检索结果-内蒙古大学图书馆

E-ffective: A visual analytic system for exploring the emotion and effectiveness of inspirational speeches

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Maher, Kevin Huang, Zeyuan Song, Jiancheng Deng, Xiaoming Lai, Yu-Kun Ma, Cuixia Wang, Hao Liu, Yong-Jin Wang, Hongan Institute of Software Chinese Academy of Sciences Tsinghua University China State Key Laboratory of Computer Science Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Cardiff University United Kingdom Alibaba Group China Tsinghua University China

What makes speeches effective has long been a subject for debate, and until today there is broad controversy among public speaking experts about what factors make a speech effective as well as the roles of these factors in speeches. Moreover, there is a lack of quantitative analysis methods to help understand effective speaking strategies. In this paper, we propose E-ffective, a visual analytic system allowing speaking experts and novices to analyze both the role of speech factors and their contribution in effective speeches. From interviews with domain experts and investigating existing literature, we identified important factors to consider in inspirational speeches. We obtained the generated factors from multi-modal data that were then related to effectiveness data. Our system supports rapid understanding of critical factors in inspirational speeches, including the influence of emotions by means of novel visualization methods and interaction. Two novel visualizations include E-spiral (that shows the emotional shifts in speeches in a visually compact way) and E-script (that connects speech content with key speech delivery information). In our evaluation we studied the influence of our system on experts' domain knowledge about speech factors. We further studied the usability of the system by speaking novices and experts on assisting analysis of inspirational speech effectiveness. Copyright © 2021, The Authors. All rights reserved.

关键词： Visualization

"They keep coming back like zombies": Improving software updating interfaces 12

学校读者我要写书评

暂无评论

"They keep coming back like zombies": Improving software upd...

12th Symposium on Usable Privacy and Security, SOUPS 2016

作者： Mathur, Arunesh Engel, Josefine Sobti, Sonam Chang, Victoria Chetty, Marshini Human-Computer Interaction Lab College of Information Studies University of Maryland College ParkMD20742 United States

ISBN: (纸本)9781931971317

Users often do not install security-related software updates, leaving their devices open to exploitation by attackers. We are beginning to understand what factors affect this software updating behavior but the question of how to improve current software updating interfaces however remains unanswered. In this paper, we begin tackling this question by studying software updating behaviors, designing alternative updating interfaces, and evaluating these designs. We describe a formative study of 30 users' software updating practices, describe the low fidelity prototype we developed to address the issues identified in formative work, and the evaluation of our prototype with 22 users. Our findings suggest that updates interrupt users, users lack sufficient information to decide whether or not to update, and vary in terms of how they want to be notified and provide consent for updates. Based on our study, we make four recommendations to improve desktop updating interfaces and outline socio-technical considerations around software updating that will ultimately affect end-user security. © 2016 by The USENIX Association All Rights Reserved.

关键词：

Crime information improvement for situation awareness based on data mining 18th

学校读者我要写书评

暂无评论

Crime information improvement for situation awareness based ...

Joint Conferences on 18th International Conference on Intelligent Systems Design and Applications, ISDA 2018 and 10th World Congress on Nature and Biologically Inspired Computing , NaBIC 2018

作者： Ladeira, Lucas Zanco Junior, Valdir Amancio Pereira Rodrigues, Raphael Zanon Botega, Leonardo Castro Computer Networks Lab State University of Campinas Cidade Universitária CampinasSP Brazil Human-Computer Interaction Group University Centre Euripides of Marília 529 Hygino Muzzi Filho Avenue MaríliaSP Brazil São Paulo State University 737 Hygino Muzzi Filho Avenue MaríliaSP Brazil

ISBN: (纸本)9783030166564

Crime records hold critical information about crime situations including the offender actions, stolen objects description, characteristics of victims, the location of the crime situation, individuals involved and more. To consume crime data, police forces and other security analysts use risk management systems which process and organize data, and summarize it into relevant and useful information on criminal situations. This type of system depends on promoting Situation Awareness to stimulate the users understanding of the crime situations and consequently the decision-making assertiveness. In this work the goal is to contribute with the typification of crime situations by machine learning driven techniques, applied in conjunction with pre-processing and transformation. Results showed that the use of pre-processing techniques improved data quality and algorithms precision. In addition, the transformation technique with the best results found was Bag of Words Binarization. Finally, the Logistic Regression algorithm presented the best results for mining the crime data. © Springer Nature Switzerland AG 2020.

关键词： Data mining

A virtual reality methodology for cardiopulmonary resuscitation training with and without a physical mannequin

学校读者我要写书评

暂无评论

Journal of Biomedical Informatics 2020年 111卷 103590-103590页

作者： Buttussi, Fabio Chittaro, Luca Valent, Francesca Human-Computer Interaction Lab Department of Mathematics Computer Science and Physics University of Udine Udine Italy SOC Istituto di Igiene ed Epidemiologia Clinica Azienda Sanitaria Universitaria Friuli Centrale Udine Italy

Background: Cardiopulmonary resuscitation (CPR) is an emergency procedure that can increase survival after a cardiac arrest. Performing CPR effectively requires both procedural knowledge and manual skills. Traditional CPR training methodology includes lessons led by instructors and supervised practice on mannequins, thus requiring considerable resources. Objective: This paper proposes a new methodology for low-cost CPR training based on virtual reality (VR) with and without the addition of a physical mannequin. Moreover, it describes an experimental evaluation of the methodology that assessed gain in manual skills during training, transfer of procedural knowledge and manual skills in a final assessment, and changes in self-efficacy with three measurements over time (pre-training, post-training, and post-assessment). Methods: We implemented a VR application that supports the proposed methodology, and can thus be used with or without a mannequin. The experimental evaluation involved 30 participants who tried CPR in VR twice, performing two repetitions of 30 chest compressions per trial. Half participants tried the VR application with the mannequin and half without it. Final assessment required all participants to perform CPR on the mannequin without the assistance of VR. To assess self-efficacy, participants filled in a questionnaire at the three times of measurement. Results: Mixed-design ANOVAs showed effects of repetition, effects of group, or interaction between the two variables on manual skills assessed during training. In the final assessment, participants in both groups correctly remembered most of the steps of the procedure. ANOVAs revealed differences between the two groups only in pressure-related skills (better with mannequin) and in the number of wrong steps added to the procedure (better without mannequin). Mixed-design ANOVA showed a self-efficacy increase in both groups after training, which was maintained after final assessment. Conclusions: The propo

关键词： Resuscitation

An alternate statistical lens to look at collaboration data: Extreme value theory 13

学校读者我要写书评

暂无评论

An alternate statistical lens to look at collaboration data:...

13th International Conference on computer Supported Collaborative Learning - A Wide Lens: Combining Embodied, Enactive, Extended, and Embedded Learning in Collaborative Settings, CSCL 2019

作者： Sharma, Kshitij Olsen, Jennifer Department of Computer Science Norwegian University of Science and Technology Norway Computer Human Interaction Lab in Learning and Instruction École Polytechnique Fédérale de Lausanne Switzerland

ISBN: (纸本)9781732467231

To provide beneficial feedback to students during their collaboration, it is important to identify behaviors that are indicative of good collaboration. However, in a collaborative learning session, students engage in a range of behaviors and it can be difficult to indicate which of those behaviors correlate with higher outcomes. In this paper, we propose using Extreme Value Theory (EVT), a method that considers the data points in the tail (upper or lower) of the distribution, to analyse the relationship between collaborative process variables and outcome measures through insights derived from high impact, low-frequency events. Specifically, in this paper, we analyse the relationship between dual gaze patterns and outcome measures across two different datasets. In both datasets we found that students with lower outcomes had lower focus during the collaborative session. This paper provides a contribution by both introducing EVT as a viable method for analysing CSCL data as well as demonstrating the effectiveness of eyetracking as a collaborative indicator to use to adapt to in real-time. © ISLS.

关键词： Students

Crowd Work on a CV? Understanding How AMT Fits into Turkers' Career Goals and Professional Profiles

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kasunic, Anna Chiang, Chun-Wei Kaufman, Geoff Savage, Saiph Human-Computer Interaction Institute Carnegie Mellon University Human Computer Interaction Lab West Virginia University

vieCap4H-VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nguyen, Thanh Tin Nguyen, Long H. Pham, Nhat Truong Nguyen, Liu Tai Do, Van Huong Nguyen, Hai Nguyen, Ngoc Duy Human Computer Interaction Lab Sejong University Seoul Korea Republic of Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam ASICLAND Suwon Korea Republic of Khoury College of Computer Sciences Northeastern University Boston United States Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia

This study presents our approach on the automatic Vietnamese image captioning for healthcare domain in text processing tasks of Vietnamese Language and Speech Processing (VLSP) Challenge 2021, as shown in Figure 1. In recent years, image captioning often employs a convolutional neural network-based architecture as an encoder and a long short-term memory (LSTM) as a decoder to generate sentences. These models perform remarkably well in different datasets. Our proposed model also has an encoder and a decoder, but we instead use a Swin Transformer in the encoder, and a LSTM combined with an attention module in the decoder. The study presents our training experiments and techniques used during the competition. Our model achieves a BLEU4 score of 0.293 on the vietCap4H dataset, and the score is ranked the 3rd place on the private leaderboard. Our code can be found at https://***/JDdJm. © 2022, CC BY.

关键词： Long short-term memory

Voxel-wise classification for porosity investigation of additive manufactured parts with 3D unsupervised and (deeply) supervised neural networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Iuso, Domenico Chatterjee, Soumick Cornelissen, Sven Verhees, Dries De Beenhouwer, Jan Sijbers, Jan Imec-Vision Lab Department of Physics University of Antwerp Antwerp2610 Belgium Faculty of Computer Science Otto von Guericke University Street Magdeburg39106 Germany Genomics Research Centre Human Technopole V.le Rita Levi-Montalcini 1 Milan20157 Italy Materialise NV. Technologielaan 15 Leuven3001 Belgium Flanders Make vzw. Oude Diestersebaan 133 Lommel3920 Belgium DynXlab Center for 4D Quantitative X-ray Imaging and Analysis Antwerp2610 Belgium

Additive Manufacturing (AM) has emerged as a manufacturing process that allows the direct production of samples from digital models. To ensure that quality standards are met in all manufactured samples of a batch, X-ray computed tomography (X-CT) is often used combined with automated anomaly detection. For the latter, deep learning (DL) anomaly detection techniques are increasingly, as they can be trained to be robust to the material being analysed and resilient towards poor image quality. Unfortunately, most recent and popular DL models have been developed for 2D image processing, thereby disregarding valuable volumetric information. This study revisits recent supervised (UNet, UNet++, UNet 3+, MSS-UNet) and unsupervised (VAE, ceVAE, gmVAE, vqVAE) DL models for porosity analysis of AM samples from X-CT images and extends them to accept 3D input data with a 3D-patch pipeline for lower computational requirements, improved efficiency and generalisability. The supervised models were trained using the Focal Tversky loss to address class imbalance that arises from the low porosity in the training datasets. The output of the unsupervised models is post-processed to reduce misclassifications caused by their inability to adequately represent the object surface. The findings were cross-validated in a 5-fold fashion and include: a performance benchmark of the DL models, an evaluation of the post-processing algorithm, an evaluation of the effect of training supervised models with the output of unsupervised models. In a final performance benchmark on a test set with poor image quality, the best performing supervised model was UNet++ with an average precision of 0.751 ± 0.030, while the best unsupervised model was the post-processed ceVAE with 0.830 ± 0.003. The VAE/ceVAE models demonstrated superior capabilities, particularly when leveraging post-processing techniques. © 2023, CC BY-NC-ND.

关键词： 3D printing

Queer in HCI: Strengthening the Community of LGBTQIA+ Researchers and Research

学校读者我要写书评

暂无评论

Queer in HCI: Strengthening the Community of LGBTQIA+ Resear...

2021 CHI Conference on human Factors in Computing Systems: Making Waves, Combining Strengths, CHI EA 2021

作者： Devito, Michael Ann Lustig, Caitlin Simpson, Ellen Allison, Kimberley Chuanromanee, Tya Spiel, Katta Ko, Amy Rode, Jennifer Dym, Brianna Muller, Michael Klaus Scheuerman, Morgan Marie Walker, Ashley Brubaker, Jed Ahmed, Alex Department of Information Science University of Colorado United States Human Centered Design and Engineering University of Washington United States School of Information Studies Syracuse University United States Department of Psychology Macquarie University Australia University of Notre Dame United States Human-Computer Interaction Group Tu Wien Austria The Information School University of Washington United States Knowledge Lab University College London United Kingdom Department of Information Science University of Colorado Boulder United States Ai Interactions Ibm Research United States Information Science University of Colorado Boulder United States Pitch Lab Northwestern University United States University of Colorado Boulder United States Carnegie Mellon University United States

ISBN: (纸本)9781450380959

As Queer human-computer interaction (HCI) becomes an established part of the larger field, both in terms of research on and with queer populations and in terms of employing queering theories and methods, the role of queer researchers has become a timely topic of discussion. However, these discussions have largely centered around member-researcher status and positionality when working with queer populations. Based on insights gathered at multiple ACM events over the past two years, we identified two pressing issues: (1) we need to better support queer people doing HCI research not specific to queer populations, and (2) we need to identify how to best support member-researchers in leading Queer HCI while including collaborators beyond the queer community. This Special Interest Group (SIG) aims to directly address these challenges by convening a broad community of queer researchers and allies, working not only on explicitly-queer topics but across a broad range of HCI topics. © 2021 Owner/Author.

关键词： Computation theory