检索结果-内蒙古大学图书馆

A Tutorial on Federated Learning from Theory to Practice:Foundations,software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： Data privacy distributed machine learning federated learning software frameworks

来源：评论

学校读者我要写书评

暂无评论

Detecting Deepfakes: Using CNN to Identify Manipulated Visual Media 8

Detecting Deepfakes: Using CNN to Identify Manipulated Visua...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sunanda, N. Shailaja, K. Babu, Jampani Satish Vamsi Krishna, K. Lakshmanpratap, N. Motupalli, Ravi Kanth and Ai&ds Hyderabad India Vasavi College of Engineering & Technology Department of Cse Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Guntur Vaddeswaram India Prowess Software Services Hyderabad India Mallareddy Engineering College Department of Ece Hyderabad India Vnr Vignana Jyothi Institute of Engineering & Technology Department of Cse Hyderabad India

ISBN: (纸本)9798350376425

Deepfake detection is a rapidly evolving field with significant implications for the integrity of visual media. This review explores techniques, challenges, and future directions in deepfake detection. Traditional image forensics techniques, deep learning models, and multi-modal fusion approaches are employed to differentiate real content from deepfakes. Addressing the challenges of evolving deepfake algorithms and the need for real-time detection, future research should focus on novel architectures, training strategies, temporal and contextual information, and ethical considerations. By advancing deepfake detection methods, researchers can contribute to combating the proliferation of synthetic content and preserving the authenticity of visual media in the digital age. © 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

A High-Gain DC-DC Boost Converter for Solar Microgrid Systems Using a Switching Inductor and a Capacitor 1

A High-Gain DC-DC Boost Converter for Solar Microgrid System...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Prasanth, S. Priyadarsini, S. Lakshmi, R. Sneha, G. Ajitha, S.S. Saravanakumar, R. Narendra, Konnaiah Gari Unnamalai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Kovilpatti India PSR Engineering College Department of Computer Science and Engineering Tamil Nadu Sivakasi India Siddharth Institute of Engineering and Technology Department of Elecrical and Electroncis Engineering Puttur India St. Joseph's Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Iconix Software Solution Tamil Nadu Tirunelveli India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electonics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331518578

This paper outlines the design and implementation of a solar microgrid-specific high-gain DC-DC booster converter that makes use of a variable inductor and capacitors. To improve the suitability of photovoltaic (PV) panels for incorporation into microgrids, the proposed converter efficiently increases their low-voltage outputs. Conventional boost converters can't offer that kind of voltage increase because they lose too much performance and put too much strain on their internal components. The converter increases the voltage gain dramatically while maintaining a high degree of efficiency thanks to a switching inductor-capacitor network. The main breakthrough is an inventive multi-stage energy transfer and storage device that cleverly employs a switching inductor and capacitor. This configuration increases the output voltage while decreasing the voltage and current ripples, which in turn reduces the amount of electromagnetic interference (EMI) and increases the life of the components. Thorough assessments of the converter's working via theoretical modeling and simulation studies confirm its performance across several load and input situations common to solar microgrids. The prototype's testing findings show a significant voltage increase and a peak efficiency of over 95% when compared to traditional boost converters. Moreover, the converter's reliable performance over a wide range of voltage sources and workload scenarios proves its suitability for practical solar applications. As a result, the proposed high-gain boost converter will greatly improve the efficiency and reliability of solar microgrids, leading to a rise in the use of renewable energy sources in DGS. © 2025 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

New Algorithms for Distributed Fair k-Center Clustering: Almost Accurate as Sequential Algorithms 23

New Algorithms for Distributed Fair k-Center Clustering: Alm...

引用

23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024

作者： Wu, Xiaoliang Feng, Qilong Huang, Ziyun Xu, Jinhui Wang, Jianxin School of Computer Science and Engineering Central South University Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Erie United States Department of Computer Science and Engineering State University of New York at Buffalo Buffalo United States Hunan Provincial Key Lab on Bioinformatics Central South University Xiangjiang Laboratory Changsha China

Fair clustering problems have been paid lots of attention recently. In this paper, we study the k-Center problem under the group fairness and data summarization fairness constraints, denoted as Group Fair k-Center (GFkC) and Data Summarization Fair k-Center (DSFkC), respectively, in the massively parallel computational (MPC) distributed model. The previous best results for the above two problems in the MPC model are a 9-approximation with violation 7 (WWW 2022) and a (17 + ∊)-approximation without fairness violation (ICML 2020), respectively. In this paper, we obtain a (3 + ∊)- approximation with violation 1 for the GFkC problem in the MPC model, which is almost as accurate as the best known approximation ratio 3 with violation 1 for the sequential algorithm of the GFkC problem. Moreover, for the DSFkC problem in the MPC model, we obtain a (4 + ∊)-approximation without fairness violation, which is very close to the best known approximation ratio 3 for the sequential algorithm of the DSFkC problem. Empirical experiments show that our distributed algorithms perform better than existing state-of-the-art distributed methods for the above two problems. © 2024 International Foundation for Autonomous Agents and Multiagent Systems.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The Impact of Stuttering Event Representation on Detection Performance 2

The Impact of Stuttering Event Representation on Detection P...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Al-Banna, Abedal-Kareem Fang, Hui Shubita, Ahmad F. Arafah, Mohammad Eqteeshat, Amani Abuaisheh, Saif B. University Of Petra Department Of Ai And Data Science Jordan Loughborough University Department Of Computer Science United Kingdom University Of Petra Department Of Software Engineering Jordan University Of Petra Department Of Computer Science Jordan Malaya University Department Of Information System Malaysia

ISBN: (纸本)9798350394962

Stuttering or stammering is a common neurogenic, psychogenic fluency disorder wherein people have uncontrolled blocks on the natural flow of speech. Automatic Stuttering Event Detection (SED) is a widely recognised challenge due to the heterogenic and overlapped nature of stuttering speech. Therefore, this comparative study investigates the impact of stuttering event representation on detection performance. The paper evaluates the performance of SED and shows the impact of employing ASR pre-trained feature extractions on each stuttering event. Moreover, the paper provides different groups of experiments that evaluate the impact of three acoustic features, the Zero Crossing Rate (ZCR), the Spectral Flux Onset Strength Envelope (SFO), and Fundamental Frequency (FF) features, on SED performance. The paper demonstrates that the fusion of spectral and ASR features improves SED performance across all stuttering events by 8%. The F1 score of the Block class increased by approximately 10%, from 15% to 25%, while the word repetition and interjection increased by 8%. In addition, our experiments proved that the fusion of temporal features increased the average F1 score of SED by 2% across all stuttering events. The F1 score of the prolongation and sound repetition classes increased by 6% and 3%, respectively. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Consensusless Blockchain: A Promising High-Performance Blockchain Without Consensus 5th

Consensusless Blockchain: A Promising High-Performance Block...

引用

5th International Conference on Blockchain and Trustworthy Systems, BlockSys 2023

作者： Zheng, Jian Wang, Qing Lin, Jianru Huang, Huawei Su, Chunhua Department of Computer Science and Engineering University of Aizu Aizu9650006 Japan School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Humi Technology Co. Ltd. Hainan570000 China School of Software Engineering Sun Yat-sen University Zhuhai519000 China

ISBN: (纸本)9789819981038

Consensus is unnecessary when the truth is available. In this paper, we present a new perspective of rebuilding the blockchain without consensus. When the consensus phase is eliminated from a blockchain, transactions could be canonized quickly using a well-defined universal rule without consuming hashing power. Thus, the transactions per second (TPS) metric of such the consensusless blockchain can be largely boosted. Although consensus blockchain is promising, several technical challenges are also crucial. For example, double-spending attacks and frequent forking events must be prevented, the credit of block’s minting must be carefully defined, and etc. To address those technical challenges, we propose several solutions for our consensusless blockchain (CB), including a naive monotonic scoring mechanism to calculate the ranking of each block in the chain, and a two-stage witness mechanism to add new blocks. The proposed CB chain is promising to offer a simplified and equipment-cheap infrastructure for rich real-world decentralized applications. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Model for Face Recognition Using SVM

引用

computers, Materials & Continua 2022年第8期72卷 2697-2712页

作者： Anil Kumar Yadav R.K.Pateriya Nirmal Kumar Gupta Punit Gupta Dinesh Kumar Saini Mohammad Alahmadi IES College of Technology Bhopal462044India Maulana Azad National Institute of Technology Bhopal462003India Department of Information Technology Manipal University JaipurJaipur303007India Department of Computer and Communication Engineering Manipal University JaipurJaipur303007India Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah23218Saudi Arabia

Face recognition systems have enhanced human-computer interactions in the last ten ***,the literature reveals that current techniques used for identifying or verifying faces are not immune to *** Component Analysis-Support Vector Machine(PCA-SVM)and Principal Component Analysis-Artificial Neural Network(PCA-ANN)are among the relatively recent and powerful face analysis *** to PCA-ANN,PCA-SVM has demonstrated generalization capabilities in many tasks,including the ability to recognize objects with small or large data *** from requiring a minimal number of parameters in face detection,PCA-SVM minimizes generalization errors and avoids overfitting problems better than ***-SVM,however,is ineffective and inefficient in detecting human faces in cases in which there is poor lighting,long hair,or items covering the subject’s *** study proposes a novel PCASVM-based model to overcome the recognition problem of PCA-ANN and enhance face *** experimental results indicate that the proposed model provides a better face recognition outcome than PCA-SVM.

关键词： Face recognition system(FRS) face identification SVM discrete cosine transform(DCT) artificial neural network(ANN) machine learning

来源：评论

学校读者我要写书评

暂无评论

Project Assessment in Offshore software Maintenance Outsourcing Using Deep Extreme Learning Machines

引用

computers, Materials & Continua 2023年第1期74卷 1871-1886页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Saqib Raza Ahmad Salman Khan Yasir Mahmood Nazri Kama Azri Azmi Assad Alzayed Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala NerusMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Advanced Informatics Department Razak Faculty of Technology and InformaticsUniversiti Teknologi Malaysia54100Kuala LumpurMalaysia Computer Science and Information Systems Department College of Business Studies Public Authority for Applied Education and Training(PAAET)AdailiyahKuwait Department of Computer Science Sharif College of Engineering&TechnologyLahore54000Pakistan

software maintenance is the process of fixing,modifying,and improving software deliverables after they are delivered to the *** can benefit from offshore software maintenance outsourcing(OSMO)in different ways,including time savings,cost savings,and improving the software quality and *** of the hardest challenges for the OSMO vendor is to choose a suitable project among several clients’*** goal of the current study is to recommend a machine learning-based decision support system that OSMO vendors can utilize to forecast or assess the project of OSMO *** projects belong to OSMO vendors,having offices in developing countries while providing services to developed *** the current study,Extreme Learning Machine’s(ELM’s)variant called Deep Extreme Learning Machines(DELMs)is used.A novel dataset consisting of 195 projects data is proposed to train the model and to evaluate the overall efficiency of the proposed *** proposed DELM’s based model evaluations achieved 90.017%training accuracy having a value with 1.412×10^(-3) Root Mean Square Error(RMSE)and 85.772%testing accuracy with 1.569×10^(-3) RMSE with five DELMs hidden *** results express that the suggested model has gained a notable recognition rate in comparison to any previous *** current study also concludes DELMs as the most applicable and useful technique for OSMO client’s project assessment.

关键词： software outsourcing deep extreme learning machine(DELM) machine learning(ML) extreme learning machine assessment

来源：评论

学校读者我要写书评

暂无评论

CIXG: A Comprehensive Approach to Driver Gene Identification and Causal Interpretation

CIXG: A Comprehensive Approach to Driver Gene Identification...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Yawen Chen, Yiwen Nie, Shanling Yang, Hai East China University of Science and Technology Department of Computer Science and Engineering Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China National University of Singapore Center for Continuing and Lifelong Education Singapore University of Sydney Faculty of Engineering Australia

ISBN: (纸本)9798350386226

With the ongoing advancements in science and technology and the increasing research focus on cancer-related issues, there has been a proliferation of omics-related resources for in-depth analysis and exploration. This burgeoning volume and complexity of biological data have fostered the integration of machine-learning techniques into biology. As a result, numerous machine-learning strategies have been established to identify driver mutations. Yet, many of these strategies produce complex models, complicating comprehension and thereby clouding the impact of input features on the resulting predictions. Our analysis presented the CIXG framework, which integrates a driver gene prediction module using XGBoost with a causality interpretation module anchored on CXPlain. This architecture enables quantifying each input feature's contribution to the prediction outcome and ensures precise predictions of driver genes. When benchmarked against the state-of-the-art (SOTA) method, CIXG demonstrated superior accuracy in pinpointing driver genes across pan-cancer studies and within the 32 specific cancer types. Importantly, our results underscored that mutation features chiefly influence CIXG's predictive prowess, with additional support from other omics features. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

TRANSIT-EEG - A Framework for Cross-Subject Classification with Subject Specific Adaptation

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Ahuja, Chirag Sethia, Divyashikha Delhi Technology University Department of Computer Science and Engineering Delhi India Delhi Technology University Department of Software Engineering Delhi India

Electroencephalography (EEG) is pivotal in monitoring and analysing cerebral activity across diverse domains, including medical diagnostics, cognitive neuroscience, and brain-computer interfaces. However, the inherent intricacy of EEG signals and their subject-specific characteristics pose formidable challenges in devising robust and generalisable classification models. Traditional EEG signal classification paradigms rely on extensive subject-specific datasets. Also, the domain adaption for new subjects often leads to "catastrophic forgetting,"thereby diminishing the performance of model trained on prior subjects. This paper proposes a novel framework, Transfer and Robust Adaptation of New Subjects in EEG Technology (TRANSIT-EEG), designed to adapt adeptly to new subjects. TRANSIT-EEG demonstrates resilience to subject-specific artefacts by integrating synthetic data generation using the proposed subject-specific augmentation model - Individualised Diffusion Probabilistic Model (IDPM). Also, it employs a robust Self Organising Graph Attention Transformer (SOGAT) that dynamically constructs a graph for each subject, fostering a more accurate classification. Moreover, TRANSIT-EEG introduces adapter-based finetuning using Low-Rank Adaptation (LoRA) for new subjects, enriching the adaptation process. The TRANSIT-EEG framework presents a promising avenue for advancing the realm of EEG signal classification. Evaluation of widely studied datasets, specifically focusing on two significant tasks, SEED for Emotion Recognition and PhyAat for Auditory Activity Recognition, substantiates the efficacy and versatility of TRANSIT-EEG. This validation indicates a substantial stride toward achieving more generalisable and accurate EEG signal classification. © 2016 IEEE.

关键词： Graph 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：