检索结果-内蒙古大学图书馆

Teaching mechanics with individual exercise assignments and automated correction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gfrerer, Michael H. Marussig, Benjamin Maitz, Katharina Bangerl, Mia M. Institute of Applied Mechanics Graz University of Technology Austria Austria Institute of Interactive Systems and Data Science Graz University of Technology Austria

Solving exercise problems by yourself is a vital part of developing a mechanical understanding. Yet, most mechanics lectures have more than 200 participants, so the workload for manually creating and correcting assignments limits the number of exercises. The resulting example pool is usually much smaller than the number of participants, making verifying whether students can solve problems themselves considerably harder. At the same time, unreflected copying of tasks already solved does not foster the understanding of the subject and leads to a false self-assessment. We address these issues by providing a scalable approach for creating, distributing, and correcting exercise assignments for problems related to statics, strength of materials, dynamics, and hydrostatics. The overall concept allows us to provide individual exercise assignments for each student. A quantitative survey among students of our recent statics lecture assesses the acceptance of our teaching tool. The feedback indicates a clear added value for the lecture, which fosters self-directed and reflective learning. © 2023, CC BY-NC-SA.

关键词： Students

A Qualitative Investigation to Design Empathetic Agents as Conversation Partners for People with Autism Spectrum Disorder

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Poglitsch, Christian Pirker, Johanna ISDS - Institute of Interactive Systems and Data Science University of Technology Graz Graz Austria Media Informatics Group Ludwig-Maximilians University Munich Munich Germany

Autism Spectrum Disorder (ASD) can profoundly affect reciprocal social communication, resulting in substantial and challenging impairments. One aspect is that for people with ASD conversations in everyday life are challenging due to difficulties in understanding social cues, interpreting emotions, and maintaining social verbal exchanges. To address these challenges and enhance social skills, we propose the development of a learning game centered around social interaction and conversation, featuring Artificial Intelligence agents. Our initial step involves seven expert interviews to gain insight into the requirements for empathetic and conversational agents in the field of improving social skills for people with ASD in a gamified environment. We have identified two distinct use cases: (1) Conversation partners to discuss real-life issues and (2) Training partners to experience various scenarios to improve social skills. In the latter case, users will receive quests for interacting with the agent. Additionally, the agent can assign quests to the user, prompting specific conversations in real life and providing rewards for successful completion of quests. © 2024, CC BY.

关键词： Chatbots

Microservice Architecture of Modern eLearning Application

学校读者我要写书评

暂无评论

Microservice Architecture of Modern eLearning Application

Communications, Information, Electronic and Energy systems (CIEES), International Conference on

作者： Alexander Schukin Nikolai Scerbakov Eugenia Rezedinova Institute of Computer Science and Cybersecurity Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

ISBN: (数字)9798350352863

ISBN: (纸本)9798350352870

Learning Management systems (LMS) have been integral to educational institutions for over 20 years. Technically, an LMS consists of functional components designed to deliver, discuss, explain educational materials, and assess user knowledge through various paradigms such as uploading assignments and online questionnaires. The prolonged and intensive use of such systems emphasizes the importance of their maintainability, allowing the accommodation of new components and the replacement of outdated ones. Over the years, the technological foundation of LMS components has transitioned from early versions of PHP to advanced Java, Python, and JavaScript packages. data repositories have evolved from local relational databases to shared NoSQL databases. Communication technologies have shifted from NNTP news servers to multiple social applications like WhatsApp and *** this paper, we present architectural solutions implemented in a modern LMS called WBT-Master. This architecture specifically addresses the maintainability of modern LMS, ensuring they evolve alongside emerging Internet technologies. The practical significance of our work lies in its ability to support very heterogeneous components within a logically unified LMS framework. By discussing the architecture of WBT-Master, we offer a method for incorporating both old and new technological platforms into a single system. Additionally, we use this architecture to interface with cloud services, foster social interactions, and optimize user experience. This contributes to the evolution of E-Learning platforms, offering enhanced and more interactive educational experiences for both learners and educators.

关键词： Training Java Electronic learning Computer architecture Relational databases User interfaces User experience Servers Usability Python

An interactive Chess-Puzzle-Simulation for Computer science Education

学校读者我要写书评

暂无评论

An Interactive Chess-Puzzle-Simulation for Computer Science ...

Immersive Learning Research Network (iLRN), Conference of the

作者： Michael Holly Jan-Heliodor Tscherko Johanna Pirker Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

The hype around the series ”The Queen’s Gambit” led to a boom in playing chess. The game enhances strategic thinking, stimulates intellectual creativity, and improves problem-solving. These skills are increasingly in demand and also essential in the field of computer science (CS). Traditional teaching approaches are often insufficient to teach CS concepts. interactive and digital experiences can be used to create an exciting, engaging, and realistic learning environment. In this paper, we explore the potential of a chess-based learning approach to increase motivation in CS. The application includes an interactive chess-puzzle simulation to teach the concept of state machines using a chessboard as an input field. We present a study with 35 students for evaluating the students’ motivation, emotions, and workload with a focus on the learning experience. The results indicate a positive impact on the learning process and engage students in learning computer science.

关键词：

A Qualitative Investigation to Design Empathetic Agents as Conversation Partners for People with Autism Spectrum Disorder

学校读者我要写书评

暂无评论

A Qualitative Investigation to Design Empathetic Agents as C...

IEEE Symposium on Computational Intelligence and Games, CIG

作者： Christian Poglitsch Johanna Pirker ISDS - Institute of Interactive Systems and Data Science University of Technology Graz Graz Austria Media Informatics Group Ludwig-Maximilians University Munich Munich Germany

ISBN: (数字)9798350350678

ISBN: (纸本)9798350350685

关键词： Training Autism Emotion recognition Oral communication Games Learning (artificial intelligence) Interviews

Beyond-Accuracy: A Review on Diversity, Serendipity and Fairness in Recommender systems Based on Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Duricic, Tomislav Kowald, Dominik Lacic, Emanuel Lex, Elisabeth Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria Know-Center Graz Austria Infobip Zagreb Croatia

By providing personalized suggestions to users, recommender systems have become essential to numerous online platforms. Collaborative filtering, particularly graph-based approaches using Graph Neural Networks (GNNs), have demonstrated great results in terms of recommendation accuracy. However, accuracy may not always be the most important criterion for evaluating recommender systems’ performance, since beyond-accuracy aspects such as recommendation diversity, serendipity, and fairness can strongly influence user engagement and satisfaction. This review paper focuses on addressing these dimensions in GNN-based recommender systems, going beyond the conventional accuracy-centric perspective. We begin by reviewing recent developments in approaches that improve not only the accuracy-diversity trade-off but also promote serendipity and fairness in GNN-based recommender systems. We discuss different stages of model development including data preprocessing, graph construction, embedding initialization, propagation layers, embedding fusion, score computation, and training methodologies. Furthermore, we present a look into the practical difficulties encountered in assuring diversity, serendipity, and fairness, while retaining high accuracy. Finally, we discuss potential future research directions for developing more robust GNN-based recommender systems that go beyond the unidimensional perspective of focusing solely on accuracy. This review aims to provide researchers and practitioners with an in-depth understanding of the multifaceted issues that arise when designing GNN-based recommender systems, setting our work apart by offering a comprehensive exploration of beyond-accuracy dimensions. © 2023, CC BY.

关键词： Recommender systems

Predicting Partial Discharges of Transformers: Decision Support System for Factory Acceptance Test

学校读者我要写书评

暂无评论

Predicting Partial Discharges of Transformers: Decision Supp...

2023 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2023

作者： Gigerl, B. Zhao, Y. Raminger, J. Bakakeu, J. Kern, R. Thalmann, S. Siemens Energy Department of Process Digitalization Weiz Austria Siemens Energy Department of Manufacturing Technology Nürnberg Germany Siemens Energy Department of Test Field Weiz Austria Alteryx Department of Sales Engineering München Germany Institute of Interactive Systems and Data Science Technical University of Graz Graz Austria Institute of Operations and Information Systems University of Graz Graz Austria

ISBN: (纸本)9798350323153

Partial discharges, mainly caused by an insufficient drying processes or different types of contamination, reduce the lifetime of a transformer, and thus lead to expensive rework costs. Herein, a decision support system for partial discharges of transformers occurring in oven and filling processes is introduced. Based on machine learning (ML), partial discharge results are evaluated in dependency of various manufacturing parameters and an automated prediction tool to guide the production with preventive actions is developed. The required data, obtained from sensors and manufacturing sources, is used to train supervised learning algorithms that aim to predict and classify partial discharges. To achieve adequate accuracy and reliability, multiple ML and data mining techniques are applied, including feature engineering, clustering, and final evaluation of performance by cost factors. The evaluation results show that the introduced ML models effectively detect and classify early test failures in oven and filling processes, resulting in a successful identification of key factors and consequently to more efficient action derivation. Overall, the potential of decision support systems as a valuable tool in the field of transformers is emphasized. © 2023 IEEE.

关键词： Decision Support System Machine Learning Partial Discharges Predictive Quality Control

Intersectional inequalities in social networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Martin-Gutierrez, Samuel Cartier van Dissel, Mauritz N. Karimi, Fariba Network Inequality Group Complexity Science Hub Josefstaedter Str. 39 Vienna1080 Austria Institute of Interactive Systems and Data Science Graz University of Technology Sandgasse 36 Graz8010 Austria

Social networks are shaped by complex, intersecting identities that drive our connection preferences. These preferences weave networks where certain groups hold privileged positions, while others become marginalized. While previous research has examined the impact of single-dimensional identities on inequalities of social capital, social disparities accumulate nonlinearly, further harming individuals at the intersection of multiple disadvantaged groups. However, how multidimensional connection preferences affect network dynamics and in what forms they amplify or attenuate inequalities remains unclear. In this work, we systematically analyze the impact of multidimensionality on social capital inequalities through the lens of intersectionality. To this end, we operationalize several notions of intersectional inequality in networks. Using a network model, we reveal how attribute correlation (or consolidation) combined with biased multidimensional preferences lead to the emergence of counterintuitive patterns of inequality that are unobservable in one-dimensional systems. We calibrate the model with real-world high school friendship data and derive analytical closed-form expressions for the predicted inequalities, finding that the model’s predictions match the observed data with remarkable accuracy. These findings hold significant implications for addressing social disparities and inform strategies for creating more equitable networks. Copyright © 2024, The Authors. All rights reserved.

关键词： Social networking (online)

The hidden architecture of connections: How do multidimensional identities shape our social networks?

学校读者我要写书评

暂无评论

arXiv 2024年

Our multidimensional identities determine how we interact with each other, shaping social networks through group-based connection preferences. While interactions along single dimensions have been extensively studied, the dynamics driving multidimensional connection preferences remain largely unexplored. In this work, we develop a network model of multidimensional social interactions to tackle two crucial questions: What is the structure of our latent connection preferences, and how do we integrate information from our multidimensional identities to connect with others? To answer these questions, we systematically model different latent preference structures and preference aggregation mechanisms. Then, we compare them using Bayesian model selection by fitting empirical data from high school friendship networks. We find that a simple latent preference model consistently outperforms more complex alternatives. The calibrated model provides robust measures of latent connection preferences in real-world networks, bringing insights into how one- and multidimensional groups interact. Finally, we develop natural operationalizations of dimension salience, revealing which aspects of identity are most relevant for individuals when forming connections. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning