检索结果-内蒙古大学图书馆

4th International Conference on Communication Technology and Information Technology, ICCTIT 2024

作者： Zhang, Runsheng Wang, Shixiao Xie, Tianfang Duan, Shiyu Chen, Mengmeng University of Southern California Los AngelesCA United States School of Visual Arts New YorkNY United States Georgia Institute of Technology AtlantaGA United States Carnegie Mellon University PittsburghPA United States New York University New YorkNY United States

ISBN: (纸本)9798331528973

This study presents a novel approach for intelligent user interaction interface generation and optimization, grounded in the variational autoencoder (VAE) model. With the rapid advancement of intelligent technologies, traditional interface design methods struggle to meet the evolving demands for diversity and personalization, often lacking flexibility in real-time adjustments to enhance user experience. human-computer interaction (HCI) plays a critical role in addressing these challenges, as it focuses on creating interfaces that are not only functional but also intuitive and responsive to user needs. This research leverages the RICO dataset to train the VAE model, enabling the simulation and creation of user interfaces that align with user aesthetics and interaction habits. Through the integration of real-time user behavior data, the system dynamically refines and optimizes the interface to improve usability, thereby underscoring the importance of HCI in achieving a seamless user experience. The experimental findings indicate that the VAE-based approach significantly enhances the quality and precision of interface generation compared to other methods, including autoencoders (AE), generative adversarial networks (GAN), conditional generative adversarial networks (cGAN), deep belief networks (DBN), and variational autoencoder generative adversarial networks (VAE-GAN). This work contributes valuable insights into human-computer interaction (HCI), providing robust technical solutions for automated interface generation and enhanced user experience optimization. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing visual Encodings of Uncertainty Through Aesthetic Depictions in Line Graph visualisations

Enhancing Visual Encodings of Uncertainty Through Aesthetic ...

引用

human Interface and the Management of Information (HIMI) part of International Conference on human-computer interaction (HCII)

作者： Pinney, Joel Carroll, Fiona Chew, Esyin Cardiff Metropolitan Univ Cardiff Sch Technol Llandaff CampusWestern Ave Cardiff CF5 2YB Wales

ISBN: (纸本)9783031351310;9783031351327

The method of representing uncertainty can drastically influence a user's interpretation of the visualised data. Whilst reasons for the scarce adoption of accepting uncertainty visualisations has been extensively researched, exploring further intuitive depiction methods has taken a back seat. Currently, most visualisation methods for uncertainty revolve around the comprehension of grasping pre-existing techniques such as confidence intervals and error bars. Moreover, this anticipates that the intended audience will be proficient in obtaining the relevant information displayed. To help establish an accessible method for the visualisation of uncertainty, we adopt a novel cross-disciplinary approach to further understand and depict the more intuitive/affective dimensions of uncertainty. The field of aesthetics is mostly associated with the discipline of art and design, but it has been applied in this research to evaluate its effectiveness for uncertainty visualisation. In a recent study with one thousand one hundred and forty-two participants, the authors examined the influence of applying aesthetic dimensions to the visualisation of a line graph. We find that certain aesthetic renderings afford a higher degree of uncertainty and provide an intuitive approach to mapping uncertainty to the data. By analysing the participants' responses to different aesthetic renderings, we aim to build a picture of how we might encourage the use of uncertainty visualisation for a lay audience.

关键词： Uncertainty visualisation aesthetics

来源：评论

学校读者我要写书评

暂无评论

Research on non-linear visual matching model under inherent constraints of images

引用

APPLIED MATHEMATICS AND NONLINEAR SCIENCES 2022年第1期8卷 2617-2627页

作者： Zhang, Xuwei Yan, Wen Deng, Li Liu, Zhiyu Southwest Petr Univ Chengdu 610500 Sichuan Peoples R China

visual matching of plane images has promoted the development of artificial intelligence and digital vision. High-precision visual matching can promote the innovation of geometric measurement, visual navigation and other fields. Therefore, a non-linear visual matching model with inherent constraints is established in this paper. First, according to the principle of visual imaging, a non-linear conversion model of visual point coordinates is proposed, and the deviation of coordinate points is proofread. Then, inherent boundary constraints are introduced into the model to improve the accuracy of visual matching. Finally, through analysis and evaluation of error, results are generated showing that the visual matching model can effectively solve the shortcoming of low-matching accuracy in feature points, and provide more accurate data support for 3D calculation of images.

关键词： visual matching bound non-linear model

来源：评论

学校读者我要写书评

暂无评论

Yugen Cloudstone Echo: Exploring Emotional Design interaction Design in Sleep Facilitation 26th

Yugen Cloudstone Echo: Exploring Emotional Design Interactio...

引用

26th International Conference on human-computer interaction (HCII)

作者： Guo, Tianxu Zhang, Mengting Macau Univ Sci & Technol Macau 999078 Peoples R China Springer Heidelberg Tiergartenstr 17 D-69121 Heidelberg Germany

ISBN: (纸本)9783031619625;9783031619632

Sleep plays a pivotal role in the preservation of human health. However, the prevalence of insomnia, attributable to multifaceted factors such as environmental disturbances, emotional distress, and cognitive hyperactivity, underscores a significant challenge to achieving restorative sleep. This research endeavors to mitigate primary insomnia through the development of an interactive smart speaker, christened the Yugen Cloudstone Echo. This innovative device amalgamates principles of emotional design, emotional design, and interactive technologies to foster a harmonious and serene sleep environment. Drawing inspiration from the Chinese concept of yugen, characterized by its embodiment of profound mystery and aesthetic beauty, and symbolized by the ethereal imagery of clouds and the enduring solidity of stones, this study delves into the symbiotic relationship between these elements to engender an ambiance conducive to restful slumber. By harnessing auditory stimuli, visual aesthetics, and intuitive interaction design, this research proposes a novel paradigm for addressing insomnia, accentuating the pivotal role of emotional resonance in the advancement of technology. This paper elucidates the mechanisms by which sound and light effects can facilitate sleep induction, elucidating the design principles underpinning the Yugen Cloudstone Echo and its application of emotional design. Furthermore, it delineates the functionalities, interactive modalities, and underlying components of the device, notably leveraging Arduino platforms for implementation. Through an interdisciplinary lens that integrates insights from design theory, psychology, and cultural studies, this paper underscores the transformative potential of emotionally resonant interaction design in augmenting both sleep quality and overall well-being.

关键词： Insomnia Auditory Therapy Light Therapy interaction Design Emotional Design

来源：评论

学校读者我要写书评

暂无评论

KYPHOTONE: Wearable Hunchback Corrector for Women

KYPHOTONE: Wearable Hunchback Corrector for Women

引用

2023 International Symposium on Design Studies and Intelligence Engineering, DSIE 2023

作者： Yao, Yousheng Xie, Yuan Ying, Fangtian Huang, Zhihao Tang, E. Pan, Xiqin Zheng, Junpeng Zhan, Junqi Peng, Jin Chen, Haoteng Zhongkai University of Agriculture and Engineering China Macau University of Science and Technology China

ISBN: (纸本)9781643684888

In human-computer interaction, there is a close relationship between "beauty" and empowerment. aesthetics in human-computer interaction is not only about pursuing external beauty and visual appeal, but also about empowering users with better experience and functionality, and enhancing the capabilities of the interaction system, thereby improving user satisfaction and efficiency. In the real world, wearable testing systems are becoming increasingly popular for autonomous health testing. Hunchback is a problem that is detrimental to healthy growth and self-confidence. In this article, we introduce KYPHOTONE, an interactive system that can help hunchbacked women with their hunchback problems, designed for women. We analyze the materials, anthropometric measurements, and garment assembly of KYPHOTONE. KYPHOTONE consists of hardware and software programs. The hardware and software are utilized to provide real-time feedback based on the movements of women with hunchbacks during the wearing process, enabling real-time medical diagnosis, correction detection, and correction management. In addition, we conducted a preliminary user study of KYPHOTONE, which showed that women with hunchbacks are willing to wear it, which gives them more confidence in preventing hunchbacks. © 2024 The Authors.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

The Impact of visual aesthetics of Different Types of APP Icons on User Cognition 24th

The Impact of Visual Aesthetics of Different Types of APP Ic...

引用

24th International Conference on human-computer interaction, HCII 2022

作者： Li, Qiang Liu, Zexue Wang, Peng Shenyang Aerospace University Shenyang China

ISBN: (纸本)9783031064166

Previous research on icons in human-computer interaction has always focused on usability and recognition efficiency, but few kinds of research on user cognition. This research aims to evaluate the relationship between icon aesthetics of different types of apps and user cognition. This study uses three types of App icons in the Huawei app store: text symbol icons, graphic icons, and image icons as examples. Through a questionnaire survey, aesthetic and cognition variables were assessed. The study confirmed that the aesthetic level of graphical icons is high, and the participant’s cognitive results of different icon types are different. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

StageAR: Markerless Mobile Phone Localization for AR in Live Events 31

StageAR: Markerless Mobile Phone Localization for AR in Live...

引用

IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

作者： Jin, Tao Wu, Shengxi Dasari, Mallesham Apicharttrisorn, Kittipat Rowe, Anthony Carnegie Mellon Univ Pittsburgh PA 15213 USA Northeastern Univ Boston MA USA Nokia Bell Labs Providence RI USA Bosch Res Renningen Germany

ISBN: (纸本)9798350374025;9798350374032

Localizing mobile phone users precisely enough to provide AR content in theaters and concert venues is extremely challenging due to dynamic staging and variable lighting. visual markers are often disruptive in terms of aesthetics, and static pre-defined feature maps are not robust to visual changes. In this paper, we study several techniques that leverage sparse fixed infrastructure to monitor and adapt to changes in the environment at runtime to enable robust AR quality pose tracking for large audiences. Our most basic technique uses one or more fixed cameras in the environment to prune away poor feature points due to motion and lighting from a static model. For more challenging environments, we propose transmitting dynamic 3D feature maps that adapt to changes in the scene in real-time. Users with a mobile phone camera can use these maps to accurately localize across highly dynamic environments without explicit markers. We show the performance trade-offs resulting from StageAR's different reconstruction techniques, ranging from multiple stereo cameras to cameras paired with LiDAR. We evaluate each approach in our system across a wide variety of simulated and real environments at auditorium/theater scale and find that our most accurate technique can match the performance of large (1.5x1.5m) back-lit static markers without being visible to users.

关键词： human-centered computing-human computer interaction (HCI)-interaction paradigms-Mixed / augmented reality

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Neural Networks-Based Approaches for Predicting visual Perception of User Interfaces 3rd

Benchmarking Neural Networks-Based Approaches for Predicting...

引用

3rd International Conference on Artificial Intelligence in HCI (AI-HCI) Held as Part of the 24th International Conference on human-computer interaction (HCII)

作者： Bakaev, Maxim Heil, Sebastian Chirkov, Leonid Gaedke, Martin Novosibirsk State Tech Univ Novosibirsk Russia Tech Univ Chemnitz Chemnitz Germany

ISBN: (纸本)9783031056437;9783031056420

Deep Learning techniques have become the mainstream and unquestioned standard in many fields, e.g. convolutional neural networks (CNN) for image analysis and recognition tasks. As testing and validation of graphical user interfaces (GUIs) is increasingly relying on computer vision, CNN models that predict such subjective and informal dimensions of user experience as aesthetic or complexity perception start to achieve decent accuracy. They however require huge amounts of human-labeled training data, which are costly or unavailable in the field of human-computer interaction (HCI). More traditional approaches rely on manually engineered features that are extracted from UI images with domain-specific algorithms and are used in "traditional" Machine Learning models, such as feedforward artificial neural networks (ANN) that generally need fewer data. In our paper, we compare the prediction quality of CNN (a modified GoogLeNet architecture) and ANN models to predict visual perception per aesthetics, Complexity, and Orderliness scales for about 2700 web UIs assessed by 137 users. Our results suggest that the ANN architecture produces smaller Mean Squared Error (MSE) for the training dataset size (N) available in our study, but that CNN should become superior with N > 2912. We also propose the regression model that can help HCI researchers to foretell MSE in their ML experiments.

关键词： User Interfaces aesthetics visual Complexity Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Innovative Approaches to Assessing Urban Space Quality: A Multi-Source Big Data Perspective on Knowledge Dynamics

引用

JOURNAL OF THE KNOWLEDGE ECONOMY 2024年第2期16卷 6803-6841页

作者： Liu, Bing Liu, Zixuan Fang, Libo Hunan Agr Univ Coll Publ Adm & Law Changsha Peoples R China Changsha Commerce & Tourism Coll Changsha Peoples R China Jishou Univ Jishou Peoples R China Hunan Urban Planning & Design Inst Changsha Peoples R China

In the context of urban development, this research paper delves into the intricate relationship between urban space quality perception and the psychological well-being of residents. Urban spaces are dynamic and possess characteristics that significantly influence individuals' psychological states. This study focuses on the specific niche of understanding the influence of spatial environment quality on residents' psychological perception from a spatial perspective, challenging conventional assumptions and aligning with evolving trends in urban studies. The study employs a unique approach, combining micro-psychological perception analysis, web-crawled Baidu Maps street data, semantic segmentation using the PSPNet model for street image elements, and a novel "man-machine confrontation-iterative feedback" evaluation methodology. Deep learning techniques are harnessed for processing street images, and human-computer interaction scores are incorporated to gauge urban block space quality perception. The findings shed light on factors influencing spatial quality perception, such as green spaces, urban infrastructure, safety, and aesthetics. Furthermore, the research highlights the practical implications for urban planning and policy development. It introduces a novel "human-machine interaction and feedback" methodology that empowers decision-makers to create more resident-centric, data-driven urban environments. The study underscores the importance of community engagement in the planning process and advocates for inclusive and sustainable urban environments. This research contributes to both theoretical and practical domains, bridging the gap between advanced technology and perceptual evaluation in the urban context. It provides a deeper understanding of human interactions with urban surroundings and offers valuable guidance for building resilient and livable cities that prioritize the well-being and happiness of their inhabitants.

关键词： Technological integration Space quality evaluation Psychological perception Deep learning applications visual perception assessment Urban planning Resident-centric Data-driven Resilient cities

来源：评论

学校读者我要写书评

暂无评论

美感与情感:美学视角下的个体交互感知机制研究

引用

现代情报 2024年第1期44卷 57-70页

作者：孙浩东柯青庾海媛曹韵秋南京大学信息管理学院江苏南京210023 国营芜湖机械厂安徽芜湖241000

[目的/意义]美学因素对用户情感体验有重要的影响作用,情感则是驱动用户交互行为的重要因素,为探讨美感和情感之间的关系,分析美学视角下的个体交互感知机制。[方法/过程]本文基于SOR理论构建了“界面美学—人体机理—美学感知”的研究... 详细信息

[目的/意义]美学因素对用户情感体验有重要的影响作用,情感则是驱动用户交互行为的重要因素,为探讨美感和情感之间的关系,分析美学视角下的个体交互感知机制。[方法/过程]本文基于SOR理论构建了“界面美学—人体机理—美学感知”的研究模型,设计了不同审美能力被试浏览不同美学水平网页界面的眼动实验。参与实验的30名被试通过梅尔美术测试区分出了高审美组和低审美组,均浏览经权威网站投票甄选出的高美学水平和低美学水平网页,眼动追踪设备会记录他们的眼动行为,同时实验中还通过情感量表、美学量表和半结构化访谈采集用户的主观感知数据。[结果/结论]统计分析发现,两组被试间的总注视时长、注视点个数和平均注视时间存在显著差异,界面美学水平显著影响被试的视觉认知加工、情感效价和美学感知;高审美组被试对美学感知更加灵敏,两组被试对界面的情感倾向较为一致,被试审美能力对界面美学感知存在调节作用,个体机理对界面美学感知存在部分中介效应。本研究丰富了人机交互过程中美感与情感关系的相关知识,为提升交互界面美学设计和情感体验提供参考。

关键词：美学情感效价眼动追踪审美能力认知

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：