检索结果-内蒙古大学图书馆

EPM: Evolutionary Perception Method for Anomaly Detection in Noisy Dynamic Graphs

IEEE Transactions on Knowledge and Data engineering 2025年第7期37卷 4035-4048页

作者： Wang, Huan Chen, Junyang Wu, Yirui Leung, Victor C. M. Wang, Di King Abdullah University of Science and Technology Division of Computer Electrical and Mathematical Sciences and Engineering Saudi Arabia Huazhong Agricultural University College of Informatics China Shenzhen University College of Computer Science and Software Engineering China Hohai University College of Computer and Information China

With the rapid expansion of interactions across various domains such as knowledge graphs and social networks, anomaly detection in dynamic graphs has become increasingly critical for mitigating potential risks. However, existing anomaly detection methods often assume noise-free dynamic graphs, overlooking the prevalence of noisy dynamic graphs in real-world applications. Specifically, noisy dynamic graphs affected by structural noises-such as spurious and missing nodes and edges-struggle to consistently provide reliable structural evidence for anomaly detection. To tackle this challenge, we propose an Evolutionary Perception Method (EPM) for identifying anomalous nodes in noisy dynamic graphs by resisting the interference of structural noises. EPM primarily consists of two components: a dynamic fitter and a filtering reviser. The dynamic fitter characterizes the interaction dynamics of nodes that removes and generates links at each period as a multiple superposition state, utilizing various link prediction algorithms to fit evolutionary mechanisms. Additionally, the filtering reviser designs evolutional entropies to quantify the evolutional uncertainty in multiple superposition states, further designing the Kalman filter to optimize these entropies. Extensive experiments show that the proposed EPM method surpasses state-of-the-art approaches in detecting anomalous nodes in noisy dynamic graphs. © 1989-2012 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Personalized Learning via Gamified Virtual Environments: Exploring Insights and Impact 19

Personalized Learning via Gamified Virtual Environments: Exp...

引用

19th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2024

作者： Strousopoulos, Panagiotis Troussas, Christos University of West Attica Department of Informatics and Computer Engineering Egaleo Greece

ISBN: (纸本)9798331504502

This paper explores the transformative potential of combining Artificial Intelligence (AI) with gamified learning environments (GLEs) to enhance personalized learning experiences. Gamified learning environments have emerged as relevant practical tools that provide dynamic learning pathways, helping learners engage better through motivation, interactivity, and entertainment. Integrating GLEs with AI amplifies the element of personalization by analyzing student progress, strengths, and weaknesses to tailor accordingly. AIdriven adaptive learning systems create a flexible and supportive learning environment in which feedback, recommending resources, and adapting levels of difficulty are tuned to the pace of the learner. This stretches even to virtual environments (VEs) that enable learning through immersive and interactive experiences about abstract concepts in learning. Gamification is changing learning with more sustained motivation. The paper, therefore, discusses the possibilities of using those technologies in reshaping education and points to AI and gamification as cutting-edge tools that would help shape adaptive, engaging, personalized learning environments. Finally, it calls on all stakeholders, the educators, the developers, and the theorists, to empower those tools toward more inclusivity and innovation in education so that, in the future, learning experiences turn out functional and enjoyable. The goals should be underscored with the true potential of AI and gamification in democratizing education and improving learning methodologies until innovation is continuous. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Hint Delivery in Multimedia Learning Environments Using Learning Styles: An Integrated Approach with Artificial Neural Networks and Weighted Sum Model 19

Personalized Hint Delivery in Multimedia Learning Environmen...

引用

19th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2024

作者： Troussas, Christos Krouska, Akrivi Papakostas, Christos Mylonas, Phivos Sgouropoulou, Cleo University of West Attica Department of Informatics and Computer Engineering Egaleo Greece

ISBN: (纸本)9798331504502

This paper introduces a novel multimedia learning environment designed to support holistic learning of web development. ANNs and the WSM model have been adopted to implement the framework of the VARK learning style model in order to dynamically provide personalized educational hints that assist learners to overcome difficulties and deepen their understanding, thus acquiring a higher level of knowledge in a more general and effective way. In our approach, hints are not an adjunct but a core feature of the learning process, dynamically tailored to each learner in their time of need. An ANN combined with a WSM collaborates to achieve optimal delivery of these hints, ensuring they are timely and context-aware according to the learning styles of individual students defined by the VARK model. Students receive the best possible guidance to make learning much more effective. A structured questionnaire-based evaluation followed by statistical hypothesis testing showed promising results for the efficacy of this multimedia learning environment. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Affective Computing in Intelligent Tutoring Systems: Exploring Insights and Innovations 9

Affective Computing in Intelligent Tutoring Systems: Explori...

引用

9th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2024

作者： Tasoulas, Theofanis Troussas, Christos Mylonas, Phivos Sgouropoulou, Cleo University of West Attica Department of Informatics and Computer Engineering Egaleo Greece

ISBN: (纸本)9798350342482

Integrating intelligent tutoring systems (ITS) into education has significantly enriched personalized learning experiences for students and educators alike. However, these systems often neglect the critical role of emotions in the learning process. By integrating affective computing, which empowers computers to recognize and respond to emotions, ITS can foster more engaging and impactful learning environments. This paper explores the utilization of affective computing techniques, such as facial expression analysis and voice modulation, to enhance ITS functionality. Case studies and existing systems have been scrutinized to comprehend design decisions, outcomes, and guidelines for effective integration, thereby enhancing learning outcomes and user engagement. Furthermore, this study underscores the necessity of considering emotional aspects in the development and deployment of educational technology to optimize its influence on student learning and well-being. A major conclusion of this research is that integration of affective computing into ITS empowers educators to customize learning experiences to students' emotional states, thereby enhancing educational effectiveness. To achieve this, it is crucial for such systems to make informed design decisions and adhere to established guidelines. These design decisions may involve selecting appropriate emotion recognition algorithms and integrating them seamlessly into the ITS interface, while guidelines can offer practical insights into effectively implementing affective computing techniques in ITS, such as ensuring data privacy and security measures are in place and providing adequate training for educators on interpreting emotional data. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Impact of Integrating ChatGPT as an Advice Generator in Educational Software 9

Assessing the Impact of Integrating ChatGPT as an Advice Gen...

引用

9th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2024

作者： Troussas, Christos Krouska, Akrivi Papakostas, Christos Mylonas, Phivos Sgouropoulou, Cleo University of West Attica Department of Informatics and Computer Engineering Egaleo Greece

ISBN: (纸本)9798350342482

This paper reports on the study of the integration of ChatGPT as an advice generator in custom educational software developed for Java programming. The software, in cooperation with ChatGPT API, pursues providing real-time, context-specific advice to students for better learning. This work adopted a two-fold evaluation approach to evaluating this integration. First, this study examines the effectiveness of this integration with the help of the Interrupted Time Series Analysis methodology to measure possible improvement in the performance metrics of the students in terms of error rates and task completion times. Second, this work presents a custom-designed questionnaire used to get student perceptions regarding the clarity, usefulness, and impact of ChatGPT's advice, and the level of student satisfaction with the user interface. The key takeaways from this research study are the substantial improvements in performance metrics that were noted quantitatively, with students achieving lower error rates and faster completion times after the intervention of ChatGPT. Qualitatively, learners express their satisfaction with the clarity of advice, which gives them an understanding that works on their learning and confidence in Java programming. These findings point toward the promise of integrating such advanced AI solutions in educational software toward a significant improvement in learning outcomes and the necessity of human-aided continuous user feedback for system refinement. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Struggling to Adapt: Exploring the Factors that Hamper the Integration of Innovative Digital Tools in Higher Education Courses 4th

Struggling to Adapt: Exploring the Factors that Hamper the I...

引用

4th International Conference on Novel and Intelligent Digital Systems, NiDS 2024

作者： Georgopoulou, Maria Sofia Troussas, Christos Sgouropoulou, Cleo Voyiatzis, Ioannis Department of Informatics and Computer Engineering University of West Attica Athens Greece

ISBN: (纸本)9783031733437

The pervasive impact of digital technologies has permeated all facets of our society. As technology continues to evolve rapidly, it is imperative for educators to adapt and integrate these advancements into their teaching methods. Nevertheless, educators face challenges in keeping pace with technological advancements for educational purposes. This study revolved around three key objectives: mapping the intricate landscape of digital inclusion in higher education, particularly within a department of informatics;exploring teaching practices that enrich and facilitate the overall educational experience;and defining the challenges that faculty members encounter. This distinctive focus represented an innovative approach, shedding light on the underlying concerns within academia regarding obstacles to incorporating digital tools into university courses. The participants in the study were faculty members and undergraduate students from the Department of informatics at a Greek university. Data was collected through two distinct questionnaires. A major conclusion of this study is that the types of digital tools faculty prefer are closely related to (a) challenges faced by higher education institutions, such as infrastructure and funding, and (b) their own perceptions and interpretations of their involvement with technology-driven strategies in the classroom. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Educational technology

来源：评论

学校读者我要写书评

暂无评论

Automatic sign language sentence recognition in the context of guided museum tours 1

Automatic sign language sentence recognition in the context ...

引用

1st International Workshop on Accessibility and Multimodal Interaction Design Approaches in Museums for People with Impairments, AMID 2023

作者： Pikoulis, Erion-Vasilis Bifis, Aristeidis Arvanitis, Nikolaos Kosmopoulos, Dimitrios Computer Engineering and Informatics Department University of Patras Rio26504 Greece

Sign Language (SL) translation remains an extremely challenging task despite recent breakthrough progress in the constituent fields of computer Vision and Machine Learning, especially when tackled under a general unconstrained setup. This is mainly due to a combination of the difficulty of the task itself on the one hand, and the absence of large-scale labeled datasets that would enable using end-toend Deep Learning based solutions, on the other. In such cases, the ability to incorporate prior information can yield a significant improvement on the translation results, by greatly restricting the search space of the potential solutions. In this work we treat the SL translation problem in the limited confinement of an interactive, guided museum tour for deaf and hard-of-hearing visitors. Prior domain knowledge enables us to compile a list of targeted questions per museum exhibit and use these lists to create an SL training dataset for the solution of the problem at hand. In our case, SL question recognition is treated as a sentence retrieval problem, whereby the goal is to predict visitor’s question that best matches the available pool of possible inquiries. Our preliminary evaluation using both tailored deep architectures and traditional non-deep solutions has led to promising results for the recognition task at hand. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Museums

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-based Recommendations for Personalized Content Creation and Instructional Design with a Tailored Prompt Generator 2

ChatGPT-based Recommendations for Personalized Content Creat...

引用

2nd International Conference on Foundation and Large Language Models, FLLM 2024

作者： Krouska, Akrivi Troussas, Christos Voyiatzis, Ioannis Mylonas, Phivos Sgouropoulou, Cleo University of West Attica Department of Informatics and Computer Engineering Egaleo Greece

ISBN: (纸本)9798350354799

Recent advancements in Artificial Intelligence (AI) have significantly influenced educational innovations, making learning environments more sophisticated with personalized learning, tailored feedback, and learning analytics. Among these advancements, Generative AI, namely ChatGPT, has emerged as a powerful tool in education. ChatGPT's ability to generate human-like content in real-time can assist educators with course design and educational material creation, allowing for enhanced instructional strategies without starting from scratch. Moreover, integrating ChatGPT into the recommendation process offers superior understanding of user needs and delivery of context-aware recommendations. In view of the above, this paper explores the integration of ChatGPT with a tailored prompt generator within an intelligent authoring system to offer effective recommendations for personalized content creation and instructional design. The system was evaluated and compared to its conversional version where instructors manually use ChatGPT. The findings indicate significant improvements in system usability, content quality, personalization, and time and effort savings, demonstrating the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality in Classrooms: Addressing Ethical Challenges in Educational Technology 4th

Virtual Reality in Classrooms: Addressing Ethical Challenges...

引用

4th International Conference on Novel and Intelligent Digital Systems, NiDS 2024

作者： Marougkas, Andreas Troussas, Christos Krouska, Akrivi Sgouropoulou, Cleo Voyiatzis, Ioannis Department of Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (纸本)9783031733437

As Virtual Reality (VR) is on the rise in popularity in learning contexts, the corresponding ethical challenges of its use increase in complexity and importance. This theoretical paper discusses the ethical consequences posed by VR use in education, with a special focus on the perspectives of privacy, data security, and psychological consequences on students. The paper will identify resulting risks and suggest necessary guidelines for educators and developers. The paper discusses how to balance innovative educational benefits with the need to protect student welfare, to promote an ethical approach to the use of VR technology in the classroom setting. This paper contributes to the ongoing debate about the responsible use of new technologies in educational settings and presents policy priorities that seek to protect student rights and welfare. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Transforming Data Lakes to Data Meshes Using Semantic Data Blueprints 19

Transforming Data Lakes to Data Meshes Using Semantic Data B...

引用

19th International Conference on Evaluation of Novel Approaches to Software engineering, ENASE 2024

作者： Pingos, Michalis Mina, Athos Andreou, Andreas S. Department of Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9789897586965

In the continuously evolving and growing landscape of Big Data, a key challenge lies in the transformation of a Data Lake into a Data Mesh structure. Unveiling a transformative approach through semantic data blueprints enables organizations to align with changing business needs swiftly and effortlessly. This paper delves into the intricacies of detecting and shaping Data Domains and Data Products within Data Lakes and proposes a standardized methodology that combines the principles of Data Blueprints with Data Meshes. Essentially, this work introduces an innovative standardization framework dedicated to generating Data Products through a mechanism of semantic enrichment of data residing in Data Lakes. This mechanism not only enables the creation readiness and business alignment of Data Domains, but also facilitates the extraction of actionable insights from software products and processes. The proposed approach is qualitatively assessed using a set of functional attributes and is compared against established data structures within storage architectures yielding very promising results. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Metadata

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：