检索结果-内蒙古大学图书馆

2022 International Electrical Engineering Congress, iEECON 2022

作者： Sonsilphong, Suphachoke Sonsilphong, Amornthep Hormdee, Daranee Khampitak, Kovit Khon Kaen University Data Science Health Informatics Program Academic Affairs Faculty of Medicine Khon Kaen Thailand Rajamangala University of Technology Isan Department of Electrical Engineering Khon Kean Thailand Khon Kaen University Embedded System RD Group Department of Computer Engineering Faculty of Engineering Khon Kean Thailand Khon Kean University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kean Thailand

ISBN: (纸本)9781665402064

This paper presents the development of an object detection system based on the deep learning approach of computer vision to support the laparoscopic surgical robotic position control system. The system comprises two main phases, the training phase, and the real-time operating phase. In the training phase, a modified YOLOv4 algorithm is proposed to be adopted within the Darknet framework for training the weights of detection models. The best detection model is then selected to be assigned to the object detector in the real-time operating phase. The validation result of the detection model across the experiment datasets is 90% accuracy on average during the training phase. To validate the viability of real-time object detection, the proposed system was implemented in two test-cases of gynecologic surgery with the soft-body cadavers. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

consexpressionR: an R package for consensus differential gene expression analysis

arXiv

引用

arXiv 2025年

作者： Costa-Silva, Juliana Menotti, David Lopes, Fabricio M. Department of Informatics Federal University of Paraná Rua Coronel Francisco Heráclito dos Santos 100 Paraná81531-990 Brazil Department of Computer Science Bioinformatics Graduate Program Federal University of Technology - Paraná Av. Alberto Carazzai 1640 - Cornélio Procópio ParanáPostal code: 86300-000 Brazil

Motivation: Bulk RNA-Seq is a widely used method for studying gene expression across a variety of contexts. The significance of RNA-Seq studies has grown with the advent of high-throughput sequencing technologies. Computational methods have been developed for each stage of the identification of differentially expressed genes. Nevertheless, there are few studies exploring the association between different types of methods. In this study, we evaluated the impact of the association of methodologies in the results of differential expression analysis. By adopting two data sets with qPCR data (to gold-standard reference), seven methods were implemented and assessed in R packages (EBSeq, edgeR, DESeq2, limma, SAMseq, NOISeq, and Knowseq), which was performed and assessed separately and in association. The results were evaluated considering the adopted qPCR data. Results: Here, we introduce consexpressionR, an R package that automates differential expression analysis using consensus of at least seven methodologies, producing more assertive results with a significant reduction in false positives. Availability: consexpressionR is an R package available via Source code and support are available at GitHub (https://***/costasilvati/consexpressionR). © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning in Predicting Financial Distress of Indonesian Public Company 8

Ensemble Learning in Predicting Financial Distress of Indone...

引用

8th International Conference on Information and Communication Technology, ICoICT 2020

作者： Rahayu, Dyah Sulistyowati Suhartanto, Heru Pancasila University Informatics Department Jakarta Indonesia University of Indonesia Faculty of Computer Science Depok Indonesia Doctorate Program Computer Science University of Indonesia Depok Indonesia

ISBN: (纸本)9781728161426

Predicting financial distress can avoid firm bankruptcy. That is an important issue in matters of company sustainability and the economic growth in general. Indonesia as a developing country needs a reliable system that is able to predict the bankruptcy of a company because it can affect the overall economic condition at different levels. The ensemble learning which is built to achieve better performance of prediction can be implemented to forecast the unhealthy company conditions. Random forest ensemble learning and AdaBoost have been proven superior to the single one. Both methods are applied to Indonesia Public Company data with 6 variables based on Altman Z-Score and one additional variable. The accuracy, precision, recall, and f1-score have an average of 91% regardless of the data imbalance. The ensemble score determines its superiority to the single machine learning. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach to discover and quantify systemic lupus erythematosus etiological heterogeneity from electronic health records

arXiv

引用

arXiv 2025年

作者： Mota, Marco Barbero Still, John M. Gamboa, Jorge L. Strobl, Eric V. Stein, Charles M. Kawai, Vivian K. Lasko, Thomas A. Vanderbilt University Medical Center Department of Biomedical Informatics United States Vanderbilt University Medical Center Department of Medicine United States Vanderbilt University Medical Center Department of Psychiatry and Behavioral Sciences United States Vanderbilt University Medical Center Department of Computer Science United States Vanderbilt DBMI PhD program 2525 West End Ave NashvilleTN United States

Systemic lupus erythematosus (SLE) is a complex heterogeneous disease with many manifestational facets. We propose a data-driven approach to discover probabilistic independent sources from multimodal imperfect EHR data. These sources represent exogenous variables in the data generation process causal graph that estimate latent root causes of the presence of SLE in the health record. We objectively evaluated the sources against the original variables from which they were discovered by training supervised models to discriminate SLE from negative health records using a reduced set of labelled instances. We found 19 predictive sources with high clinical validity and whose EHR signatures define independent factors of SLE heterogeneity. Using the sources as input patient data representation enables models to provide with rich explanations that better capture the clinical reasons why a particular record is (not) an SLE case. Providers may be willing to trade patient-level interpretability for discrimination especially in challenging cases. © 2025, CC BY-NC-ND.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation

arXiv

引用

arXiv 2024年

作者： Tang, Xiangru Dai, Howard Knight, Elizabeth Wu, Fang Li, Yunyang Li, Tianxiao Gerstein, Mark Department of Computer Science Yale University New HavenCT06520 United States School of Medicine Yale University New HavenCT06520 United States Computer Science Department Stanford University CA94305 United States Program in Computational Biology & Bioinformatics Yale University New HavenCT06520 United States Department of Molecular Biophysics & Biochemistry Yale University New HavenCT06520 United States Department of Statistics & Data Science Yale University New HavenCT06520 United States Department of Biomedical Informatics & Data Science Yale University New HavenCT06520 United States

Artificial intelligence (AI)-driven methods can vastly improve the historically costly drug design process, with various generative models already in widespread use. Generative models for de novo drug design, in particular, focus on the creation of novel biological compounds entirely from scratch, representing a promising future direction. Rapid development in the field, combined with the inherent complexity of the drug design process, creates a difficult landscape for new researchers to enter. In this survey, we organize de novo drug design into two overarching themes: small molecule and protein generation. Within each theme, we identify a variety of subtasks and applications, highlighting important datasets, benchmarks, and model architectures and comparing the performance of top models. We take a broad approach to AI-driven drug design, allowing for both micro-level comparisons of various methods within each subtask and macro-level observations across different fields. We discuss parallel challenges and approaches between the two applications and highlight future directions for AI-driven de novo drug design as a whole. An organized repository of all covered sources is available at https://***/gersteinlab/GenAI4Drug. © 2024, CC BY.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Digital art technology publication in indonesia: A bibliometric analysis (2011-2020) technology 6

Digital art technology publication in indonesia: A bibliomet...

引用

6th International Conference on Information Management and Technology, ICIMTech 2021

作者： Maulana, Fairuz Iqbal Audia Agustina, Ira Gasa, Frederik Masri Rahmadika, Sandi Ramdania, Diena Rauda Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Design Interior Design Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Economics Communication Communication Science Department Jakarta11480 Indonesia National University Busan Interdisciplinary Program of Information Security Graduate School Pukyong Korea Republic of UIN Sunan Gunung Djati Department of Informatics Bandung Indonesia

ISBN: (纸本)9781665449373

Digital art technology is a form of technology in the form of hardware or software that can produce artistic works or practices as part of the creative process. This research is an idea about the publication of digital art technology, which shows its widespread use based on data from publications in Indonesia. This study visually maps scientific publications in digital techniques indexed with bibliometric analysis at the Indonesian state level. This study collected data from the Scopus database, used the Scopus website analysis feature, and visualized the bibliometric network using Vosviewer. The method used consists of five phases: search keyword determination, initial search results, search results refinement, preliminary compilation and data analysis. 57 academic documents published in Indonesia between 2011 and 2020 were obtained in the search for data based on the Scopus database. The processed data show patterns and trends in the increasing number of international publications in digital art technology indexed by Scopus. This study proposes a classification of the convergence axis. © 2021 IEEE.

关键词： Arts computing

来源：评论

学校读者我要写书评

暂无评论

Utilization of Linguistic Data for Learner Assessment on e-Learning: Instrument and Processing

Utilization of Linguistic Data for Learner Assessment on e-L...

引用

International Conference on informatics and Computing (ICIC)

作者： Wenty Dwi Yuniarti Sri Hartati Sigit Priyanta Herman Dwi Surjono Doctoral Program of Computer Science Universitas Gadjah Mada Yogyakarta Indonesia Universitas Islam Negeri Walisongo Semarang Indonesia Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia Department of Informatics Engineering Education Faculty of Engineering Universitas Negeri Yogyakarta Yogyakarta Indonesia

ISBN: (纸本)9798350345728

The increasingly massive use of e-Learning illustrates the speed and need for innovation in learning. According to the National Higher Education Standards (SN-Dikti), constructive alignment is required between learning outcomes, processes, and assessments to properly implement learning in e-Learning. Assessment is an essential component of e-Learning. Unfortunately, the problem of assessment in e-Learning is still found. One of them is the limitations of e-Learning in accommodating and processing various assessment data, primarily linguistic. Even though the variety of assessment data, both numerical, linguistic, and a combination of the two, supports a comprehensive assessment. On the other hand, the accommodation of linguistic data raises problems regarding how to process of unifying linguistic data is carried out. Research related to linguistic data using computing with words has been carried out, but it still needs more precise results from the unification of the linguistic data. Therefore, this study proposes providing an assessment instrument to accommodate linguistic data in e-Learning, as well as showing how to process of unifying linguistic data is carried out using 2-Tuple Fuzzy Linguistic. This approach can avoid the loss of assessment information by presenting more informative and precise results in a 2-tuple (s, α) where $s$ indicates the ability level, and α shows a comparison of abilities with other learners and the potential of the learner to achieve higher abilities. This proposal has the potential to be applied in a learner assessment system for higher education e-Learning.

关键词： Technological innovation Electronic learning Instruments Education Linguistics Proposals informatics

来源：评论

学校读者我要写书评

暂无评论

Using CRF+LG for automated classification of named entities in newspaper texts 46

Using CRF+LG for automated classification of named entities ...

引用

46th Latin American Computing Conference, CLEI 2020

作者： De Oliveira Lima, Jaimel Da Silveira Colombo, Cristiano Izo, Flavio Pirovani, Juliana Campos Pinheiro De Oliveira, Elias Postgraduate Program in Informatics Federal University of Espirito Santo Brazil Department of Computer Science Federal University of Espirito Santo Brazil

ISBN: (纸本)9780738130644

Information production has been growing at an accelerated rate. There is a large amount of information to be processed, which makes tasks related to the collection and explotation of text challenging, requiring effort from the most diverse areas, especially computational linguistics. One of the goals of computational linguistics is to enable the collection and explotation of linguistic datasets, through empirical evidence, extracted with the application of computational resources. This work presents the creation of dataset extracted from a newspaper. Techniques were used for extracting sentences, tokenization, named entities recognition (NER), as well as statistical methods for describing the dataset. Other researchers can directly benefit from the available corpus. This work presents a corpus with 1029 annotated news articles in Portuguese for entities according to HAREM categories. In a sample of 108 pages, our experiments show a 97.0% similarity compared to gold standard texts from the same newspaper. For the NER task and automatic annotation of the extracted dataset, proportions of the datasets of Second Harem and aTribuna100 were used to train a hybrid model CRF+LG. With the trained model, the 1029 articles extracted were automatically annotated. In general, the values of the metrics demonstrate that optimal metrics achievements for the classification model for the 70/30 Proportion, especially for the Person (PER) category, reaching 91.11% and 95.82% for precision and recall, respectively. Overall, the model showed 95.86% accuracy. © 2020 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Air Box Application for Indoor Environment Classification and LSTM Microclimate Prediction

Low-Cost Air Box Application for Indoor Environment Classifi...

引用

International Conference on Control and Robots (ICCR)

作者： Hu Hsun-Jui Chiu Yu-Hsien Yang Pei-Ching Master Degree Program in Information and Design Chang Jung Christian University Tainan Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Artificial Intelligence Research Center Chang Jung Christian University Tainan Taiwan Department of Computer Science and Information Engineering Chang Jung Christian University Tainan Taiwan

ISBN: (数字)9798331518158

ISBN: (纸本)9798331518165

Air pollution is a significant issue because it burdens human health and the environment. Particulate matter with a diameter of 2.5 micrometers or smaller (PM2.5) can penetrate the lungs and enter the bloodstream, seriously affecting the cardiovascular system, causing strokes, and impacting the respiratory system. Modern individuals spend 70% to 90% of their time indoors, making indoor air quality even more important than outdoor air quality. To estimate and predict indoor air quality, this study utilizes low-cost, self-assembled air boxes based on the Internet of Things to collect various air quality data. The collected data is then used in an indoor air quality forecasting system that combines Long Short-Term Memory (LSTM) and K-means clustering methods to compare the overall performance of the algorithms. The experimental results are analyzed and statistically described based on each model method prediction accuracy and clustering results. These methods are integrated to develop an indoor air quality forecasting system to help indoor populations prevent issues in advance or optimize energy usage.

关键词： Temperature measurement Temperature sensors Atmospheric modeling Predictive models Air quality Data models Forecasting Long short term memory Monitoring Indoor air quality

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

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：