检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Zhao, Jie Wu, Daiyang Wu, JiaXin Ye, Wenhao Huang, Faliang Wang, Jiahai See-To, Wing-Kuen Eric Department of Data Science and Business Intelligence Guangdong University of Technology Guangzhou China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong

Fuzzy Rough Set Theory (FRST)-based feature selection has been widely used as a preprocessing step to handle dynamic and large datasets. However, large-scale or high-dimensional datasets remain intractable for FRST-based feature selection approaches due to high space complexity and unsatisfactory classification performance. To overcome these challenges, we propose a Consistency Approximation (CA)-based framework for incremental feature selection. By exploring CA, we introduce a novel significance measure and a tri-accelerator. The CA-based significance measure provides a mechanism for each sample in the universe to keep members with different class labels within its fuzzy neighbourhood as far as possible, while keeping members with the same label as close as possible. Furthermore, our tri-accelerator reduces the search space and decreases the computational space with a theoretical lower bound. The experimental results demonstrate the superiority of our proposed algorithm compared to state-of-the-art methods on efficiency and classification accuracy, especially for large-scale and high-dimensional datasets. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Incremental Feature Selection for Dynamic Incomplete Data Using Sub-Tolerance Relation

SSRN

引用

SSRN 2023年

作者： Zhao, Jie Ling, Yun Huang, Faliang Wang, Jiahai See-To, Eric Wing kuen Department of Data Science and Business Intelligence Guangdong University of Technology Guangzhou China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong

TRS theory is widely used for feature selection with incomplete data. However, the traditional positive region-based measure ignores uncertainty, resulting in redundant features and poor classification accuracy. In addition, the computation of the positive region incurs significant time and space costs. To address these limitations, we extend the tolerance class to a Subrelation Tolerance Class (STC) by decomposing the tolerance relation into two subrelations. STC transforms feature selection into a two-stage certainty measurement by partitioning the universe into certainty and uncertainty regions. By progressively filtering out certain regions, the computational space is reduced. Furthermore, we propose a new significance measure that incorporates both certain and uncertain information. This measure effectively reduces redundant features, resulting in improved computational efficiency and classification accuracy. Using STC and our measure, we develop an incremental feature selection algorithm for dealing with incomplete streaming data, which is validated through extensive experiments and comparisons. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Incorporating simulated spatial context information improves the effectiveness of contrastive learning models

arXiv

引用

arXiv 2024年

作者： Zhu, Lizhen Wang, James Z. Lee, Wonseuk Wyble, Brad Data Science and Artificial Intelligence Area College of Information Sciences and Technology The Pennsylvania State University University ParkPA United States Human-Computer Interaction Area College of Information Sciences and Technology The Pennsylvania State University University ParkPA United States Department of Communication and Media School of Social Sciences and Humanities Loughborough University Leicestershire Loughborough United Kingdom Department of Computer Science and Engineering The Pennsylvania State University University ParkPA United States Department of Psychology The Pennsylvania State University University ParkPA United States

Visual learning often occurs in a specific context, where an agent acquires skills through exploration and tracking of its location in a consistent environment. The historical spatial context of the agent provides a similarity signal for self-supervised contrastive learning. We present a unique approach, termed Environmental Spatial Similarity (ESS), that complements existing contrastive learning methods. Using images from simulated, photorealistic environments as an experimental setting, we demonstrate that ESS outperforms traditional instance discrimination approaches. Moreover, sampling additional data from the same environment substantially improves accuracy and provides new augmentations. ESS allows remarkable proficiency in room classification and spatial prediction tasks, especially in unfamiliar environments. This learning paradigm has the potential to enable rapid visual learning in agents operating in new environments with unique visual characteristics. Potentially transformative applications span from robotics to space exploration. Our proof of concept demonstrates improved efficiency over methods that rely on extensive, disconnected datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A model for structuring UML class diagrams to support non-visual interpretation and navigation 20

A model for structuring UML class diagrams to support non-vi...

引用

20th British computer Society Conference on human-computer interaction: Engage, HCI 2006

作者： Metatla, Oussama Bryan-Kinns, Nick Stockman, Tony Interaction Media and Communication Group Department of Computer Science Queen Mary University of London E1 4NS United Kingdom

Accessing textual information non-visually can be performed directly using Braille translators or text-to-speech engines. Problems arise when faced with graphically represented information, such as a diagram. For blind and visually impaired people, screen-readers are the most commonly used tools for accessing on-screen information, but they typically fail to deliver graphical information in appropriate and flexible ways. As a result, diagrammatic representations are inaccessible for such a population of users. We present the design of an experiment exploring a task-oriented approach for integrating speech and non-speech sounds to support the interpretation and navigation of conceptually relevant information encoded in a diagram. © BCS HCI group Conference: Engage, HCI *** right reserved.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Investigating the interaction Experience with Augmented Reality Based Writing Tools 21st

Investigating the Interaction Experience with Augmented Real...

引用

21st International Conference on human-computer interaction, HCI International 2019

作者： Zheng, Wei Yi, Xin Shi, Yuanchun Pervasive Human-Computer Interaction Group Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9783030235277

The contents of this paper include the design methodology of perceptual computing products, the innovative design of the AR writing and its technical feasibility, the writing interactive experience test of different hardware platforms, etc. It has certain reference value for the research work of paperless writing. © Springer Nature Switzerland AG 2019.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Acupuncture State Detection at Zusanli (ST-36) Based on Scalp EEG and Transformer

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4023-4034页

作者： Wenhao Rao Meiyan Xu Haochen Wang Weicheng Hua Jiayang Guo Yongheng Zhang Haibin Zhu Ziqiu Zhou Jiawei Xiong Jianbin Zhang Yijie Pan Peipei Gu Duo Chen School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Department of Computer Science and the Institute of Human Factors Engineering Minnan Normal University Zhangzhou China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China China Mobile Group Jiangsu Company Ltd Sihong Branch Suqian China Second Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing University of Chinese Medicine Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo China College of Software Engineering Zhengzhou University of Light Industry Zhengzhou China

In clinical acupuncture practice, needle twirling (NT) and needle retention (NR) are strategically combined to achieve different therapeutic effects, highlighting the importance of distinguishing between different acupuncture states. Scalp EEG has been proven significantly relevant to brain activity and acupuncture stimulation. In this work, we designed an acupuncture paradigm to collect scalp EEG to study the differences in EEG changes during different acupuncture states. Since deep learning (DL) has been increasingly used in EEG analysis, we propose the Acupuncture Transformer Detector (ATD), a model based on Convolutional Neural Networks (CNN) and Transformer technology. ATD encapsulates the local and global features of EEG under the acupuncture states of Zusanli acupoint (ST-36) in an end-to-end classification framework. The experiment results from 28 healthy participants show that the proposed model can efficiently classify the EEG in different states, with an accuracy of $85.47\pm 0.73\%$ . In this study, time-frequency analysis revealed that power changes were mainly confined to the delta frequency band under different acupuncture states. Brain topography revealed that ST-36 was activated primarily on the left frontal and parieto-occipital areas. This method provides new ideas for automatic recognition of acupuncture status from the perspective of DL, offering new solutions for standardizing acupuncture procedures.

关键词： Acupuncture Electroencephalography Transformers Convolutional neural networks Needles Brain modeling Medical diagnostic imaging Training Temperature measurement Feature extraction

来源：评论

学校读者我要写书评

暂无评论

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

arXiv

引用

arXiv 2023年

作者： Ma, Yifeng Wang, Suzhen Hu, Zhipeng Fan, Changjie Lv, Tangjie Ding, Yu Deng, Zhidong Yu, Xin Department of Computer Science and Technology BNRist THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University China Virtual Human Group Netease Fuxi AI Lab China Zhejiang University China University of Technology Sydney Australia

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://***/FuxiVirtualhuman/styletalk. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Recognition of Food-Texture Attributes Using an In-Ear Microphone 25th

Recognition of Food-Texture Attributes Using an In-Ear Micro...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Papapanagiotou, Vasileios Diou, Christos van den Boer, Janet Mars, Monica Delopoulos, Anastasios Multimedia Understanding Group Department of Electrical and Computer Engineering Faculty of Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Informatics and Telematics Harokopio University of Athens Kallithea Greece Department of Biomedical Signals and Systems Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands Division of Human Nutrition and Health Wageningen University Wageningen Netherlands

ISBN: (纸本)9783030688202

Food texture is a complex property;various sensory attributes such as perceived crispiness and wetness have been identified as ways to quantify it. Objective and automatic recognition of these attributes has applications in multiple fields, including health sciences and food engineering. In this work we use an in-ear microphone, commonly used for chewing detection, and propose algorithms for recognizing three food-texture attributes, specifically crispiness, wetness (moisture), and chewiness. We use binary SVMs, one for each attribute, and propose two algorithms: one that recognizes each texture attribute at the chew level and one at the chewing-bout level. We evaluate the proposed algorithms using leave-one-subject-out cross-validation on a dataset with 9 subjects. We also evaluate them using leave-one-food-type-out cross-validation, in order to examine the generalization of our approach to new, unknown food types. Our approach performs very well in recognizing crispiness (0.95 weighted accuracy on new subjects and 0.93 on new food types) and demonstrates promising results for objective and automatic recognition of wetness and chewiness. © 2021, Springer Nature Switzerland AG.

关键词： Microphones

来源：评论

学校读者我要写书评

暂无评论

Dose-response effect of pre-exercise carbohydrates under muscle glycogen unavailability:Insights from McArdle disease

引用

Journal of Sport and Health science 2024年第3期13卷 398-408页

作者： Pedro L.Valenzuela Alfredo Santalla Lidia B.Alejo Andrea Merlo Asuncion Bustos Laura Castellote-Belles Roser Ferrer-Costa Nicola A.Maffiuletti David Barranco-Gil Tomas Pinos Alejandro Lucia Physical Activity and Health Research Group(“PaHerg”) Research Institute of Hospital“12 de Octubre”(“imas12”)Madrid 28041Spain Department of Systems Biology University of AlcalaMadrid 28871Spain Department of Sport and Computer Science Section of Physical Education and SportsFaculty of SportUniversidad Pablo de OlavideSevilla 41013Spain EVOPRED Research Group Universidad Europea de CanariasTenerife 38300Spain Faculty of Sport Sciences Universidad Europea de MadridMadrid 28670Spain Gait&Motion Analysis Laboratory Sol et Salus HospitalTorre Pedrera di Rimini(RN)47922Italy Department of Clinical Biochemistry Laboratoris ClınicsHospital Universitari Vall d’HebronBarcelona 08035Spain Human Performance Lab Schulthess ClinicZurich 8008Switzerland Biomedical Research Networking Center on Rare Disorders(CIBERER) Barcelona 08035Spain Mitochondrial and Neuromuscular Disorders Unit Vall d’Hebron Institut de RecercaUniversitat Autonoma de BarcelonaBarcelona 08035Spain

Background:This study aimed to determine the effect of different carbohydrate(CHO)doses on exercise capacity in patients with McArdle disease—the paradigm of“exercise intolerance”,characterized by complete muscle glycogen unavailability—and to determine whether higher exogenous glucose levels affect metabolic responses at the McArdle muscle cell(in vitro)***:Patients with McArdle disease(n=8)and healthy controls(n=9)underwent a 12-min submaximal cycling constant-load bout followed by a maximal ramp test 15 min after ingesting a non-caloric *** a randomized,double-blinded,cross-over design,patients repeated the tests after consuming either 75 g or 150 g of CHO(glucose:fructose=2:1).Cardiorespiratory,biochemical,perceptual,and electromyographic(EMG)variables were ***,glucose uptake and lactate appearance were studied in vitro in wild-type and McArdle mouse myotubes cultured with increasing glucose concentrations(0.35,1.00,4.50,and 10.00 g/L).Results:Compared with controls,patients showed the“classical”second-wind phenomenon(after prior disproportionate tachycardia,myalgia,and excess electromyographic activity during submaximal exercise,all p<0.05)and an impaired endurance exercise capacity(-51%ventilatory threshold and55%peak power output,both p<0.001).Regardless of the CHO dose(p<0.05 for both doses compared with the placebo),CHO intake increased blood glucose and lactate levels,decreased fat oxidation rates,and attenuated the second wind in the ***,only the higher dose increased ventilatory threshold(+27%,p=0.010)and peak power output(+18%,p=0.007).In vitro analyses revealed no differences in lactate levels across glucose concentrations in wild-type myotubes,whereas a doseresponse effect was observed in McArdle ***:CHO intake exerts beneficial effects on exercise capacity in McArdle disease,a condition associated with total muscle glycogen *** of these benefits are dose dependent.

关键词： Endurance Glycogen storage disease Glycogenosis Nutrition Supplement

来源：评论

学校读者我要写书评

暂无评论

Bidirectional human-AI Alignment: Emerging Challenges and Opportunities

Bidirectional Human-AI Alignment: Emerging Challenges and Op...

引用

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

作者： Shen, Hua Knearem, Tiffany Ghosh, Reshmi Liu, Michael Xieyang Monroy-Hernández, Andrés Wu, Tongshuang Yang, Diyi Huang, Yun Mitra, Tanushree Li, Yang Hearst, Marti The Information School University of Washington Seattle WA United States Google San Francisco CA United States Microsoft Corp Microsoft AI Development Acceleration Program Cambridge MA United States Google DeepMind Pittsburgh PA United States Princeton University Princeton NJ United States Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA United States Computer Science Department Stanford University Stanford CA United States School of Information Sciences University of Illinois at Urbana-Champaign Champaign IL United States University of Washington Seattle WA United States Google Research Mountain View CA United States UC Berkeley Berkeley CA United States

ISBN: (纸本)9798400713958

Recent advancements in general-purpose AI have highlighted the urgent need to align AI systems with the goals, ethical principles, and values of individuals and society. Existing alignment research has been primarily approached as an AI-centered, static, and unidirectional process. However, this unidirectional perspective falls short of taking into account the dynamic and evolving interaction between humans and AI, necessitating a shift toward a bidirectional, interconnected mode of human-AI alignment. This SIG aims to outline the emerging areas of bidirectinoal human-AI alignment research, propose a blueprint of future goals and challenges for fundamental alignment research, and establish a shared platform to bring together experts from HCI, AI, social sciences, and more to advance interdisciplinary research and collaboration on human-AI alignment. © 2025 Copyright held by the owner/author(s).

关键词： bidirectional human-AI alignment human-AI interactive alignment social impact of AI alignment value-centered design

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：