检索结果-内蒙古大学图书馆

From EEG to Eye Movements: Cross-modal Emotion Recognition Using Constrained Adversarial Network with Dual Attention

引用

IEEE Transactions on Affective Computing 2024年

作者： Wang, Yiting Liu, Jia-Wen Lu, Bao-Liang Zheng, Wei-Long Karolinska Institutet Department of Clinical Neuroscience Stockholm171 77 Sweden Shanghai Jiao Tong University China Shanghai Jiao Tong University Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai200240 China Shanghai Jiao Tong University School of Medicine RuiJin-Mihoyo Laboratory Clinical Neuroscience Center RuiJin Hospital Shanghai200020 China Shanghai Emotionhelper Technology Co. Ltd. Shanghai China

Emotion recognition is a fundamental part of affective computing, obtaining performance gain from multimodal methods. Electroencephalography (EEG) and eye movements are extensively used as they contain complementary information. However, the inconvenient acquisition of EEG is hindering the extensive adoption of multimodal emotion recognition in daily applications while eye movements are more convenient to collect but with lower performance. To tackle this issue, we propose a Constrained Adversarial Network with Dual Attention (CANDA), exploiting the complementary information from multiple modalities during training to improve the test-time performance of single easily acquired modality, i.e., transferring knowledge from a stronger modality to a weaker modality. During training, a common joint space is learned to diminish the distribution discrepancy among different modalities and incorporate the multimodal representations. During test, single modality is converted to the common space achieving comparable performance to multiple modalities. Extensive experiments demonstrate that our model achieves the state-of-the-art performance for cross-modal emotion recognition. Specifically, the mean accuracy increases around 15% on SEED, 15% on SEED-IV, and 2% on SEED-V compared to the latest baseline for emotion recognition. Visualization of features in the joint space illustrates that the distribution of different modalities aligns together with the discriminative ability regarding various emotions. © 2010-2012 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

The Definitions of Health Apps and Medical Apps From the Perspective of Public Health and Law: Qualitative Analysis of an Interdisciplinary Literature Overview

引用

JMIR mHealth and uHealth 2022年第10期10卷 e37980-e37980页

作者： Maaß, Laura Freye, Merle Pan, Chen-Chia Dassow, Hans-Henrik Niess, Jasmin Jahnel, Tina Department of Health Long-Term Care and Pensions Research Center on Inequality and Social Policy University of Bremen Bremen Germany Leibniz ScienceCampus Digital Public Health Bremen Germany Institute for Information Health and Medical Law University of Bremen Bremen Germany Unit of Lifestyle-Related Disorders Department of Epidemiological Methods and Etiological Research Leibniz Institute for Prevention and Epidemiology Bremen Germany Department of Prevention and Health Promotion Institute for Public Health and Care Research University of Bremen Bremen Germany Institute for Philosophy University of Bremen Bremen Germany Human Computer Interaction Research Group Institute of Computer Science University of St. Gallen St. Gallen Switzerland Department of Health Services Research Institute for Public Health and Care Research University of Bremen Bremen Germany

Background: The terms health app and medical app are often used interchangeably but do not necessarily mean the same thing. To better understand these terms and better regulate such technologies, we need distinct definitions of health and medical apps. Objective: This study aimed to provide an overview of the definitions of health and medical apps from an interdisciplinary perspective. We summarized the core elements of the identified definitions for their holistic understanding in the context of digital public health. Methods: The legal frameworks for medical device regulation in the United States, the European Union, and Germany formed the basis of this study. We then searched 6 databases for articles defining health or medical apps from an interdisciplinary perspective. The narrative literature review was supported by a forward and backward snowball search for more original definitions of health and medical apps. A qualitative analysis was conducted on the identified relevant aspects and core elements of each definition. On the basis of these findings, we developed a holistic definition of health and medical apps and created a decision flowchart to highlight the differences between the 2 types. Results: The legal framework showed that medical apps could be regulated as mobile medical devices, whereas there is no legal term for health apps. Our narrative literature review identified 204 peer-reviewed publications that offered a definition of health and medical apps. After screening for original definitions and applying the snowball method, 11.8% (24/204) of the publications were included in the qualitative analysis. Of these 24 publications, 22 (88%) provided an original definition of health apps and 11 (44%) described medical apps. The literature suggests that medical apps are a part of health apps. To describe health or medical apps, most definitions used the user group, a description of health, the device, the legal regulation, collected data, or technological

关键词： DiGA digital care applications digital health digital health applications DiPA health app medical app mobile health mobile medical device mobile phone regulation snowball search

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AI

arXiv

引用

arXiv 2024年

作者： Zhang, Liang Lin, Jionghao Sabatini, John Borchers, Conrad Weitekamp, Daniel Cao, Meng Hollander, John Hu, Xiangen Graesser, Arthur C. Institute for Intelligent Systems University of Memphis MemphisTN38152 United States Arkansas State University JonesboroAR72401 United States Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA15213 United States Faculty of Education The University of Hong Kong Hong Kong Centre for Learning Analytics Faculty of Information Technology Monash University ClaytonVIC3800 Australia Department of Applied Social Sciences Hong Kong Polytechnic University Hong Kong

Learning performance data, such as correct or incorrect answers and problem-solving attempts in Intelligent Tutoring Systems (ITSs), facilitate the assessment of knowledge mastery and the delivery of effective instructions. However, these data tend to be highly sparse (80%∼90% missing observations) in most real-world applications. This data sparsity presents challenges to using learner models to effectively predict learners’ future performance and explore new hypotheses about learning. This article proposes a systematic framework for augmenting learning performance data to address data sparsity. First, learning performance data can be represented as a 3-Dimensional (3D) tensor with dimensions corresponding to learners, questions, and attempts, effectively capturing longitudinal knowledge states during learning. Second, a tensor factorization method is used to impute missing values in sparse tensors of collected learner data, thereby grounding the imputation on knowledge tracing tasks that predict missing performance values based on real observations. Third, data augmentation using Generative Artificial Intelligence (GenAI) models, including Generative Adversarial Network, specifically Vanilla Generative Adversarial Networks (GAN), and Generative Pretrained Transformers (GPT, specifically GPT-4o), generate data tailored to individual clusters of learning performance. We tested this systemic framework on adult literacy datasets from AutoTutor lessons developed for Adult Reading Comprehension (ARC). We found that: (1) tensor factorization outperformed baseline knowledge tracing techniques in tracing and predicting learning performance, demonstrating higher fidelity in data imputation, and 2) the Vanilla GAN-based augmentation demonstrated greater overall stability across varying sample sizes, whereas GPT-4o based augmentation exhibited higher variability, with occasional cases showing closer fidelity to the original data distribution. This framework facilitates the eff

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Link Prediction Accuracy on Real-World Networks Under Non-Uniform Missing Edge Patterns

arXiv

引用

arXiv 2024年

作者： He, Xie Ghasemian, Amir Lee, Eun Schwarze, Alice C. Clauset, Aaron Mucha, Peter J. The Department of Mathematics Dartmouth College HanoverNH03755 United States The Human Nature Lab Yale University CT06520 United States The Computational Social Science Lab The University of Pennsylvania PA19104 United States The Department of Scientific Computing Pukyong National University Busan Korea Republic of The Department of Computer Science The BioFrontiers Institute The University of Colorado BoulderCO80309 United States The Santa Fe Institute Santa FeNM87501 United States

Real-world network datasets are typically obtained in ways that fail to capture all edges. The patterns of missing data are often non-uniform as they reflect biases and other shortcomings of different data collection methods. Nevertheless, uniform missing data is a common assumption made when no additional information is available about the underlying missing-edge pattern, and link prediction methods are frequently tested against uniformly missing edges. To investigate the impact of different missing-edge patterns on link prediction accuracy, we employ 9 link prediction algorithms from 4 different families to analyze 20 different missing-edge patterns that we categorize into 5 groups. Our comparative simulation study, spanning 250 real-world network datasets from 6 different domains, provides a detailed picture of the significant variations in the performance of different link prediction algorithms in these different settings. With this study, we aim to provide a guide for future researchers to help them select a link prediction algorithm that is well suited to their sampled network data, considering the data collection process and application domain. © 2024, CC BY.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Empowering Caregivers of People Living with Dementia to Use Music Therapeutically at Home: Design Opportunities 20

Empowering Caregivers of People Living with Dementia to Use ...

引用

Proceedings of the 32nd Australian Conference on human-computer interaction

作者： Romina Carrasco Felicity A. Baker Anna A. Bukowska Imogen N. Clark Libby M. Flynn Kate McMahon Helen Odell-Miller Karette Stensaeth Jeanette Tamplin Tanara Vieira Sousa Jenny Waycott Thomas Wosch Human-Computer Interaction Group The University of Melbourne Australia Music Therapy Faculty of Fine Arts and Music The University of Melbourne Australia Department of Occupational Therapy University of Physical Education Poland Cambridge Institute for Music Therapy Research Anglia Ruskin University United Kingdom Centre for Research in Music and Health Norwegian Academy of Music Norway Centre for Health Policy Health Economic Unit The University of Melbourne Australia Hochschule für angewandte Wissenschaften Würzburg-Schweinfurt Germany

ISBN: (纸本)9781450389754

human-computer interaction researchers have explored how to design technologies to support people with dementia (PwD) and their caregivers, but limited attention has been given to how to facilitate music therapy in dementia care. The use of music to help manage the symptoms of dementia is often guided by a music therapist who adapts the intervention to respond to the changing needs of the person living with dementia. However, as the incidence of dementia increases worldwide, individualised therapy programs are less feasible, making it valuable to consider technology-based approaches. In this paper, we analyze data from case studies of home-based music therapy training interventions with two families. The findings show that embodied interactions supported the therapist in responding to the needs of the PwD and built an empathic environment that empowered the caregivers’ learning. We discuss opportunities and challenges for designing technologies that support family caregivers’ therapy-informed music use in dementia care.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using eye movements to determine referents in a spoken dialogue system 01

Using eye movements to determine referents in a spoken dialo...

引用

2001 Workshop on Perceptive User Interfaces, PUI 2001

作者： Campana, Ellen Baldridge, Jason Dowding, John Hockey, Beth Ann Remington, Roger W. Stone, Leland S. Department of Brain and Cognitive Sciences University of Rochester Meliora Hall RC Box 270268 RochesterNY14627 United States ICCS Division of Informatics University of Edinburgh 2 Buccleuch Place EdinburghEH8 9LW United Kingdom Research Institute for Advanced Computer Science NASA Ames Research Center Mail Stop T27-A Moffett FieldCA94035 United States Human Factors Research and Technology Division NASA Ames Research Center MS 262-4 Moffett FieldCA94035 United States Human Factors Research and Technology Division NASA Ames Research Center MS 262-2 Moffett FieldCA94035 United States

ISBN: (纸本)1581134487

Most computational spoken dialogue systems take a "literary" approach to reference resolution. With this type of approach, entities that are mentioned by a human interactor are unified with elements in the world state based on the same principles that guide the process during text interpretation. In human-to-human interaction, however, referring is a much more collaborative process. Participants often under-specify their referents, relying on their discourse partners for feedback if more information is needed to uniquely identify a particular referent. By monitoring eye-movements during this interaction, it is possible to improve the performance of a spoken dialogue system on referring expressions that are underspecified according to the literary model. This paper describes a system currently under development that employs such a strategy. Copyright © 2001 ACM.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

The micro-randomized trial for developing digital interventions: Data analysis methods

arXiv

引用

arXiv 2020年

作者： Qian, Tianchen Russell, Michael A. Collins, Linda M. Klasnja, Predrag Lanza, Stephanie T. Yoo, Hyesun Murphy, Susan A. Department of Statistics Harvard University Methodology Center Department of Biobehavioral Health Pennsylvania State University Methodology Center Department of Human Development & Family Studies Pennsylvania State University School of Information University of Michigan Kaiser Permanente Washington Health Research Institute Edna Bennett Pierce Prevention Research Center Department of Biobehavioral Health Pennsylvania State University Department of Statistics University of Michigan Departments of Statistics and Computer Science Harvard University

Although there is much excitement surrounding the use of mobile and wearable technology for the purposes of delivering interventions as people go through their day-to-day lives, data analysis methods for constructing and optimizing digital interventions lag behind. Here, we elucidate data analysis methods for primary and secondary analyses of micro-randomized trials (MRTs), an experimental design to optimize digital just-in-time adaptive interventions. We provide a definition of causal "excursion" effects suitable for use in digital intervention development. We introduce the weighted and centered least-squares (WCLS) estimator which provides consistent causal excursion effect estimators for digital interventions from MRT data. We describe how the WCLS estimator along with associated test statistics can be obtained using standard statistical software such as SAS (SAS Institute Inc., 2019) or R (R Core Team, 2019). Throughout we use HeartSteps, an MRT designed to increase physical activity among sedentary individuals, to illustrate potential primary and secondary analyses. Copyright © 2020, The Authors. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Multimodal emotion recognition using deep canonical correlation analysis

arXiv

引用

arXiv 2019年

作者： Liu, Wei Qiu, Jie-Lin Zheng, Wei-Long Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai200240 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Neurology Massachusetts General Hospital Harvard Medical School BostonMA02114 United States

Multimodal signals are more powerful than unimodal data for emotion recognition since they can represent emotions more comprehensively. In this paper, we introduce deep canonical correlation analysis (DCCA) to multimodal emotion recognition. The basic idea behind DCCA is to transform each modality separately and coordinate different modalities into a hyperspace by using specified canonical correlation analysis constraints. We evaluate the performance of DCCA on five multimodal datasets: the SEED, SEED-IV, SEED-V, DEAP, and DREAMER datasets. Our experimental results demonstrate that DCCA achieves state-of-the-art recognition accuracy rates on all five datasets: 94.58% on the SEED dataset, 87.45% on the SEED-IV dataset, 84.33% and 85.62% for two binary classification tasks and 88.51% for a four-category classification task on the DEAP dataset, 83.08% on the SEED-V dataset, and 88.99%, 90.57%, and 90.67% for three binary classification tasks on the DREAMER dataset. We also compare the noise robustness of DCCA with that of existing methods when adding various amounts of noise to the SEED-V dataset. The experimental results indicate that DCCA has greater robustness. By visualizing feature distributions with t-SNE and calculating the mutual information between different modalities before and after using DCCA, we find that the features transformed by DCCA from different modalities are more homogeneous and discriminative across emotions. Copyright © 2019, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Coverage and Depth of Transcriptome by RNA-Seq in Chickens

Evaluation of Coverage and Depth of Transcriptome by RNA-Seq...

引用

第五届中国畜牧科技论坛

作者： Wang Ying Noushin Ghaffari Charles D.Johnson Ulisses M.Braga-Neto Wang Hui Chen Rui Zhou Huai-jun Department of Poultry Science Texas A&M University College StationTX 77843-2472USA AgriLife Genomics and Bioinformatics Services Texas A&M UniversityCollege StationTX 77843-2312USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege StationTX 77843USA Department of Molecular and Human Genetics Baylor College of MedicineHoustonTX 77030USA Department of Poultry Science exas A &M University College StationTX 77843-2472USA

Background RNA-Seq is the recently developed high-throughput sequencing technology for profiling the entire transcriptome in any *** has several major advantages over current hybridizationbased approach such as ***,the cost per sample by RNA-Seq is still prohibitive for most *** continued improvement in sequence output,it would be cost-effective if multiple samples are multiplexed and sequenced in a single lane with sufficient transcriptome *** objective of this analysis is to evaluate what coverage might be sufficient to interrogate gene expression profiling in the chicken by *** Two cDNA libraries from chicken lungs were sequenced early,and 4.9 million(M) and 1.6 M(60 bp) reads were generated,*** significant improvements in sequencing technology, two technical replicate cDNA libraries were *** of 29.6 M and 28.7 M(75 bp) reads were obtained with the two *** than 90%of annotated genes were detected in the data sets with 28.7-29.6 M reads,while only 68%of genes were detected in the data set with 1.6 M *** correlation coefficients of gene expression between technical replicates within the same sample were 0.9458 and *** evaluate the appropriate depth needed for mRNA profiling,a random sampling method was used to generate different number of reads from each *** was a significant increase in correlation coefficients from a sequencing depth of 1.6 M to 10 M for all genes except highly abundant *** significant improvement was observed from the depth of 10 M to 20 M(75 bp) *** The analysis from the current study demonstrated that 30 M (75 bp) reads is sufficient to detect all annotated genes in chicken *** million(75 bp) reads could detect about 80%of annotated chicken genes,and RNA-Seq at this depth can serve as a replacement of microarray ***,the depth of sequencing had a significant impact on measuring gene ex

关键词： Evaluation of Coverage and Depth of Transcriptome by RNA-Seq in Chickens RNA

来源：评论

学校读者我要写书评

暂无评论

应用定量超声评估非酒精性脂肪肝病人的脂肪变性

引用

国际医学放射学杂志 2020年第3期 363-363页

作者： A.G.Han Y.Z.N.Zhang A.S.Boehringer V.Montes M.P.Andre J.W.Jr Erdman 李文萃 Bioacoustics Research Laboratory Department of Elec-trical and Computer Engineering and Department of Food Science and Human Nutrition University of Illinois at Urbana -Champaign

摘要先进的混杂-校正化学位移编码MRI衍生质子密度脂肪分数(PDFF)是非酒精性脂肪肝(NAFLD)脂肪分数量化的主要参数。由于这种MRI技术效能有限,因此有必要开

关键词：

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：