检索结果-内蒙古大学图书馆

A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models

Cognitive Computation 2024年第3期16卷 1073-1091页

作者： Heidari, Arash Navimipour, Nima Jafari Dag, Hasan Talebi, Samira Unal, Mehmet Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Information Technology Kadir Has University Istanbul Turkey Department of Computer Science University of Texas at San Antonio San AntonioTX United States Department of Computer Engineering Nisantasi University Istanbul Turkey

In recent years, the proliferation of deep learning (DL) techniques has given rise to a significant challenge in the form of deepfake videos, posing a grave threat to the authenticity of media content. With the rapid advancement of DL technology, the creation of convincingly realistic deepfake videos has become increasingly prevalent, raising serious concerns about the potential misuse of such content. Deepfakes have the potential to undermine trust in visual media, with implications for fields as diverse as journalism, entertainment, and security. This study presents an innovative solution by harnessing blockchain-based federated learning (FL) to address this issue, focusing on preserving data source anonymity. The approach combines the strengths of SegCaps and convolutional neural network (CNN) methods for improved image feature extraction, followed by capsule network (CN) training to enhance generalization. A novel data normalization technique is introduced to tackle data heterogeneity stemming from diverse global data sources. Moreover, transfer learning (TL) and preprocessing methods are deployed to elevate DL performance. These efforts culminate in collaborative global model training zfacilitated by blockchain and FL while maintaining the utmost confidentiality of data sources. The effectiveness of our methodology is rigorously tested and validated through extensive experiments. These experiments reveal a substantial improvement in accuracy, with an impressive average increase of 6.6% compared to six benchmark models. Furthermore, our approach demonstrates a 5.1% enhancement in the area under the curve (AUC) metric, underscoring its ability to outperform existing detection methods. These results substantiate the effectiveness of our proposed solution in countering the proliferation of deepfake content. In conclusion, our innovative approach represents a promising avenue for advancing deepfake detection. By leveraging existing data resources and the power of FL

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An Efficient Dialogue Policy Agent with Model-Based Causal Reinforcement Learning 31

An Efficient Dialogue Policy Agent with Model-Based Causal R...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Kai Wang, Zhenyu Zhao, Yangyang Fang, Bopeng School of Software Engineering South China University of Technology Guangdong China Department of Computer and Communication Engineering Changsha University of Science and Technology Changsha China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798891761964

Dialogue policy trains an agent to select dialogue actions frequently implemented via deep reinforcement learning (DRL). The model-based reinforcement methods built a world model to generate simulated data to alleviate the sample inefficiency. However, traditional world model methods merely consider one-step dialogues, leading to an inaccurate environmental simulation. Furthermore, different users may have different intention preferences, while most existing studies lack consideration of the intention-preferences causal relationship. This paper proposes a novel framework for dialogue policy learning named MCA, implemented through model-based reinforcement learning with automatically constructed causal chains. The MCA model utilizes an autoregressive Transformer to model dialogue trajectories, enabling a more accurate simulation of the environment. Additionally, it constructs a causal chains module that outputs latent preference distributions for intention-action pairs, thereby elucidating the relationship between user intentions and agent actions. The experimental results show that MCA can achieve state-of-the-art performances on three dialogue datasets over the compared dialogue agents, highlighting its effectiveness and robustness. © 2025 Association for Computational Linguistics.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Deep Q-Networks for Efficient Edge Federated Learning Communications in software-Defined IoT

引用

computers, Materials & Continua 2022年第5期71卷 3319-3335页

作者： Prohim Tam Sa Math Ahyoung Lee Seokhoon Kim Department of Software Convergence Soonchunhyang UniversityAsan31538Korea Department of Computer Science Kennesaw State UniversityMariettaGA 30060USA Department of Computer Software Engineering Soonchunhyang UniversityAsan31538Korea

Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging ***,in large-scale heterogeneous Internet of Things(IoT)cellular networks,massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled *** paper introduces the system model of converging softwaredefined networking(SDN)and network functions virtualization(NFV)to enable device/resource abstractions and provide NFV-enabled edge FL(eFL)aggregation servers for advancing automation and ***-agent deep Q-networks(MADQNs)target to enforce a self-learning softwarization,optimize resource allocation policies,and advocate computation offloading *** gathered network conditions and resource states,the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state *** exploration phase,optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value ***-based virtual network functions(VNF)forwarding graph(VNFFG)is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure(NFVI).The proposed scheme indicates deficient allocation actions,modifies the VNF backup instances,and reallocates the virtual resource for exploitation *** neural network(DNN)is used as a value function approximator,and epsilongreedy algorithm balances exploration and *** scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term *** results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service(QoS)performance metrics,including packet

关键词： Deep Q-networks federated learning network functions virtualization quality of service software-defined networking

来源：评论

学校读者我要写书评

暂无评论

Design of an Automatic Price Tag System for Web-Based Retail Business 9

Design of an Automatic Price Tag System for Web-Based Retail...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Liawatimena, Suryadiputra Gunawan, Devina Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Computer Science Deparment BINUS Graduate Program Master of Computer Science Jakarta11480 Indonesia Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

Modern retail businesses face a significant challenge with the inefficiency of manually changing price labels on shelves. This manual process not only consumes valuable time and resources but also increases the likelihood of errors, leading to potential inaccuracies in pricing and a less streamlined shopping experience for customers. The proposed solution is the implementation of an Electronic Shelf Label (ESL) system that automatically displays the prices of goods on retail business shelves. This system connects a website (front end and back end) to e-paper via a Wi-Fi network and microcontroller, allowing retail business owners to update prices more easily. Additionally, buyers can search for desired items through the website. The results are the time to send data from the website to the e-paper, namely, to know the performance of the e-paper used. The average time required from 10 attempts to send data from the website to the e-paper is 20.935 seconds. Since the data is connected to the server and will be updated automatically, using this system will be more efficient than manually changing the price label, although it takes time to transfer data from the website to the e-paper. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Web-Based Application for Managing Agricultural Health Products 4

Design and Implementation of a Web-Based Application for Man...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Oluwagbemi, Olugbenga O. Onyeka, Emebo Ishieka, Ikashi S. Wieclaw, Anna Azeta, Ambrose A. Middlesex University Department of Computer Science London United Kingdom Virginia Tech University Department of Computer Science Blacksburg United States Namibia University of Science and Technology Department of Software Engineering Windhoek Namibia

ISBN: (纸本)9798350353266

Caring for the health of food crops and plants can help boost food production and eradicate hunger according to the second United Nations (UN) Sustainable Development Goal (SDG). The procurement of agricultural health products such as fertilizers, fungicides, pesticides, and herbicides are a major problem for an average Nigerian farmer. This results in low crop yield and negatively impacts on food production which eventually causes hunger in the land. Existing methods of procuring these health products have majorly been through offline platforms such as agricultural stores and other relevant stores. This has its disadvantages such as inaccessible roads to stores where such products can be obtained, varying prices, health products out of stock, ignorance in the application of such products. These barriers deter farmers from procuring these health products. In this paper, a survey was conducted on the needs and problems of farmers. The results of the survey informed the design and implementation of an agricultural health Informatics web application for health product management for food crops. The application was designed using unified modelling language class diagram and implemented using Python. SQLite3 serves as the backend database. The agricultural informatics solution will help farmers in Nigeria to easily procure health products for food crops and get the products delivered without stress and worry when fully deployed. This will boost food production, thus eradicating hunger;it will also help in exporting food crops to other countries. © 2024 IEEE.

关键词： Agriculture AI Application Chatbot Farmers Health Informatics

来源：评论

学校读者我要写书评

暂无评论

Skin cancer detection with MobileNet-based transfer learning and MixNets for enhanced diagnosis

引用

Neural Computing and Applications 2024年第34期36卷 21383-21413页

作者： Zakariah, Mohammed Al-Razgan, Muna Alfakih, Taha Department of Computer Sciences and Engineering College of Applied Science King Saud University Riyadh11543 Saudi Arabia Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11345 Saudi Arabia Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia

Skin cancer poses a significant health hazard, necessitating the utilization of advanced diagnostic methodologies to facilitate timely detection, owing to its escalating prevalence in recent years. This paper proposes a novel approach to tackle the issue by introducing a method for detecting skin cancer that uses MixNets to enhance diagnosis and leverages mobile network-based transfer learning. Skin cancer has diverse forms, each distinguishable by its structural attributes, morphological characteristics, texture, and coloration. The pressing demand for accurate and efficient diagnostic instruments has spurred the investigation of novel techniques. The present study utilizes the ISIC dataset, comprising a validation set of 660 images and a training set of 2637 images. Moreover, the research employs a combination of MixNets and mobile network-based transfer learning as its chosen approach. Transfer learning is a technique that leverages preexisting models to enhance the diagnostic capabilities of the proposed system. Integrating MobileNet and MixNets allows for utilizing their respective functionalities, resulting in a dual-model methodology that enhances the comprehensiveness of skin cancer diagnosis. The results demonstrate impressive performance metrics, with MobileNet and MixNets models, and the proposed approach achieves an outstanding accuracy rate of 99.58%. The above findings underscore the efficacy of the dual-model method in effectively discerning between benign and malignant skin lesions. Moreover, the present study aims to examine the potential integration of emerging technologies to enhance the accuracy and practicality of diagnostics within real-world healthcare settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Evolution of Research on Adaptive Gamification: A Bibliometric Study

Evolution of Research on Adaptive Gamification: A Bibliometr...

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Vijay, Margret Jayan, J.P. Department of Computer Science Tamil Nadu India Department of Software Engineering Tamil Nadu India

ISBN: (纸本)9798350333244

This study explores the evolving landscape of adaptive gamification-related research from 2014 to 2022. A comprehensive analysis of 1110 documents from journals and books was conducted to investigate publication trends, prominent countries, authors, and the development of knowledge in the field. The findings reveal a consistent growth in publications, with an annual growth rate of 26.89%. Gamification emerges as a dominant cluster, consistently exhibiting high centrality and density scores, indicating its strong interconnectedness and influence within the research network. The country-wise analysis demonstrates a diverse global research landscape, with the United States contributing the highest number of publications, followed by Spain and Germany. Prominent authors from universities and institutions worldwide have made significant contributions to the field. The thematic evolution demonstrates a shift from collaborative learning to gamification and online learning, followed by a focus on technology-driven themes and the emergence of machine learning as a prominent area of research. The increasing relevance of machine learning indicates its growing significance in the domain of adaptive gamification. These findings contribute to the knowledge base of adaptive gamification and offer insights for researchers in shaping the future of gamified learning environments. © 2023 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Improving Breast Cancer Detection Accuracy Through Random Forest Machine Learning Algorithm

Improving Breast Cancer Detection Accuracy Through Random Fo...

引用

International Conference on Advanced engineering, Technology and Applications, ICAETA 2024

作者： Agrawal, Atul Khanday, Akib MohiUd Din Alazzawi, Esraa Mohammed Bhushan, Bharat Baniya, Pashupati Jamil, Akhtar Department of Computer Science and Engineering ITS Engineering College Greater Noida India Department of Computer Science and Engineering Sharda University Greater Noida India Department of Computer Science and Software Engineering United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates Department of Computer Engineering University of Baghdad Al-Jadriya Baghdad10071 Iraq Department of Computer Science National University of Computer and Emerging Sciences Islamabad44000 Pakistan

ISBN: (纸本)9783031709234

Breast cancer continues to be a significant global health issue that greatly affects the well-being of people worldwide. Detecting breast cancer early is vital for improving the outcomes of patients. One promising method for breast cancer detection is the use of the Random Forest machine learning algorithm. In a recent research paper, we investigated how Random Forest can be used to predict breast cancer by employing explainable AI techniques. We analyzed the specific features that the algorithm relies on to classify breast cancer and highlighted the advantages of Random Forest compared to other machine learning algorithms in diagnosing breast cancer. Our model offers a well-thought-out, efficient, and easily understandable approach to predicting breast cancer using explainable machine learning techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

BIFT: A federated learning System for Connected and Autonomous Vehicles Based on Blockchain 3

BIFT: A federated learning System for Connected and Autonomo...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Yadav, Aarti Kaur, Amandeep Vivekananda Global University Department of Computer Science Engineering Jaipur India Chandigarh School of Business Department of Master of Computer Application Jhanjeri India

ISBN: (纸本)9798350399264

Algorithms for machine learning(ML) are essential for autonomous driving. The vast majority of history's automated and connected cars send a significant quantity of movement data collected from many automobiles to a central server for regular training. Nonetheless, the info process has made the safety and confidentiality of information essential. Nowadays, the development of federated learning (FL) for data security has the potential to potential to enhance distributed machine learning's data privacy. The malicious attackers might still target the training process, though. FL is extremely vulnerable because of its total dependency on the central server. We suggest BIFT as a solution to the aforementioned issue, which consists of two parts: 1) a completely decentralized 2) A blockchain-based machine learning system for CAVs that guarantees privacy. With the use of their own driving data, BIFT's scattered CAVs may train local machine learning models, which they can subsequently upload to improve the global model. In order to fend off potential attackers, BIFT offers a consensus mechanism called Proof of Federated Learning. We assess BIFT's performance and demonstrate that it is scalable, reliable, and capable of fending off harmful assaults. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Pre-Trained Language Models Represent Some Geographic Populations Better Than Others 30

Pre-Trained Language Models Represent Some Geographic Popula...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Dunn, Jonathan Adams, Benjamin Madabushi, Harish Tayyar University of Illinois Urbana-Champaign Department of Linguistics United States University of Canterbury Department of Computer Science and Software Engineering New Zealand University of Bath Department of Computer Science United Kingdom

ISBN: (纸本)9782493814104

This paper measures the skew in how well two families of LLMs represent diverse geographic populations. A spatial probing task is used with geo-referenced corpora to measure the degree to which pre-trained language models from the opt and bloom series represent diverse populations around the world. Results show that these models perform much better for some populations than others. In particular, populations across the US and the UK are represented quite well while those in South and Southeast Asia are poorly represented. Analysis shows that both families of models largely share the same skew across populations. At the same time, this skew cannot be fully explained by sociolinguistic factors, economic factors, or geographic factors. The basic conclusion from this analysis is that pre-trained models do not equally represent the world's population: there is a strong skew towards specific geographic populations. This finding challenges the idea that a single model can be used for all populations. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： geographic corpora population skew spatial probing under-represented populations

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：