检索结果-内蒙古大学图书馆

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Maurya, Jyoti Prakash, Shiva Madan Mohan Malaviya University of Technology Department of Information Technology and Computer Application Gorakhpur273010 India

ISBN: (纸本)9798350322842

In the context of artificial intelligence, the traditional centralized server-based machine learning model training approaches have significant security and privacy issues. The federated learning (FL) approach was created to address these problems. FL uses a privacy-by-design architecture, in which several devices work together to develop any machine learning system that does not reveal users' personal information under the control of a single server. In federated learning, privacy preservation is achieved through several techniques that involve adding noise, secure aggregation, local training, and model compression. These techniques aid in making sure that raw data is not transmitted over the network and that only the required information is shared to train a global model. This research study has discussed about the federated learning-related privacy threats and defenses. The existing research works are divided into two types as attack methods and corresponding defense mechanism and further analyzed the relevant research papers from the last few years, and then further discussed the research challenges, and finally concluded the research study. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics on Twitter Sentiments in Cloud Environment: A Review

Big Data Analytics on Twitter Sentiments in Cloud Environmen...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Kumar, Durgesh Dwivedi, Rajendra Kumar Madan Mohan Malaviya University of Technology Dept. of Information Technology and Computer Application Gorakhpur India

ISBN: (纸本)9798350302820

The Internet plays a significant part in the digital world. With the expanding use of web and online applications, different ventures go to huge information answers for adapt up to the evolving request. In this large information period, information is the most important element as it is mainly utilized by organizations for future expectation and decision making. The internet has a seriously advanced a clever way for individuals to communicate their perspectives and suppositions about various themes, patterns and issues. The opinion examination recognized the sensations of client about a few items, subjects into three preset classes: positive, negative or impartial alongside the issue of mining. This paper presents a study on big information analytics on twitter opinion in cloud climate and how huge information controls a lot of information. This paper presents a concise investigation of methodologies which have been utilized in huge information analytics on twitter opinion in cloud climate. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Smart Health Diagnosis:Harnessing Data Mining for Predictive Healthcare 1

Smart Health Diagnosis:Harnessing Data Mining for Predictive...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Indrakumari, R. Pandey, Vishal Sinha, Ashish Kumar Kumar, Ankesh Galgotias University School of Computer Science and Engineering India Galgotias University School of Computing Application and Technology India

ISBN: (纸本)9798350356816

The use of Smart Health Diagnosis: Data Mining for Predictive Healthcare is to provide a user- friendly and easily accessible platform where individuals can get instant health advice through an intelligent online healthcare system. By the analysis of the reported symptoms, the system can predict potential future diseases and provide relevant recommendations to healthcare providers on courses of action. Intelligent methods accurately determine potential interferences based on patient symptoms. Medical record database was used and symptoms were assigned to underlying diseases using Naive Bayesian calculations. Fast, reliable access to health care is a cornerstone of individual and social health but many people face barriers in receiving timely care. We are trying to solve these problems by introducing Health Prediction System, a revolutionary online healthcare solution that uses data mining for quick support and customized recommendations. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

DBST:a lightweight block cipher based on dynamic S-box

引用

Frontiers of computer Science 2023年第3期17卷 177-185页

作者： Liuyan YAN Lang LI Ying GUO College of Computer Science and Technology Hengyang Normal UniversityHengyang 421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang 421002China

IoT devices have been widely used with the advent of *** devices contain a large amount of private data during *** is primely important for ensuring their ***,we proposed a lightweight block cipher based on dynamic S-box named *** is introduced for devices with limited hardware resources and high throughput *** is a 128-bit block cipher supporting 64-bit key,which is based on a new generalized Feistel variant *** retains the consistency and significantly boosts the diffusion of the traditional Feistel *** SubColumns of round function is implemented by combining bit-slice technology with *** S-box is dynamically associated with the *** has been demonstrated that DBST has a good avalanche effect,low hardware area,and high *** S-box has been proven to have fewer differential features than RECTANGLE *** security analysis of DBST reveals that it can against impossible differential attack,differential attack,linear attack,and other types of attacks.

关键词： internet of things 5G dynamic S-box bit-slice technology lightweight block cipher

来源：评论

学校读者我要写书评

暂无评论

Loan Status Prediction using SVM and Logistic Regression 14

Loan Status Prediction using SVM and Logistic Regression

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Yadav, Khushboo Singh, Sarvpal Madan Mohan Malaviya University of Technology Dept. of Information Technology and Computer Application Gorakhpur India

ISBN: (纸本)9798350335095

Over the past few years, credit lines are the primary source of income for banks. The assets of bank are determined by how much "Loans"they have provided to the customer. Behind this credit line, one more important is that "Will the customer be capable of repaying the debt in a given time?". We can consider many attributes such as age, gender, income source & expenditure which limit the customer to pay the loan over a definite period [1]. To maximize the profit of bank, it's very important to analyze the various models and compare them. One of the very effective models is Logistic regression. This model is widely used because it predicts over a group of independent variables, the categorical dependent variable. We have gathered data from Kaggle for our research and forecasting purpose. The data obtained from here will act as base for loan default prediction because it contains customer personal attribute like age, objective, previous credit utilization, credit extent, and credit period. After evaluating customer on following attribute, the bank should realize to whom they should provide the loan or to whom they shouldn't. This can be analyzed by Logistic Regression and Support Vector Machine technique for truthful results. Our model doesn't consider only the rich people should be given loan but it considers customer characteristics who satisfies the following above attribute, which plays an important role in credit choice and forecasting lone defaulters. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

SepFE:Separable Fusion Enhanced Network for Retinal Vessel Segmentation

引用

computer Modeling in Engineering & Sciences 2023年第9期136卷 2465-2485页

作者： Yun Wu Ge Jiao Jiahao Liu College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002China

The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable ***,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular *** view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional *** complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for *** ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the ***,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct ***,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is *** superiority of SepFE is further demonstrated through comparisons with other advanced methods.

关键词： Retinal vessel segmentation U-Net depth-wise separable convolution feature fusion

来源：评论

学校读者我要写书评

暂无评论

Real-time distance field acceleration based free-viewpoint video synthesis for large sports fields

引用

Computational Visual Media 2024年第2期10卷 331-353页

作者： Yanran Dai Jing Li Yuqi Jiang Haidong Qin Bang Liang Shikuan Hong Haozhe Pan Tao Yang School of Telecommunications Engineering Xidian UniversityXi’an 710071China National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology SAIIPthe School of Computer ScienceNorthwestern Polytechnical UniversityXi’an 710129China

Free-viewpoint video allows the user to view objects from any virtual perspective,creating an immersive visual *** technology enhances the interactivity and freedom of multimedia ***,many free-viewpoint video synthesis methods hardly satisfy the requirement to work in real time with high precision,particularly for sports fields having large areas and numerous moving *** address these issues,we propose a freeviewpoint video synthesis method based on distance field *** central idea is to fuse multiview distance field information and use it to adjust the search step size *** step size search is used in two ways:for fast estimation of multiobject three-dimensional surfaces,and synthetic view rendering based on global occlusion *** have implemented our ideas using parallel computing for interactive display,using CUDA and OpenGL frameworks,and have used real-world and simulated experimental datasets for *** results show that the proposed method can render free-viewpoint videos with multiple objects on large sports fields at 25 ***,the visual quality of our synthetic novel viewpoint images exceeds that of state-of-the-art neural-rendering-based methods.

关键词： free-viewpoint video view synthesis camera array distance field sports video

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Data Processing Support Model of Government Information System Based on Deep Learning

Research on Intelligent Data Processing Support Model of Gov...

引用

2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing, CITSC 2025

作者： Lu, Dapeng Liu, Haojie Zhuhai College of Science and Technology School of Tourism and Public Administration Guangdong Zhuhai519000 China Henan University of Technology Computer Application Technology Zhengzhou450001 China

ISBN: (纸本)9798331504205

This study constructs a data processing model that supports government information system. By designing a deep learning algorithm suitable for government scenarios, intelligent processing functions such as text analysis and image recognition are integrated into the system, aiming to achieve accurate processing of multi-source government data. The model design includes data preprocessing, feature extraction, algorithm optimization and adaptive learning modules to improve the recognition and analysis capabilities of complex government data. Through system simulation, this paper verifies the effectiveness of the proposed model. The simulation data shows that the model is significantly superior to traditional methods in data processing speed, accuracy and resource utilization. Precise experimental results show that the accuracy of the model in text data classification, image data recognition and other aspects reaches more than 96%. At the same time, it can effectively shorten the processing time in large-scale data processing tasks, providing technical support for the practical application of intelligent government information system. This study provides an efficient and scalable solution for intelligent data processing in government information system. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Recommender System: Bibliometric Analysis of a Decade 3

Recommender System: Bibliometric Analysis of a Decade

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Bansal, Saumya Baliyan, Niyati Bharati Vidyapeeth's Institute of Computer Application and Management New Delhi India National Institute of Technology Department of Computer Science and Engineering Kurukshetra India

ISBN: (纸本)9798331518592

With the rise of Internet, plethora of content has been uploaded on various platforms such as social media, e-commerce, e-business websites, etc. As a result, research on recommender system has gained significant attention since the year 2000. Therefore, with an aim to provide a coherent overview of research in the field of recommender systems with respect to sustainability, Web of Science database is mined from the year 2014 to 2024. The analysis is done on 7776 documents retrieved based on country, bibliographic coupling, publication year, citations, and publisher. From the analysis, it was found that China contributed highest number of documents. Further, there is linear increase in number of publications over years in the field of sustainable recommender system. This study aims to gather statistical information thereby assisting researchers in analyzing trends and parameters such as publication venue, collaboration, top researchers, etc delving into this research field. © 2024 IEEE.

关键词： Data reliability

来源：评论

学校读者我要写书评

暂无评论

Video Inter-frame Tampering Detection Based on SN-VGG+BiLSTM-AE Composite Model 10

Video Inter-frame Tampering Detection Based on SN-VGG+BiLSTM...

引用

10th International Conference on Information technology: IoT and Smart City, ICIT 2022

作者： Xing, Qi Luo, Yun Zhang, Zhaoyuan Zhang, Fan Beijing Institute of Computer Technology and Application China

ISBN: (纸本)9781450397438

Video inter-frame tampering detection is the most common type of forensics in video forensics. The traditional detection method is to detect tampering by extracting digital image features of video frames, such as SIFT, HOG, and ORB. The accuracy of frame discrimination and localization is limited. This paper introduces deep learning into the problem of tampering detection, and proposes a composite network model structure using the Siamese network Siamese and the bidirectional long short-term memory network autoencoder BiLSTM AutoEncoder to detect tampered frames. Among them, Siamese calculates the inter-frame distance by calculating the depth features of the frames extracted by VGG-16, and inputs them into BiLSTM AutoEncoder for frame sequence anomaly detection and localization. The model is experimented on two different datasets with good results, validating the model generalization performance. Compared with the classical method, this model obtains higher precision(93.7%) of tamper points, which verifies the superiority of this deep learning model. © 2022 ACM.

关键词： Anomaly detection

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：