检索结果-内蒙古大学图书馆

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

作者： P. S. Arthy K. Sanjai Kumar S. Vinson Joshua G. Sahaana R. Kalpana D. David Neels Ponkumar S. Siamala Devi S. Jeya Lakshmi Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Dhanalakshmi College of Engineering Chennai Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering (Cyber Security) Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

This research study enhances secure data transmission by embedding sensitive information within audio files. Using Python for the frontend and PHP with MySQL as the backend, this approach employs reversible data hiding (RDH) to ensure that the original content of the audio file can be fully restored. Audio steganography is used to conceal encrypted messages within a WAV file, leveraging its varying compression rates for optimal steganographic performance. The Least Significant Bit (LSB) technique, a widely used method, embeds the hidden message into the audio stream without noticeable distortion. In this system, the secret message is scrambled, divided into segments, and embedded in even-value bytes of the audio file, with the first bit position chosen randomly for enhanced security. A permutation codebook is employed to rearrange and decrypt the message during recovery, ensuring both data confidentiality and complete reversibility of the audio file. This method provides a secure, efficient solution for transmitting sensitive information through audio channels.

关键词： Steganography data privacy Distortion Encryption data communication Informatics Mobile computing

来源：评论

学校读者我要写书评

暂无评论

REAL-TIME DIGITAL TWIN PLATFORM: A CASE STUDY ON CORE NETWORK SELECTION IN AERONAUTICAL AD-HOC NETWORKS

arXiv

引用

arXiv 2024年

作者： Cakir, Lal Verda Kocak, Mihriban Özdem, Mehmet Canberk, Berk School of Computing Engineering and The Built Environment Edinburgh Napier University United Kingdom BTS Group Turkey Department of Computer Science Aalto University Finland Turk Telekom Turkey Department of Artificial Intelligence and Data Engineering Istanbul Technical University Turkey

The development of Digital Twins (DTs) is hindered by a lack of specialized, open-source solutions that can meet the demands of dynamic applications. This has caused state-of-the-art DT applications to be validated using offline data. However, this approach falls short of integrating real-time data, which is one of the most important characteristics of DTs. This can limit the validating effectiveness of DT applications in cases such as aeronautical ad-hoc networks (AANETs). Considering this, we develop a Real-Time Digital Twin Platform and implement core network selection in AANETs as a case study. In this, we implement microservice-based architecture and design a robust data pipeline. Additionally, we develop an interactive user interface using open-source tools. Using this, the platform supports real-time decision-making in the presence of data retrieval failures. Copyright © 2024, The Authors. All rights reserved.

关键词： Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based AI Solutions for Early Wound Infection Detection and Treatment Recommendations

Cloud-Based AI Solutions for Early Wound Infection Detection...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Mothiram Rajasekaran Chitra Sabapathy Ranganathan G Manikandan G Bhuvaneswari T. R. GaneshBabu M. Rajmohan Pine Candle Way Saint Augustine Florida USA Mphasis Corporation Chandler Arizona USA Department of Artificial Intelligence and Data Science RMK Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Electronics and Communication Muthayammal Engineering College (Autonomous) Namakkal Tamil Nadu India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Wound infections are a major problem for healthcare systems worldwide. Infections cause patients to remain in the hospital longer., which increases healthcare expenses and negatively impacts their health outcomes. For patient care to be successful, it is crucial to identify these illnesses quickly and treat them appropriately. Recent developments in cloud computing and artificial intelligence (AI) have encouraged optimism for the potential of these technologies to improve wound infection diagnosis and treatment. Within healthcare systems, this research outlines a new method for early wound infection diagnosis and treatment recommendations generation using cloud-based AI algorithms. The proposed method employs machine learning to appropriately detect early indications of infection by analyzing a variety of patient data inputs, such as wound features, vital signs, laboratory findings, and medical history. Also, healthcare practitioners may benefit from real-time monitoring and decision assistance due to cloud-based architecture's easy interaction with existing electronic health record (HER) systems. The system is designed with a dynamic feedback loop that can be updated with fresh data inputs to make it more accurate and flexible. The proposed cloud-based AI system has been thoroughly tested and proven reliable in improving the early diagnosis and treatment of wound infections. This has led to better patient outcomes and more efficient use of healthcare resources. Key challenges include data privacy issues, the integration of diverse technologies, the reliability of precise forecasts, and maintaining system resiliency in changing environments.

关键词： Cloud computing data privacy Machine learning algorithms Medical services Wounds Real-time systems Reliability Artificial intelligence Usability Standards

来源：评论

学校读者我要写书评

暂无评论

Lattice mismatches caused by intrinsic stacking faults promote cracks initiation in Ni–Cu alloys

引用

Journal of Materials Research and Technology 2025年 36卷 9504-9517页

作者： Yu Zhou Yongchao Liang Yuanwei Pu Lili Zhou Zean Tian Qian Chen Yunfei Mo Institute of Advanced Optoelectronic Materials and Technology College of Big Data and Information Engineering Guizhou University Guiyang 550025 China Department of Information Engineering Gannan Medical University Ganzhou 341000 China College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China School of Electronic Information and Electrical Engineering Changsha University Changsha 410003 China

Metals are prone to cracking during processing, and the existence of cracks reduces the mechanical properties and service life. Therefore, molecular dynamics simulation method in this study is used to explore the initiation and propagation mechanism of Ni–Cu alloy cracks, so as to improve their mechanical properties. The results show that the intrinsic stacking faults (ISFs) were generated at the torsional end, resulting in the emission of dislocations and the initiation of shear transition zones (STZs). In the yielding stage, the rapidly growing ISFs led to the initiation of a large number of dislocations. At this time, STZs formed shear bands which caused the model to yield. The ISFs led severe lattice mismatch, increased dislocation density, and formed a large number of dislocation entanglements, thereby promoting the formation of cracks. The number and area of cracks rapidly increased during the plastic deformation stage, which eventually led to irrecoverable fracture of the material. The number and area of cracks are the largest at a high twisting rate. High Ni content can increase the yield strength and reduce the number of cracks. The study employed the construct surface mesh method to establish the relationship between shear bands, ISFs, dislocations, and cracks. The study investigates the mechanisms of crack initiation and propagation, providing a theoretical basis for optimizing the preparation process of Ni–Cu alloy and enhancing its mechanical properties.

关键词： Ni–Cu alloy Molecular dynamics simulation Intrinsic stacking faults Crack initiation Lattice mismatch

来源：评论

学校读者我要写书评

暂无评论

Face recognition Using Convolutional Neural Networks 2

Face recognition Using Convolutional Neural Networks

引用

2021 2nd International Conference on Machine Learning and computer Application, ICMLCA 2021

作者： Wang, Qi Yu, Zhenyue Zhang, Yiting Aliyun School of Big Data Changzhou University Changzhou China Electrical and Computer Engineering Department Queen's University Kingston Canada School of Computer Engineering and Science Shanghai University Shanghai China

ISBN: (纸本)9783800757398

The realization of automatic face image recognition by computers has seen attractive application prospects in the fields of information security, human-machine interaction and monitoring. Studies of face recognition have a significant influence on modern society in that they not only promote the understanding of the human visual system itself but also meet the needs of artificial intelligence applications. Compared with traditional machine learning algorithms, convolutional neural networks (CNN) can yield better performance and higher efficiency in face recognition. In this paper, we illustrate the mechanism of CNN methods, followed by discussions on the latest research progress of face recognition using CNN methods and comparisons between different algorithms. Furthermore, we describe a state-of-the-art CNN model, which takes advantage of the internal and external features of the face. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Transformers with Probabilistic Attention Keys 39

Improving Transformers with Probabilistic Attention Keys

引用

39th International Conference on Machine Learning, ICML 2022

作者： Nguyen, Tam Nguyen, Tan M. Le, Dung D. Nguyen, Duy Khuong Tran, Viet-Anh Baraniuk, Richard G. Ho, Nhat Osher, Stanley J. FPT Software AI Center Ha Noi Viet Nam Department of Mathematics University of California Los Angeles United States College of Engineering and Computer Science VinUniversity Ha Noi Viet Nam Deezer Research France Department of Electrical and Computer Engineering Rice University Houston United States Department of Statistics and Data Sciences The University of Texas Austin United States

Multi-head attention is a driving force behind state-of-the-art transformers, which achieve remarkable performance across a variety of natural language processing (NLP) and computer vision tasks. It has been observed that for many applications, those attention heads learn redundant embedding, and most of them can be removed without degrading the performance of the model. Inspired by this observation, we propose Transformer with a Mixture of Gaussian Keys (Transformer-MGK), a novel transformer architecture that replaces redundant heads in transformers with a mixture of keys at each head. These mixtures of keys follow a Gaussian mixture model and allow each attention head to focus on different parts of the input sequence efficiently. Compared to its conventional transformer counterpart, Transformer-MGK accelerates training and inference, has fewer parameters, and requires fewer FLOPs to compute while achieving comparable or better accuracy across tasks. Transformer-MGK can also be easily extended to use with linear attention. We empirically demonstrate the advantage of Transformer-MGK in a range of practical applications, including language modeling and tasks that involve very long sequences. On the Wikitext-103 and Long Range Arena benchmark, Transformer-MGKs with 4 heads attain comparable or better performance to the baseline transformers with 8 heads. Copyright © 2022 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benchmarking data Heterogeneity Evaluation Approaches for Personalized Federated Learning

arXiv

引用

arXiv 2024年

作者： Li, Zhilong Wu, Xiaohu Tang, Xiaoli He, Tiantian Ong, Yew-Soon Chen, Mengmeng Liu, Qiqi Lao, Qicheng Li, Xiaoxiao Yu, Han Beijing University of Posts and Telecommunications China College of Computing and Data Science Nanyang Technological University Singapore Singapore Westlake University China Department of Electrical & Computer Engineering The University of British Columbia Canada

There is growing research interest in measuring the statistical heterogeneity of clients’ local datasets. Such measurements are used to estimate the suitability for collaborative training of personalized federated learning (PFL) models. Currently, these research endeavors are taking place in silos and there is a lack of a unified benchmark to provide a fair and convenient comparison among various approaches in common settings. We aim to bridge this important gap in this paper. The proposed benchmarking framework currently includes six representative approaches. Extensive experiments have been conducted to compare these approaches under five standard non-IID FL settings, providing much needed insights into which approaches are advantageous under which settings. The proposed framework offers useful guidance on the suitability of various data divergence measures in FL systems. It is beneficial for keeping related research activities on the right track in terms of: (i) designing PFL schemes, (ii) selecting appropriate data heterogeneity evaluation approaches for specific FL application scenarios, and (iii) addressing fairness issues in collaborative model training. The code is available at https://***/Xiaoni-61/DH-Benchmark. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Theoretical Perspectives on Deep Learning Methods in Inverse Problems

arXiv

引用

arXiv 2022年

作者： Scarlett, Jonathan Heckel, Reinhard Rodrigues, Miguel R.D. Hand, Paul Eldar, Yonina C. The Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore Singapore The Department of Electrical and Computer Engineering Technical University of Munich Germany The Department of Electronic and Electrical Engineering University College London United Kingdom The College of Science The Khoury College of Computer Sciences Northeastern University United States The Department of Computer Science and Applied Mathematics Weizmann Institute of Science Israel

In recent years, there have been significant advances in the use of deep learning methods in inverse problems such as denoising, compressive sensing, inpainting, and super-resolution. While this line of works has predominantly been driven by practical algorithms and experiments, it has also given rise to a variety of intriguing theoretical problems. In this paper, we survey some of the prominent theoretical developments in this line of works, focusing in particular on generative priors, untrained neural network priors, and unfolding algorithms. In addition to summarizing existing results in these topics, we highlight several ongoing challenges and open problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Development of Recommender Systems for Better Services and Products using data science

Development of Recommender Systems for Better Services and P...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： S. Padmapriya Thamizhamuthu R S. Jagadeesh D. M. Kalai Selvi M. Ahsan Shariff Department of Artificial Intelligence and Data Science Velammal Institute of Technology Chennai Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus-Chengalpattu Chennai Tamil Nadu India Department of Electronics and Communication Engineering Sridevi Women’s Engineering College Hyderabad Telangana India Department of Computer Science and Engineering R.M.D. Engineering College Chennai Tamil Nadu India M. Tech - Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India

Online social networking and e-commerce are becoming increasingly popular. Recommender Systems (RS) let users find relevant information from several possibilities. Internet applications currently need RS. This technology uses huge data to provide customized suggestions to improve customer happiness. Concerns and ideas help customers choose items. Sentiment Analysis (SA) may increase RS recommendation accuracy by improving user behaviour, views, and responses. RS solves information overload in information retrieval, but data sparsity remains a big problem. SA is notable for reading text and expressing user preferences. It helps E-Commerce to monitor product feedback and to understand what client wants and their preferences. This research presents a hybrid recommendation approach to increase RS accuracy and correctness. The hybrid approach beats standard models in several assessment criteria. Modern retailing businesses’ e-commerce operations are impossible without RSs. The content-based and context-aware techniques are hybridized for providing promising results. Content-based approaches connect consumers to new things based on prior ratings and activities. Create user profiles and classify it. Knowledge-based algorithms propose customized items with minimal use history. These systems use case-based recommendations or limitations to make recommendations. Finally, ensemble recommender systems combine data source prediction power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis

arXiv

引用

arXiv 2023年

作者： Haoran, Sun Yang, Wang Haipeng, Liu Biao, Qian Meng, Wang Key Laboratory of Knowledge Engineering With Big Data Ministry of Education Hefei University of Technology Hefei China Department of Computer Science and Information Engineering Hefei University of Technology Hefei China

Text-to-image synthesis refers to generating visual-realistic and semantically consistent images from given textual descriptions. Previous approaches generate an initial low-resolution image and then refine it to be high-resolution. Despite the remarkable progress, these methods are limited in fully utilizing the given texts and could generate text-mismatched images, especially when the text description is complex. We propose a novel Fine-grained text-image Fusion based Generative Adversarial Networks, dubbed FF-GAN, which consists of two modules: Fine-grained text-image Fusion Block (FF-Block) and Global Semantic Refinement (GSR). The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details. And the GSR is proposed to improve the global semantic consistency between linguistic and visual features during the refinement process. Extensive experiments on CUB-200 and COCO datasets demonstrate the superiority of FF-GAN over other state-of-the-art approaches in generating images with semantic consistency to the given *** is available at htt s:// ithub com/haoranhfut/FF-GAN Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial 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：