检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Zhang, Liang Lin, Jionghao Sabatini, John Zapata-Rivera, Diego Forsyth, Carol Jiang, Yang Hollander, John Hu, Xiangen Graesser, Arthur C. Institute for Intelligent Systems University of Memphis MemphisTN United States Department of Electrical and Computer Engineering University of Memphis MemphisTN United States Faculty of Education The University of Hong Kong Hong Kong Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Centre for Learning Analytics Monash University MelbourneVIC Australia Department of Psychology University of Memphis MemphisTN United States Educational Testing Service PrincetonNJ United States Department of Psychology and Counseling Arkansas State University JonesboroAR United States Department of Applied Social Sciences Hong Kong Polytechnic University Hong Kong

As human learners respond to questions in Intelligent Tutoring Systems (ITSs), their performance data (correct or incorrect answers) is crucial for assessing and predicting their knowledge states. However, data sparsity, often arising from skipped or incomplete responses, hampers accurate assessment and personalized instruction. To address this challenge, we propose a Generative Adversarial Imputation Networks (GAIN) method using a three-dimensional representation (learners, questions, and attempts) with Convolutional Neural Networks (CNNs) in the input and output layers. We evaluate our method on three ITS datasets, AutoTutor ARC, ASSISTments, and MATHia, where it outperforms baselines, including tensor factorization methods and other GAN variants, across multiple maximum attempt settings. To confirm imputation effectiveness for learner modeling, we applied Bayesian Knowledge Tracing (BKT) and observed significant reductions in RMSE compared to original sparse data, indicating substantial improvements in modeling accuracy. Moreover, analyzing divergence of key BKT parameters (initial knowledge \(P(L_0)\), learning rate \(P(T)\), guess rate \(P(G)\), and slip rate \(P(S)\)) via Kullback-Leibler (KL) divergence shows that the imputed data preserves essential learning characteristics. Our findings highlight GAIN’s potential for mitigating data sparsity in ITSs, enabling more adaptive, individualized instruction and fostering more effective AI-driven education. © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Markerless Sagittal Gait Analysis of Cerebral Palsy in Children Using Pose Estimation Techniques

Markerless Sagittal Gait Analysis of Cerebral Palsy in Child...

引用

Innovation in Computing and Engineering (ICE), International Conference on

作者： Vinay Kumar Vats Chandra Prakash Amandeep Kaur Rajesh Kumar Computer Science and Engineering National Institute of Technology Delhi India Computational Intelligence and Smart Motion Research (CISMR) Lab SVNIT Surat India Malaviya National Institute of Technology Jaipur India Department of Human Anatomy and Physiology Faculty of Health Sciences University of Johannesburg Johannesburg South Africa

ISBN: (数字)9798350380460

ISBN: (纸本)9798350380477

Cerebral Palsy (CP) is a neurological disorder affecting children’s motor function and posture. Early detection and monitoring of Cerebral palsy is crucial for effective intervention and improved quality of life. Gait analysis is a critical tool for assessing motor function in children with cerebral palsy, often requiring controlled environments and markers for accuracy. Markerless gait analysis has emerged as a promising tool for objectively evaluating gait abnormalities in children with CP. In this study, we propose a markerless methodology utilising pose estimation to analyse gait patterns from sagittal video recordings captured in unconstrained environments. The dataset consists of 49 children, including 10 typically developing children and 39 with cerebral palsy, focusing on side-view videos for the analysis. Given the motor disabilities of these children, conducting gait analysis in a constrained environment can alter their natural walking patterns, making our approach particularly advantageous. Then we identify the key gait events, heel strike and toe-off, to distinguish gait between cycles by tracing knee joint movements. This technique demonstrates the potential for practical, non-invasive gait assessment in natural settings, offering insights into the distinct gait characteristics of children with cerebral palsy compared to their typically developing peers.

关键词： Legged locomotion Neurological diseases Cerebral palsy Technological innovation Pose estimation Motors Motion control Gait recognition Video recording Monitoring

来源：评论

学校读者我要写书评

暂无评论

From awareness to connectedness;the design and deployment of presence displays

From awareness to connectedness;the design and deployment of...

引用

CHI 2006: Conference on human Factors in Computing Systems

作者： Dey, Anind K. De Giizman, Edward S. Human-Computer Interaction Institute Carnegie Mellon University Department of Computer Science University of Illinois Urbana-Champaign

ISBN: (纸本)1595931783

computer displays can be helpful for making users aware of the remote presence of friends and family. In many of the research projects that have explored the use of novel displays, the real goal is to improve a user's sense of connectedness to those remote loved ones. However, very few have leveraged a user-centered design process or empirically studied the effects of using a display on users' sense of awareness and connectedness. In this paper, we present our multi-phase, user-centered design process for building displays that support awareness and connectedness: Presence Displays, which are physical, peripheral awareness displays of online presence of close friends or family. We present evidence, from a 5-week long field study, that these displays provide significantly better awareness of and connectedness to a loved one, than a traditional graphical display of online presence. Copyright 2006 ACM.

关键词： Display devices

来源：评论

学校读者我要写书评

暂无评论

Social discovery framework: Building capacity and seeking solutions 11

Social discovery framework: Building capacity and seeking so...

引用

8th ACM Conference on Creativity and Cognition, C and C 2011

作者： Shneiderman, Ben Department of Computer Science and Human-Computer Interaction Lab University of Maryland College ParkMD United States

ISBN: (纸本)9781450308205

While journalists often portray discovery as the thrilling insight of a brilliant individual, many discoveries require years of work by competing and collaborating teams. Often large amounts of foundational work are necessary and dialogs among participants help clarify goals. The Social Discovery Framework suggests that (1) there are important processes in building capacity and then seeking solutions and (2) those that initiate requests are often as important as those who seek solutions. The implications of the Social Discovery Framework are that improved social tools to build capacity, initiate requests, and support dialog would accelerate the discovery process as much as the more visible tools for individuals seeking solutions. Copyright 2011 ACM.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Product-based learning in software engineering education

Product-based learning in software engineering education

引用

39th Annual Frontiers in Education Conference: Imagining and Engineering Future CSET Education, FIE 2009

作者： Ragan, Eric D. Frezza, Stephen Cannell, Jeremy Center for Human-Computer Interaction Department of Computer Science Virginia Tech United States Computer and Information Science Department Gannon University United States Computer and Information Science Department United Kingdom

ISBN: (纸本)9781424447152

Problem-based learning is a pedagogy that employs open-ended problems as a means of increasing student motivation and interaction in addition to achieving the intended educational goals. We present product-based learning as an extension of collaborative problem-based learning by focusing on the design and development of a product as a solution to a proposed problem. In this approach, the instructor becomes an active member of the project team, working with the students to achieve the product vision. Through this method, students take control of their own learning while working together towards group success. Such a course design allows students to become active learners in achieving learning objectives, while at the same time providing project management and team-working experience. We explain the concept of product-based learning and demonstrate the process through the design and development of an educational software application. This project shows that the product-based method can promote positive attitudes, social interaction, and intentional learning in students while motivating them to achieve the intended learning objectives. ©2009 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Who Blocks Who: Simultaneous Segmentation of Occluded Objects

引用

Journal of computer science & Technology 2013年第5期28卷 890-906页

作者：王楠艾海舟汤锋 Department of Computer Science and Technology Tsinghua University Multimedia Interaction and Understanding Lab HP Labs

In this paper we present a simultaneous segmentation algorithm for multiple highly-occluded objects, which combines high-level knowledge and low-level information in a unified framework. The high-level knowledge provides sophis- ticated shape priors with the consideration of blocking relationship between nearby objects. Different from conventional layered model which attempts to solve the full ordering problem, we decompose the problem into a series of pairwise ones and this makes our algorithm scalable to a large number of objects. Objects are segmented in pixel level with higher-order soft constraints from superpixels, by a dual-level conditional random field. The model is optimized alternately by object layout and pixel-wise segmentation. V^e evaluate our system on different objects, i.e., clothing and pedestrian, and show impressive segmentation results and significant improvement over state-of-the-art segmentation algorithms.

关键词： object segmentation occlusion reasoning object graph conditional random field random forest,

来源：评论

学校读者我要写书评

暂无评论

Integrating HRV and Activity Data for ADHD Classification Using Machine Learning Methodologies 10th

Integrating HRV and Activity Data for ADHD Classification Us...

引用

10th International Conference on Health Informatics and Medical Systems, HIMS 2024 and 10th International Conference on Biomedical Engineering, BIOENG 2024, held as part of the World Congress in computer science, computer Engineering and Applied Computing, CSCE 2024

作者： Ji, Yanqing Zhang-Lea, Janet Tran, John Department of Electrical and Computer Engineering Gonzaga University SpokaneWA99258 United States Department of Human Physiology University of Oregon EugeneOR97403 United States Department of Psychiatry and Behavioral Science University of California San Francisco FresnoCA93701 United States

ISBN: (纸本)9783031859076

This study explores reliable approaches to identifying Attention-Deficit/Hyperactivity Disorder (ADHD), a neurodevelopmental condition impacting various aspects of life. While traditionally diagnosed through subjective clinical evaluation, this work examines the integration of sensory data and machine learning techniques for more objective ADHD detection. Investigating diverse machine learning algorithms, including Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), LightGBM (LGBM), Neural Network (NN), and Support Vector Machine (SVM), the research analyzes both activity and heart rate variability (HRV) data from a dataset of 103 participants. Results indicate comparable performance between activity and HRV data individually, with notable improvement seen in a combined dataset. The SVM model emerges as the top performer, achieving an F1-Score of 0.87 and a Matthews Correlation Coefficient of 0.77. This study underscores the great potential of interdisciplinary collaboration and diverse data resources in advancing ADHD detection through innovative machine learning techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Evolvable dialogue state tracking for statistical dialogue management

引用

Frontiers of computer science 2016年第2期10卷 201-215页

作者： Kai YU Lu CHEN Kai SUN Qizhe XIE Su ZHU Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive EngineeringSpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China Department of Computer Science Cornell University Ithaca NY 14853 USA

Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking （DST） is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges （DSTC） have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. This makes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.

关键词： dialogue management domain extension,evolvable dialogue state tracking parser tracker

来源：评论

学校读者我要写书评

暂无评论

Effects of navigation design on Contextualized Video Interfaces

Effects of navigation design on Contextualized Video Interfa...

引用

IEEE Symposium on 3D User Interfaces

作者： Wang, Yi Bowman, Doug A. Dept. of Computer Science Center for Human-Computer Interaction Virginia Tech United States

ISBN: (纸本)9781457700620

Real-time monitoring and responding to events observed across multiple surveillance cameras can pose an overwhelmingly high mental workload. Contextualized Video Interfaces (which place the surveillance videos within their spatial context) can be used to support these tasks. In order for users to integrate information from the videos and the spatial context as the events progress in real time, navigation interfaces are required. However, different tasks seem to favor different navigation techniques. In this paper, we describe the formal evaluation of four navigation designs for Contextualized Video Interfaces. The four designs arise from the consideration of two important factors of navigation techniques: navigation mode (manual or semi-automatic) and navigation context (overview or detailed view). To avoid a piecemeal understanding of the navigation techniques, we evaluated them using three tasks that have different information requirements. While semi-automatic navigation was generally preferable, low-DOF manual navigation techniques were found to be useful in certain situations. The choice between overview navigation and detailed-view navigation depends primarily on the user's information requirement in the task. Based on the findings, we provide guidelines on how to select designs according to task features. © 2011 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Technology for Older People: A Critical Review

Technology for Older People: A Critical Review

引用

作者： Petrie, Helen Gallagher, Bláithín Darzentas, Jenny Human Computer Interaction Research Group Department of Computer Science University of York United Kingdom University of the Aegean Greece

We will present the results of a critical review of research published in a range of peer-reviewed conferences in the period 2005 - 2012 on the use of technology to support older people. We explore what problems faced by older people are being addressed by the research;whether the research is motivated by user needs;the methodologies used;the levels of target user involvement in the research;and the outcomes achieved. Eight major topics of research have been identified: mobility and wayfinding;communication and social interaction;interaction with technology;using the web;access to and exploration of information;education;support for daily living;and games and play. In addition, we have categorized the research into four main types: research that proposes technologies for older people;research to understand the use of technology by older people and their attitudes to technology;research on guidelines, standards or other information to support developers and researchers;and research that on methodologies for working with older people in the development of new technological solutions. Important gaps and weaknesses in the current research portfolio are explored. The review will provide an overview of the state of the art of technologies for promoting independent living and wellbeing of older people, which should be useful for researchers, developers and practitioners in the field. © Springer International Publishing Switzerland 2014.

关键词： Engineering education

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：