检索结果-内蒙古大学图书馆

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Nithila, Ezhil E. Bibin Christopher, V. Raj, J. Relin Francis Srinivasan, A. Soundiraraj, N. Krishnan, R. Santhana Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai Avadi India School of Computing College of Engineering and Technology Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies Chennai Kattankulathur India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Velammal College of Engineering and Technology Department of Information Technology Madurai India Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India

ISBN: (纸本)9798350379945

'DensePneumoNct' is a specialized deep learning algorithm designed for accurate and efficient detection of pneumonia from CT chest images. Leveraging the DenseNet architecture within TensorFlow, this algorithm demonstrates superior performance across critical metrics including accuracy, recall, precision, and F1 score. The implementation utilizes the ImageNet dataset, preprocessed to ensure standardization and resizing, optimizing input uniformity for robust model training. The DenseNet model architecture features dense blocks and transition layers, fostering strong feature propagation and effective downsampling of feature maps. Hyperparameter tuning, including a learning rate of 0.001, a batch size of 64, and training over 100 epochs, enhances model convergence and performance refinement. Training enhancements such as early stopping and learning rate scheduling further stabilize model training and prevent overfitting. Evaluation on a validation set showcases 'DensePneumoNet''s capability to distinguish COVID-19 pneumonia, viral pneumonia, and healthy lung tissues with unparalleled accuracy. Comparative analysis against ResNet-50, Inception-v3, SqueezeNet, and LeNet confirms DensePneumoNet's superiority in all evaluated parameters, affirming its efficacy for critical medical imaging tasks. 'DensePneumoNet' represents a significant advancement in pneumonia detection, poised to enhance diagnostic accuracy and clinical decision-making in medical settings. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Security Perspectives in Integrity Verification for Shared Data in Cloud—A Survey 1

引用

9th International Conference on Cyber Security, Privacy in Communication Networks, ICCS 2023

作者： Pailkar, Harsh Murugan, Thangavel School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Bhopal India Department of Information Systems and Security College of Information Technology United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates

ISBN: (数字)9789819739738

ISBN: (纸本)9789819739721

As businesses move their data and services to cloud computing environments, it is crucial to ensure the security and integrity of that shared data. In order to study the new security perspectives in the context of integrity verification for shared data in the cloud, this research article conducts an extensive examination of the existing solutions. A key component of cloud security, data integrity, is thoroughly examined with an emphasis on the difficulties it faces and the consequences it may have in cloud-based scenarios. Analyzing the distinctive qualities of shared data in the cloud reveals the complications that develop when organizations access and work together on data inside a shared ecosystem. This article addresses research gaps and limitations within the existing solutions by critically examining prior studies. It emphasizes the requirement for novel strategies and answers to deal with the complex data integrity problems of shared data in cloud. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor Using Transfer Learning Using Conventional Autoencoder with Long Short Term Memory Method

Detection of Brain Tumor Using Transfer Learning Using Conve...

引用

Mobile computing and Sustainable Informatics (ICMCSI), International Conference on

作者： D Agalya S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Brain tumor (BT) has generate a significant health challenge by putting pressure on healthy brain parts or spreading into other areas as well as blocking the flow of fluid around the brain. BT diagnosis is an extensive and time consumption process that depends primarily on radiologists experience and interpretive capabilities. For the area of medical imaging, automatic segmentation of images by means of Deep Learning (DL) approaches. The DL approaches assist in transforming the sector, resulted in improving precision and effectiveness of investigations. However, there are various feature extraction mechanisms available. Therefore, the Recurrent Neural Network (RNN) is utilized for feature extraction and image classification. In model execution, the data have trained in transforming the test image as well as data features for minimizing the domain shift is calculated through the Convolutional Autoencoder (CAE) for reconstruction loss. This research has concentrated in building a model with VGG16 as a single test that subjected at inference and existing method is adopted as neural networks for AE as Transfer Learning (TL) that performs an image analysis task such as segmentation and even set as an adopter for pre training the model. The AE used to train from the source dataset and perform as the adaptors in optimizing during testing using a test subject for effective computation. Moreover, the Long Short Term Memory (LSTM) is utilized as RNN model with CAE for providing improved detection of BT in health care industries. Hence, the proposed CAE with LSTM is compared with AE with Convolutional Neural Network (CNN) for evaluating BT detection using MRI dataset with various BT type classifications.

关键词： Training Recurrent neural networks Computational modeling Autoencoders Transfer learning Predictive models Convolutional neural networks Long short term memory Image classification Testing

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-subset Fine-grained Authorization PSI over Outsourced Encrypted Datasets

Efficient Multi-subset Fine-grained Authorization PSI over O...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Jinlong Zheng Jia-Nan Liu Minhua Su Dingcheng Li Kai He Xueqiao Liu School of Computer Science and Technology Dongguan University of Technology Dongguan China School of Computing and Information Technology University of Wollongong Wollongong Australia

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Private set intersection (PSI) is an important cryptographic primitive with many real-world applications. Delegating PSI computation to the cloud can effectively reduce management and computational costs of data owners, and therefore has received widespread attention from researchers. However, in the existing delegated PSI schemes, it is hard for the data owner to authorize only a part of its outsourced data, and for users to flexibly select a part of the outsourced encrypted data of the data owner for intersection computation. In this paper, we propose the multi-subset fine-grained authorization PSI (MA-PSI) over outsourced encrypted datasets. Specially, our protocol is designed for the multi-subset case where each subset is associated with one single tag for data classification. Through tag classification and encryption technology, the data owner can perform fine-grained authorization on its subsets. By querying tags, the user can flexibly select any subset of the data owner for intersection computation. The security definition of the MA-PSI protocol is given, and its security is proved in the semi-honest model. Experimental results show that our protocol is very efficient and the computational cost is linear with the size of the subset. Specifically, the intersection algorithm SetI in our MA-PSI is about 80× (the subset size is 2 15 ) - 2500× (the subset size is 2 10 ) faster than APSI (Wang et al., IEEE TIFS 2021).

关键词： Authorization Data privacy Cloud computing Protocols Computational modeling Computational efficiency Encryption

来源：评论

学校读者我要写书评

暂无评论

Strategies to Minimize Network Latency for Better Electromagnetic Compatibility 5th

Strategies to Minimize Network Latency for Better Electromag...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Sampath, A.K. Savita Karthikeyan, M.P. Ramola, Abhishek C. Selection Grade School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Electrical Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India

ISBN: (纸本)9789819780426

Latency in a community will profoundly impact the electromagnetic compatibility (EMC) of a machine, wherein latency can cause interference and reduce the performance of a machine. Several techniques can be employed. The strategies encompass growing network throughput, minimizing interrupt latency, decreasing latency from packet scheduling, and optimizing higher-layer protocols. Growing network throughput can be accomplished by using more bandwidth, better throughput links, or including redundant hyperlinks in the community route. Minimizing interrupt latency may be executed by using interrupt coalescence, optimizing tool drivers, and shifting devices to isolated hardware additives. Furthermore, network topology designs can be stepped forward to lessen the time spent processing packets. It could be executed by setting nodes closer to each other or by imparting routers with more excellent computing assets, including more processing cores. Similarly, information transmission can be optimized to lessen latency, for instance, by using strategies such as selective acknowledgment or direction exploration. Eventually, interference may be minimized through filters and antennas, allowing it to restrict the communication variety. In conjunction with others, these techniques can ensure that community latency is minimized so EMC is improved. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： conjunction encompass minimized

来源：评论

学校读者我要写书评

暂无评论

Generic Sentimental Analysis in Web Data Recommendation Based on Social Media Scalable Data Analytics Using Machine Learning Architecture

Generic Sentimental Analysis in Web Data Recommendation Base...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Sekaran, Ramesh Rajeyyagari, Sivaram Munnangi, Ashok Kumar Parasuraman, Manikandan Ramachandran, Manikandan Kumar, Anil Karnataka Bengaluru562112 India Department of Computer Science College of Computing and Information Technology Shaqra University Shaqra Saudi Arabia Department of Information Technology Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh Vijayawada520007 India School of Computing SASTRA Deemed University Tamil Nadu Thanjavur613401 India Tula’s Institute Dehradun248197 India

ISBN: (纸本)9789819965434

Sentimental analysis is a method for distinguishing proof of articulation, mentality, or sensations of clients. It characterized as bad, positive, good, ominous, and so on from a piece of text in the record. Recommendation systems are important intelligent systems that assume a crucial part in giving specific data to users. Deep learning emerged as an important approach to settling opinion order issues in the late days. This research proposes a novel technique in generic sentimental analysis for web data classification with a recommendation system in social media analytics using machine learning techniques. Here, the web data input is processed, and remove missing values and normalization. Then the processed data is classified using convolutional discriminant kernel component analysis and their data recommendation in social media using reinforcement multilayer neural networks. The experimental analysis is carried out for various social media datasets regarding the accuracy, average precision, recall, actual positive rate, and F-measure. The proposed technique attained an accuracy of 98%, average precision of 79%, recall of 72%, real positive rate of 63%, and F-measure of 68%. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Integrative Technologies for Real-Time Crowd Management: A Case Study of the Hajj 18

Integrative Technologies for Real-Time Crowd Management: A C...

引用

18th INDIAcom;11th International Conference on computing for Sustainable Global Development, INDIACom 2024

作者： Almutairi, Mishaal M. Apostolopoulou, Dimitra Stupples, David Sen, Adnan Ahmed Abi Yamin, Mohammad Halikias, George City University of London School of Science and Technology Dept. of Electrical and Electronic Engg. London United Kingdom Islamic University Deanship of Information Technology Madinah Saudi Arabia The Australian National University School of Computing College of Engineering and Computer Science Canberra Australia University of Athens Department of Mathematics Greece

ISBN: (纸本)9789380544519

Crowd management is a very complex process, which requires the integration of many technologies together to create a reliable tool in crowd flow control. The historical events resulting from stampedes are the greatest evidence of the need for an effective solution. Relying on one method is not a reliable solution in such critical systems that require real-time response. The purpose of this research is to develop a smart framework that uses Artificial Intelligence (AI) and other technologies to control and manage crowds. The methodology involved conducting literature review and using a case study of Hajj event to develop a Python-based solution for running the framework. The findings shows that the framework is effective in crowd management, but it would be improved using advanced machine learning techniques. The proposed approach will help government agencies and other bodies to focus on adopting modern levels of technology in crowd management. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： artificial intelligence crowd management Hajj privacy security

来源：评论

学校读者我要写书评

暂无评论

GENSIMO - A Generic Framework for Modelling Social Insurance Systems 25th

GENSIMO - A Generic Framework for Modelling Social Insuranc...

引用

25th International Workshop on Multi-Agent-Based Simulation, MABS 2024

作者： de Haan, Fjalar J. Thompson, Jason School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Parkville Australia Melbourne Centre for Data Science The University of Melbourne Parkville Australia Department of Psychiatry Faculty of Medicine Dentistry and Health Sciences The University of Melbourne Parkville Australia

ISBN: (纸本)9783031880162

We report on the design, development and prototype testing of gensimo (GENeric Social Insurance MOdeling), a free and open-source software framework for modelling and simulation of social insurance systems. We discuss the conceptual and software design considerations of the framework in general before demonstrating how it works in detail by setting it up to model a particular social insurance scheme. We then present how we used this prototype set up to model the impact of a policy intervention on the workload of the insurer. While gensimo is under active development and we are a while away from serious verification and validation, this prototype testing shows realistic results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Occlusion Face Recognition Feature Fusion Network Based on Precise Guidance Mask Extraction

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-12页

作者： Ye, Jihua Zhang, Lei Wang, Chao Tu, Qixuan Zheng, Rehua Huang, Huiyuan Jiang, Aiwen School of Computer and Information Engineering Jiangxi Normal University Nanchang330022 China Jiangxi Provincial Key Laboratory for High Performance Computing Jiangxi Normal University Nanchang330022 China State International Science & Technology Cooperation Base of Networked Supporting Software Jiangxi Normal University Nanchang330022 China

The uncertainty in the position and size of occluding objects greatly affects the extraction of identity features in facial recognition, which is a challenge that existing methods fail to effectively address. To tackle this issue, this paper introduces a novel feature fusion network for occluded facial recognition that adaptively handles arbitrary occlusions and accurately extracts occlusion information masks. The network effectively mitigates the impact of occlusions on facial identity features through a feature fusion module. The proposed method employs an occlusion classification module and an occlusion classification loss to precisely guide the extraction of accurate occlusion masks. Subsequently, an occlusion-aware hybrid attention module is introduced, which focuses on the relationship between facial features and occlusion masks across channel and spatial dimensions. This fusion strategy enables the extraction of facial identity features that are resilient to occlusions. Experimental results indicate that the proposed method holds a significant advantage in handling facial recognition tasks with arbitrary occlusions. On the LFW and MF1 synthetic occlusion datasets, the average accuracy rates reached 93.19% and 72.57%, respectively, showing improvements of 1.7 and 2.39 percent points over mainstream methods. © Shanghai Jiao Tong University 2025.

关键词： A feature fusion occluded facial recognition occlusion mask occlusion perception TP391.41

来源：评论

学校读者我要写书评

暂无评论

A Way for Diagnosing Motor Faults Utilizing Deep Learning Techniques

A Way for Diagnosing Motor Faults Utilizing Deep Learning Te...

引用

New Power System and Power Electronics (NPSPE), International Conference on

作者： Yi Gong Ruyue Gong School of Information Science and Technology Qingdao University of Science and Technology Qingdao China School of Computing Neusoft Institute Guangdong Foshan China

ISBN: (数字)9798350389869

ISBN: (纸本)9798350389876

Considering motors' widespread application in manufacturing, energy production, transportation, and numerous industrial areas, it's vital to diagnose malfunctions to ensure the reliability of the equipment. In recent years, techniques for diagnosing faults using Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have become more mature. The conventional approach overly depends on expert knowledge, which facilitates the convergence of training outcomes to a locally optimal solution in the training process, leading to an exponential increase in computational demands due to the expansion of time series data. Addressing these issues, the research suggests a motor fault detection approach utilizing Swin-Transformer and Global-Attention-BiGRU parallel techniques. Initially, the one-dimensional fault signal underwent decomposition via VMD and transformation through FFT, and the final results were stacked; Next, the gathered data was inputted into the two-dimensional convolutional structure of the Swin-Transformer model to identify and extract the fault signal's local spatial characteristics, meanwhile the BiGRU network, refined through Global-Attention, is employed to extract the Global time domain characteristics of the fault signal; Ultimately, by merging local and global characteristics, the motor's present fault mode was estimated. Furthermore, the research employed t-SNE to simplify the data samples for visual representation, thereby improving the model's clarity. Confirmed through the CWRU public dataset, the findings indicate the technique's efficacy in diagnosing and identifying motor-bearing breakdown.

关键词： Training Fault diagnosis Adaptation models Recurrent neural networks Computational modeling Power system stability Motors Data models Data mining Convolutional neural networks

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：