检索结果-内蒙古大学图书馆

Comparative research on block design-based protocol and blowfish for secured key generation and data sharing on cloud

引用

Soft Computing 2024年第23期28卷 13701-13713页

作者： Hombal, Uma Rangapura Basavaraju, Dayananda Shinde, Ashwini S. Department of Computer Science and Engineering KSIT Bengaluru India Department of Computer Science and Engineering MSRIT Bengaluru India Department of CSE-AI Nutan College of Engineering and Research Pune India

Confidentiality of maintaining the Electronic Health Records of patients is a major concern to both the patient and Doctor. Sharing the data on cloud is one of the most efficient technology infrastructures with extensive potential application, but at the same time there is a threat of hacking the data. Here we implement the concept for sharing of electronic health record on cloud that permits multiple members of the group to easily share the group data. With the increase in size of healthcare data the time and space complexity increases. The main challenge here is data security. This research article emphasis on a secured method for sharing the data on cloud and generation of the key that is safe from unauthorized user. In this Research article, we implement the soft computing approach for key agreement protocol using Block based design to support several users that can adapt it-self to upsurge the number of users in the cloud which depends on the assembly of the block design. This protocol generates a common conference key for all members. On comparing our results with some prevailing techniques, we accomplish that the results of our research have a better computational complexity. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Personal computing

来源：评论

学校读者我要写书评

暂无评论

VAEMRS: Variational Autoencoder Based Movie Recommender System

引用

Journal of engineering science and Technology Review 2024年第6期17卷 23-29页

作者： Behera, Gopal Swain, Basanta Kumar Soni, Ravindra Kumar Parmar, Jitendra Department of CSE Government College of Engineering Kalahandi Odisha India Department of AI and ML Manipal University Jaipur India School of Computing Science and Engineering VIT Bhopal India

Nowadays, deep learning is an emerging technique used in many research domains. The recommender system, specifically collaborative filtering, has significantly improved its performance by deploying this technique. Neural collaborative networks and their related neural network models are the bench- mark models in this domain. However, these models do not exhibit to create a continuous, robust, and structured latent space like autoencoder. On the other hand, autoencoder does not perform well in sparse data like Movielens. This article proposes a variational autoencoder based movie recommendation system (VAEMRS) to handle the above issues. In our proposed model, we consider implicit data like click vectors, normalize the interaction matrix, and pass them to the dropout layer to learn the VAE. Further, our approach applies variational concepts in neural networks. Also, use multinomial likelihood and Bayesian inference for parameter estimation. The proposed model has been tested using different quality measures on open-source datasets such as Movielens and compared with baselines. The performance results of the proposed work show the superiority over the baselines. © (2024), (International Hellenic University School of science and Technology). All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Advancing Drowsiness Detection Using Head-Angle and Eye-Aspect Ratio 8

A Novel Approach to Advancing Drowsiness Detection Using Hea...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Shashidhar, V. Ahmed, Mueezuddin Razeena, M. Rajesh, K.S. Bharath, J. Bangalore India Rajarajeswari College of Engineering Department of Computer Science & Engineering Bangalore India Rajarajeswari College of Engineering Department of Ai&ml Bangalore India

ISBN: (纸本)9798331505462

Drowsiness is a significant risk factor for accidents, particularly in situations requiring sustained attention, such as driving or operating machinery. This research proposes an innovative methodology for detecting driver drowsiness using advanced computer vision algorithms and techniques. Our system employs a shapeshift predictor and face-tracking algorithms to monitor the driver's facial features and head movements. Specifically, it detects three distinct indicators of drowsiness: excessive head tilting to the right or left, significant drooping of the chin, and prolonged eye closure (defined as eyes remaining closed for more than 24 consecutive frames). When any of these conditions are met, an alarm is triggered, alerting the driver to their potentially hazardous state. The proposed system offers a robust and non-intrusive solution for real-time drowsiness monitoring, with potential applications in various fields where vigilance is critical for safety. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Twin attention based multi-task convolutional bidirectional long short term memory for facial expression recognition

引用

Multimedia Tools and Applications 2025年第10期84卷 8037-8070页

作者： Sreenivas, Velagapudi Sivaneasan, B. Vani, K. Suvarna Chakrabarti, Prasun Singapore Institute of Technology Singapore138683 Singapore Engineering Cluster Singapore Institute of Technology Singapore138683 Singapore Department of Computer Science and Engineering AI/ML Research Group Head VR Siddhartha Engineering College Andhra Pradesh Vijayawada520007 India Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur313601 India

Facial Expression Recognition (FER) aims to detect the emotional state of facial images. It is playing an increasingly important role in several application areas, including human–computer interaction (HCI), video transcriptions, and social communications. This article provides an adequate attention-based multi-task deep learning method for facial expression recognition. First, the input videos are collected from the RAVDESS and MELD datasets. Then, the input videos are converted using a threshold-based keyframe extraction algorithm. Next, the input data is pre-processed using the Adaptive Pixel Density Median Filtering (A-PDMF) method. Key features such as shape, color and texture are extracted from the pre-processed images. Finally, the facial expressions are recognized by proposing a novel twin attention-based multi-task convolutional bidirectional long-short-term memory method (TA-MC-BiLSTM). In addition, the classification parameters are optimally tuned using the EX-AHA method (Extended Artificial Hummingbird Algorithm). The proposed model reduces the size of facial features while accurately identifying the wide range of facial expressions. For simulation, the proposed method prefers python tool and results are analyzed using RAVDESS and MELD datasets. The simulation results show that the proposed model provides better results than other existing models in terms of accuracy of 99.6% for RAVEDESS and 99.4% for MELD. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Crop Disease Detection with Autonomous Robotic Systems 1

Crop Disease Detection with Autonomous Robotic Systems

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Rithani, M. Shabarirajan, K.J. Shivanesh, B. Syamdev, R.S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India New Horizon College of Engineering Department of AI & ML Bangalore India

ISBN: (纸本)9798331518943

Crop disease detection is an important maintenance aspect for the upkeep of agricultural productivity. This paper presents a novel autonomous robot system designed to navigate and monitor crop health. The system was developed within a ROS framework using a camera to capture real-time video feeds of crops and a YOLO v8 model for detecting the presence of three specific plant diseases. Such a configuration resembles a farm in the presence of crops and trees and hence can be termed as a dirty farm. Automated navigation will cover all the area. The detection model processes each frame to detect plant disease. Such an approach has the potential to make improvements in early detection of diseases, thus leading to proper management and informed decisions about precision agriculture. © 2024 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Detection and Quantification of TB Bacilli in Sputum Smear Images 1

Detection and Quantification of TB Bacilli in Sputum Smear I...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Rithani, M. Jeevanantham Sona, B. Syamdev, R.S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India New Horizon College of Engineering Department of AI \& ML Bangalore India

ISBN: (纸本)9798331518943

Early and precise detection is essential to stop the spread of tuberculosis (TB) and enhance patient outcomes. This research aims to create an automated system that employs cutting-edge image processing and machine-learning approaches to identify tuberculosis (TB) bacilli in sputum smear microscopy pictures. An automated solution is required to increase diagnostic accuracy and efficiency because traditional diagnostic methods are labor-intensive, time-consuming, and prone to human mistakes. In the end, we optimize the best-performing model to reduce processing time while preserving diagnostic accuracy. Our goal is to assess the performance of several models in terms of training time, testing time, and accuracy. By enabling the use of sophisticated diagnostic technologies in environments with limited resources, the suggested method supports international efforts to combat tuberculosis. © 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

AquaRescue: Intelligent Drowning Detection and Swift Rescue System Using Integrated Approach 4

AquaRescue: Intelligent Drowning Detection and Swift Rescue ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Rakshitha Sowmya, P. Shettigar, Rashmitha Nishanth, N. Durgaprasad Kumar, Dhanush Department of Ai&ml Nitte574110 India Department of Computer Science and Engineering Nitte574110 India /CS East Mumbai400068 India

ISBN: (纸本)9798350387490

Drowning accidents, in pools continue to be a concern calling for creative solutions to improve safety standards. The research aims to establish a framework for identifying and saving drowning cases in pools. Cutting-edge technologies such as computer vision, Artificial Intelligence, and IoT are integrated into the system to quickly and precisely recognize incidents and trigger rescue operations. Utilizing cameras and advanced algorithms like YOLO v3 and CNN, the system continuously observes the pool environment. By assessing people's movements and locations in the water, it accurately detects drowning cases. Once an incident is identified, the system automatically starts rescue procedures by dispatching rescue tools and notifying lifeguards with alarms across the pool premises. Moreover, it enables emergency calls through GSM SIM900A module in case the lifeguard is not present nearby. This innovative detection and rescue system not only enhances swimmer safety but also reduces the workload on lifeguards, allowing them to react more effectively in emergencies. The ultimate goal of this system, driven by technological advancements, is to minimize drowning incidents in pools. The system's performance has been evaluated against other models like Faster R-CNN, YOLO v3, and SSD. YOLO v3 demonstrated superior accuracy of 90% with combined datasets (GF-1 & GF -2). © 2024 IEEE.

关键词： Guards (shields)

来源：评论

学校读者我要写书评

暂无评论

BPCPR-FC: blockchain-based privacy preservation with confidentiality using proxy reencryption and ring signature in fog computing environments

引用

International Journal of Information Technology (Singapore) 2023年第6期15卷 3343-3357页

作者： Gowda, Naveen Chandra Bharathi Malakreddy, A. School of Computer Science and Engineering REVA University Bengaluru India Department of AI and ML BMS Institute of Technology & Management Bengaluru India

The usage of edge devices in distributed fog and cloud computing applications is increasing day by day in the current digital communication world. The edge devices can be mobile devices, smart devices, IoT devices, and vehicular devices. The edge devices produce a variety of data in various applications such as healthcare, educational, vehicular networks, smart systems and industrial IoT. The private data of a user or any generated data at the edge devices will be stored in the centralized cloud server and then can be accessed by any user when required upon permission by the data owner. An increase in the rate of data sharing in current digital communications directly increases vulnerable activities which require security services like access control, privacy, data confidentiality, anonymity, unforgeability, and nonframeability. In this article, a blockchain-based privacy preservation with confidentiality using proxy reencryption and ring signature in fog computing environments (BPCPR-FC) mechanism is proposed to achieve the requirements. The proposed BPCPR-FC is verified using mathematical analysis for a set of security issues and an informal security analysis is carried out for a set of common attacks. Cryptanalysis of the proposed BPCPR-FC scheme is discussed and shows the improvement of encryption and decryption time by 8–22% and 10–23% compared to existing schemes. The blockchain implementation of the proposed BPCPR-FC is carried out in the Truffle suite and discussed the improvement of block preparation time by 7–17% compared to suitable existing works. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Blockchain Cloud computing Confidentiality Fog computing Privacy Proxy reencryption Ring signature

来源：评论

学校读者我要写书评

暂无评论

Towards Enabling Data Security: NFT Generator Automation for Blockchain User Experience 3

Towards Enabling Data Security: NFT Generator Automation for...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Kishan, Makadiya Madhu, Shukla Krunal, Vaghela Marwadi University Department of Computer Engineering Rajkot India Marwadi University Department of AI ML and DS Rajkot India

ISBN: (纸本)9798350354171

Non-fungible tokens (NFTs) have become increasingly more popular in recent years as a manner to represent particular virtual assets on the blockchain. However, the creation of NFTs can be a complicated and technical process that calls for an understanding of blockchain technology and programming. To make the procedure more accessible to a wider target audience, NFT turbines have been developed to enable customers to create their very own NFTs without the want for technical knowhow. This paper pursues to discover the consumer experience of NFT mills and their capability effect on the adoption of NFTs. We conducted a literature evaluation to study present studies on NFTs and case studies of NFT generator structures and remarks from popular NFT generator systems to gain insights into the person revealed. Our analysis revealed that NFT turbines can substantially simplify the procedure of making and selling NFTs. By supplying person-pleasant interfaces and automation of technical duties, NFT turbines can allow a much broader audience to take part in the NFT marketplace. There also are demanding situations that want to be addressed to make sure a fine user enjoy. These encompass issues around the protection, transparency, and authenticity of NFTs. We identified numerous key layout concerns for NFT turbines, which include ease of use, customization alternatives, and assistance for a couple of blockchains. we discovered that Mintable gives a streamlined and consumer-friendly revel in for developing and selling NFTs, with several customization options and aid for multiple blockchains. NFT generators will possibly play an increasingly vital function in permitting users to take part in this emerging economy. Overall, this research highlights the significance of personal experience within the design of NFT generators and gives insights and hints for designers looking to create NFT generator systems that are consumer-friendly, on-hand, and secure. © 2024 IEEE.

关键词： Sales

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：