检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Nishi, Kento Okawa, Maya Ramesh, Rahul Khona, Mikail Tanaka, Hidenori Lubana, Ekdeep Singh CBS-NTT Program in Physics of Intelligence Harvard University United States Computer and Information Science University of Pennsylvania United States Department of Physics Massachusetts Institute of Technology United States Physics and Informatics Lab NTT Research Inc United States

Knowledge Editing (KE) algorithms alter models’ weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations. To better identify the possibilities and limitations of these approaches, recent work has shown that applying KE can adversely affect models’ factual recall accuracy and diminish their general reasoning abilities. While these studies give broad insights into the potential harms of KE algorithms, e.g., via performance evaluations on benchmarks, we argue little is understood as to why such destructive failures occur. Is it possible KE methods distort representations of concepts beyond the targeted fact, hence hampering abilities at broad? If so, what is the extent of this distortion? Motivated by such questions, we define a novel synthetic task wherein a Transformer is trained from scratch to internalize a "structured" knowledge graph. The structure enforces relationships between entities of the graph, such that editing a factual association has "trickling effects" on other entities in the graph (e.g., altering X’s parent is Y to Z affects who X’s siblings’ parent is). Through evaluations of edited models and analysis of extracted representations, we show that KE inadvertently affects representations of entities beyond the targeted one, distorting relevant structures that allow a model to infer unseen knowledge about an entity. We call this phenomenon representation shattering and demonstrate that it results in degradation of factual recall and reasoning performance more broadly. To corroborate our findings in a more naturalistic setup, we perform preliminary experiments with pre-trained Llama and Mamba models, reproducing the representation shattering effect therein as well. Overall, our work yields a precise mechanistic hypothesis to explain why KE has adverse effects on model abilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A BCLC Staging System for Hepatocellular Carcinoma using Swin Transformer and CT Imaging 46

A BCLC Staging System for Hepatocellular Carcinoma using Swi...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Chang, Shun-Cheng Wang, Pochuang Wang, Weichung Su, Tung-Hung Kao, Jia-Horng Lin, Che Taipei10617 Taiwan Department of Computer Science and Information Engineering Ntu Taipei10617 Taiwan Institute of Applied Mathematical Sciences Ntu Taipei10617 Taiwan Division of Gastroenterology and Hepatology Department of Internal Medicine National Taiwan University Hospital Taipei10048 Taiwan Department of Electrical Engineering Ntu Taipei10617 Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taipei10617 Taiwan Smart Medicine and Health Informatics Program Ntu Taipei10617 Taiwan

ISBN: (纸本)9798350371499

The Barcelona Clinic Liver Cancer (BCLC) staging system plays a crucial role in clinical planning, offering valuable insights for effectively managing hepatocellular carcinoma. Accurate prediction of BCLC stages can significantly ease the workload on radiologists. However, few datasets are explicitly designed for discerning BCLC stages. Despite the common practice of appending BCLC labels to clinical data within datasets, the inherent imbalance in BCLC distribution is further amplified by the diverse purposes for which datasets are curated. In this study, we aim to develop a BCLC staging system using the advanced Swin Transformer model. Additionally, we explore the integration of two datasets, each originally intended for separate objectives, highlighting the critical challenge of preserving class distribution in practical study designs. This exploration is pivotal for ensuring the applicability of our developed staging system in the designed clinical settings. Our resulting BCLC staging system demonstrates an accuracy of 55.81% (±7.8%), contributing to advancing medical image-based research for predicting BCLC stages. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

ReViT: A Hybrid Approach for BCLC Staging of Hepatocellular Carcinoma Using 3D CT with Multiple Instance Learning

ReViT: A Hybrid Approach for BCLC Staging of Hepatocellular ...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health informatics, BHI 2024

作者： Chang, Shun-Cheng Yu, Hsin-Pei Hsieh, Yi-Hsien Wang, Pochuang Wang, Weichung Su, Tung-Hung Kao, Jia-Horng Lin, Che Taipei10617 Taiwan Department of Computer Science and Information Engineering Ntu Taipei10617 Taiwan Institute of Applied Mathematical Sciences Ntu Taipei10617 Taiwan National Taiwan University Hospital Division of Gastroenterology and Hepatology Department of Internal Medicine Taipei10048 Taiwan Department of Electrical Engineering Ntu Taipei10617 Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taipei10617 Taiwan Smart Medicine and Health Informatics Program Ntu Taipei10617 Taiwan

ISBN: (纸本)9798350351552

Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortality cancer. An automated BCLC staging system could significantly enhance diagnosis and treatment planning efficiency. However, we found that BCLC staging, which is directly related to the size and number of liver tumors, aligns well with the principles of the Multiple Instance Learning (MIL) framework. To effectively achieve this, we proposed a new preprocessing technique called Masked Cropping and Padding(MCP), which addresses the variability in liver volumes and ensures consistent input sizes. This technique preserves the structural integrity of the liver, facilitating more effective learning. Furthermore, we introduced Re ViT, a novel hybrid model that integrates the local feature extraction capabilities of Convolutional Neural Networks (CNNs) with the global context modeling of Vision Transformers (ViTs). Re ViT leverages the strengths of both architectures within the MIL framework, enabling a robust and accurate approach for BCLC staging. We will further explore the trade-off between performance and interpretability by employing TopK Pooling strategies, as our model focuses on the most informative instances within each bag. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Crowd and Urban Storytelling: Evaluating a Collective Intelligence Model to Support Discussions about the City 25

Crowd and Urban Storytelling: Evaluating a Collective Intell...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Chaves, Ramon Motta, Claudia Correia, Antonio Paredes, Hugo Caetano, Barbara De Souza, Jano Moreira Schneider, Daniel Postgraduate Program in Informatics PPGI/UFRJ Rio de Janeiro Brazil Federal University of Rio de Janeiro Brazil Inesc Tec University of Tr s-os-Montes e Alto Douro Utad Quinta de Prados Apartado 1013 Vila Real Portugal Systems Engineering and Computer Science Program PESC/COPPE/UFRJ Rio de Janeiro Brazil

ISBN: (纸本)9781665405270

In recent years, digital technologies have been used to support discussions about the city and also to involve citizens in participatory public processes. However, despite the widespread use of social media platforms, old issues related to engagement and participation still persist in digital initiatives. The main goal of this study is to carry out an empirical evaluation of a collective intelligence model that combines crowdsourcing and social storytelling to support discussions about the city from a bottom-up perspective. Within a design science research approach we designed a participatory action study that was carried out through a workshop with students and professionals from different areas, such as architecture, urban design and information technology. As a result, we were able to assess whether the collective intelligence model was acceptable to the participants by investigating whether the behavioral assumptions were valid and thus outlining some contributions to the field of urban informatics. © 2022 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Sustainability in Disruption: SC Intelligence, Customer Knowledge Transfer, and the Mediating Role of IS/IT

引用

IEEE Engineering Management Review 2025年

作者： Ratna, Silvia Saide, Saide Rater, Salya Svyazhanovna, Baizakova Saule Herzavina, Herzavina Faculty of Information Technology Department of Informatics Engineering and Department of Information Systems Banjarmasin Indonesia State Islamic University of Sultan Syarif Kasim Riau Universitas Islam Negeri Sultan Syarif Kasim Riau-UIN SUSKA Riau Department of Information Systems Faculty of Science and Technology Indonesia PRO Knowledge Indonesia Pekanbaru Indonesia Universitas Pahlawan Tuanku Tambusai Indonesia Lembaga Enreach UIN Suska Riau Indonesia Politeknik Aceh Selatan Department of Informatics Engineering Aceh Indonesia Information Communication Technologies Robotics in Arkalyk Pedagogical Institute Master of Natural Sciences Educational Program for the Informatics Computer Science Kazakhstan Universitas Pahlawan Tuanku Tambusai Department of Informatics Engineering Indonesia National Taiwan University of Science and Technology Taiwan

Knowledge resource and information system/technology (IS/IT) capability have been considered to improve firm performance, however there is still a gap regarding the sustainability of supply chain to face and recover from disruption (e.g., COVID-19). Questionnaire-based surveys was adopted and received feedback from sixty (160) Indonesian companies or about 28.07% of response rate. © 1973-2011 IEEE.

关键词： customer knowledge transfer disruption information system/technology (IS/IT) responding knowledge management resource-based view (RBV) Supply chain (SC) sustainability supply chain knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

lab: an R package for generating analysisready data from laboratory records

引用

PeerJ computer science 2023年 9卷 e1528页

作者： Tseng, Yi-Ju Chen, Chun Ju Chang, Chia Wei Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Computational Health Informatics Program Boston Children’s Hospital BostonMA United States Department of Information Management National Taiwan University Taipei Taiwan

Background: Electronic health records (EHRs) play a crucial role in healthcare decision-making by giving physicians insights into disease progression and suitable treatment options. Within EHRs, laboratory test results are frequently utilized for predicting disease progression. However, processing laboratory test results often poses challenges due to variations in units and formats. In addition, leveraging the temporal information in EHRs can improve outcomes, prognoses, and diagnosis predication. Nevertheless, the irregular frequency of the data in these records necessitates data preprocessing, which can add complexity to time-series analyses. Methods: To address these challenges, we developed an open-source R package that facilitates the extraction of temporal information from laboratory records. The proposed lab package generates analysis-ready time series data by segmenting the data into time-series windows and imputing missing values. Moreover, users can map local laboratory codes to the Logical Observation Identifier Names and Codes (LOINC), an international standard. This mapping allows users to incorporate additional information, such as reference ranges and related diseases. Moreover, the reference ranges provided by LOINC enable us to categorize results into normal or abnormal. Finally, the analysis-ready time series data can be further summarized using descriptive statistics and utilized to develop models using machine learning technologies. Results: Using the lab package, we analyzed data from MIMIC-III, focusing on newborns with patent ductus arteriosus (PDA). We extracted time-series laboratory records and compared the differences in test results between patients with and without 30-day in-hospital mortality. We then identified significant variations in several laboratory test results 7 days after PDA diagnosis. Leveraging the time series– analysis-ready data, we trained a prediction model with the long short-term memory algorithm, achieving an area un

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

The Scientific Progress and Prospects of Artificial Intelligence for Cancer Detection: A Bibliometric Analysis

The Scientific Progress and Prospects of Artificial Intellig...

引用

International Seminar on Intelligent Technology and Its Applications (ISITIA)

作者： Fairuz Iqbal Maulana Puput Dani Prasetyo Adi Dian Lestari Sandy Vikki Ariyanto Agung Purnomo Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Telecommunication Research Center National Research and Innovation Agency Jakarta Indonesia Faculty of Medicine Universitas Airlangga Surabaya Indonesia Informatics Engineering Study Program University of Madura Pamekasan Indonesia Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia

Using the Scopus database, this study aims to investigate the use of artificial intelligence for cancer detection in the last ten years from 2013 to 2022. The researchers used bibliometric analysis combined with VosViewer and Rstudio software quantification method for literature analysis. The results of the flushed articles show data such as publication year, journal, country, keywords, and authors, to the highest number of citations. Common keywords used by researchers are artificial intelligence, medical, and human. Researchers limited the findings through keywords such as in the last ten years, documents are journals, and English only so that 1868 articles were obtained. The results found that Harvard Medical School affiliation had the highest number of articles, with 101 articles, by subject area, Medicine had a proportion of 41.9% (n=1320). This bibliometric study will be useful for other researchers to examine the development of research on Artificial Intelligence for Cancer Detection in the last ten years.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Villages Status Classification Analysis Involving K-Means Algorithm to Support Kementerian Desa Pembangunan Daerah Tertinggal dan Transmigrasi Work programs 1

Villages Status Classification Analysis Involving K-Means Al...

引用

1st International Conference on Advanced Information Scientific Development, ICAISD 2020

作者： Hasugian, Paska Marto Hutahaean, Harvei Desmon Sinaga, Bosker Sriadhi Silaban, Saranom Informatics Engineering Study Program STMIK Pelita Nusantara Computer Science and Informatics Education Study Program Faculty of Engineering Universitas Negeri Medan Medan20221 Indonesia

Data mining is a technique of extracting information that has not been known before in a collection of data in the database. Data mining has been applied in various fields that require extracting information, some of the work that can be generated with data mining is classification, prediction, and data grouping. In this study, an analysis of village data collection was carried out to explore the potential or knowledge of the data that has been presented with the main objective of producing a grouping of village status. To support clustering or grouping activities the K-means algorithm used with the general process is to carry out the modeling process without supervision and is one of the methods for grouping data with a system partition, with the principle of allocating each data to the centroid or the closest average, work steps conducted in support of this research is to collect data related to the analysis of data grouping and proceed with the calculation process in accordance with the work steps of the K-means algorithm, the amount of data used as a test of 303 villages scattered in the old Padang regency. The results of calculations by displaying a new group of Cluster 0 is occupied by 120 villages, cluster 1 with a total data of 123 villages, Cluster 2 with a total of 6 villages, cluster 3 with a total of 33 villages while cluster 4 with a total of 21. © 2020 Published under licence by IOP Publishing Ltd.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis

arXiv

引用

arXiv 2024年

作者： Su, Jiayu Knowles, David A. Rabadan, Raul Program for Mathematical Genomics United States Department of Systems Biology Columbia University United States Department of Biomedical Informatics Columbia University United States Department of Computer Science Columbia University United States New York Genome Center United States

The success of machine learning models relies heavily on effectively representing high-dimensional data. However, ensuring data representations capture human-understandable concepts remains difficult, often requiring the incorporation of prior knowledge and decomposition of data into multiple subspaces. Traditional linear methods fall short in modeling more than one space, while more expressive deep learning approaches lack interpretability. Here, we introduce Supervised Independent Subspace Principal Component Analysis (sisPCA), a PCA extension designed for multi-subspace learning. Leveraging the Hilbert-Schmidt Independence Criterion (HSIC), sisPCA incorporates supervision and simultaneously ensures subspace disentanglement. We demonstrate sisPCA's connections with autoencoders and regularized linear regression and showcase its ability to identify and separate hidden data structures through extensive applications, including breast cancer diagnosis from image features, learning aging-associated DNA methylation changes, and single-cell analysis of malaria infection. Our results reveal distinct functional pathways associated with malaria colonization, underscoring the essentiality of explainable representation in high-dimensional data analysis. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based real time detection for cardiac objects with fetal ultrasound video

引用

informatics in Medicine Unlocked 2023年 36卷

作者： Iriani Sapitri, Ade Nurmaini, Siti Naufal Rachmatullah, Muhammad Tutuko, Bambang Darmawahyuni, Annisa Firdaus, Firdaus Rini, Dian Palupi Islami, Anggun Intelligent System Research Group Faculty of Computer Science Universitas Sriwijaya Palembang 30139 Indonesia Doctoral Program Faculty of Engineering Universitas Sriwijaya Palembang 30139 Indonesia Department of Informatics Engineering Faculty of Computer Science Universitas Sriwijaya Palembang 30139 Indonesia

Fetal cardiac anatomical structure interpretation by ultrasound (US) is a key part of prenatal assessment. Unfortunately, the numerous speckles in US video, the small size of fetal cardiac structures, and unfixed fetal positions make manual detection processes difficult. To alleviate such problems, a deep learning model was developed to fully automate the processing of fetal echocardiographs with 2-dimensional cross-sectional images. The weakness of such an approach is that a physician immediately interprets US video with 3-dimensional objects to diagnose patients in clinical practice. To improve fetal cardiac anatomical structure interpretation via US for accurate and real time diagnosis, this paper proposes a real-time fetal cardiac substructure detection using US video with the You Only Look Once (YOLO) framework. In YOLO, an end-to-end neural network makes predictions for cardiac substructure objects, boxes, and class probabilities simultaneously. To achieve reliable performance, 40 fetal echocardiography videos were trained with the new YOLOv7 architecture and fine-tuned to work optimally and run efficiently. We conducted with nine fetal cardiac substructure objects such as the left atrium, right atrium, left ventricle, right ventricle, tricuspid valve, pulmonary valve, mitral valve, aortic valve, and aorta. The results yielded the highest mean average precision of 82.10%, reaching 17 frames per second (FPS) for nine cardiac substructure objects in 0.3 ms. The main finding of our study is that with even a limited number of US videos, YOLOv7 can detect fetal cardiac substructure objects in real-time. Such a network can work efficiently to detect small fetal cardiac objects automatically in a rapid phase with the help of proper fine-tuning. This work mainly assists medical experts in the fetal cardiac anatomy diagnostic process. © 2022 The Authors

关键词： computer vision Fetal echocardiography Object detection YOLOv7

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：