检索结果-内蒙古大学图书馆

Non-Visual Interfaces for Visual Learners: Multisensory learning of Graphic Primitives

IEEE ACCESS 2024年 12卷 189926-189940页

作者： Doore, Stacy A. Brown, Justin R. Imai, Saki Dimmel, Justin K. Giudice, Nicholas A. Colby Coll Dept Comp Sci INSITE Lab Waterville ME 04901 USA Univ Maine VEMI Lab Orono ME 04469 USA Northeastern Univ Khoury Coll Comp Sci Boston ME 02115 USA Univ Maine Sch Learning & Teaching IMRE Lab Orono ME 04469 USA Univ Maine Sch Comp & Informat Sci Spatial Comp Program Orono ME 04469 USA

Multimodal learning systems have been found to be effective in studies investigating cognitive theory of multimedia learning. Yet this research is rarely put into practice in Science, Technology, Engineering, and Math (STEM) learning environments, which are dominated by visual graphics. Introducing multimodal learning systems into STEM settings and allowing students to access dual channel cues beyond visual perception may help more students process information in their preferred modality. The purpose of this study was to investigate the usability, effectiveness, and design of multimodal interfaces for enhancing access to graphical representations. We used existing theories of multisensory information processing to study how sighted participants could learn and interpret spatial primitives and graphical concepts presented via three non-visual conditions: natural language (NL) descriptions, haptic renderings, and a NL-Haptic combination. The results showed that access to haptic-only renderings produced the least accurate responses, whereas NL descriptions with and without haptics led to similar performance by participants when learning graphical content without vision. Performance was also impacted by the complexity of the graphical content, with the highest level of accuracy observed for closed forms, compared to paired line segments and line/polygon intersections. We argue that universally designed, multimodal learning environments can transcend traditional, visual diagrams by utilizing non-visual channels and commercial hardware to support learners with different sensory abilities, preferences, and processing needs. Findings contribute to extending theoretical insights of non-visual information processing to better understand multisensory learning in sighted individuals.

关键词： Visualization Natural languages STEM Accuracy learning systems Force feedback Vibrations Touch sensitive screens Complexity theory Usability Education and learning interfaces multimodal interfaces interaction design multisensory information non-visual information access

来源：评论

学校读者我要写书评

暂无评论

When adaptive learning is effective learning: comparison of an adaptive learning system to teacher-led instruction

引用

INTERACTIVE learning ENVIRONMENTS 2023年第2期31卷 793-803页

作者： Wang, Shuai Christensen, Claire Cui, Wei Tong, Richard Yarnall, Louise Shear, Linda Feng, Mingyu SRI Int Educ Div 333 Ravenswood Ave Menlo Pk CA 94025 USA Squirrel AI Learning Yixue Educ Grp Shanghai Peoples R China WestEd Sci Technol Engn & Math Program San Francisco CA USA

Adaptive learning systems personalize instruction to students' individual learning needs and abilities. Such systems have shown positive impacts on learning. Many schools in the United States have adopted adaptive learning systems, and the rate of adoption in China is accelerating, reaching almost 2 million unique users for one product alone in the past 3 years. Given such rapid adoption in China, it is useful to examine the efficacy of adaptive learning within that country's educational system. This study aimed to compare the learning impacts of individualized adaptive learning courseware to two common instructional approaches in China: large-group and small-group classroom instruction. This paper describes the results of two efficacy studies of one of China's first adaptive learning systems, Squirrel AI learning. One study compares classroom-based individualized adaptive learning instruction to large-group instruction, and another to small-group instruction. Chinese eighth-grade students from two provinces randomly assigned to use Squirrel AI learning showed greater gains on a mathematics test than those randomly assigned to whole-class or small-group instruction led by expert teachers. Findings provide a basis for further research into the selection, use, and impact of adaptive learning systems in Chinese education.

关键词： Artificial intelligence adaptive learning system efficacy study mathematics education

来源：评论

学校读者我要写书评

暂无评论

Aspect-based Sentiment Analysis using Long Short-term Memory Model for Leveraging Restaurant Service Management

Aspect-based Sentiment Analysis using Long Short-term Memory...

引用

2023 International Conference on Computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

In general, the hospitality industry has been acknowledged as a major sector that gives a high contribution to economic development in many countries including Indonesia. For that reason, many initiatives have been implemented to help the growth of the hospitality industry in many countries including Indonesia to rebound from the harsh impact of the Covid-19 Pandemic. One such initiative is improving restaurant services as the main sector of the hospitality industry. This paper presents empirical results of sentiment analysis as a means to assess the quality of restaurant services as the first step to improving service quality. In particular, this study explores the aspect-based sentiment analysis method to identify some aspects of restaurant service which need improvement by learning the polarity of customers toward the restaurant services without having to meet the customers directly. By using the aspect-based sentiment analysis method, the customer sentiments comprising opinions, sentiments, evaluations, attitudes, and emotions from restaurant service can be analyzed using customers' online reviews as input. The main experiment findings showed that the Long Short-term Memory model can achieve high performance in predicting aspect polarization in restaurant service reviews. Other findings suggest that Sigmoid as an activation function achieved 0.97 average training accuracy and 0.69 average testing accuracy giving a better performance to the model in comparison to ReLU, Tanh, and ELU activation functions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

The effects of self-explanation on game-based learning: Evidence from eye-tracking analyses

引用

COMPUTERS IN HUMAN BEHAVIOR 2025年 163卷

作者： Chiou, Guo-Li Tsai, Meng-Jung Hsu, Chung-Yuan Natl Taiwan Normal Univ Inst Res Excellence Learning Sci Program Learning Sci 162 Sect 1Heping E Rd Taipei 106 Taiwan Natl Pingtung Univ Sci & Technol Dept Child Care 1 Shuefu Rd Pingtung 91201 Taiwan

The purpose of this study was to examine the effect of self-explanation prompts on game performance using eyetracking techniques. We adopted an experimental design for the study. A total of 40 4th graders participated and were randomly assigned to either the experimental or control group. While the experimental group played a computer game with self-explanation prompts, the control group played the same game without any prompts. A Tobii 4C eye tracker with a sampling rate of 90 Hz was used to record the eye movements of the participants while they were playing the game. A pre-test and post-test were used to assess the participants' understanding of the target concepts of the game before and after their game-playing, respectively. The results indicated an interaction effect between self-explanation and prior knowledge on the learning outcomes. Regarding the participants with lower-level prior knowledge, the experimental group gained significantly better scores on the posttest than the control group. In contrast, with respect to the participants with higher-level prior knowledge, the self-explanation prompts did not demonstrate a positive effect on the experimental group. Moreover, the results of the lag sequential analysis provide solid evidence of the differences in visual transitional patterns between the participants with different levels of prior knowledge while they were reacting to the self-explanation prompts. These results could account for the different learning outcomes achieved by the participants with different levels of prior knowledge in the experimental group.

关键词： Games Pedagogical issues Elementary education Teaching/learning strategies

来源：评论

学校读者我要写书评

暂无评论

Restaurant Customer Feedback Sentiment Analysis using Aspect Embedding Long Short-term Memory Model

Restaurant Customer Feedback Sentiment Analysis using Aspect...

引用

2023 International Conference on Computer Science, Information Technology and Engineering, ICCoSITE 2023

ISBN: (纸本)9798350320954

In the past ten years, there has been a proliferation of unstructured textual data from a variety of fields, allowing for the analysis of the sentiment polarity of the text authors in each of those datasets. To analyze sentiment polarity from unstructured data, machine learning tasks such as aspect-based sentiment analysis are used. The public dataset of restaurant patron feedback was used as the input for this study's empirical results of aspect-based sentiment analysis utilizing the Aspect Embedding Long Short-Term Memory model. The primary experiment's results show that the aspect embedding long short-term memory model can predict aspect sentiment polarization from customer feedback to restaurant service and aspect text representation (aspect text embedding) as input with excellent performance. For example, the Aspect Embedding Long Short-term Memory model, which uses ReLU as its activation function in the Dense layer tends to achieve higher performance (0.97 average accuracies) than the same model equipped with Sigmoid, and Tanh functions which achieve 0.954 and 0.956 average training accuracy respectively. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

HATCHet2: clone- and haplotype-specific copy number inference from bulk tumor sequencing data

引用

GENOME BIOLOGY 2024年第1期25卷 1-28页

作者： Myers, Matthew A. Arnold, Brian J. Bansal, Vineet Balaban, Metin Mullen, Katelyn M. Zaccaria, Simone Raphael, Benjamin J. Princeton Univ Dept Comp Sci Princeton NJ 08544 USA Princeton Univ Ctr Stat & Machine Learning Princeton NJ USA Princeton Univ Princeton Res Comp Princeton NJ USA UCL Canc Inst Computat Canc Genom Res Grp London England Mem Sloan Kettering Canc Ctr Human Oncol & Pathogenesis Program New York NY USA

Bulk DNA sequencing of multiple samples from the same tumor is becoming common, yet most methods to infer copy-number aberrations (CNAs) from this data analyze individual samples independently. We introduce HATCHet2, an algorithm to identify haplotype- and clone-specific CNAs simultaneously from multiple bulk samples. HATCHet2 extends the earlier HATCHet method by improving identification of focal CNAs and introducing a novel statistic, the minor haplotype B-allele frequency (mhBAF), that enables identification of mirrored-subclonal CNAs. We demonstrate HATCHet2's improved accuracy using simulations and a single-cell sequencing dataset. HATCHet2 analysis of 10 prostate cancer patients reveals previously unreported mirrored-subclonal CNAs affecting cancer genes.

关键词： Copy-number aberrations Cancer Genomics Tumor heterogeneity Clone Allele-specific Haplotype DNA sequencing

来源：评论

学校读者我要写书评

暂无评论

Building and integrating brain-wide maps of nervous system function in invertebrates

引用

CURRENT OPINION IN NEUROBIOLOGY 2024年 86卷 102868-102868页

作者： Kramer, Talya S. Flavell, Steven W. MIT Picower Inst Learning & Memory Dept Brain & Cognit Sci Cambridge MA 02139 USA MIT Biol Grad Program Cambridge MA USA

The selection and execution of context-appropriate behaviors is controlled by the integrated action of neural circuits throughout the brain. However, how activity is coordinated across brain regions, and how nervous system structure enables these functional interactions, remain open questions. Recent technical advances have made it feasible to build brain-wide maps of nervous system structure and function, such as brain activity maps, connectomes, and cell atlases. Here, we review recent progress in this area, focusing on C. elegans and D. melanogaster, as recent work has produced global maps of these nervous systems. We also describe neural circuit motifs elucidated in studies of specific networks, which highlight the complexities that must be captured to build accurate models of whole-brain function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KIF1A novel frameshift variant p.(Ser887Profs*64) exhibits clinical heterogeneity in a Pakistani family with hereditary sensory and autonomic neuropathy type IIC

引用

INTERNATIONAL JOURNAL OF NEUROSCIENCE 2024年第6期134卷 665-675页

作者： Ghafoor, Saima Rafiq, Muhammad Arshad Abbas Shah, Syed Tahir Ansar, Muhammad Paton, Tara Ajmal, Muhmmad Agha, Zehra Qamar, Raheel Azam, Maleeha COMSATS Univ Islamabad Translat Genom Lab Islamabad Pakistan Hosp Sick Children Genet & Genome Biol Program Toronto ON Canada Inst Mol & Clin Ophthalmol Basel Switzerland Hosp Sick Children Peter Gilgan Ctr Res & Learning Ctr Appl Genom TCAG Toronto ON Canada Pakistan Acad Sci Islamabad Pakistan ICESCO Sci & Technol Sect Rabat Morocco

Background: Hereditary sensory and autonomic neuropathies (HSANs) are rare heterogeneous group of neurological disorders caused by peripheral nerve deterioration. The HSANs sub-clinical classes have clinical and genetic overlap which often lead to misdiagnosis. In the present study a Pakistani family with five affected members suffering from severe neuropathy were genetically analyzed to identify the disease causative element in the family. Methods: Genome wide high-density single nucleotide polymorphism (SNP) microarray analysis was carried out followed by whole exome sequencing of the affected proband and another affected sibling. Shared homozygous regions in all severely affected members were identified through homozygosity mapping approach. Results: The largest homozygous region of 14.1 Mb shared by the five severely affected members of the family was identified on chromosome 2. Subsequent exome sequencing identified a novel single nucleotide deletion c.2658del;p.(Ser887Profs*64) in KIF1A. Segregation analysis revealed that this mutation was homozygous in all five affected individuals of the family with severe clinical manifestation, while members of the family that were heterozygous carriers shared abnormal skin features (scaly skin) only with the homozygous affected members. Conclusions: A novel frameshift mutation p.(Ser887Profs*64) in KIF1A is the potential cause of severe HSANIIC in a Pakistani family along with incomplete penetrance in mutation carriers. We demonstrate that using a combination of different techniques not only strengthens the gene finding approach but also helps in proper sub-clinical characterization along with identification of mutated alleles exhibiting incomplete penetrance leading to intrafamilial clinical variability in HSAN group of inherited diseases.

关键词： HSNIIC Consanguineous family exome sequencing KIF1A frameshift mutation incomplete penetrance

来源：评论

学校读者我要写书评

暂无评论

Service-learning in Catholic Universities: Results from a Global Mapping Survey

引用

REVIEW OF FAITH & INTERNATIONAL AFFAIRS 2023年第1期21卷 44-52页

作者： Argarate, Tomas Brosse, Richard Budani, Agustina Bustamante, Rodrigo Elesgaray, Leandro Luft, Maximiliano Pisano, David Tapia, Maria Rosa Tapia, Nieves Ulla, Tamara Wodon, Quentin ZIGLA Buenos Aires DF Argentina Porticus Amsterdam Netherlands Porticus Effect Philanthropy Amsterdam Netherlands Latin Amer Ctr Serv Learning CLAYSS Youth Volunteer Program Americas PaSo Joven Distance Educ Courses & Solidar Sch Support Programs Buenos Aires DF Argentina Latin Amer Ctr Serv Learning CLAYSS Buenos Aires DF Argentina Argentine Minist Educ Natl Serv Learning Programme Buenos Aires DF Argentina Int Assoc Res Serv Learning New Orleans LA USA Acad Community Engagement Scholarship ACES Garner NC USA UNESCO Int Inst Capac Bldg Africa Addis Ababa Ethiopia World Bank Bretton Woods NH USA

Service-learning can be a powerful tool to implement the commitments suggested by Pope Francis under the idea of a Global Compact on Education. The practice is considered high-impact for students. It can also help Catholic higher education institutions support their students' search for meaning while strengthening their own Catholic identity in a way that respects the diversity of views about faith in the student body. Service-learning may also contribute to a culture of encounter, bringing more tolerance and compassion into the world. Do Catholic universities provide adequate service-learning opportunities to their students? Based on a recent survey, this article provides a diagnostic of the level of institutionalization of service-learning and community engagement activities in Catholic universities globally. While most Catholic universities do have a range of service-learning initiatives, these activities are fully integrated in only one-fourth of the universities that responded to the survey. There is however a lot of interest in doing better, and clear pathways for that purpose.

关键词： service-learning social engagement Catholic universities Catholic social thought global mapping institutions

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effect of Attention Mechanism and Aspect Embedding on the Performance of Long Short-term Memory Model for Aspect-Based Sentiment Analysis

Comparing the Effect of Attention Mechanism and Aspect Embed...

引用

2023 International Conference on Computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The attention mechanism is one of the key enablers which have positioned transformer models as the state-of-the-art models in Natural Language Processing. By having the attention mechanism, the first version (vanilla) transformer model can retrieve the hidden state but at the same time can maintain a low requirement on the context vector dimension by selectively choosing to which encoder hidden states to give priority attention. The objective of this study is to evaluate the effect of modified Long Short-term Memory models architecture on the model performance as a predictive model. The first model is modified by adding an attention mechanism to its architecture;whilst, the second model is modified by adding additional input to its architecture. The performance of both models is compared by assigning each model the same task: to address the aspect-based sentiment analysis task. The experiment results show that adding an attention mechanism is not significantly increase the performance of the Long Short-term Memory model in comparison to adding input to the same model. In particular, the average training accuracy of the former model is 0.885;whilst, the average training accuracy of the latter model is 0.942. © 2023 IEEE.

关键词： Sentiment analysis

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：