检索结果-内蒙古大学图书馆

Machine learning-based prediction of low-value care for hospitalized patients

Intelligence-Based Medicine 2023年 8卷 100115-100115页

作者： King, Andrew J. Tang, Lu Davis, Billie S. Preum, Sarah M. Bukowski, Leigh A. Zimmerman, John Kahn, Jeremy M. Department of Critical Care Medicine University of Pittsburgh School of Medicine Pittsburgh PA United States Department of Biostatistics University of Pittsburgh School of Public Health Pittsburgh PA United States Department of Computer Science Dartmouth College Hanover NH United States Human-Computer Interaction Institute Carnegie Mellon University School of Computer Science Pittsburgh PA United States

Objective: Low-value care (i.e., costly health care treatments that provide little or no benefit) is an ongoing problem in United States hospitals. Traditional strategies for reducing low-value care are only moderately successful. Informed by behavioral science principles, we sought to use machine learning to inform a targeted prompting system that suggests preferred alternative treatments at the point of care but before clinicians have made a decision. Methods: We used intravenous administration of albumin for fluid resuscitation in intensive care unit (ICU) patients as an exemplar of low-value care practice, identified using the electronic health record of a multi-hospital health system. We divided all ICU episodes into 4-h periods and defined a set of relevant clinical features at the period level. We then developed two machine learning models: a single-stage model that directly predicts if a patient will receive albumin in the next period;and a two-stage model that first predicts if any resuscitation fluid will be administered and then predicts albumin only among the patients with a high probability of fluid use. Results: We examined 87,489 ICU episodes divided into approximately 1.5 million 4-h periods. The area under the receiver operating characteristic curve was 0.86 for both prediction models. The positive predictive value was 0.21 (95% confidence interval: 0.20, 0.23) for the single-stage model and 0.22 (0.20, 0.23) for the two-stage model. Applying either model in a targeted prompting system could prevent 10% of albumin administrations, with an attending physician receiving one prompt every 4.2 days of ICU service. Conclusion: Prediction of low-value care is feasible and could enable a point-of-care, targeted prompting system that offers suggestions ahead of the moment of need before clinicians have already decided. A two-stage approach does not improve performance but does interject new levers for the calibration of such a system. © 2023 The Authors

关键词： Clinical decision support Evidence-based medicine Low-value care Machine learning Resuscitation

来源：评论

学校读者我要写书评

暂无评论

Immersive Neural Graphics Primitives

arXiv

引用

arXiv 2022年

作者： Li, Ke Rolff, Tim Schmidt, Susanne Bacher, Reinhard Frintrop, Simone Leemans, Wim Steinicke, Frank Human-Computer Interaction Group Department of Informatics Universität Hamburg Germany Computer Vision Group Department of Informatics Universität Hamburg Germany Deutsches Elektronen-Synchrotron DESY Germany

Neural radiance field (NeRF), in particular its extension by instant neural graphics primitives, is a novel rendering method for view synthesis that uses real-world images to build photo-realistic immersive virtual scenes. Despite its potential, research on the combination of NeRF and virtual reality (VR) remains sparse. Currently, there is no integration into typical VR systems available, and the performance and suitability of NeRF implementations for VR have not been evaluated, for instance, for different scene complexities or screen resolutions. In this paper, we present and evaluate a NeRF-based framework that is capable of rendering scenes in immersive VR allowing users to freely move their heads to explore complex real-world scenes. We evaluate our framework by benchmarking three different NeRF scenes concerning their rendering performance at different scene complexities and resolutions. Utilizing super-resolution, our approach can yield a frame rate of 30 frames per second with a resolution of 1280×720 pixels per eye. We discuss potential applications of our framework and provide an open source implementation online.1 Copyright © 2022, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

AuRoRA: A One-for-all Platform for Augmented Reasoning and Refining with Task-Adaptive Chain-of-Thought Prompting 30

AuRoRA: A One-for-all Platform for Augmented Reasoning and R...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zou, Anni Zhang, Zhuosheng Zhao, Hai Li, Xiaoshan Bian, Minjie Department of Computer Science and Engineering Shanghai Jiao Tong University China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Technology Innovation Department Shanghai Data Group Co. Ltd. China Shanghai Data Group Co. Ltd. China

ISBN: (纸本)9782493814104

Large language models (LLMs) empowered by chain-of-thought (CoT) prompting have yielded remarkable prowess in reasoning tasks. Nevertheless, current methods predominantly lean on handcrafted or task-specific demonstrations, lack reliable knowledge basis and thus struggle for trustworthy responses in an automated pattern. While recent works endeavor to improve upon one certain aspect, they ignore the importance and necessity of establishing an integrated and interpretable reasoning system. To address these drawbacks and provide a universal solution, we propose AuRoRA: a one-for-all platform for augmented reasoning and refining based on CoT prompting that excels in adaptability, reliability, integrity, and interpretability. The system exhibits superior performances across six reasoning tasks and offers real-time visual analysis, which has pivotal academic and application value in the era of LLMs. The AuRoRA platform is available at https://***/spaces/Anni123/AuRoRA. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Refining

来源：评论

学校读者我要写书评

暂无评论

Circumstantial Discussion on Security and Privacy Protection using Cloud Computing Technology 2

Circumstantial Discussion on Security and Privacy Protection...

引用

2nd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2022

作者： Lourens, Melanie Naureen, Ayesha Guha, Shouvik Kumar Ahamad, Shahanawaj Dharamvir Tripathi, Vikas Durban University of Technology Department of Human Resources Management South Africa B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Narsapur502313 India The West Bengal National University of Juridical Sciences India University of Hail College of Computer Science and Engineering Hail City Saudi Arabia The Oxford College of Engineering Bommanhalli Dept of Mca Bangalore560068 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9781665437899

Cloud computing is becoming a demanding technology due to its flexibility, sensibility and remote accessibility. Apart from these applications of cloud computing, privacy and security are two terms that pose a circumstantial discussion. Various authors have argued on this topic that cloud computing is more secure than other data sharing and storing methods. The conventional data storing system is a computer system or smartphone storage. The argument debate also states that cloud computing is vulnerable to enormous types of attacks which make it a more concerning technology. This current study has also tried to draw the circumstantial and controversial debate on the security and privacy system of cloud computing. Primary research has been conducted with 65 cloud computing experts to understand whether a cloud computing security technique is highly secure or not. An online survey has been conducted with them where they provided their opinions based on the security and privacy system of cloud computing. Findings showed that no particular technology is available which can provide maximum security. Although the respondents agreed that blockchain is a more secure cloud computing technology;however, the blockchain also has certain threats which need to be addressed. The study has found essential encryption systems that can be integrated to strengthen security;however, continuous improvement is required. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures 23

FlexiFed: Personalized Federated Learning for Edge Clients w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Chen, Chunyang Huang, Faliang Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia Faculty of Information Technology Monash University Australia Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed;and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×. © 2023 ACM.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Surfacing Structural Barriers to Community-Collaborative Approaches in human-computer interaction 26

Surfacing Structural Barriers to Community-Collaborative App...

引用

26th ACM Conference on computer-Supported Cooperative Work and Social Computing, CSCW 2023

作者： Liang, Calvin Alan Tseng, Emily Dewitt, Akeiylah Kotturi, Yasmine Ghoshal, Sucheta Smith, Angela D. R. Wong-Villacres, Marisol Wilcox, Lauren Erete, Sheena Human Centered Design and Engineering University of Washington United States Information Science Cornell University United States Human-Computer Interaction Institute Carnegie-Mellon University United States School of Information The University of Texas Austin United States Facultad de Ingeniería en Electricidad y Computación Escuela Superior Politécnica Del Litoral Ecuador Google United States College of Information Studies University of Maryland College Park United States

ISBN: (纸本)9798400701290

Community-collaborative approaches to technology research promise a more just, equitable, and societally impactful future for computer-supported collaborative work (CSCW). But how can we ensure that CSCW builds knowledge with communities as meaningful partners, rather than conducting research activities on them? And what would it take for our research activities to go a step further, with the aim of helping communities work towards alternative social structures and counter harmful structural oppression? With growing interest in community-collaborative approaches (CCA) in CSCW among both academic and industry institutions, it is time to reflect upon the field's history of these forms of engagement to develop pathways for the future. This interactive workshop draws from an expert roundtable featuring CSCW and human-computer interaction (HCI) researchers with a collectively rich wealth of knowledge on enacting, critiquing, and navigating community-based research. Together, we explore the structural challenges of CCA for communities, research institutions, and individual researchers, with an explicit focus on how the values of computing research do and do not align with what is needed for truly community-collaborative work. © 2023 Copyright held by the owner/author(s).

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Self-Disclosure in Digital Healthcare: Enhancing User Engagement

Self-Disclosure in Digital Healthcare: Enhancing User Engage...

引用

IEEE International Conference on Agents (ICA)

作者： Michelle Goh Harim Jeong Joo Hun Yoo Oakyoung Han Department of Interaction Science Sungkyunkwan University Seoul Republic of Korea Department of Artificial Intelligence Sungkyunkwan University Suwon Republic of Korea Department of Computer Education Sungkyunkwan University Seoul Republic of Korea

In the growing digital healthcare field, enhancing user engagement is crucial for the sustained usage of e-intervention treatments. This study focuses on improving user engagement by investigating how users interact with agents in a conversational context. To achieve this, we examined communication techniques for building relationships in counseling and selected self-disclosure (SD) as our approach to assess its effectiveness. We created conversational scripts based on iCBT, a prevalent psychotherapy method in digital mental healthcare, and conducted an empirical study with 40 participants. Participants were randomly assigned to two groups: one that contained SD and one without. Our analysis focused on the user experience and its impact on engagement. The findings indicate that employing SD enhances user engagement, agent perception, and intention to use. Conversely, conversations without SD are perceived as task-focused, resulting in reduced engagement and intention to use. This study serves as a foundation for understanding the potential of SD and underscores the need for further exploration in diverse digital healthcare contexts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Security Enhancement in Consumer Enterprises Using Neural Nets Within the SIEM Framework

Security Enhancement in Consumer Enterprises Using Neural Ne...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Saksham Arora Sudhakar Kumar Sunil K. Singh Sahil Garg Brij B. Gupta Shavi Bansal Kwok Tai Chui Computer Science and Engineering Chandigarh College of Engineering and Technology Chandigarh India Department of Computer Science and Information Engineering Asia University Taiwan University of Economics and Human Sciences in Warsaw Poland Insights2Techinfo India Hong Kong Metropolitan University Hong Kong

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

With internet popularity increasing every day and more physical activities being brought to the online spectrum, Security Information and Event Management (SIEM) tools have emerged as the main way to tackle any threat intrusions in the network infrastructure of organizations. Threats are evolving and becoming more advanced with the advancements in technology, and detecting and preventing the attacks need more human inter-vention than ever. To prevent these attacks, artificial intelligence and neural networks are a great way to tackle the increasing needs of human intervention. This article, thus, proposes a novel framework that uses a neural network named FeedForward to develop a model for anomaly and threat protection. It then prompts the user and takes input when a threat is detected. On confirmation of a threat, the feedback is sent back to the neural network to train itself better for future threats and keep itself updated. Therefore, this article proposes a supervised learning and retraining framework on the neural network. The dataset chosen has 763,144 instances that are divided into 80% training and 20% testing dataset. On running the neural network on the dataset, we achieved an astonishing 99.2% accuracy.

关键词： Training Technological innovation Accuracy Scalability Neural networks Supervised learning Threat assessment computer security Protection Testing

来源：评论

学校读者我要写书评

暂无评论

LLM in the Loop: A Framework for Contextualizing Counterfactual Segment Perturbations in Point Clouds

引用

IEEE Access 2025年 13卷 85507-85525页

作者： Kočić, Veljka Lukač, Niko Rožajac, Džemail Schweng, Stefan Gollob, Christoph Nothdurft, Arne Stampfer, Karl del Ser, Javier Holzinger, Andreas BOKU University Human-Centered AI Laboratory Institute of Forest Engineering Department of Ecosystem Management Climate and Biodiversity Vienna1190 Austria Institute of Human-Centered Computing TU Graz Faculty of Computer Science and Biomedical Engineering Graz8010 Austria University of Maribor Faculty of Electrical Engineering and Computer Science Maribor2000 Slovenia BOKU University Institute of Forest Growth Department of Ecosystem Management Climate and Biodiversity Vienna1190 Austria Derio48160 Spain Department of Mathematics Leioa48940 Spain

Point Cloud Data analysis has seen a major leap forward with the introduction of PointNet algorithms, revolutionizing how we process 3D environments. Yet, despite these advancements, key challenges remain, particularly in optimizing segment perturbations to influence model outcomes in a controlled and meaningful way. Traditional methods struggle to generate realistic and contextually appropriate perturbations, limiting their effectiveness in critical applications like autonomous systems and urban planning. This paper takes a bold step by integrating Large Language Models into the counterfactual reasoning process, unlocking a new level of automation and intelligence in segment perturbation. Our approach begins with semantic segmentation, after which LLMs intelligently select optimal replacement segments based on features such as class label, color, area, and height. By leveraging the reasoning capabilities of LLMs, we generate perturbations that are not only computationally efficient but also semantically meaningful. The proposed framework undergoes rigorous evaluation, combining human inspection of LLM-generated suggestions with quantitative analysis of semantic classification model performance across different LLM variants. By bridging the gap between geometric transformations and high-level semantic reasoning, this research redefines how we approach perturbation generation in Point Cloud Data analysis. The results pave the way for more interpretable, adaptable, and intelligent AI-driven solutions, bringing us closer to real-world applications where explainability and robustness are paramount. © 2013 IEEE.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

A 'plug and play' approach to testing virtual environment interaction techniques 6

A 'plug and play' approach to testing virtual environment in...

引用

6th Eurographics Workshop on Virtual Environments, EGVE 2000

作者： Willans, James S. Harrison, Michael D. Human-Computer Interaction Group Department of Computer Science University of York Heslington YorkYO10 5DD United Kingdom

ISBN: (纸本)3211835164

It is generally agreed that the usability of virtual environment interaction techniques is very poor. One reason for this is because toolkits used by virtual environment developers supply a small number of predefined techniques which are expected to be used regardless of context. In addition, there is no software to facilitate the design and testing of interaction techniques akin to that found for the appearance of the environment. We have developed the Marigold toolset to aid in the systematic design, testing and refining of virtual environment interaction techniques. The toolset uses a visual hybrid specification as a starting point. In this paper we demonstrate how Marigold can be used to aid in determining the suitability of interaction techniques by the rapid testing of alternatives in a `plug and play' style. © 2000 Proceedings of the 6th Eurographics Workshop on Virtual Environments, EGVE 2000. All rights reserved.

关键词： Virtual reality

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：