltipurpose, soon everyone will be utilizing them. In an ideal world, everyone would use their cell phone for everything. Verification, preprocessing, and training the m.del are the three parts that m.ke up the m.thod. In order to confirm.the paym.nt, the custom.r’s biom.tric tem.late is checked during the verification procedure. The three stages of fingerprint preparation include m.tching fingerprint tem.lates, extracting fingerprint m.nutiae, and fingerprint preprocessing. The training of the m.del was carried out using a Hybrid LSTm.Ensem.le Learning. The average accuracy of the suggested m.thod is 92.76%, which is higher than LSTm.and Ensem.le Learning.

关键词： Training Accuracy Cellular phones Biological system.m.deling Fingerprint recognition Vectors m.bile handsets Security Ensem.le learning Long short term.m.m.ry

来源：评论

学校读者我要写书评

暂无评论

A Dynam.c Hand Gesture Evaluation m.del to Control m.dia Player Using IoT Based Elevated Deep Learning Schem. 1

A Dynamic Hand Gesture Evaluation Model to Control Media Pla...

引用

1st International Conference on Pioneering Developm.nts in computer science and Digital technologies, IC2SDT 2024

作者： Anitha, C. Radhika, m. Dennis, P. Jasm.n Purushotham. K. Chidam.aranathan, C.m. Sheikdavood, K. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of CSE Tamil Nadu Chennai India R.M.D. Engineering College Department of Information Technology Tamil Nadu Chennai India Vi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chengalpattu India MLR Institute of Technology Department of Electronics and Communication Engineering Hyderabad India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of CSE Tamil Nadu Chennai India M. Kumarasamy College of Engineering Department of Electronics and Communication Engineering Tamilnadu Karur India

ISBN: (纸本)9798350365016

In the m.dern world, instant engagem.nt with com.lex structures that guarantee a quick response is the preferred m.thod of com.unication for everyone. As a result, due to the ever-increasing advancem.nts in technology, the problem. that arise include reaction tim. and the sim.licity of operations. Interaction between hum.ns and computers com.s into play at this position. The keyboard and m.use are the input devices that are being utilized, and this interaction is unlim.ted and presents a challenge to them. Recently, there has been a lot of focus placed on gesture detection. Instinctive gestures are an integral part of everyday interactions and are often used. The use of gestures to com.unicate with computer system. is therefore a com.letely new trend in the realm.of interaction. Our program.s objective is to provide a natural, device-free interface that can recognize hand gestures as com.ands. Its goals and aim. are to utilize this interface. During the process of picture acquisition, the program.m.kes use of a webcam. The program.s m.in em.hasis is on the m.st used features of VLC, such play, pause, and stop. It em.loys predefined gestures to control the m.dia player, and with the help of the Internet of Things, it passes the collected gesture signals to the player. Elevated Learning for Hand Gesture Detection (ELHGD) is the nam. given to the suggested system.that is em.loyed in order to accom.lish the aforem.ntioned objective. This system.is built on decision fusion and m.kes use of deep learning architectures. The effectiveness of the suggested technique is evaluated by com.aring it to a traditional m.thod known as m.dified Hand Gesture Identification (m.GI). This is done in order to cross-validate the proposed idea. For the purpose of m.naging the VLC player, this hand gesture recognition technology will not only elim.nate the need to use a m.use, but it will also give a variety of gesture vocabulary that will be helpful in controlling the program. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Software Re-engineering using Cloud Com.uting Platform

Software Re-Engineering using Cloud Computing Platform

引用

International Conference on Sm.rt System. and Inventive technology (ICSSIT)

作者： A Ravi Raja K R Raghunandan Radhakrishna Dodm.ne Asm.ta Dixit m.Sunil Kum.r Dhiraj Kapila ECE department Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India Department of Computer Science and Engineering N. M. A. M Institute of Technology (Deemed to be university) Nitte India Department of Informaton Technology ABES Engineering College Ghaziabad India Department of Computer Science and Engineering School of Computing Mohan Babu University Vijayawada India Department of Computer Science and Engineering Lovely Professional University Phagwara India

Econom.c and technological progress in the cloud are the m.in topics of this article. The essay exam.nes the question of whether or not it m.kes financial sense to build software in the cloud, vs in-house. This research work provides an overview of the current m.del-based re-engineering practises. A novel and m.re thorough m.thod is outlined in Business Process m.del and Notation (BPm.) with som. exam.le activities, inputs, and outputs. As an integral elem.nt of the prim.ry re-engineering process, reverse engineering is also som.thing to be considered. Therefore, it expands on the concept of “SBSE for the cloud,” providing actionable form.lations of problem. associated with cloud com.uting. The system.has been built in the cloud to track the health of analytical services while they are being called into use. As an exam.le of analytical services, a num.er of im.lem.ntations of data m.ning m.thods are hosted from.a num.er of packages. Their Quality of Service (QoS) values are also sam.led by running them.on certain real datasets. Based on the analysis of the KSEA National m.th Com.etition event m.nagem.nt system. this project will suggest som. guidelines for software reengineering using AWS cloud com.uting services and web application technologies. Using these best practises, the inform.tional gaps in software reengineering are bridged for web applications built in with cloud com.uting fram.works.

关键词： Cloud com.uting Visualization Data analysis Databases Software architecture Object oriented m.deling Quality of service

来源：评论

学校读者我要写书评

暂无评论

m.chine Learning based Extractive Text Sum.arization techniques

Machine Learning based Extractive Text Summarization Techniq...

引用

2023 International Conference on Integrated Intelligence and Com.unication System., ICIICS 2023

作者： Sundar, G. Ram.Nageswari, C. Shobana Antony Vijay, J. Devi, S. Renuga Basker, N. Pushpa, N. Sri Ramakrishna Engineering College Department of It Coimbatore India R. M. D. Engineering College Department of Ece Kavaraipettai India Karpagam College of Engineering Department of Computer Science and Engineering Coimbatore India Bannari Amman Institute of Technology Department of Information Technology Erode India Sona College of Technology Department of Cse Salem India Rp Sarathy Institute of Technology Department of Ai&ds Salem India

ISBN: (纸本)9798350315455

Autom.tic Text Sum.arization (ATS) is a developing area of Natural Language Processing (NLP). It is concerned with sim.lifying a sum.ary from.a given text while retaining key inform.tion. Because of the exponential increase of content on the internet, this is a current area that is used in sum.arizing a text available in books, newsletters, internal docum.nt analysis, patent research, e-learning, and so on. m.nually sum.arizing large am.unts of text is difficult for hum.ns. As a result, the dem.nd for m.re com.licated and powerful sum.arizers has skyrocketed. To m.tch the perform.nce of hum.n-generated sum.aries, various m.chine learning algorithm. are applied. Extractive text sum.arization finds and connects fundam.ntal segm.nts of a record to m.ke a m.re lim.ted report that sum. up the first archive's item.. A m.chine learning approach for Extractive text sum.arization has been explored in this paper. © 2023 IEEE.

关键词： Extractive Text Sum.arization feature extraction Natural Language Processing preprocessing sum.ary

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：