检索结果-内蒙古大学图书馆

43rd European Conference on Information Retrieval Research, ECIR 2021

作者： Alshehri, Jumanah Stanojevic, Marija Dragut, Eduard Obradovic, Zoran Center for Data Analytics and Biomedical Informatics Temple University PhiladelphiaPA United States

ISBN: (纸本)9783030721121

Social scientists have shown that up to 50 % of the comments posted to a news article have no relation to its journalistic content. In this study we propose a classification algorithm to categorize user comments posted to a news article based on their alignment to its content. The alignment seeks to match user comments to an article based on similarity of content, entities in discussion, and topics. We propose a BERTAC, BERT-based approach that learns jointly article-comment embeddings and infers the relevance class of comments. We introduce an ordinal classification loss that penalizes the difference between the predicted and true labels. We conduct a thorough study to show influence of the proposed loss on the learning process. The results on five representative news outlets show that our approach can learn the comment class with up to 36 % average accuracy improvement comparing to the baselines, and up to 25 % comparing to the BA-BC. BA-BC is our approach that consists of two models aimed to capture dis-jointly the formal language of news articles and the informal language of comments. We also conduct a user study to evaluate human labeling performance to understand the difficulty of the classification task. The user agreement on comment-article alignment is "moderate" per Krippendorff’s alpha score, which suggests that the classification task is difficult. © 2021, Springer Nature Switzerland AG.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Autonomous Navigation for Drone Swarms in GPS-Denied Environments Using Structured Learning 16th

Autonomous Navigation for Drone Swarms in GPS-Denied Environ...

引用

16th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2020

作者： Power, William Pavlovski, Martin Saranovic, Daniel Stojkovic, Ivan Obradovic, Zoran Center for Data Analytics and Biomedical Informatics Temple University PhiladelphiaPA United States

ISBN: (纸本)9783030491857

Drone swarms are becoming a new tool for many tasks including surveillance, search, rescue, construction, and defense related activities. As their usage increases, so does the possibility of adversarial attacks on their contribution to these use cases. One possible avenue, whether deliberate or not, is to deny access to the position feedback offered by the Global Positioning System (GPS). Operating in these ‘GPS denied’ environments poses a new challenge;both in navigation, and in collision avoidance. This study proposes two novel concepts;a structural model of environmental deviance to aid in autonomous navigation, and a method to use the output of said model to implement a collision avoidance system. Both of these concepts are developed and tested in the framework of a simulated environment that mimics a GPS-denied scenario. Using data from hundreds of simulated swarm flights, this work shows structured learning can improve navigational accuracy without the need for externally provided position feedback. © 2020, IFIP International Federation for Information Processing.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Onset Detection of Pulse-Shaped Bioelectrical Signals Using Linear State Space Models

引用

Current Directions in biomedical Engineering 2022年第2期8卷 101-104页

作者： Waldmann, Frédéric Baeriswyl, Christof Andonie, Raphael Wildhaber, Reto A. Institute for Medical Engineering and Medical Informatics University of Applied Sciences and Arts Northwestern Switzerland Muttenz Switzerland STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium Bern University of Applied Sciences Biel Switzerland Hearing Research Laboratory ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland Institute for Medical Engineering and Medical Informatics University of Applied Sciences and Arts Northwestern Switzerland Hofackerstrasse 30 Muttenz Switzerland ETH Zurich Sternwartstrasse 7 Zurich Switzerland

Bioelectrical signals are often pulse-shaped with superimposed interference signals. In this context, accurate identification of features such as pulse onsets, peaks, amplitudes, and duration is a frequent problem. In this paper, we present a versatile method of rather low computational complexity to robustly identify such features in real-world signals. For that, we take use of two straight-line models fit to the observations by minimizing a quadratic cost term, and then identify desired features by tweaked likelihood measures. To demonstrate the idea and facilitate access to the method, we provide examples from the field of cardiology. © 2022 The Author(s), published by De Gruyter.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing

arXiv

引用

arXiv 2024年

作者： Hsu, Enshuo Roberts, Kirk McWilliams School of Biomedical Informatics University of Texas Health Science Center at Houston HoustonTX United States Center for Health Data Science & Analytics Houston Methodist HoustonTX United States Enterprise Dev & Integration University of Texas MD Anderson Cancer Center HoustonTX United States

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled data for training a downstream BERT model. The weakly supervised model is then further fine-tuned on small amounts of gold standard data. We evaluate this approach using Llama2 on three different n2c2 datasets. With no more than 10 gold standard notes, our final BERT models weakly supervised by fine-tuned Llama2-13B consistently outperformed out-of-the-box PubMedBERT by 4.7% to 47.9% in F1 scores. With only 50 gold standard notes, our models achieved close performance to fully fine-tuned systems. © 2024, CC BY-NC-ND.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Stay on topic, please: Aligning user comments to the content of a news article

arXiv

引用

arXiv 2021年

作者： Alshehri, Jumanah Stanojevic, Marija Dragut, Eduard Obradovic, Zoran Center for Data Analytics and Biomedical Informatics Temple University PhiladelphiaPA United States

Social scientists have shown that up to 50% of the comments posted to a news article have no relation to its journalistic content. In this study we propose a classification algorithm to categorize user comments posted to a news article based on their alignment to its content. The alignment seeks to match user comments to an article based on similarity of content, entities in discussion, and topics. We propose a BERTAC, BERT-based approach that learns jointly article-comment embeddings and infers the relevance class of comments. We introduce an ordinal classification loss that penalizes the difference between the predicted and true labels. We conduct a thorough study to show influence of the proposed loss on the learning process. The results on five representative news outlets show that our approach can learn the comment class with up to 36% average accuracy improvement comparing to the baselines, and up to 25% comparing to the BA-BC. BA-BC is our approach that consists of two models aimed to capture dis-jointly the formal language of news articles and the informal language of comments. We also conduct a user study to evaluate human labeling performance to understand the difficulty of the classification task. The user agreement on comment-article alignment is "moderate" per Krippendorff’s alpha score, which suggests that the classification task is difficult. Copyright © 2021, The Authors. All rights reserved.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

ClusterLDA: Clustering-Based Topic Extraction for Online News

ClusterLDA: Clustering-Based Topic Extraction for Online New...

引用

Women in data Science at Prince Sultan University (WiDS PSU), International Conference of

作者： Juan Kenichi Sutan Jumanah Alshehri Rafaa Aljurbua Zoran Obradovic Department of Computer and Information Sciences Center for Data Analytics and Biomedical Informatics Temple University Philadelphia PA USA Department of Management Information Systems College of Business Administration Imam Abdulrahman bin Faisal University Dammam Saudi Arabia Department of Computer Science College of Computer Qassim University Buraydah Saudi Arabia

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Topic extraction from large text datasets is a critical task for understanding and analyzing thematic patterns across documents. This study explores three methods for improving topic modeling: standard Latent Dirichlet Allocation (LDA), a clustering-based approach combined with LDA, and an experimental method enhanced with Wikipedia-supplemented clustering. We demonstrate that applying clustering prior to LDA significantly improves topic extraction by aligning the modeling process with the natural structure of the data, allowing for the identification of smaller, yet meaningful, topics that are often overshadowed in standard LDA due to thematic imbalances. Additionally, we applied the improved topic modeling approach to construct an entity-topic network that contextualizes entities' sentiments within the topics they were mentioned in, providing a nuanced view of the dataset. Although our hypothesis that Wikipedia-enhanced clustering would further improve topic extraction was not supported, as it introduced noise and worsened performance, ClusterLDA approach proved effective in enhancing the granularity of topic extraction and addressing the limitations of standard LDA. These findings highlight the potential of clustering to support more coherent and semantically relevant topic extraction, offering a foundation for future advancements in topic modeling and sentiment analysis.

关键词： Text mining Electronic publishing Sentiment analysis Noise Encyclopedias data models Internet Online services Resource management Standards

来源：评论

学校读者我要写书评

暂无评论

DSLA 2023 Facing the dangers of data illiteracy

引用

Significance 2023年第5期20卷 26-29页

作者： Gascon, Gregg M. Wallman, Katherine K. Ravula, Sridhar Cappelleri, Joseph C. Lee, Julia Lum, Kristian Nagaraja, Chaitra H. Paul, Sudeshna Roy, Dooti Wu, Edward The Department of Biomedical Informatics The Ohio State University College of Medicine United States United States The Human Relations Area Files The Yale University United States The Statistical Research and Data Science Center Pfizer Inc United States The Division of Biostatistics Department of Preventive Medicine the Feinberg School of Medicine Northwestern University United States The Data Science Institute University of Chicago United States The Department of Mathematics and Statistics University of Exeter United Kingdom The School of Nursing Emory University United States Boehringer Ingelheim Inc. United States The Social and Decision Analytics Division The Biocomplexity Institute University of Virginia United States

The data Science and Literacy Act (DSLA) of 2023 aims to boost data literacy and data science education across the USA. Gregg M. Gascon, Katherine K. Wallman, Sridhar Ravula, Joseph Cappelleri, Julia Lee, Kristian Lum, Chaitra H. Nagaraja, Sudeshna Paul, Dooti Roy and Edward Wu explain why this opportunity demands our attention © 2023 Blackwell Publishing Ltd. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Node2VecFuseClassifier: Bridging Perspectives in Modeling Transplantation Attitudes Among Dialysis Patients

Node2VecFuseClassifier: Bridging Perspectives in Modeling Tr...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Rafaa Aljurbua Avrum Gillespie Jumanah Alshehri Abdulrahman Alharbi Nouf Albarakati Zoran Obradovic Temple University Philadelphia PA USA Center for Data Analytics and Biomedical Informatics. Department of Computer Science College of Computer Qassim University Buraydah Saudi Arabia Department of Medicine Division of Nephrology Lewis Katz School of Medicine Hypertension and Kidney Transplantation Imam Abdulrahman bin Faisal University Dammam Saudi Arabia

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

The study of patient attitudes toward transplantation is crucial for dialysis clinic decision-makers. Understanding the factors influencing patient attitudes toward transplantation helps improving transplant access. While many studies attempt to predict patient attitudes toward transplantation from a patient-centric point of view by focusing on patient information, there is a limited number of studies that explore the influence of social interaction among dialysis patients on predicting their attitudes toward transplantation. In this study, we utilize machine learning-based models and social networks to classify hemodialysis patients' attitudes toward transplantation taking into account the influence of social interaction among dialysis patients. We conduct a questionnaire among 110 participants from two hemodialysis centers. We investigate the performance of machine learning algorithms, including linear, non-linear model, and graph-based machine learning models. We use developed models to classify hemodialysis clinic patients into positive and negative attitudes toward transplantation. We introduce a graph-based model named Node2VecFuseClassifier that integrates both patient inter-actions and patient features. To emphasize the significance of social interaction, we compare the benefits of using a sociodemographic patient-centric versus a social-centric problem representation that considers patient-to-patient and patient-to-staff interactions. We believe that including the social aspect, patient-to-patient, and patient-to-staff network features enhances all machine learning models' performance as compared to relying on patient-centric features alone. By combining patient experiences with staff expertise, the multilevel analysis enhances predictive capabilities by incorporating diverse roles like patients and staff. Thus, we combine patient and staff networks and observe that such a multi-network approach boosts the F1-score in predicting patient attitude toward tran

关键词： Surveys Machine learning algorithms Social networking (online) Diversity reception Focusing Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Onset Detection of Pulse-Shaped Bioelectrical Signals Using Linear State Space Models

Onset Detection of Pulse-Shaped Bioelectrical Signals Using ...

引用

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Software package for regression algorithms based on Gaussian Conditional Random Fields

Software package for regression algorithms based on Gaussian...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Tijana Markovic Vladan Devedzic Fang Zhou Zoran Obradovic School of Innovation Design and Engineering Malardalen University Vasteras Sweden Faculty of Organizational Sciences University of Belgrade Belgrade Serbia School of Data Science and Engineering East China Normal University Shanghai China Center for Data Analytics and Biomedical Informatics Temple University Philadelphia USA

The Gaussian Conditional Random Fields (GCRF) algorithm and its extensions are used for machine learning regression problems in which the attributes of objects and the correlation between objects should be considered when making predictions. These algorithms can be applied in different domains where problems can be seen as graphs, but their implementation requires complex calculations and good programming skills. This paper presents an open source software package that includes a tool with graphical user interface (GCRFs tool) and Java library (GCRFs library). GCRFs tool is software that integrates various GCRF-based algorithms and supports training and testing of those algorithms on real-world datasets. The main goal of GCRFs tool is to provide a straightforward and user-friendly graphical user interface that will simplify the use of GCRF-based algorithms. GCRFs Java library contains basic classes for GCRF concepts and can be used by researchers who have experience in Java programming. Also, this paper presents the results of a pilot usability evaluation of the GCRFs tool, where the software was evaluated with expert and non-expert users. This evaluation gave us detailed insight into the experiences and opinions of the users and helped us outline priorities for future development.

关键词： Training Java Machine learning algorithms Software packages Software algorithms Programming Prediction algorithms

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：