检索结果-内蒙古大学图书馆

Research Square 2024年

作者： Velentza, Anna-Maria Lefkos, Ioannis Fachantidis, Nikolaos Laboratory of Informatics and Robotics Applications in Education and Society – LIRES University of Macedonia Greece

— Online classes are increasingly gaining popularity in both children's and adult education, although, the challenge of the students’ engagement remains. Evidence has shown that co-teaching is beneficial for both tutors and students, however, especially on a university level, tutors are not always able to co-teach classes. Additionally, socially assistive robots (SAR) have been proven advantageous in educational roles, as they deliver teaching material and provide support to students across various educational levels. This research paper specifically examines the performance of SAR in place of university co-tutors in online classes, in the field of computer science, measuring three outcomes, knowledge acquisition (academic test), enjoyment level (questionnaire), and engagement (qualitative and quantitative analysis of verbal and chat discussions and threads during class). We also aim to fill in the gap of having structured human-robot collaboration guidelines for educational environments. This will be accomplished through a sequence of three experiments: 1. A co-tutored lecture involving one human and one robot, 2. A co-tutored lecture involving two humans, 3. A second instance of a co-tutored lecture involving both human and robot. Results indicated that students taught by a collaborative team of human and robot tutors exhibited a greater level of knowledge acquisition, while maintaining comparable levels of enjoyment, in comparison to those instructed by a collaborative team of two human tutors. Moreover, engagement remained high during the lectures, and we are addressing the differences in students’ communication channels and discussed topics when lectured by two humans vs a human and a robot. Finally, the human-robot collaboration managed to eliminate the negative outcomes of the presence of a robot, such as the surprise effect based on the literature the students face the first time they are being lectured by a robot-tutor. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

‘Do you trust me with your secret if I wear the clothes you made for me’? Kids knitting clothes for SARs and choosing one to share a secret wish

‘Do you trust me with your secret if I wear the clothes you...

引用

2024 ALTRUIST Workshop on SociAL RoboTs for PeRsonalized, ContinUous and AdaptIve ASsisTance, BAILAR Workshop on Behavior Adaptation and Learning for Assistive robotics, SCRITA Workshop on Trust, Acceptance and Social Cues in Human-Robot Interaction, and WARN Workshop on Weighing the Benefits of Autonomous Robot PersoNalisation, ALTRUIST-BAILAR-SCRITA-WARN 2024

作者： Gioumatzidou, Sofia Velentza, Anna-Maria Fischer, Katrin Fachantidis, Nikolaos School of Educational & Social Policies University of Macedonia Thessaloniki Greece Laboratory of Informatics and Robotics in Education and Society Thessaloniki Greece Communication Department University of Southern California Los AngelesCA United States

Recent studies in child-robot interaction indicate a propensity for children to trust robots with humanoid characteristics, fostering social relationships that enhance interaction quality. Trust is fundamental in Human-Robot Interaction (HRI) and can be affected by parameters such as the robot’s appearance, texture, or performed activity. In the current paper, we investigate whether children’s trust in a SAR, specifically the Nao robot, increases after they design and dress it with handmade clothes using the felting technique. Children had the chance to interact with robots both naked and dressed in and without their creations and share a secret wish with one of them. Behavioral observations and wish content analysis provided insights into children’s emotional engagement and trust preferences. Most children chose to confide in the robot wearing their crafted outfit, using wish statements that reflect aspirational desires, contrasting with immediate wants expressed to the’naked’ robot. This study underscores the role of co-design and initial interaction quality in fostering trust and emotional engagement between children and SARs, highlighting avenues for enhancing HRI outcomes. © 2024 Copyright for this paper by its authors.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Step by Step Building and Evaluation of Low-Cost Capacitive Technology Touch System for Human-Social Robot Interaction

Step by Step Building and Evaluation of Low-Cost Capacitive ...

引用

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： Konstantinos Tsirkas Anna-Maria Velentza N. Fachantidis School of Educational & Social Policy University of Macedonia Thessaloniki Greece Laboratory of Informatics and Robotics Applications in Education and Society (LIRES) University of Macedonia Greece

The development of social robots aims to create machines that can interact and collaborate with people in a natural way. To achieve this, social robots must be designed to make people feel physically and psychologically comfortable with them, with haptic communication being a crucial factor. Capacitive touch technology has been implemented in robotics for sensing contact in various areas of a robot's body during human-robot interaction. However, there is a need for low-cost haptic systems that can be easily built and deployed by professionals without engineering backgrounds, such as educators. This study presents a low-cost haptic system built with consumer materials and tested for accuracy and user experience. Results show that the system is more than 80% accurate and persistent and has a high score in user experience across users from different backgrounds. We used Adafruit MPR121, Arduino and 3D printed materials. The system can be easily adapted to different robotic systems and hard materials to enhance human-robot interaction for various social applications. The study highlights the importance of developing low-cost and accessible haptic systems for social robots, which can help increase trust and acceptance of these machines in everyday life.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Inference for MEC Services Based on Multimodal Deep Neural Network

Collaborative Inference for MEC Services Based on Multimodal...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Liu, Yu Wang, Chuxuan Xiao, Yilin Lv, Zefang Xiao, Liang Ji, Xiangyang Xiamen University School of Informatics Xiamen China Xiamen University Dept. of Institute of Artificial Intelligence Xiamen China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Tsinghua University Department of Automation Beijing China

ISBN: (纸本)9798350345384

Collaborative inference can effectively ease the computational burden imposed on mobile devices by deep neural networks (DNNs), such as employing multimodal DNNs to achieve a comprehensive understanding of the environment. Although reinforcement learning (RL)-based collaborative inference adapts to dynamic environments and enhances inference performance for DNNs, especially those with chain-structured architectures, the policy selection for multimodal DNNs must account for multiple computation-intensive feature encoders. This paper proposes a hierarchical reinforcement learning (RL)-based collaborative inference scheme for multimodal DNNs that concurrently determines the partition point and identifies the appropriate DNN-based feature encoder for each modality within the mobile edge computing system. The hierarchical structure designed for policy selection has alleviated the exponential growth of the modalities. Moreover, the mobile device maintains a confidence score based on probabilities of predefined classes to assess the risk of inference policies that results in low inference accuracy and thus avoids exploring the risk policy. Simulation results demonstrate that our proposed scheme surpasses the Neurosurgeon benchmark in reducing inference latency and energy consumption, all while maintaining a high level of confidence score without significant degradation. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Collaborative Inference for MEC Services Based on Multimodal Deep Neural Network

Collaborative Inference for MEC Services Based on Multimodal...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Yu Liu Chuxuan Wang Yilin Xiao Zefang Lv Liang Xiao Xiangyang Ji Dept. of Institute of Artificial Intelligence Xiamen University Xiamen China Ministry of Education of China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Informatics Xiamen University Xiamen China Department of Automation Tsinghua University Beijing China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects of Lighting Variations in Virtual Learning Environments

Effects of Lighting Variations in Virtual Learning Environme...

引用

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： A.M. Velentza E. Economou Lab of Experimental Psychology University of Crete Rethymnon Crete Greece Laboratory of Informatics and Robotics Applications in Education and Society (LIRES) University of Macedonia Greece

ISBN: (数字)9781665422284

ISBN: (纸本)9781665422291

The use of virtual reality in education is giving researchers new designing opportunities to create learning environments with characteristics that are difficult or even impossible to implement in the real world. There are plenty of educational, cognitive, architectural and neuroscience theories suggesting that certain environmental aspects can enhance the learning process. Such an example is the variation of lighting conditions, in terms of intensity (high or low luminance) and/or temperature (cold or warm), that have been shown to improve memory, attention and executive functions. In this paper, we investigate the differences between a real and a Virtual Learning Environment (VLE) regarding the effects of the lighting conditions on several cognitive functions while we apply, for the first time, certain lighting theories directly into a University level VLE. The first main outcome of our study is that lighting conditions in VLEs affect students' cognitive functions in a similar way to traditional/physical learning environments, i.e. high luminance enhance memory, attention and executive functions when compared with low luminance. Our results indicate that if we need to test a cognitive or learning hypothesis, we can test it directly into a virtual environment since it gives us similar results/outcomes with those triggered in real one. Moreover, our results demonstrate that exposure to blue (cold) lighting in VLEs increase students' scores, in the given pseudoword test, in comparison with their exposure to red (warm) lighting.

关键词： Neuroscience education Lighting Virtual environments Task analysis

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：