检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Hsu-Hsiang Chang Te-Cheng Hsu Yi-Hsien Hsieh Che Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Institute of Communications Engineering National Tsing Hua University (NTHU) Hsinchu Taiwan Department of Electrical Engineering National Taiwan University (NTU) Taipei Taiwan Center for Computational and Systems Biology and Center for Biotechnology NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

Data imbalance is a practical and crucial issue in deep learning. Moreover, real-world datasets, such as electronic health records (EHR), often suffer from high missing rates. Both issues can be understood as noises in data that may lead to bad generalization results for standard deep-learning algorithms. This paper introduces a novel meta-learning approach to deal with these noise issues in an EHR dataset for a binary classification task. This meta-learning approach leverages the information from a selected subset of balanced, low-missing rate data to automatically assign proper weight to each sample. Such weights would enhance the informative samples and suppress the opposites during training. Furthermore, the meta-learning approach is model-agnostic for deep learning-based architectures that simultaneously handle the high imbalanced ratio and high missing rate problems. Through experiments, we demonstrate that this meta-learning approach is better in extreme cases. In the most extreme one, with an imbalance ratio of 172 and a 74.6% missing rate, our method outperforms the original model without meta-learning by as much as 10.3% of the area under the receiver-operating characteristic curve (AUROC) and 3.2% of the area under the precision-recall curve (AUPRC). Our results mark the first step towards training a robust model for extremely noisy EHR datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks applied to gene expression analysis: An interdisciplinary perspective

Computational and Systems Oncology

引用

Computational and Systems Oncology 2023年第3期3卷

作者： Ai, Xusheng Smith, Melissa C Feltus, Frank Alex Electrical and Computer Engineering Department Clemson University Clemson SC United States Department of Genetics and Biochemistry Biomedical Data Science & Informatics Program Clemson Center for Human Genetics Clemson University Clemson SC United States

The remarkable flexibility and adaptability of generative adversarial networks (GANs) have led to the proliferation of its models in bioinformatics research. Proteomic and transcriptomic profiles have been shown to be promising methods for discovering and identifying disease biomarkers. However, those analyses were performed by trained human examiners making the process tedious, time consuming, and hard to standardize. With the development of GANs, it is now possible to reduce computational costs and human time for bioinformatics analysis to produce effective biomarkers. Moreover, GANs help address the lack of phenotypic state transitional gene expression data as well as avoid protected human data constraints by generating RNA sequencing (RNA-seq) data from random vectors. The purpose of this review is to summarize the use of GAN approaches and techniques to augment RNA-seq expression data and identify clinically useful biomarkers. We compare different studies that use different types of GAN models to examine the biomarkers. Also, we identify research gaps and challenges that apply GANs to bio-informatics. Finally, we propose potential directions for future research. © 2023 The Authors. Computational and Systems Oncology published by Wiley Periodicals LLC.

关键词： biomarkers data augmentation generative adversarial network RNA sequencing

来源：评论

学校读者我要写书评

暂无评论

Sensing Architecture in Smart City: A Review Paper

Sensing Architecture in Smart City: A Review Paper

引用

International Conference on ICT For Smart Society (ICISS)

作者： Mindit Eriyadi Suhono Harso Supangkat Fadhil Hidayat Doctoral Program of Instiut Teknologi Bandung Bandung Indonesia School of Applied Science Universitas Telkom Bandung Indonesia School of Electrical Engineering and Informatics Instiut Teknologi Bandung Bandung Indonesia Smart City and Community Innovation Center Institut Teknologi Bandung Bandung Indonesia

Relevant smart city research involves many highly futuristic applications, such as smart transportation, in which smart roads warn drivers of impending traffic jams, smart parking, which communicates the location of available parking spaces to drivers, and smart environments, which allow homes and workplaces to fully automatically adjust their temperature to save energy. Complexity in the city sensing section is caused by the complexity of urban systems. The enormous number of sensor types and technologies utilized for municipal data collecting provide a problem. Some of the issues in city sensing are node deployment, sensing management, sensor network types, and their derivative variables, necessitating the development of a city sensing architecture capable of contributing to advances in efficiency, accuracy, and real-timeness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computer Modelling of the Information Properties of Hyper Chaotic Lorenz System and Its Application in Secure Communication System 1

Computer Modelling of the Information Properties of Hyper Ch...

引用

1st Paris Van Java International Seminar on Computer, Science, engineering, and Technology, PVJ ISComSET 2020

作者： Rusyn, Volodymyr Mujiarto Mamat, Mustafa Azharul, Firmansyah Mada Sanjaya, W.S. Sambas, Aceng Dwipriyoko, Estiyan Sutoni, Akhmad Yuriy Fedkovych Chernivtsi National University Kotsybynsky str. 2 Chernivtsi58012 Ukraine Department of Mechanical Engineering Universitas Muhammadiyah Tasikmalaya Indonesia Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Kuala Terengganu Malaysia Department of Mechanical Engineering Sekolah Tinggi Teknologi Cileungsi Indonesia Department of Physics Universitas Islam Negeri Sunan Gunung Djati Bandung Indonesia Informatics Study Program Universitas Langlangbuana Bandung Indonesia Department of Industrial Engineering Universitas Suryakancana Cianjur Indonesia

This paper presents computer modeling, analysis and research of the hyper-chaotic Lorenz system based on programming interface that has been developed in LabView software environment. This study allows for generating and research of the main information properties of hyper-chaotic Lorenz system, focusing on time distribution of the four chaotic coordinates, phase portraits and Lyapunov exponents. The programming interface demonstrates the algorithm of masking and decrypt of the information carrier. © Published under licence by IOP Publishing Ltd.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Application for Airport Tenant Selection Using Weighted Product-based Decision Support System

Application for Airport Tenant Selection Using Weighted Prod...

引用

Electrical and Information Technology (IEIT), International Conference on

作者： Arwin Datumaya Wahyudi Sumari Muhamad Andika Saputra Astika Ayuningtyas Catur Sudarmadi Aerospace Intelligent System and Data Engineering Research Group Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Cognitive Artificial Intelligence Research Group Politeknik Negeri Malang Malang Indonesia Informatics Study Program Faculty of Industrial Technology Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Health Informatics Research Group Faculty of Industrial Technology Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia

This research aims to develop an application for selecting the best new tenant at PT Angkasa Pura II Sultan Thaha Jambi Airport Branch by utilizing Weighted Product (WP) method as the decision support system. Our approach is descriptive research with data analysis technique using four prospective tenants coded A_1 to A_4. The data was collected through observation, interviews, documentation, and literature study. The steps for selecting the best new tenant using the WP method include determining the criteria, sorting the suitability of alternatives and criteria, determining the weight of each criterion and its normalization, calculating the score, S value as an alternative preference, and calculating the ranking, V value as the final alternative preference. Based on the final calculation results, the new tenant coded A_4 is the best alternative based on the data collected from the Financial Management (FHFM) Unit and the Commercial Unit, with a value of V_4 is 0.294.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Land Cover Segmentation Using Multispectral Dataset 8

Improving Land Cover Segmentation Using Multispectral Datase...

引用

8th International Conference on informatics and Computing, ICIC 2023

作者： Herlawati, Herlawati Handayanto, Rahmadya Trias Heryadi, Yaya Abdurachman, Edi Soeparno, Haryono Irwansyah, Edy Miranda, Eka Informatics Universitas Bhayangkara Jakarta Raya Jakarta Indonesia Universitas Islam 45 Computer Engineering Bekasi Indonesia BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Trisakti Institute of Transportation and Logistic Jakarta13410 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia

ISBN: (纸本)9798350342604

Computer vision has been used in many areas such as medical, transportation, military, geography, etc. The fast development of sensor devices inside camera and satellite provides not only red-greed-blue (RGB) images but also multispectral dataset with some channels including RGB, infrared, short-wave, and thermal wave. Most of the dataset is panchromatic (black and white) and RGB, for example Google Map and other satellite-based map applications. This study examines the effects of multispectral dataset for semantic segmentation of land cover. The comparison between RGB with band 2 to band 7 of Landsat 8 Satellite shows an improvement of accuracy from 90.283 to 94.473 for U-Net and from 91.76 to 95.183 for DeepLabV3+. In addition, this research also compares two well-known semantic segmentation methods, namely U-Net and DeepLabV3+, that shown that DeepLabV3+ outperformed U-Net regarding to speed and accuracy. Testing was conducted in the Karawang Regency area, West Java, Indonesia. © 2023 IEEE.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Classification Based on Texture Analysis for Synthetic Hazy Image from Mount Kelud Haze Image Density

Classification Based on Texture Analysis for Synthetic Hazy ...

引用

International Conference on Electrical, Electronics and Information engineering (ICEEIE)

作者： Fresy Nugroho Puspa Miladin Safitri A. Basid Yunifa Miftachul Arif Norizan Mat Diah Firma Sahrul Bahtiar Hani Nurhayati Fachrul Kurniawan Nurizal Dwi Priandani Dodik Arwin Dermawan Informatics Engineering Faculty of Science and Technology Universitas Islam Negeri Maulana Malik Ibrahim Malang Indonesia School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi MARA Shah Alam Malaysia Faculty of Science and Technology Library and Information Science Universitas Islam Negeri Maulana Malik Ibrahim Malang Indonesia Manajemen Informatika Program Vokasi Universitas Negeri Surabaya Surabaya Indonesia

This paper classifies the simulations of homogeneous synthetic images, heterogeneous synthetic hazy images, and original hazy images taken from CCTV (Close Circuit Television) of Mt. Kelud crater using the GLCM (Gray Level Co-Occurrence Matrix) method. The average feature values obtained using the GLCM (Gray Level Co-Occurrence Matrix) method are used to compare the similarity of gray feature values of the three and then classify thin, medium, and thick images. The results for classifying thin haze, medium haze, and thick haze on the homogeneous synthetic hazy image test data obtained an accuracy value of 50%, a precision value of 46%, and a sensitivity value of 65%. As for the classification of thin, medium, and thick fog on heterogeneous synthetic hazy images, test data obtained an accuracy value of 42%, a precision value of 32%, and a sensitivity value of 48%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SWING-BY DYNAMICS IN CONCEPT LEARNING AND COMPOSITIONAL GENERALIZATION

arXiv

引用

arXiv 2024年

作者： Yang, Yongyi Park, Core Francisco Lubana, Ekdeep Singh Okawa, Maya Hu, Wei Tanaka, Hidenori CBS-NTT Physics of Intelligence Program Harvard University CambridgeMA United States Physics & Informatics Laboratories NTT Research Inc. SunnyvaleCA United States Computer Science and Engineering University of Michigan Ann ArborMI United States Department of Physics Harvard University CambridgeMA United States

Prior work has shown that text-conditioned diffusion models can learn to identify and manipulate primitive concepts underlying a compositional data-generating process, enabling generalization to entirely novel, out-of-distribution compositions. Beyond performance evaluations, these studies develop a rich empirical phenomenology of learning dynamics, showing that models generalize sequentially, respecting the compositional hierarchy of the data-generating process. Moreover, concept-centric structures within the data significantly influence a model’s speed of learning the ability to manipulate a concept. In this paper, we aim to better characterize these empirical results from a theoretical standpoint. Specifically, we propose an abstraction of prior work’s compositional generalization problem by introducing a structured identity mapping (SIM) task, where a model is trained to learn the identity mapping on a Gaussian mixture with structurally organized centroids. We mathematically analyze the learning dynamics of neural networks trained on this SIM task and show that, despite its simplicity, SIM’s learning dynamics capture and help explain key empirical observations on compositional generalization with diffusion models identified in prior work. Our theory also offers several new insights—e.g., we find a novel mechanism for non-monotonic learning dynamics of test loss in early phases of training. We validate our new predictions by training a text-conditioned diffusion model, bridging our simplified framework and complex generative models. Overall, this work establishes the SIM task as a meaningful theoretical abstraction of concept learning dynamics in modern generative models. © 2024, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

A Need Analysis in Developing Tutorial Video to Improve Computer Assembling Skills of TKJ Students in Vocational High Schools 3

A Need Analysis in Developing Tutorial Video to Improve Comp...

引用

3rd International Conference on Electrical, Electronics, informatics, and Vocational Education, ICE-ELINVO 2020

作者： Yanti, N.E. Soenarto, S. Instructional Technology Post Graduate Program Universitas Negeri Yogyakarta Jl. Colombo No. 1 Yogyakarta55281 Indonesia Electronics and Informatics Engineering Education Department Universitas Negeri Yogyakarta Jl. Colombo No. 1 Yogyakarta55281 Indonesia

Technological developments in the current era make use of various media for learning. Learning media can facilitate and support practical activities to improve skills, one of which is by using video tutorial media because the video tutorials show the natural form of real objects to follow the instructions easily. This initial research aims to determine the need to develop video tutorial media used by teachers and students in the learning process to assemble computers at the Muhammadiyah 3 Yogyakarta vocational high school. This study used a descriptive-qualitative method by conducting interviews with one teacher and distributing needs analysis questionnaires to 30 students of class X TKJ as research subjects. The results obtained from the statement questionnaire given to students, 93% agreed to develop a video tutorial to facilitate understanding of the material to assemble a computer used for independent or group study wherever and whenever. This research can be used as a criterion for developing instructional media for video tutorials following the material's characteristics for assembling computers. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Students

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

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

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

ISBN: (数字)9798350351552

ISBN: (纸本)9798350351569

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.

关键词： Visualization Accuracy Three-dimensional displays Liver Transformers Planning Convolutional neural networks Context modeling Biomedical imaging Tumors

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：