检索结果-内蒙古大学图书馆

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Luo, Ying Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781952148255

In this paper, we propose a novel bipartite flat-graph network (BiFlaG) for nested named entity recognition (NER), which contains two subgraph modules: a flat NER module for outermost entities and a graph module for all the entities located in inner layers. Bidirectional LSTM (BiLSTM) and graph convolutional network (GCN) are adopted to jointly learn flat entities and their inner dependencies. Different from previous models, which only consider the unidirectional delivery of information from innermost layers to outer ones (or outside-to-inside), our model effectively captures the bidirectional interaction between them. We first use the entities recognized by the flat NER module to construct an entity graph, which is fed to the next graph module. The richer representation learned from graph module carries the dependencies of inner entities and can be exploited to improve outermost entity predictions. Experimental results on three standard nested NER datasets demonstrate that our BiFlaG outperforms previous state-of-the-art models. © 2020 Association for Computational Linguistics

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Approaching ocular risks during spaceflight with 3D printing: Technical strategies to protect astronaut vision

引用

Life sciences in Space Research 2025年 47卷 98-104页

作者： Saif Pasha Joshua Ong Yannie Guo Ryung Lee Ethan Waisberg Andrew G. Lee Prithul Sarker Alireza Tavakkoli Virginia Tech Carilion School of Medicine Roanoke VA USA Department of Ophthalmology and Visual Sciences University of Michigan Kellogg Eye Center Ann Arbor MI USA Baylor College of Medicine Houston TX USA Touro College of Osteopathic Medicine New York NY USA Department of Clinical Neuroscience University of Cambridge Cambridge UK Center for Space Medicine Baylor College of Medicine Houston TX USA Department of Ophthalmology Blanton Eye Institute Houston Methodist Hospital Houston TX USA The Houston Methodist Research Institute Houston Methodist Hospital Houston TX USA Departments of Ophthalmology Neurology and Neurosurgery Weill Cornell Medicine New York New York USA Department of Ophthalmology University of Texas Medical Branch Galveston TX USA University of Texas MD Anderson Cancer Center Houston TX USA Texas A&M School of Medicine Bryan TX USA Department of Ophthalmology The University of Iowa Hospitals and Clinics IA City IA USA Human-Machine Perception Laboratory Department of Computer Science and Engineering University of Nevada Reno NV USA Department of Computer Science University of Nevada Reno Reno NV USA

Long-duration spaceflight poses significant risks to ocular health due to prolonged microgravity exposure and space environmental stressors, contributing to conditions such as Spaceflight-Associated Neuro-ocular Syndrome (SANS) and Spaceflight-Associated Dry Eye Syndrome (SADES). These conditions, along with radiation exposure and risk of ocular trauma in resource-limited environments, necessitate development of innovative countermeasures to safeguard astronauts' vision, particularly for future planetary missions such as Mars. Traditional ophthalmic care depends on specialized equipment and materials impractical for cargo limitations and transport in space, highlighting the need for adaptive solutions. Advances in 3D printing and bioprinting offer an innovative approach to space ophthalmology by enabling on-demand fabrication of customized eyewear, contact lenses, moisture chambers, radiation-shielding lenses, and surgical tools. Furthermore, emerging bioprinting capabilities may facilitate production of biocompatible tissues for ocular repair. The precision, adaptability, and mission-specific applicability of 3D printing provide a strategic advantage to address preventive and therapeutic ocular health needs. However, challenges include optimizing biocompatible materials, refining high-resolution printing techniques, and ensuring structural and functional viability of printed tissues in space conditions. Further research is required to improve material durability, integrate protective elements such as boron nitride nanotubes, and adapt 3D printing processes to the constraints of microgravity. Beyond space medicine, 3D printing applications in space can drive innovations for ophthalmic care on Earth, from customized intraocular lenses to regenerative therapies. This review highlights the critical role of 3D printing in space ophthalmology and need for continued development and deployment to ensure success of future deep-space missions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation

arXiv

引用

arXiv 2022年

作者： Zhang, Kuangen Chen, Jiahong Wang, Jing Chen, Xinxing Leng, Yuquan de Silva, Clarence W. Fu, Chenglong Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China Department of Mechanical Engineering The University of British Columbia VancouverBC Canada Department of Electrical and Computer Engineering The University of British Columbia VancouverBC Canada

Recognizing human locomotion intent and activities is important for controlling the wearable robots while walking in complex environments. However, human-robot interface signals are usually user-dependent, which causes that the classifier trained on source subjects performs poorly on new subjects. To address this issue, this paper designs the ensemble diverse hypotheses and knowledge distillation (EDHKD) method to realize unsupervised cross-subject adaptation. EDH mitigates the divergence between labeled data of source subjects and unlabeled data of target subjects to accurately classify the locomotion modes of target subjects without labeling data. Compared to previous domain adaptation methods based on the single learner, which may only learn a subset of features from input signals, EDH can learn di- Copyright © 2022, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Toward Efficient Automated Feature Engineering

arXiv

引用

arXiv 2022年

作者： Wang, Kafeng Wang, Pengyang Xu, Chengzhong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences University of Macau China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China

utomated Feature Engineering (AFE) refers to automatically generate and select optimal feature sets for downstream tasks, which has achieved great success in real-world applications. Current AFE methods mainly focus on improving the effectiveness of the produced features, but ignoring the low-efficiency issue for large-scale deployment. Therefore, in this work, we propose a generic framework to improve the efficiency of AFE. Specifically, we construct the AFE pipeline based on reinforcement learning setting, where each feature is assigned an agent to perform feature transformation and selection, and the evaluation score of the produced features in downstream tasks serve as the reward to update the policy. We improve the efficiency of AFE in two perspectives. On the one hand, we develop a Feature Pre-Evaluation (FPE) Model to reduce the sample size and feature size that are two main factors on undermining the efficiency of feature evaluation. On the other hand, we devise a two-stage policy training strategy by running FPE on the pre-evaluation task as the initialization of the policy to avoid training policy from scratch. We conduct comprehensive experiments on 36 datasets in terms of both classification and regression tasks. The results show 2.9% higher performance in average and 2x higher computational efficiency comparing to state-of-the-art AFE methods. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

GroundTruth: Augmenting expert image geolocation with crowdsourcing and shared representations

引用

Proceedings of the ACM on human-computer interaction 2019年第CSCW期3卷 1-30页

作者： Venkatagiri, Sukrit Thebault-Spieker, Jacob Kohler, Rachel Purviance, John Mansur, Rifat Sabbir Luther, Kurt Department of Computer Science and Center for Human-Computer Interaction Virginia Tech ArlingtonVA United States BNSF Railway Company Fort WorthTX United States Bloomberg L.P New YorkNY United States

Expert investigators bring advanced skills and deep experience to analyze visual evidence, but they face limits on their time and attention. In contrast, crowds of novices can be highly scalable and parallelizable, but lack expertise. In this paper, we introduce the concept of shared representations for crowd–augmented expert work, focusing on the complex sensemaking task of image geolocation performed by professional journalists and human rights investigators. We built GroundTruth, an online system that uses three shared representations—a diagram, grid, and heatmap—to allow experts to work with crowds in real time to geolocate images. Our mixed-methods evaluation with 11 experts and 567 crowd workers found that GroundTruth helped experts geolocate images, and revealed challenges and success strategies for expert–crowd interaction. We also discuss designing shared representations for visual search, sensemaking, and beyond. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： crowd crowd-augmented expert work crowdsourcing expert geolocation investigation journalism misinformation real-time crowdsourcing sensemaking shared representations verification visual search

来源：评论

学校读者我要写书评

暂无评论

Active Shooter response training environment for a building evacuation in a collaborative virtual environment

Active Shooter response training environment for a building ...

引用

2020 Engineering Reality of Virtual Reality Conference, ERVR 2020

作者： Sharma, Sharad Bodempudi, Sri Teja Scribner, David Grazaitis, Peter Department of Computer Science Bowie State University BowieMD20715 United States CCDC Army Research Laboratory Human Research and Engineering Directorate Aberdeen Proving GroundMD21005 United States

During active shooter events or emergencies, the ability of security personnel to respond appropriately to the situation is driven by pre-existing knowledge and skills, but also depends upon their state of mind and familiarity with similar scenarios. human behavior becomes unpredictable when it comes to making a decision in emergency situations. The cost and risk of determining these human behavior characteristics in emergency situations is very high. This paper presents an immersive collaborative virtual reality (VR) environment for performing virtual building evacuation drills and active shooter training scenarios using Oculus Rift head-mounted displays. The collaborative immersive environment is implemented in Unity 3D and is based on run, hide, and fight mode for emergency response. The immersive collaborative VR environment also offers a unique method for training in emergencies for campus safety. The participant can enter the collaborative VR environment setup on the cloud and participate in the active shooter response training environment, which leads to considerable cost advantages over large-scale real-life exercises. A presence questionnaire in the user study was used to evaluate the effectiveness of our immersive training module. The results show that a majority of users agreed that their sense of presence was increased when using the immersive emergency response training module for a building evacuation environment. © 2020, Society for Imaging science and Technology

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

Identifying Anomalous Behavior in a Building Using HoloLens for Emergency Response

Identifying Anomalous Behavior in a Building Using HoloLens ...

引用

2020 Engineering Reality of Virtual Reality Conference, ERVR 2020

作者： Sharma, Sharad Bodempudi, Sri Teja Scribner, David Department of Computer Science Bowie State University BowieMD20715 United States CCDC Army Research Laboratory Human Research and Engineering Directorate Aberdeen Proving GroundMD21005 United States

During emergencies communicating in multi-level built environment becomes challenging because architectural complexity can create problems with visual and mental representation of 3D space. Our Hololens application gives a visual representation of a building on campus in 3D space, allowing people to see where exits are in the building as well as creating alerts for anomalous behavior for emergency response such as active shooter, fire, and smoke. It also gives path to the various exits;shortest path to the exits as well as directions to a safe zone from their current position. The augmented reality (AR) application was developed in Unity 3D for Microsoft HoloLens and also is deployed on tablets and smartphones. It is a fast and robust marker detection technique inspired by the use of Vuforia AR library. Our aim is to enhance the evacuation process by ensuring that all building patrons know all of the building exits and how to get to them, which improves evacuation time and eradicates the injuries and fatalities occurring during indoor crises such as building fires and active shooter events. We have incorporated existing permanent features in the building as markers for the AR application to trigger the floor plan and subsequent location of the person in the building. This work also describes the system architecture as well as the design and implementation of this AR application to leverage HoloLens for building evacuation purposes. We believe that AR technologies like HoloLens could be adopted for all building evacuating strategies during emergencies as it offers a more enriched experience in navigating large-scale environments. © 2020, Society for Imaging science and Technology

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Supporting child–group interactions with hands-off museum exhibit

引用

International Journal of Child-computer interaction 2021年 27卷

作者： Kotut, Lindah Hoang, Ann Panda, Havisha Shenk, Jennifer Newbill, Phyllis Kellogg, Derek Scott McCrickard, D. Department of Computer Science Virginia Tech Blacksburg VA United States Center for Human Computer Interaction Virginia Tech Blacksburg VA United States Institute of Creativity Arts and Technology (ICAT) Virginia Tech Blacksburg VA United States Science Museum of Western Virginia Roanoke VA United States

Technology can be used to augment visitors’ experience with a museum exhibit and provide museum visitors with means of interacting with otherwise hands-off exhibits. However, introducing technology to support interactivity has the likelihood of usurping users’ attention from the exhibit or diminishing interactions with other visitors. Our approach to this problem involves supporting hands-on interactions for groups visiting a pollinator garden—a science museum exhibit containing fragile species where touching is discouraged. Through interviews with museum experts and docents, we elicited design goals that we then enfolded into an Android application that leverages visual recognition to support interactions with the exhibit. We tested our application in-situ with 65 children in three groups and subsequently propose and describe design approaches that uses the ethos of scaling to support different number of users and leveling to varied cognitive levels. We conclude by recommending reusable designs guidelines to support interactions within other evolving and hands-off contexts. © 2020 Elsevier B.V.

关键词： Child–group interaction Child–mobile interactions Hands-off exhibits Museum

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：