检索结果-内蒙古大学图书馆

Mood Recognition during Online Self-Assessment Tests

IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES 2009年第1期2卷 50-61页

作者： Moridis, Christos N. Economides, Anastasios A. Univ Macedonia Dept Informat Syst Thessaloniki 54006 Greece Univ Macedonia Dept Informat Syst Thessaloniki 54006 Greece

Individual emotions play a crucial role during any learning interaction. Identifying a student's emotional state and providing personalized feedback, based on integrated pedagogical models, has been considered to be one of the main limits of traditional tools of e-learning. This paper presents an empirical study that illustrates how learner mood may be predicted during online self-assessment tests. Here, a previous method of determining student mood has been refined based on the assumption that the influence on learner mood of questions already answered declines in relation to their distance from the current question. Moreover, this paper sets out to indicate that "exponential logic" may help produce more efficient models if integrated adequately with affective modeling. The results show that these assumptions may prove useful to future research.

关键词： Computer uses in education education human-centered computing human information processing personalization self-assessment Web-based interaction

来源：评论

学校读者我要写书评

暂无评论

HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2021年第2期27卷 1407-1416页

作者： Park, Heungseok Nam, Yoonsoo Kim, Ji-Hoon Choo, Jaegul NAVER Corp Clara AI Res Seongnam Si South Korea Korea Adv Inst Sci & Technol Daejeon South Korea

To mitigate the pain of manually tuning hyperparameters of deep neural networks, automated machine learning (AutoML) methods have been developed to search for an optimal set of hyperparameters in large combinatorial search spaces. However, the search results of AutoML methods significantly depend on initial configurations, making it a non-trivial task to find a proper configuration. Therefore, human intervention via a visual analytic approach bears huge potential in this task. In response, we propose HyperTendril, a web-based visual analytics system that supports user-driven hyperparameter tuning processes in a model-agnostic environment. HyperTendril takes a novel approach to effectively steering hyperparameter optimization through an iterative, interactive tuning procedure that allows users to refine the search spaces and the configuration of the AutoML method based on their own insights from given results. Using HyperTendril, users can obtain insights into the complex behaviors of various hyperparameter search algorithms and diagnose their configurations. In addition, HyperTendril supports variable importance analysis to help the users refine their search spaces based on the analysis of relative importance of different hyperparameters and their interaction effects. We present the evaluation demonstrating how HyperTendril helps users steer their tuning processes via a longitudinal user study based on the analysis of interaction logs and in-depth interviews while we deploy our system in a professional industrial environment.

关键词： Visual analytics deep learning machine learning automated machine learning human-centered computing

来源：评论

学校读者我要写书评

暂无评论

The Importance of Worker Reputation Information in Microtask-Based Crowd Work Systems

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2017年第2期28卷 558-571页

作者： Tarable, Alberto Nordio, Alessandro Leonardi, Emilio Ajmone Marsan, Marco CNR IEIIT Turin Italy Politecn Torino Dept Elect & Telecommun Turin Italy IMDEA Networks Inst Leganes Madrid Spain

This paper presents the first systematic investigation of the potential performance gains for crowd work systems, deriving from available information at the requester about individual worker reputation. In particular, we first formalize the optimal task assignment problem when workers' reputation estimates are available, as the maximization of a monotone (submodular) function subject to Matroid constraints. Then, being the optimal problem NP-hard, we propose a simple but efficient greedy heuristic task allocation algorithm. We also propose a simple "maximum a-posteriori" decision rule and a decision algorithm based on message passing. Finally, we test and compare different solutions, showing that system performance can greatly benefit from information about workers' reputation. Our main findings are that: i) even largely inaccurate estimates of workers' reputation can be effectively exploited in the task assignment to greatly improve system performance;ii) the performance of the maximuma-posteriori decision rule quickly degrades as worker reputation estimates become inaccurate;iii) when workers' reputation estimates are significantly inaccurate, the best performance can be obtained by combining our proposed task assignment algorithm with the message-passing decision algorithm.

关键词： human-centered computing human information processing systems and information theory

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Effects of Virtual Reality Environment Learning on Subsequent Robot Teleoperation in an Unfamiliar Building

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2023年第5期29卷 2220-2229页

作者： Eisentrager, Karl Haubner, Judith Brade, Jennifer Einhauser, Wolfgang Bendixen, Alexandra Winkler, Sven Klimant, Philipp Jahn, Georg Humboldt Univ Berlin Germany Tech Univ Chemnitz Chemnitz Germany

Using a map in an unfamiliar environment requires identifying correspondences between elements of the map's allocentric representation and elements in egocentric views. Aligning the map with the environment can be challenging. Virtual reality (VR) allows learning about unfamiliar environments in a sequence of egocentric views that correspond closely to the perspectives and views that are experienced in the actual environment. We compared three methods to prepare for localization and navigation tasks performed by teleoperating a robot in an office building: studying a floor plan of the building and two forms of VR exploration. One group of participants studied a building plan, a second group explored a faithful VR reconstruction of the building from a normal-sized avatar's perspective, and a third group explored the VR from a giant-sized avatar's perspective. All methods contained marked checkpoints. The subsequent tasks were identical for all groups. The self-localization task required indication of the approximate location of the robot in the environment. The navigation task required navigation between checkpoints. Participants took less time to learn with the giant VR perspective and with the floorplan than with the normal VR perspective. Both VR learning methods significantly outperformed the floorplan in the orientation task. Navigation was performed quicker after learning in the giant perspective compared to the normal perspective and the building plan. We conclude that the normal perspective and especially the giant perspective in VR are viable options for preparing for teleoperation in unfamiliar environments when a virtual model of the environment is available.

关键词： Navigation Buildings Task analysis Robots Avatars Floors Virtual environments human computer interaction (HCI) human-centered computing virtual reality human factors teleoperation robot

来源：评论

学校读者我要写书评

暂无评论

Efficient Decoding of Affective States from Video-elicited EEG Signals: An Empirical Investigation

引用

ACM TRANSACTIONS ON MULTIMEDIA computing COMMUNICATIONS AND APPLICATIONS 2024年第10期20卷 1-24页

作者： Latifzadeh, Kayhan Gozalpour, Nima Traver, V. Javier Ruotsalo, Tuukka Kawala-Sterniuk, Aleksandra Leiva, Luis A. Univ Luxembourg Esch Sur Alzette Luxembourg Univ Jaume 1 INIT Castellon de la Plana Spain Univ Copenhagen Copenhagen Denmark LUT Univ Lahti Finland Opole Univ Technol Opole Poland

Affect decoding through brain-computer interfacing (BCI) holds great potential to capture users' feelings and emotional responses via non-invasive electroencephalogram (EEG) sensing. Yet, little research has been conducted to understand efficient decoding when users are exposed to dynamic audiovisual contents. In this regard, we study EEG-based affect decoding from videos in arousal and valence classification tasks, considering the impact of signal length, window size for feature extraction, and frequency bands. We train both classic Machine Learning models (SVMs and k-NNs) and modern Deep Learning models (FCNNs and GTNs). Our results show that: (1) affect can be effectively decoded using less than 1 minute of EEG signal;(2) temporal windows of 6 and 10 seconds provide the best classification performance for classic Machine Learning models but Deep Learning models benefit from much shorter windows of 2 seconds;and (3) any model trained on the Beta band alone achieves similar (sometimes better) performance than when trained on all frequency bands. Taken together, our results indicate that affect decoding can work in more realistic conditions than currently assumed, thus becoming a viable technology for creating better interfaces and user models.

关键词： human-centered computing User models Ambient intelligence computing methodologies Machine learning approaches

来源：评论

学校读者我要写书评

暂无评论

Automated recognition of hypertension through overnight continuous HRV monitoring

引用

JOURNAL OF AMBIENT INTELLIGENCE AND humanIZED computing 2018年第6期9卷 2011-2023页

作者： Ni, Hongbo Cho, Sunyoung Mankoff, Jennifer Yang, Jun Dey, Anind k. Northwestern Polytech Univ Sch Comp Sci Xian Shaanxi Peoples R China Carnegie Mellon Univ Pittsburgh PA 15213 USA Beijing Aviat Med Inst Beijing Peoples R China

Hypertension is a common and chronic disease, caused by high blood pressure. Since hypertension often has no warning signs or symptoms, many cases remain undiagnosed. Untreated or sub-optimally controlled hypertension may lead to cardiovascular, cerebrovascular and renal morbidity and mortality, along with dysfunction of the autonomic nervous system. Therefore, it could be quite valuable to predict or provide early warnings about hypertension. Heart rate variability (HRV) analysis has emerged as the most valuable non-invasive test to assess autonomic nervous system function, and has great potential for detecting hypertension. However, HRV indicators may be subtle and present at random, resulting in two challenges: how to support continuous monitoring for hours at a time while being unobtrusive, and how to efficiently analyze the collected data to minimize data collection and user burden. In this paper, we present a machine learning-based approach for detecting hypertension, using a waist belt continuous sensing system that is worn overnight. Using 24 hypertension patients and 24 healthy controls, we demonstrate that our approach can differentiate hypertension patients from healthy controls with 93.33% accuracy. This represents a promising approach for performing hypertension classification in the field, and also we would improve its performance based on a large number of hypertensive subjects monitored by the proposed pervasive sensors.

关键词： human-centered computing Ubiquitous computing computing methodologies Machine learning Electrocardiogram Pyramid methods Healthcare Heart rate sensing

来源：评论

学校读者我要写书评

暂无评论

High dietary inflammatory index scores are associated with an elevated risk of hepatocellular carcinoma in a case-control study

引用

FOOD & FUNCTION 2018年第11期9卷 5832-5842页

作者： Wang, Xiao-Yan Fang, Ai-Ping Chen, Pei-Yan Liao, Gong-Cheng Zhang, Yao-Jun Shivappa, Nitin Hebert, James R. Chen, Yu-Ming Zhu, Hui-Lian Sun Yat Sen Univ Sch Publ Hlth Dept Nutr Guangzhou 510080 Guangdong Peoples R China Guangdong Prov Key Lab Food Nutr & Hlth Guangzhou 510080 Guangdong Peoples R China Sun Yat Sen Univ Ctr Canc Dept Hepatobiliary Surg Guangzhou 510060 Guangdong Peoples R China Univ South Carolina Arnold Sch Publ Hlth Dept Epidemiol & Biostat Columbia SC 29208 USA Univ South Carolina Canc Prevent & Control Program Columbia SC 29208 USA Connecting Hlth Innovat LLC Columbia SC 29201 USA

Chronic inflammation and diet play crucial roles in the development of hepatocellular carcinoma (HCC);yet the association between dietary inflammatory potential and risk of HCC has rarely been investigated. This study aimed to examine whether a higher dietary inflammatory index (DII (R)) score (indicating a pro-inflammatory diet) is associated with an increased risk of HCC in a matched case-control study conducted between September 2013 and October 2017 in South China. A total of 659 cases with newly diagnosed, previously untreated HCC and 659 controls individually matched on age (+/- 3 years) and sex were included in this study. DII scores were computed based on dietary intake information collected via a validated 79-item food frequency questionnaire (FFQ) during the one year prior to diagnosis (for the cases) or interview (for the controls). Logistic regression was used to estimate the odds ratio (OR) and 95% confidence interval (CI) between the DII score and the risk of HCC, adjusted for age, energy intake, body mass index, physical activity, marital status, education, household income, smoking status, and hepatitis B virus (HBV) infection status. Compared with subjects in the lowest DII tertile, subjects in the highest tertile had an elevated risk of HCC (fully adjusted OR: 3.22, 95% CI: 1.30-7.98, P-trend = 0.009). In stratified analyses, a significantly positive association was observed only in men, individuals with lower education level, smokers and non-alcohol drinkers. In conclusion, a higher DII score, representing a more inflammatory diet, was associated with an increased risk of HCC, in men, individuals with lower education level, smokers and non-alcohol drinkers.

关键词： Hepatocellular Cancer Matched Case-Control Studies human-centered computing Case-Control Studies

来源：评论

学校读者我要写书评

暂无评论

Predictive side decoding for human-centered multiple description image coding

引用

EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING 2020年第1期2020卷 1-14页

作者： Xu, Yuanyuan Hohai Univ Coll Comp & Informat 8 Fo Cheng Rd Nanjing Peoples R China

Multiple description coding (MDC) provides a favorable solution for human-centered image communication, which takes into account people's varying watching situations as well as people's demand for real-time image display. As an effective technique for MDC, three-description lattice vector quantization (3D-LVQ) is considered for image coding in this paper. Based on intra- and inter-correlation in the 3D-LVQ index assignment as well as wavelet intra-subband correlation, a novel predictive decoding method for 3D-LVQ-based image coding is proposed to enhance side decoding performance, which attempts to predict lost descriptions (sublattice points) in a good way for better reconstructions of wavelet vectors (fine lattice points) in the side decoding. Experimental results validate effectiveness of the proposed decoding scheme in terms of rate-distortion performance.

关键词： Image coding human-centered computing Multiple description coding Lattice vector quantization

来源：评论

学校读者我要写书评

暂无评论

Programmers Are Users Too: human-centered Methods for Improving Programming Tools

引用

COMPUTER 2016年第7期49卷 44-52页

作者： Myers, Brad A. Ko, Andrew J. LaToza, Thomas D. Yoon, YoungSeok Carnegie Mellon Univ Human Comp Interact Inst Sch Comp Sci Pittsburgh PA 15213 USA Univ Washington Informat Sch Seattle WA 98195 USA Univ Washington Comp Sci & Engn Dept Seattle WA 98195 USA George Mason Univ Comp Sci Volgenau Sch Engn Fairfax VA 22030 USA Google Mountain View CA USA

human-centered methods can help researchers better understand and meet programmers’ needs. Because programming is a human activity, many of these methods can be used without change. However, some programmer needs require new methods, which can also be applied to domains other than software engineering. This article features five Web extras. The video at https://***/4PH9-qi-yTQ demonstrates Azurite, an Eclipse plug-in with a selective undo feature that lets programmers more easily backtrack their code. The video at https://***/gOSlR62-rd8 describes Graphite, an Eclipse plug-in offering active code completion, a simple but powerful technique that integrates useful code-generation tools directly into the editor. The video at https://***/zyrqcYxqDtI describes HANDS, a new programming system that emphasizes usability by building on children’s and beginning programmers’ natural problem-solving tendencies. The video extra at https://***/80EctbI7PFc describes Whyline, a debugging tool that lets developers ask questions about their program’s output and behavior. The video at https://***/3L4MK2dG_6k demonstrates the prototype for Whyline, a debugging tool that lets developers pose questions about their program’s output.

关键词： Java program debugging software tools user centred design Azurite Eclipse plug-in Graphite HANDS Whyline active code completion debugging tool human activity human-centered methods natural problem-solving tendencies programming tools software engineering undo feature Data mining human computer interaction human-centered computing human-computer interaction Natural language processing Programming Software engineering A/B testing HCI contextual inquiry data mining end-user software engineering evaluation studies exploratory lab studies human-centered computing human-computer interaction log analysis natural-programming elicitation rapid prototyping software development software engineering software psychology studies of program constructs think-aloud usability evaluation user interfaces

来源：评论

学校读者我要写书评

暂无评论

Consolidation of Usability Problems With Novice Evaluators Re-Examined in Individual vs. Collaborative Settings

引用

INTERACTING WITH COMPUTERS 2019年第6期31卷 525-538页

作者： Hoffmann, Rebekka Jonsdottir, Anna Helga Hvannberg, Ebba Thora Univ Iceland Fac Psychol Sch Hlth Sci Reykjavik Iceland Univ Iceland Fac Ind Engn Mech Engn & Comp Sci Sturlugata 3 IS-102 Reykjavik Iceland Univ Iceland Fac Phys Sci Sch Engn & Nat Sci Dunhaga 5 IS-107 Reykjavik Iceland Univ Iceland Sch Engn & Nat Sci Fac Ind Engn Mech Engn & Comp Sci Dunhaga 5 IS-107 Reykjavik Iceland

Usability testing can involve multiple users and evaluators. In such cases, consolidating usability problems (UPs) constitutes an essential part of data analysis. In a between-subjects design, this study aims to re-examine a previous study by comparing the results of novice evaluators merging UPs individually vs. collaboratively and to assess the quality of the final UP lists, by computing the merging rate and the accuracy rate, respectively. Law and Hvannberg compared the results of evaluators merging UPs individually vs. collaboratively in a within-subjects design, revealing a tendency towards merging UPs in collaborative settings. In the present study, 45 novice evaluators consolidated four UP lists into a single UP master list while working alone or with a partner. The results showed no significant difference between evaluators in the two settings, suggesting that the UP consolidation process does not benefit from positive group decision effects. RESEARCH HIGHLIGHTS Based on a between-subjects design, the study results indicate no difference in merging rate or quality of consolidation output between novice evaluators consolidating individually or collaboratively. Working together neither helps nor impairs novices during the consolidation activity. The study showed that collaborative UP consolidation takes more time than individual consolidation without resulting in higher quality. Thus, investing in more manpower of novices does not appear to be beneficial. According to group performance models, the lack of performance gains in the collaborative setting, as found in the current study, could stem partly from the use of participants with little evaluation experience.

关键词： usability testing HCI design and evaluation methods usability problems consolidation group decision effects evaluator effect human-centered computing

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：