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： Ming-Che Cheng Yi-Hsien Hsieh Te-Cheng Hsu Tung-Hung Su Che Lin Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Dept. of Internal Medicine Division of Gastroenterolgy 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)9798350371499

ISBN: (纸本)9798350371505

Electronic Health Records (EHRs) are a cornerstone of modern healthcare analytics, offering rich datasets for various disease analyses through advanced deep learning algorithms. However, the pervasive issue of missing values in EHRs significantly hampers the development and performance of these models. Addressing this challenge is crucial for enhancing clinical decision-making and patient care. Existing methods for handling missing data, ranging from simple imputation to more sophisticated approaches, often fall short of capturing the temporal dynamics inherent in EHRs. To bridge this gap, we introduce the Deep Stochastic Time-series Imputation (Deep STI) algorithm, an innovative end-to-end deep learning model that seamlessly integrates a sequence-to-sequence generative network with a prediction network. Deep STI is designed to leverage the observed time-series data in EHRs, learning to infer missing values from the temporal context with high accuracy. We evaluated Deep STI on the liver cancer data from the National Taiwan University Hospital (NTUH), Taiwan. Our results showed that Deep STI achieved better 5-year hepatocellular carcinoma predictions (19.21% in the area under the precision-recall curve) than extreme gradient boosting (18.15%) and Transformer (18.09%). The ablation study also illustrates the efficacy of our generative architecture design compared to regular imputations. This approach not only promises to improve the reliability of disease analysis in the presence of incomplete data but also sets a new standard for utilizing EHRs in predictive healthcare. Our work aims to advance the field of healthcare analytics and open new avenues for research in deep learning applications to EHRs.

关键词： Deep learning Time series analysis Stochastic processes Predictive models Transformers Imputation Reliability Electronic medical records Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Analysis of the Urban Transport System in the Context of Smart Cities

Vulnerability Analysis of the Urban Transport System in the ...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Antônio A. F. G. M. Pertence Raquel A. F. Mini Humberto Torres Marques-Neto Graduate Program in Informatics Pontifical Catholic University of Minas Gerais Belo Horizonte Brazil

ISBN: (数字)9781728182940

ISBN: (纸本)9781728182957

Large cities seek to incorporate intelligent systems into their infrastructure, industrial, educational, and social activities to improve the quality of service provided to citizens and make all processes more efficient. To this end, these cities use technologies that involve the areas of the Internet of Things, Big Data, and Governance to make decisions by governments and authorities. In the field of Urban Computing, it is possible to use open data in the GTFS format to solve the problems of the urban transport system using complex network metrics that make it possible to model complex interactions between objects in high dimensionality. Stops and routes are modeled as a graph, characterized by complex network metrics. According to the literature, if there is an interruption of the urban transport system, we make an evaluation of the degree of vulnerability of the system in the search for solutions. The main goal of this paper is to propose an approach to analyze the vulnerability of the urban transport system using complex network metrics along with GTFS data in scenarios targeted failures. As a contribution, the proposed approach uses the concept of skewness in the methodology established in the literature. The skewness enables a better understanding and differential the failure conditions from the evaluation of the vulnerability the urban transport system, through a quantitative indication of which local metrics most influence the decay of network metrics. The analysis of the results obtained in the proposed approach serves as a subsidy for studies in the search for solutions to the problems of the urban transport system, providing a tool to the set of technological options for the planning of urban transport systems of smart cities available to governments and authorities. The proposed approach can be applied in different cities, regardless of their size and location, as long as you have access to open geographic data in the GTFS format.

关键词： Measurement Smart cities Government Complex networks Tools Search problems Planning

来源：评论

学校读者我要写书评

暂无评论

Genomic data processing with GenomeFlow

arXiv

引用

arXiv 2025年

作者： Park, Junseok Maury, Eduardo A. Oh, Changhoon Shin, Donghoon Denisko, Danielle Lee, Eunjung Alice Division of Genetics and Genomics Boston Children’s Hospital 3 Blackfan Circle BostonMA United States Department of Pediatrics Harvard Medical School 25 Shattuck St BostonMA United States Bioinformatics Integrative Genomics Program Harvard/MIT MD-PHD Program Harvard Medical School BostonMA United States Program in Medical and Population Genetics Broad Institute of MIT and Harvard CambridgeMA United States Graduate School of Information Yonsei University 50 Yonsei-ro Seodaemun-gu Seoul Korea Republic of Department of Human Centered Design and Engineering University of Washington SeattleWA United States Department of Biomedical Informatics Harvard Medical School BostonMA United States

Advances in genome sequencing technologies generate massive amounts of sequence data that are increasingly analyzed and shared through public repositories. On-demand infrastructure services on cloud computing platforms enable the processing of such large-scale genomic sequence data in distributed processing environments with a significant reduction in analysis time. However, parallel processing on cloud computing platforms presents many challenges to researchers, even skillful bioinformaticians. In particular, it is difficult to design a computing architecture optimized to reduce the cost of computing and disk storage as genomic data analysis pipelines often employ many heterogeneous tools with different resource requirements. To address these issues, we developed GenomeFlow, a tool for automated development of computing architecture and resource optimization on Google Cloud Platform, which allows users to process a large number of samples at minimal cost. We outline multiple use cases of GenomeFlow demonstrating its utility to significantly reduce computing time and cost associated with analyzing genomic and transcriptomic data from hundreds to tens of thousands of samples from several consortia. Here, we describe a step-by-step protocol on how to use GenomeFlow for a common genomic data processing task. We introduce this example protocol geared toward a bioinformatician with little experience in cloud computing. © 2025, CC BY.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Factors affecting the use of Zoom app in online lectures during Covid-19 pandemic

引用

AIP Conference Proceedings 2023年第1期2714卷

作者： Sukri Syafrudin Kartika Handayani Ranu Agastya Nugraha Siti Lestari Lindung Parningotan Manik Computer Science Graduate Program University of Nusa Mandiri Jakarta Indonesia Research Center for Informatics National Research and Innovation Agency Jakarta Indonesia

The rapid global spread of the Covid-19 led to the utilization of online tools for various lecturing activities. Online learning is a change mandated on lecturers and students to achieve significant educational goals, irrespective of time and location. This research investigates factors affecting the use of the videoconferencing app, Zoom in supporting the online lectures. This study is quantitative research with the unified theory of acceptance and the use of technology (UTAUT) model to analyze online learning software acceptance. The research subjects consist of students and lecturers from the University of Bina Sarana Informatika (UBSI) Indonesia. The result shows that the performance and effort expectancies, as well as the social factors, affect users’ attitude towards the software use and their behavioral intention. Also, the facilitating conditions affect their attitude with no significant effect on intention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quality and complexity assessment of learning-based image compression solutions

arXiv

引用

arXiv 2021年

作者： Dick, João Abreu, Brunno Grellert, Mateus Bampi, Sergio Informatics Institute PGMICRO Federal University of Rio Grande do Sul Porto Alegre Brazil Graduate Program in Computer Science Federal University of Santa Catarina Florianópolis Brazil

This work presents an analysis of state-of-the-art learning-based image compression techniques. We compare 8 models available in the Tensorflow Compression package in terms of visual quality metrics and processing time, using the KODAK data set. The results are compared with the Better Portable Graphics (BPG) and the JPEG2000 codecs. Results show that JPEG2000 has the lowest execution times compared with the fastest learning-based model, with a speedup of 1.46× in compression and 30× in decompression. However, the learning-based models achieved improvements over JPEG2000 in terms of quality, specially for lower bitrates. Our findings also show that BPG is more efficient in terms of PSNR, but the learning models are better for other quality metrics, and sometimes even faster. The results indicate that learning-based techniques are promising solutions towards a future mainstream compression method. © 2021, CC BY-NC-SA.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Glucose-mediated mitochondrial reprogramming by cholesterol export at TM4SF5-enriched mitochondria-lysosome contact sites

引用

Cancer Communications 2024年第1期44卷 47-75页

作者： Ji Eon Kim So-Young Park Chulhwan Kwak Yoonji Lee Dae-Geun Song Jae Woo Jung Haesong Lee Eun-Ae Shin Yangie Pinanga Kyung-hee Pyo Eun Hae Lee Wonsik Kim Soyeon Kim Chang-Duck Jun Jeanho Yun Sun Choi Hyun-Woo Rhee Kwang-Hyeon Liu Jung Weon Lee Department of Pharmacy College of PharmacySeoul National UniversitySeoulRepublic of Korea Research Institute of Pharmaceutical Sciences College of PharmacySeoul National UniversitySeoulRepublic of Korea BK21 FOUR Community-Based Intelligent Novel Drug Discovery Education Unit College of Pharmacy and Research Institute of Pharmaceutical SciencesKyungpook National UniversityDaeguRepublic of Korea Department of Chemistry Seoul National UniversitySeoulRepublic of Korea College of Pharmacy Chung-Ang UniversitySeoulRepublic of Korea Natural Product Informatics Research Center Korea Institute of Science and Technology(KIST)Gangneung-siGangwon-doRepublic of Korea School of Life Sciences Gwangju Institute of Science and Technology(GIST)GwangjuRepublic of Korea Department of Biochemistry College of MedicineDong-A UniversityBusanRepublic of Korea Global AI Drug Discovery Center College of Pharmacy and Graduate School of Pharmaceutical SciencesEwha Womans UniversitySeoulRepublic of Korea Interdisciplinary Program in Genetic Engineering Seoul National UniversitySeoulRepublic of Korea

Background:Transmembrane 4 L six family member 5(TM4SF5)translocates subcellularly and functions metabolically,although it is unclear how intracellu-lar TM4SF5 translocation is linked to metabolic *** is thus of interests to understand how the traffic dynamics of TM4SF5 to subcellular endosomal membranes are correlated to regulatory roles of ***:Here,we explored the metabolic significance of TM4SF5 localization at mitochondria-lysosome contact sites(MLCSs),using in vitro cells and in vivo animal systems,via approaches by immunofluorescence,proximity labelling based proteomics analysis,organelle reconstitution ***:Upon extracellular glucose repletion following depletion,TM4SF5 became enriched at MLCSs via an interaction between mitochondrial FK506-binding protein 8(FKBP8)and lysosomal *** labeling showed molecular clustering of phospho-dynamic-related protein I(DRP1)and certain mitophagy receptors at TM4SF5-enriched MLCSs,leading to mitochondrial fis-sion and ***4SF5 bound NPC intracellular cholesterol transporter 1(NPC1)and free cholesterol,and mediated export of lysosomal cholesterol to mitochondria,leading to impaired oxidative phosphorylation but intact tri-carboxylic acid(TCA)cycle andβ-*** mouse models,hepatocyte Tm4sf5 promoted mitophagy and cholesterol transport to mitochondria,both with positive relations to liver ***:Our findings suggested that TM4SF5-enriched MLCSs regu-late glucose catabolism by facilitating cholesterol export for mitochondrial reprogramming,presumably while hepatocellular carcinogenesis,recapitulating aspects for hepatocellular carcinoma metabolism with mitochondrial repro-gramming to support biomolecule synthesis in addition to glycolytic energetics.

关键词： cholesterol fluorescent imaging glucose catabolism hepatocellular carcinogenesis mem-brane contact sites mitochondria function mitophagy oxidative phosphorylation protein-protein interaction tetraspanin

来源：评论

学校读者我要写书评

暂无评论

Vehicular Perception Based on Inertial Sensing: A Structured Mapping of Approaches and Methods

引用

SN Computer Science 2020年第5期1卷 1-24页

作者： Menegazzo, Jeferson von Wangenheim, Aldo Graduate Program in Computer Science (PPGCC) Image Processing and Computer Graphics Lab (LAPIX) Department of Informatics and Statistics (INE) Brazilian Institute for Digital Convergence (INCoD) Federal University of Santa Catarina (UFSC) Santa Catarina Florianópolis Brazil

In this paper, we present a structured literature mapping of the state-of-the-art of vehicular perception methods and approaches using inertial sensors. An in-depth investigation and classification were performed employing the results of a systematic literature review. The analysis focused on identifying methods that capture signals provided by inertial sensors such as accelerometers and gyroscopes to recognize transient or persistent events associated with the vehicle’s movement. We classified these events into vehicular exteroception, associated with potholes, cracks, speed bumps, pavement type, conservation state;and vehicular proprioception, associated with lane change, braking, skidding, aquaplaning, turning right or left. Through the comprehensive study of publications in a 7-year time window, in addition to the methods, we have also identified their dependency factors, hardware platforms and applications. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Driver behaviour Driving style Inertial sensors Intelligent transport systems Road conditions Road surface anomaly

来源：评论

学校读者我要写书评

暂无评论

Contour Detection from Ultrasound Kidney Images with A Coarse-to-Fine Approach

Contour Detection from Ultrasound Kidney Images with A Coars...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Peng, Tao Gu, Yidong Xu, Yanqing Wang, Caishan Zhang, Lei Cai, Jing School of Future Science and Engineering Soochow University Suzhou China UT Southwestern Medical Center Department of Radiation Oncology DallasTX United States The Affiliated Suzhou Hospital of Nanjing Medical University Department of Medical Ultrasound Suzhou Municipal Hospital Jiangsu Suzhou China University of Texas Southwestern Medical Center McDermott Center for Human Growth and Development DallasTX United States The Second Affiliated Hospital of Soochow University Department of Ultrasound Suzhou China Duke Kunshan University Graduate Program of Medical Physics and Data Science Research Center Jiangsu Kunshan China The Hong Kong Polytechnic University Department of Health Technology and Informatics Hong Kong Hong Kong

ISBN: (纸本)9798350337020

Ultrasound kidney image segmentation presents significant challenges due to missing or ambiguous boundaries. In this study, we introduce a coarse-to-refinement approach incorporating four novel aspects. Firstly, we leverage the properties of a principal curve (PC) to automatically fine-tune the curve shape and employ a neural network's learning ability to reduce model error. Secondly, a deep fusion learning network is utilized for the coarse segmentation step, incorporating a parallel architecture to enhance deep-learning performance. Thirdly, addressing the limitation of standard PC-based methods in determining the number of vertices automatically, we propose an automatic searching polygon tracking method using a mean shift clustering-based approach to replace the projection and vertex extension step in standard PC-based methods. Lastly, we develop an explainable mathematical map function for the kidney contour, as denoted by the neural network output (i.e., optimized vertices), which aligns well with the ground truth contour. We conducted various experiments to evaluate our method's performance, demonstrating its effectiveness in ultrasound kidney image segmentation. © 2023 IEEE.

关键词： Artificial intelligence Explainable mathematical model Ultrasound kidney segmentation

来源：评论

学校读者我要写书评

暂无评论

Air Medical Blood Transfusion as a Trigger of Massive Transfusion Protocol

引用

Air Medical Journal 2023年第5期42卷 353-357页

作者： Cornelius, Brian Thompson, Dennis Kilgore, Phillip Cvek, Urska Trutschl, Marjan Samra, Navdeep Cornelius, Angela Graduate Program in Nurse Anesthesia Texas Wesleyan University Fort Worth TX United States Department of Anesthesia John Peter Smith Hospital Fort Worth TX United States Department of Anesthesia Ochsner LSU Health Shreveport LA United States Department of Emergency Medicine Louisiana State University Health Sciences Center Shreveport LA United States Laboratory for Advanced Biomedical Informatics Department of Computer Science Louisiana State University Shreveport LA Department of Trauma and Surgical Critical Care Louisiana State University Health Sciences Center Shreveport LA United States Department of Emergency Medicine John Peter Smith Hospital Fort Worth TX United States

Air medical services can improve access to blood products at the point of injury. Studies have shown that early activation of mass transfusion protocols (MTPs) can improve the survival of trauma patients by up to 25%. There are several scoring systems to guide early activation, but the use of a single criterion has been elusive. Our study sought to determine if air medical administration of blood products was a risk factor for massive transfusion activation and utilization of prehospital vital signs for calculation of the shock index. In our retrospective study, we evaluated adult trauma patients transfused by helicopter emergency medical services (HEMS) and as a control all patients in our institution receiving the MTP. Our study found HEMS blood transfusion was not a reliable trigger for MTP, although the sample size may have limited our findings. We found that HEMS care resulted in an overall reduction in the volume of transfusion and an improvement in hemodynamic parameters upon trauma center arrival. HEMS transfusion and a higher rate of tranexamic acid administration may have contributed to these findings. Of note, the assessment of blood consumption score and shock index were nonspecific in the study populations. © 2023 Air Medical Journal Associates

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating action plans for smart poultry houses

arXiv

引用

arXiv 2020年

作者： Klotz, Darlan Felipe Ribeiro, Richardson Enembreck, Fabrcio Denardin, Gustavo Barbosa, Marco Casanova, Dalcimar Teixeira, Marcelo Graduate Program in Electrical Engineering Federal University of Technology Paran Pato Branco Brazil Graduate Program in Informatics of the Pontifical Catholic University of Paran Curitiba Brazil

In poultry farming, the systematic choice, update, and implementation of periodic (t) action plans define the feed conversion rate (FCRhti), which is an acceptable measure for successful production. Appropriate action plans provide tailored resources for broilers, allowing them to grow within the so-called thermal comfort zone, without wast or lack of resources. Although the implementation of an action plan is automatic, its configuration depends on the knowledge of the specialist, tending to be inefficient and error-prone, besides to result in different FCRhti for each poultry house. In this article, we claim that the specialist’s perception can be reproduced, to some extent, by computational intelligence. By combining deep learning and genetic algorithm techniques, we show how action plans can adapt their performance over the time, based on previous well succeeded plans. We also implement a distributed network infrastructure that allows to replicate our method over distributed poultry houses, for their smart, interconnected, and adaptive control. A supervision system is provided as interface to users. Experiments conducted over real data show that our method improves 5% on the performance of the most productive specialist, staying very close to the optimal FCR(t).MSC Codes 68T35 (Primary) 93C40 (Secondary) Copyright © 2020, The Authors. All rights reserved.

关键词： Adaptive control systems

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：