检索结果-内蒙古大学图书馆

64th International Annual Meeting of the human Factors and Ergonomics Society, HFES 2020

作者： Miller, Linda Kraus, Johannes Babel, Franziska Messner, Matthias Baumann, Martin Faculty of Engineering Computer Science and Psychology Department Human Factors Ulm University Ulm Germany

From once being utopian, robots become more and more common in public and private social life. One area of application are robots, which are able to perform chores in domestic environments. To support users accustoming to the new robot companion, psychological mechanisms that enhance the interaction with robots need to be understood. In this research, the effects of robot’s height and manipulator position on proximity, affect and trust with regards to a humanoid robot were investigated in a laboratory experiment. Results indicated an effect of robot’s height on the comfort distance. On the other hand, a habituation effect after a second robot-human approach was found, in which the influence of the robot’s height on proximity diminished. Similar effects with an anxiety decrease and trending trust increase in the tall robot over time emphasize the importance of first encounters, which should be paid special attention to by designers of robotic systems. © 2020 by human Factors and Ergonomics Society. All rights reserved.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

DOES CROSSING THE ROAD IN A GROUP INFLUENCE PEDESTRIANS' GAZE BEHAVIOR? 64th

DOES CROSSING THE ROAD IN A GROUP INFLUENCE PEDESTRIANS' GAZ...

引用

64th International Annual Meeting of the human Factors and Ergonomics Society, HFES 2020

作者： Lanzer, Mirjam Baumann, Martin Faculty of Engineering Computer Science and Psychology Department of Human Factors Ulm University Ulm Germany

So far, research on pedestrians’ gaze behavior while crossing roads has mainly focused on individual pedestrians rather than groups. However, pedestrians often travel in groups especially in downtown areas. This observational study investigated how group characteristics (group size and movement of the group), situational factors (presence of traffic), and demographic variables (age and gender) influence pedestrians’ gaze behavior towards traffic during road crossing. A total of N = 197 pedestrians were observed of whom n = 24 traveled alone, n = 128 traveled in groups of two or three, and n = 45 traveled in groups of four or more. Results indicated that with increasing group size, the odds to observe traffic decreased. Diffusion of responsibility among group members might explain this effect. Finally, pedestrians’ group characteristics should be considered when developing automated vehicles that interact with vulnerable road users. © 2020 by human Factors and Ergonomics Society. All rights reserved.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

After you: Merging at Highway On-Ramps 64th

After you: Merging at Highway On-Ramps

引用

64th International Annual Meeting of the human Factors and Ergonomics Society, HFES 2020

作者： Stoll, Tanja Weihrauch, Lucas Baumann, Martin Faculty of Engineering Computer Science and Psychology Department of Human Factors Ulm University Ulm Germany

Vehicle-to-vehicle and vehicle-to-infrastructure communication offer new possibilities for cooperatively interactive driving. It enables vehicles to carry out maneuvers cooperatively with other vehicles. However, these maneuvers have to be predictable and understandable to a human driver to prevent the driver from intervening with the automation. In a video-based study, we investigated potential influencing factors on the willingness to behave cooperatively in an on-ramp situation on a highway: The situation’s criticality for the lane-changing vehicle, the way the intention to change the lane was indicated and the scope of action. More-over, we asked participants to rate their perceived criticality. Participants preferred to change lanes to the left or decelerate to let the other vehicle merge in front of them. If a lane change was not possible, participants rated the situation as more critical. These results are useful for the developing process of human-machine interfaces for cooperatively interacting vehicles. © 2020 by human Factors and Ergonomics Society. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Modality-Agnostic Learning for Medical Image Segmentation Using Multi-modality Self-distillation

arXiv

引用

arXiv 2023年

作者： He, Qisheng Summerfield, Nicholas Dong, Ming Glide-Hurst, Carri Wayne State University Department of Computer Science 5057 Woodward Ave DetroitMI48202 United States University of Wisconsin-Madison Department of Human Oncology Department of Medical Physics 600 Highland Ave MadisonWI53792 United States

Medical image segmentation of tumors and organs at risk is a time-consuming yet critical process in the clinic that utilizes multimodality imaging (e.g, different acquisitions, data types, and sequences) to increase segmentation precision. In this paper, we propose a novel framework, Modality-Agnostic learning through Multi-modality Self-distillation (MAG-MS), to investigate the impact of input modalities on medical image segmentation. MAG-MS distills knowledge from the fusion of multiple modalities and applies it to enhance representation learning for individual modalities. Thus, it provides a versatile and efficient approach to handle limited modalities during testing. Our extensive experiments on benchmark datasets demonstrate the high efficiency of MAG-MS and its superior segmentation performance than current state-of-the-art methods. Furthermore, using MAG-MS, we provide valuable insight and guidance on selecting input modalities for medical image segmentation tasks. © 2023, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

High Performance Adaptive Genetic Algorithms for Real Time Decision Making in Complex Systems

High Performance Adaptive Genetic Algorithms for Real Time D...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Krishnamurty Raju Mudunuru Bhargav H K Somnath Banerjee Hemantha. C Pooja Sapra Shreyasi Bhattacharya Department of Computer Science and Engineering Shridevi Institute of Engineering and Technology Industry Institute Interaction Cell(IIIC) Tumakuru India Department of Mechanical Engineering BGS Institute of Technology Adichunchanagiri University Mandya India Department of Information Technology Faculty of Engineering and Technology Parul Institute of Engineering and Technology Parul University P.O.Limda India Faculty of Law Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

Complex systems need instant decision capabilities which traditional algorithms cannot deliver without difficulty. The adaptive genetic algorithms solve optimization problems through dynamic evolutionary optimization strategy development. The proposed research develops a high-performance framework of adaptive genetic algorithm which combines variables-dependent mutation rates along with automatic crossover probability adjustment and parallel processing. The algorithm received testing in different complex system environments which included logistics networks and financial modeling alongside autonomous control systems. The adaptive framework achieved enhanced performance results that attained 94.8% accuracy in logistics optimization and 92.3% accuracy in financial forecasting along with 89.7% accuracy in autonomous control systems. The performance boost using adaptive genetic algorithms reached a 78.6% increase versus classic genetic algorithms during execution. High-performance adaptive genetic algorithms develop resilient solutions for real-time complex system decision making that optimizes performance based on changing environmental conditions and provides scalable real-time solutions with maintained adaptability.

关键词： Adaptive systems Accuracy Heuristic algorithms Parallel processing Control systems Real-time systems Complex systems Optimization Genetic algorithms Logistics

来源：评论

学校读者我要写书评

暂无评论

A deep learning based automated hand hygiene training system

arXiv

引用

arXiv 2021年

作者： Shahbandeh, Mobina Ghaffarpour, Fatemeh Vali, Sina Haghpanah, Mohammad Amin Torkamani, Amin Mousavi Masouleh, Mehdi Tale Kalhor, Ahmad School of Electrical and Computer Engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory University of Tehran Tehran Iran Department of Computational Engineering Lappeenranta University of Technology Lappeenranta Finland School of Electrical and Computer Engineering Human and Robot Interaction Laboratory University of Tehran Tehran Iran

Hand hygiene is crucial for preventing viruses and infections. Due to the pervasive outbreak of COVID-19, wearing a mask and hand hygiene appear to be the most effective ways for the public to curb the spread of these viruses. The World Health Organization (WHO) recommends a guideline for alcohol-based hand rub in eight steps to ensure that all surfaces of hands are entirely clean. As these steps involve complex gestures, human assessment of them lacks enough accuracy. However, Deep Neural Network (DNN) and machine vision have made it possible to accurately evaluate hand rubbing quality for the purposes of training and feedback. In this paper, an automated deep learning based hand rub assessment system with real-time feedback is presented. The system evaluates the compliance with the 8-step guideline using a DNN architecture trained on a dataset of videos collected from volunteers with various skin tones and hand characteristics following the hand rubbing guideline. Various DNN architectures were tested, and an Inception-ResNet model led to the best results with 97% test accuracy. In the proposed system, an NVIDIA Jetson AGX Xavier embedded board runs the software. The efficacy of the system is evaluated in a concrete situation of being used by various users, and challenging steps are identified. In this experiment, the average time taken by the hand rubbing steps among volunteers is 27.2 seconds, which conforms to the WHO guidelines. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Walking the Future: Bridging Foot Augmentation into Next Steps of human Augmentation

Walking the Future: Bridging Foot Augmentation into Next Ste...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI EA 2025

作者： Sabnis, Nihar Wittchen, Dennis Otaran, Ata Badmos, Fatima Liu, Siyi Saini, Aryan Regal, Georg van Rheden, Vincent Mueller, Florian Nanayakkara, Suranga Matthies, Denys J.C. Nachtigall, Troy Strohmeier, Paul Vidal, Laia Turmo Elvitigala, Don Samitha Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken Germany Faculty of Informatics / Mathematics Dresden University of Applied Sciences Saxony Dresden Germany Saarland University Saarland Informatics Campus Saarland Saarbrücken Germany Technological University Dublin Dublin Ireland Faculty of Information Technology Monash University Melbourne Australia Exertion Games Lab. Department of Human-Centred Computing Monash University MelbourneVIC Australia Center for Technology Experience AIT Austrian Institute of Technology GmbH Vienna Austria Human Computer Interaction Division University of Salzburg Salzburg Austria Augmented Human Lab. School of Computing National University of Singapore Singapore Singapore Augmented Human Lab. Auckland Bioengineering Institute Auckland New Zealand Eindhoven University of Technology Eindhoven Netherlands KTH Royal Institute of Technology Stockholm Sweden Department of Human Centred Computing Faculty of Information Technology Monash University Melbourne Australia

ISBN: (纸本)9798400713958

Over the past decade, a noticeable increase in literature can be seen in wearable foot interfaces, which have evolved from activity tracking to enhancing human capabilities. Our legs, being the largest body limbs, play an essential role in various functions such as locomotion, maintaining balance, supporting proper posture and providing ground-contact using our feet. Hence, foot augmentations offer the opportunity to augment our entire body. However, most prior research focuses on specific application areas, thus affording a research agenda to further understand the full potential of feet in designing augmentations and to contextualize it in the broader human augmentation space. To achieve this, in this workshop, we invite researchers, designers, and practitioners, novice and expert, interested in designing human and foot augmentations. We will discuss how early foot interfaces helped in augmenting humans, and based on current work and trends in foot augmentation, we will formulate strategies for the next steps and discuss the applicability of such strategies in the broader space of human augmentation. © 2025 Copyright held by the owner/author(s).

关键词： human engineering

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptation and Generalization from human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Analysis

Learning Adaptation and Generalization from Human-Inspired M...

引用

Artificial Intelligence and Knowledge Engineering (AIKE)

作者： Joshua Ho Chien-Min Wang Chung-Ta King Yi-Hsin You Chi-Wei Feng Yen-Min Chen Bo-Yi Kuo Academia Sinica Institute of Information Science Taipei Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei Taiwan Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Computer Science National Taiwan University Taipei Taiwan

Over the last decades, there has been growing interest in research in multiple and interdisciplinary fields of human-AI computing. In particular, approaches integrating the intersecting design with reinforcement learning (RL) have received more attention. However, the current research on RL may need to consider its enhancement from a human-inspired approach further. In the present work, we focus on enabling a meta-reinforcement learning (meta-RL) agent to achieve adaptation and generalization according to modeling Markov decision processes using Bayesian knowledge and analysis. By introducing a novel framework called human-inspired meta-RL (HMRL), we incorporate the agent performing resilient actions to leverage the dynamic dense reward based on the knowledge and prediction of a Bayesian analysis. The proposed framework can make the agent learn generalization and prevent the agent from failing catastrophically. The experimental results show that our approach helps the agent reduce computational costs with learning adaptation. Finally, we conclude and anticipate that integrating human-inspired meta-RL can enable learning more formulations relating to robustness and scalability, leading to promising directions and more complex AI goals in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position: topological deep learning is the new frontier for relational learning 24

Position: topological deep learning is the new frontier for ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Tolga Birdal Michael Bronstein Gunnar Carlsson Justin Curry Yue Gao Mustafa Hajij Roland Kwitt Pietro Liò Paolo Di Lorenzo Vasileios Maroulas Nina Miolane Farzana Nasrin Karthikeyan Natesan Ramamurthy Bastian Rieck Simone Scardapane Michael T. Schaub Petar Veličković Bei Wang Yusu Wang Guo-Wei Wei Ghada Zamzmi Department of Mathematics The University of Manchester Manchester UK Department of Computing Imperial College London London UK Department of Computer Science University of Oxford Oxford UK Department of Mathematics Stanford University Stanford and BlueLightAI Inc University at Albany New York School of Software Tsinghua University Beijing China University of San Francisco San Francisco Department of Artificial Intelligence and Human Interfaces University of Salzburg Austria Department of Computer Science and Technology University of Cambridge Cambridge UK Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy Department of Mathematics University of Tennessee Knoxville Department of Electrical and Computer Engineering UC Santa Barbara Santa Barbara Department of Mathematics University of Hawai' at M-ānoa Hawai'i IBM Corporation New York Helmholtz Munich Munich Germany and Technical University of Munich Munich Germany Technical University of Munich Munich Germany Google DeepMind and Department of Computer Science and Technology University of Cambridge Cambridge UK School of Computing University of Utah Utah Computer Science and Engineering Department University of California San Diego San Diego Department of Mathematics Michigan State University East Lansing Michigan University of South Florida Florida

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When differential privacy meets NLP: The devil is in the detail

arXiv

引用

arXiv 2021年

作者： Habernal, Ivan Trustworthy Human Language Technologies Department of Computer Science Technical University of Darmstadt

Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our contribution is a formal analysis of ADePT, a differentially private auto-encoder for text rewriting (Krishna et al, 2021). ADePT achieves promising results on downstream tasks while providing tight privacy guarantees. Our proof reveals that ADePT is not differentially private, thus rendering the experimental results unsubstantiated. We also quantify the impact of the error in its private mechanism, showing that the true sensitivity is higher by at least factor 6 in an optimistic case of a very small encoder's dimension and that the amount of utterances that are not privatized could easily reach 100% of the entire dataset. Our intention is neither to criticize the authors, nor the peer-reviewing process, but rather point out that if differential privacy applications in NLP rely on formal guarantees, these should be outlined in full and put under detailed scrutiny. © 2021, CC BY-SA.

关键词： Privatization

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：