检索结果-内蒙古大学图书馆

9th International Conference on information Technology and Quantitative Management, ITQM 2022

作者： Trillo, José Ramón Herrera-Viedma, Enrique Higueras-Ruiz, María José Alonso, Sergio Morente-Molinera, Juan Antonio Cabrerizo, Francisco Javier Department of Computer Science and Artificial Intelligence Andalusian Research Institute of Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain Department of Information and Communication University of Granada Granada18071 Spain Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain

Nowadays, group decision-making is an everyday event, since we usually live in a community. Nevertheless, when the number of participants is large, it starts to generate a lot of information that is complex to manage, and unlike group decision-making, where the participants are usually experts, when the number of participants increases, not all of them are, which generates a conflict of interest because the value of the vote of an expert and a (non-expert) user is worth the same. Moreover, it may happen that not all participants who start a process will finish it and not all of them will be able to make all the assessments, since they do not know all the options. Therefore, to solve all the drawbacks, this paper presents a large-scale group decision-making system in a modifiable scenario environment that groups participants according to their preferred alternative and also performs knowledge differentiation, clustering them into experts and users. This allows for optimising the consensus process, as the consensus is made by comparing the clusters and the participants with each other. © 2022 The Authors. Published by Elsevier B.V.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

General Dynamic Regularization Federated Learning with Hybrid Sharpness-Aware Minimization

General Dynamic Regularization Federated Learning with Hybri...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fengchun Zhang Dongfen Li Jinshan Lai Yang Zhang Fengli Zhang Ruijin Wang School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Computer and Network Security Chengdu University of Technology Chengdu China Science Research Centre The Second Research Institute of CAAC Chengdu China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

One of the main challenges in federated learning is its non-independent and identically distributed (non-IID) nature, where independent client training leads to overfitting and model deviations, negatively impacting overall performance. To address this, most research focuses on aligning local and global models to reduce client drift. However, existing algorithms use Empirical Risk Minimization (ERM) as the local optimizer, leading the global model to sharp minima, increasing bias in some clients and lowering generalization. To address these challenges, we propose GFed-HSAM, a general federated learning method that improves both local and global model generalization. GFed-HSAM uses Hybrid Sharpness-Aware Minimization (HSAM) as the local optimizer to smooth gradients with zeroth-order and first-order sharpness measures. It also includes a dynamic regularizer (DR) to align global and local models at the parameter level. Experiments show that GFed-HSAM outperforms state-of-theart methods in accuracy and generalization across different data heterogeneity settings on CIFAR10/CIFAR100.

关键词： Training Accuracy Risk minimization Federated learning Heuristic algorithms Perturbation methods Signal processing algorithms Signal processing Minimization Speech processing

来源：评论

学校读者我要写书评

暂无评论

Transforming Online Learning with CNN and NLP: Personalized Education

Transforming Online Learning with CNN and NLP: Personalized ...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Abilash Lathaharan Danushan Ravendran Agash Varatharasa Abinaya Thayaparan Sanvitha Kasthuriarachchi Karthiga Rajendran Department of Computer Science & Software Engineering Sri Lanka Institute of Information Technology New Kandy Road Malabe Sri Lanka Department of Information Technology SSri Lanka Institute of Information Technology New Kandy Road Malabe Sri Lanka

In the rapidly evolving landscape of online education, ensuring easy and healthy learning experiences has become paramount. This research paper presents "Sparkle Edu," an innovative application that integrates multiple components to address the unique challenges of online learning. The components include stress detection through facial emotions and drowsiness analysis, facial authentication with personalized course recommendations, an AI-powered mental health therapist utilizing voice-to-text input, and document reconstruction for damaged images to predict missing letters and words. Through the implementation of these components, Sparkle Edu aims to create an engaging and supportive platform that prioritizes students' well-being and promotes effective learning. This research contributes valuable insights into the advancement of online education, fostering a brighter and more accessible future for learners worldwide.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges in Fuzzy Decision Making for Future Research 21

Challenges in Fuzzy Decision Making for Future Research

引用

21st International Conference on New Trends in Intelligent software Methodologies, Tools and Techniques, SoMeT 2022

作者： Trillo, José Ramón Herrera-Viedma, Enrique Higueras-Ruiz, María José Alonso, Sergio Morente-Molinera, Juan Antonio Cabrerizo, Francisco Javier Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain Department of Information and Communication University of Granada Granada18071 Spain Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain

ISBN: (纸本)9781643683164

Fuzzy Decision Making is a line of research that has had an important presence in the literature since 1965 until nowadays. From that year to the present, the line of research has been consolidated. The research field goals have evolved along with all the research that makes use of these systems and the new technologies requirements. Therefore, new challenges, different from the ones that were faced at the beginning, need to be solved. The aim of this paper is to describe the recent challenges faced by those working in this line of research. This paper will help researchers to know how their work should be oriented in the future. © 2022 The authors and IOS Press. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Design of a Secure Machine Learning-Based Malware Detection and Analysis Scheme

Design of a Secure Machine Learning-Based Malware Detection ...

引用

2023 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2023

作者： Kumar, Pankaj Obaidat, Mohammad S. Pandey, Piyush Wazid, Mohammad Das, Ashok Kumar Singh, Devesh Pratap Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India King Abdullah Ii School of Information Technology The University of Jordan Amman11942 Jordan School of Computing Srm University Jordan University of Science and Technology Beijing Beijing100083 China School of Computing Srm University TN Kattankulathur603203 India Algorithmic Research International Institute of Information Technology Center for Security Theory Hyderabad India

ISBN: (纸本)9798350302561

Today's world is rapidly growing towards the advanced concept of technology. Technology nowadays is at its peak of development and has great advantages in all fields of work, whether it is in industrial automation, farming, weather forecasting, or disease detection and control. Despite its great advantages, it does have its negative side because a major population is using technology and general-purpose computing devices (i.e., desktops, laptops, smartphones, tablets, etc.). Therefore, most of their personal data is available online. The data is constantly in danger of getting stolen by malicious actors (i.e., hackers), who can find a way to get their hands on this data and then use it for their personal gain (i.e., money-making). The best-known technique to get this information is by using malware exploitation on the machine of the target. Malware is an executable or a binary that is malicious in nature. It may have various devastating effects, and in order to detect and make the system defensive, we need to propose a scheme to detect the malware in the system, analyze the particular file, and then mitigate it. In this paper, we propose a secure machine learning-based malware detection and analysis scheme (in short, SML-MDA). The conducted security analysis and formal security verification of the proposed SMLMDA prove its security against various types of potential attacks. The proposed SML-MDA is then compared with the other similar competing schemes, and its performance has been found to be better in terms of various performance metrics like accuracy and F1-score. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

arXiv

引用

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Multi Model Approach to Evaluate and Enhance Student - Teacher Interactions

Multi Model Approach to Evaluate and Enhance Student - Teach...

引用

Advancements in Computing (ICAC), International Conference on

作者： Nisal Daksith Sathsara Wanaguru Uresha Kolonne Amaya Dolawatta Lakmini Abeywardhana Dharshana Kasthurirathna Department of Information Technology Sri Lanka Institute of Inoformation Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Sri Lanka Institute of Inoformation Technology Malabe Sri Lanka

Advancements in artificial intelligence (AI) and machine learning (ML) have enabled the development of tools to address issues in Virtual Classrooms. This research focuses on utilizing AI and ML to monitor student behavior in virtual classrooms by analyzing facial expressions, background noise, and keystroke patterns. An AI based approach is proposed to analyze real-time webcam data, detecting patterns of inattention, and notifying teachers accordingly. The application also monitors background noise levels, identifying non-conducive learning environments, and analyzes keystroke patterns to detect unrelated activities. The research draws from academic literature to evaluate the effectiveness of the application while considering ethical implications such as potential bias and student privacy protection. Overall, this study contributes to the existing literature on AI and ML-based applications in education, demonstrating how these technologies can revolutionize student behavior monitoring, leading to enhanced outcomes for virtual classroom learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing User Data Privacy and Confidentiality in Cloud Storage Systems Through Advanced Obfuscrypt Encryption Methods for Enhanced Security and Efficient Data Protection

Optimizing User Data Privacy and Confidentiality in Cloud St...

引用

Recent Advances in science and engineering Technology (ICRASET), International Conference on

作者： P.S. Ramesh I. Sudha J. Jagannathan Rajkumar Pandiarajan A. Ponmalar 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 Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS University Chennai Tamil Nadu India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Katpadi Vellore India Department of Information and Technology School of Computing Kalasalingam Academy Of Research and Education Krishnankoil Virudhunagar India R.M.K. Engineering College Chennai Tamilnadu India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

With a steady increase in the adoption of cloud storage systems, the client’s data are at risk of being leaked. There are several methods of encrypting data which are quite useful but they lack some of the features of today’s sophisticated threats. The methodology used in this research propose an encryption framework known as Obfuscrypt to improve the issues of data privacy as well as confidentiality of data stored in cloud storage systems. Obfuscrypt uses conventional encryption strategies incorporated with obfuscation and post-quantum cryptographic algorithms to provide a complex security plan immune to classic and quantum approaches. Some of the proposed other innovations include the decentralised key management with multi-factor authentication and RBAC-ABE as the fine-grained access control techniques. These features make it possible for only the authorized personnel to be in a position to be in a position of decrypting and retrieving the stored data thereby minimizing the possibility of the data being accessed by unauthorized people. The work also considers the issue of performance efficiency of the cloud storage systems. Similar to other symmetric encryption programs, Obfuscrypt uses light encryption algorithms and brings in to play the hardware acceleration so that it may infuse lesser computational overhead in the process of encryption and decryption. As can be clearly seen from the results, the actual work proves that the proposed framework not only offers a higher level of security but does not affect the system performance to a great extent. Also, the study addresses the post-quantum cryptographic algorithm for making the system resistant to an attack that can be posed by quantum computing systems. With the help of these improved algorithms, Obfuscrypt guarantees the permanent data security in the world of constantly emerging cyber threats.

关键词： Resistance Cloud computing Technological innovation Multi-factor authentication Quantum computing System performance Memory management software performance Encryption Protection

来源：评论

学校读者我要写书评

暂无评论

A Light Gradient Residual Encoder-Decoder Network for Multimodal Image Fusion

A Light Gradient Residual Encoder-Decoder Network for Multim...

引用

Intelligent Computing, Communication, Networking and Services (ICCNS), International Conference on

作者： Muhammad Ishfaq Hussain Zubia Naz Linh Van Ma Jeonghwan Gwak Moongu Jeon School of Electrical Engineering and Computer Sciene Gwangju Institute of Science and Technology (GIST) South Korea Large-scale AI Research Group Korea Institute of Science and Technology Information (KISTI) South Korea Department of Software Korea National University of Transportation South Korea

ISBN: (数字)9798350354690

ISBN: (纸本)9798350354706

Image fusion combines the complementary traits of source images into a single output, enhancing both human visual observation and machine vision perception. The existing fusion algorithms typically prioritize visual enhancement, often overlooking the real-time needs for critical surveillance applications. To address these real-time deployment needs, we present a compact fusion network for combining infrared and visible image representations, named Light-weight Fusion (LightFusion). This network employs incremental semantic integration and scene recognition accuracy constraints by incorporating three different bands of images (IR, RGB, and Grayscale) to fuse the data. Our approach includes a sparse semantic perception branch that captures critical semantic features, which are then integrated into the fusion network through a semantic injection module. This ensures that high-level vision tasks are adequately addressed. The scene fidelity path ensures that fusion features preserve all details required to reconstruct the original images. The importance and applicability of the proposed network are enhanced by employing an extra input in the form of a grayscale image, obtained by converting the RGB image for improved contrast, along with prominent target masks to enhance the visual quality of the fusion results. Our extensive analysis shows that the lightweight LightFusion network outperforms existing methods in both visual quality and semantic integrity, even under challenging conditions. The source code will be released at https://***/MI-HussainiLightFusion.

关键词： Visualization Image recognition Surveillance Source coding Semantics Gray-scale Real-time systems Robustness Image reconstruction Image fusion

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：