检索结果-内蒙古大学图书馆

FedRDF: A Robust and Dynamic Aggregation Function Against Poisoning Attacks in Federated Learning

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING 2025年第1期13卷 48-67页

作者： Campos, Enrique Marmol Gonzalez-Vidal, Aurora Hernandez-Ramos, Jose L. Skarmeta, Antonio Univ Murcia Murcia 30100 Spain

Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks, which can significantly degrade model performance and hinder convergence. The effectiveness of existing approaches to mitigate complex attacks, such as median, trimmed mean, or Krum aggregation functions, has been only partially demonstrated in the case of specific attacks. Our study introduces a novel robust aggregation mechanism utilizing the Fourier Transform (FT), which is able to effectively handle sophisticated attacks without prior knowledge of the number of attackers. Employing this data technique, weights generated by FL clients are projected into the frequency domain to ascertain their density function, selecting the one exhibiting the highest frequency. Consequently, malicious clients' weights are excluded. Our proposed approach was tested against various model poisoning attacks, demonstrating superior performance over state-of-the-art aggregation methods.

关键词： Federated learning Convergence fourier transform robust aggregation function Federated learning Convergence fourier transform robust aggregation function

来源：评论

学校读者我要写书评

暂无评论

Searching for New Four-membered Palladacycles Derived from Anilines: Influence of the N-Substituents in the Reaction Outcome

引用

EUROPEAN JOURNAL OF INORGANIC CHEMISTRY 2025年第6期28卷

作者： Chicote, Maria-Teresa Bautista, Delia Vicente, Jose Saura-Llamas, Isabel Univ Murcia Fac Quim Dept Quim Inorgan Murcia 30100 Spain Univ Murcia ACTI Murcia 30100 Spain

The reactions of iodoanilines IC6H4NRR '-2 with [Pd(PPh3)4] gave complexes [Pd(C6H4NRR '-2}I(PPh3)2] [R=H, R'=H (1 a), Me (1 b);R=R'=Me (1 c)] while a mixture of 1 a, and the dimeric [Pd{mu-C,N-C6H4NH2-2)I(PPh3)]2 (2 a) was obtained when the appropriate iodoaniline was reacted with [Pd(dba)2] (dba=dibenzylideneacetone) and 1 equiv. of PPh3. The phosphonium salts [Ph3PC6H4NRMe-2]OTf [R=H (3 b), Me (3 c)] formed upon reacting complexes 1 b,c with TlOTf (OTf=CF3SO3). Complexes of the type [Pd(C6H4NRR '-2}I(N N)] (4) were obtained from the reaction of [Pd(dba)2] with the appropriate iodoaniline and a N N bidentate ligand (N N=4,4 '-di-tert-butyl-2,2 '-bipyridine or N,N,N ',N '-tetramethylethylenediamine). Complexes 4 reacted with TlOTf and PPh3 or XyNC (Xy=C4H4Me2-2,6) to give [Pd(C6H4NRR '-2)(N N)(PPh3)]OTf (5) or [Pd{C,N-C(=NHXy)C6H4NRR '-2)(N N)]OTf (6), respectively. In the absence of any added ligand, the reactions of complexes 4 with TlOTf produced the dimeric complexes [Pd{mu-C,N-C6H4NHR-2)(N N)]2(OTf)2 (7) or the four-membered palladacycles [Pd(kappa 2-C6H4NMe2-2)(N N)]OTf (8), depending on the substitution degree of the aniline reagent.

关键词： Palladium Metallacycles Four-membered palladacycles Metalated anilines

来源：评论

学校读者我要写书评

暂无评论

VolRec: 4D real-time volumetric reconstruction of OCT data

引用

JOURNAL OF SUPERCOMPUTING 2025年第3期81卷 1-22页

作者： Vicente-Jaen, Arturo Mompean, Juan Aragon, Juan L. Artal, Pablo Univ Murcia Lab Opt Murcia 30100 Spain Univ Murcia Dept Ingn & Tecnol Comp Murcia 30100 Spain

This work presents the design, analysis and development of VolRec, a volumetric 4D reconstruction system for OCT (optical coherence tomography) data. VolRec is able to obtain and process more than 25 high-resolution OCT data volumes per second. This way, VolRec allows OCT systems to perform real-time measurements that could help doctors and physicians in many different cases, e.g., during surgical interventions or during exams to restless patients, such as kids. Moreover, VolRec allows to adapt to telemedicine techniques such as telesurgery or image-guided medical robots. To achieve real-time performance, it is necessary to address the limitations of current OCT systems, which are restricted by both the acquisition and processing of massive amounts of data. To overcome those limitations, this work proposes an approach based on a 4D reconstruction. Our proposal allows to generate high-resolution volumes from acquired low-resolution ones. Hence, increasing the acquisition speed while reducing the acquisition resolution without sacrificing image quality. To this end, we use parallel programming mechanisms such as OpenMP (for CPUs) and CUDA to exploit the computing capabilities of modern GPUs. Our real-time volumetric reconstruction algorithm efficiently achieves a very high performance, reaching a processing rate of 18 GigaVoxels/s and about 72 x \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times$$\end{document} speedup over a parallel CPU-based algorithm using a GPU, by efficiently exploiting the vast amount of data-level parallelism inherent to OCT data volumes.

关键词： CUDA GP-GPU OCT OpenMP Parallelism

来源：评论

学校读者我要写书评

暂无评论

Developing configurations and solutions for logical puzzles with UML and OCL

引用

SOFTWARE AND SYSTEMS MODELING 2025年 1-25页

作者： Gogolla, Martin Cuadrado, Jesus Sanchez Univ Bremen Bremen Germany Univ Murcia Murcia Spain

Logical puzzles can be important factors for the development of rational analysis and application capabilities for pupils and students. Therefore, logical puzzles can also take a prominent supporting role in computer science education. This contribution proposes a UML class model with accompanying OCL constraints for developing logical puzzles. The class model acts as a metamodel for the description of the basic puzzle organization and the logical clues presented to the learners. The constraints express, for example, statements about uniqueness of solutions, and the degree of puzzle complexity may be tuned by appropriate model elements. Given a puzzle specification which simply comprises the domain elements of the puzzle plus constraints, our implementation uses a UML and OCL solver to construct a puzzle instance (i.e., a set of clues and solutions) automatically. The puzzle is made playable by a graphical user interface. We have validated this approach for developing puzzles by building several puzzles from the literature of increasing complexity and performed a student survey.

关键词： Logical puzzle Formal method UML OCL Metamodel

来源：评论

学校读者我要写书评

暂无评论

The Iceberg Profile Does Not Influence the Performance of Elite League of Legends Players, but Changes With the Events of the Game

引用

IEEE TRANSACTIONS ON GAMES 2025年第1期17卷 76-87页

作者： Mateo-Orcajada, Adrian Abenza-Cano, Lucia Rey-Lopez, Juan Pablo Vaquero-Cristobal, Raquel UCAM Univ Catolica Murcia Fac Deporte Murcia 30107 Spain Univ Murcia Fac Sport Sci Dept Phys Act & Sport Murcia 30003 Spain

Little is known about the interactions between the iceberg profile, which is characterized by high vigor scores, as opposed to low scores in tension, depression, anger, fatigue, and confusion, and performance in League of Legends (LOL). For these reasons, the objectives of the present research were to analyze whether the performance was influenced by the presence of the iceberg profile before the start of the game and to determine the changes produced in the iceberg profile of esports players as a function of the final outcome of the game, the players' performance during the game, and pregame anxiety and self-confidence. The participants were players in a professional LOL esports team during a SuperLiga Orange spring split. The profile of mood states and competitive state anxiety inventory-2 questionnaires were used. Performance was assessed using in-game variables, such as game result, favorable and unfavorable plays, and kills/deaths/assists ratio. The results showed that no changes were found in the performance of the players according to the pregame iceberg profile. Changes were found in the pre- and postgame iceberg profile, according to the final outcome of the game, and the favorable and unfavorable plays. Furthermore, the psychological variables cognitive and somatic anxiety, and self-confidence, had a relationship with the presence or absence of the iceberg profile. To conclude, the iceberg profile does not seem to influence the performance of esports players, although it is modified by events that occur during the game.

关键词： Games Icebergs Sports Mood Anxiety disorders Fatigue Depression Esports mood state professional self-confidence videogames

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence to Support the Training and Assessment of Professionals: A Systematic Literature Review

引用

ACM COMPUTING SURVEYS 2025年第3期57卷 1-29页

作者： Albaladejo-gonzalez, Mariano Ruiperez-valiente, JOSe A. Marmol, FeLIX GoMEZ Univ Murcia Dept Informat & Commun Engn Murcia Spain

Advances in Artificial Intelligence (AI) and sensors are significantly impacting multiple areas, including education and workplaces. Following the PRISMA methodology, this review explores the current status of using AIto support the training and assessment of professionals. We examined 83 research papers, analyzing (1) the targeted professionals, (2) the skills assessed, (3) the AI algorithms utilized, (4) the data and devices employed, (5) data fusion techniques utilized, (6) the architecture of the proposed platforms, (7) the management of ethics and privacy, and (8) validations of the proposals. The review highlights a trend in evaluating healthcare professionals (especially surgeons) motivated by the critical role of hands-on training in these professions. Besides, the review reveals that data fusion techniques and certain technologies, like transfer learning and explainable AI, are not widely utilized despite their huge potential. Finally, the review underscores that most proposals remain within the research domain, lacking the integration and maturity needed for sustained use in real-world environments. Therefore, most of the proposals are not currently available to support the training of professionals. The insights of this review can guide researchers aiming to improve the training of professionals and, consequently, their education.

关键词： Systematic review artificial intelligence data fusion workforce training professional competence

来源：评论

学校读者我要写书评

暂无评论

Utilising Explainable AI to Enhance Real-Time Student Performance Prediction in Educational Serious Games

引用

EXPERT SYSTEMS 2025年第3期42卷

作者： Gomez, Manuel J. Armada Sanchez, Alvaro Albaladejo-Gonzalez, Mariano Garcia Clemente, Felix J. Ruiperez-Valiente, Jose A. Univ Murcia Dept Informat & Commun Engn Murcia Spain

In recent years, serious games (SGs) have emerged as a powerful tool in education by combining pedagogy and entertainment, facilitating the acquisition of knowledge and skills in engaging environments. SGs enable the collection of valuable interaction data from students, allowing for the analysis of student performance, with artificial intelligence (AI) playing a key role in processing this data to make informed inferences about their knowledge and skills. However, the lack of explainability in AI models represents a significant challenge. This research aims to develop an interpretable model for predicting students' performance in real-time while playing an SG by: (1) calculating the performance of an interpretable prediction model of task completion in an SG and (2) demonstrating the application of the interpretable model for just-in-time (JIT) classroom interventions. Our results show that we are able to predict students' task completion in real-time with a balanced accuracy result of 77.21% after a short playtime has elapsed. In addition, an explainable artificial intelligence (XAI) approach has been applied to ensure the interpretability of the developed models. This approach supports personalised learning experiences, unlocks AI benefits for non-technical users, and maintains transparency in education.

关键词： artificial intelligence just-in-time interventions learning analytics machine learning xAI

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Method Allocation for Intent-based Security Orchestration

引用

JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT 2025年第1期33卷 1-28页

作者： Robles-Enciso, Alberto murcia, Jose Manuel Bernabe Zarca, Alejandro Molina Gomez, Antonio Skarmeta Univ Murcia Dept Informat & Commun Engn Murcia 30100 Murcia Spain Spanish Air Force Acad Univ Ctr Def San Javier 30720 Murcia Spain

In today's dynamic cybersecurity landscape, static and deterministic services orchestration which does not consider security as part of the orchestration process are proving insufficient against the evolving threat landscape. Security must be an intrinsic part of the orchestration processes. In this regard, this paper introduces an innovative paradigm shift: Intent & AI-based Optimized Security Orchestration. On the one hand, leveraging the capabilities of an Intent-based solution, this approach enables proactive and reactive threat mitigation in next generation heterogenous environments of the computing continuum, abstracting and homogenizing the complexity of underlying technologies. On the other hand, leveraging the capabilities of a dynamic allocation approach that applies different techniques for selecting the most suitable enforcement point (hardware/software) as well as the most suitable allocation for deploying/configuring them, always considering security properties during decision stages. Thus, the solution allows organizations adaptively optimizing resource allocation considering intent-based security requirements. The implementation considers different algorithms to perform the allocation decision depending on a variety of parameters. The performance has been also provided for validating the proposed solution. The results show that combining the security orchestrator with a Dynamic Allocation Engine improves the efficiency of decision making due to the ability to dynamically choose which algorithm is the most appropriate to solve the assignment problem in the best possible way and in the shortest possible time.

关键词： Orchestration AI Intent-based Security Optimal allocation

来源：评论

学校读者我要写书评

暂无评论

Factors associated with physical activity engagement among adolescents in a southeastern region of Spain

引用

PREVENTIVE MEDICINE REPORTS 2025年 53卷 103063-103063页

作者： Lorente, Jose Ramon Solano Cutillas, Mario Diaz Rivas, Sara Luna de los Santos, Francisco Jose Rivera Diaz, Anibal Nieto Piqueras, Olga Monteagudo Univ Murcia Murcia Spain Univ Seville Seville Spain

Objective: To identify factors associated with physical activity engagement among adolescents in southeastern Spain. Methods: A cross-sectional study was conducted with a representative sample of 1817 adolescents from the Region of murcia, using data from the 2018 HBSC Spain study. Two logistic regression models were analyzed. Model 1 included the full sample, with the dependent variable being compliance with the World Health Organization's physical activity recommendations (WHO-PAR), which include both moderate and vigorous physical activity. Model 2 focused on adolescents who did not meet the WHO-PAR but reported engaging in vigorous physical activity during leisure time at least four times per week. Results: In total, 19.7 % of adolescents met the WHO-PAR. Among those who did not, 24.8 % engaged frequently in vigorous physical activity (>= 4 times per week). In Model 1, being female (OR 0.43), older age (OR 0.87), and overweight/obesity (OR 0.59) were associated with lower odds of meeting the WHO-PAR. High family affluence (OR 1.71) and high perceived quality of life (OR 1.99) were associated with greater odds. In Model 2, being male (OR 1.94), high family affluence (OR 1.55), and high quality of life (OR 1.98) increased the likelihood of engaging in vigorous physical activity, while overweight/obesity (OR 0.61) decreased it. Conclusions: Not meeting the WHO physical activity recommendations and not engaging in vigorous activity were associated with low family affluence, being female, overweight/obesity, and low or medium perceived quality of life. These factors should be addressed in interventions to promote adolescent physical activity.

关键词： Physical activity Adolescents Sedentary lifestyle Childhood obesity Quality of life Socioeconomic factors

来源：评论

学校读者我要写书评

暂无评论

Substitution effects and spatial factors in the social demand for landscape aesthetics in agroecosystems

引用

LANDSCAPE AND URBAN PLANNING 2025年 257卷

作者： Albaladejo-Garcia, Jose A. Martinez-Paz, Jose M. Univ Murcia Dept Econ Aplicada Murcia Spain

One of the cultural ecosystem services provided by agroecosystems is landscape aesthetics, which has a very positive effect on social well-being. In many areas, such as the Mediterranean, changes in land use have been negatively affecting the provision of this service, which is becoming increasingly crucial in the formulation of agricultural policies. The objective of this paper was to assess the social demand for agricultural landscape aesthetics, considering both the levels of use and the willingness to contribute to its conservation. This was done while considering the existence of substitute landscapes and spatial effects. The flowering fruit trees in Cieza (SESpain) were used as a representative case study of semi-arid Mediterranean agricultural landscapes. A survey of 493 households was conducted, in which a contingent valuation exercise was implemented. The results demonstrated the availability of alternative spaces in the region and spatial effects, such as distance decay or distance increase, were factors that explain the diverse aspects of the social demand for the agricultural landscape. This justifies the suitability of carrying out this type of analysis of complete social demand as a preliminary step towards the formulation of more effective agricultural and land management measures to achieve social well-being.

关键词： Agricultural landscape Contingent valuation Distance decay Social perception Substitute

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：