检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gilson, Aidan Ai, Xuguang Xie, Qianqian Srinivasan, Sahana Pushpanathan, Krithi Singer, Maxwell B. Huang, Jimin Kim, Hyunjae Long, Erping Wan, Peixing Del Priore, Luciano V. Ohno-Machado, Lucila Xu, Hua Liu, Dianbo Adelman, Ron A. Tham, Yih-Chung Chen, Qingyu Department of Ophthalmology Massachusetts Eye and Ear Harvard Medical School BostonMA United States Department of Biomedical Informatics and Data Science Yale School of Medicine Yale University New Haven United States Singapore Eye Research Institute Singapore National Eye Centre Singapore Centre for Innovation and Precision Eye Health Department of Ophthalmology Yong Loo Lin School of Medicine National University of Singapore Singapore Department of Ophthalmology and Visual Science Yale School of Medicine Yale University New Haven United States Department of Computer Science Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Division of Cancer Epidemiology and Genetics National Cancer Institute National Institutes of Health BethesdaMD United States Center for Cancer Research National Cancer Institute National Institutes of Health BethesdaMD United States Ophthalmology and Visual Science Academic Clinical Program Duke-NUS Medical School Singapore Singapore

Large Language Models (LLMs) are poised to revolutionize healthcare. Ophthalmology-specific LLMs remain scarce and underexplored. We introduced an open-source, specialized LLM for ophthalmology, termed Language Enhanced Model for Eye (LEME). LEME was initially pre-trained on the Llama2 70B framework and further fine-tuned with a corpus of ~127,000 non-copyrighted training instances curated from ophthalmology-specific case reports, abstracts, and open-source study materials. We benchmarked LEME against eight other LLMs, namely, GPT-3.5, GPT-4, three Llama2 models (7B, 13B, 70B), PMC-LLAMA 13B, Meditron 70B, and EYE-Llama (another ophthalmology-specific LLM). Evaluations included four internal validation tasks: abstract completion, fill-in-the-blank, multiple-choice questions (MCQ), and short-answer QA. External validation tasks encompassed long-form QA, MCQ, patient EHR summarization, and clinical QA. Evaluation metrics included Rouge-L scores, accuracy, and expert evaluation of correctness, completeness, and readability. In internal validations, LEME consistently outperformed its counterparts, achieving Rouge-L scores of 0.20 ± 0.03 in abstract completion (all p © 2024, CC BY.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Airplane type identification based on mask RCNN and drone images

arXiv

引用

arXiv 2021年

作者： Alshaibani, Waleed Tawfik Abdullah Helvaci, Mustafa Shayea, Ibraheem Saad, Sawsan A. Azizan, Azizul Yakub, Fitri Institute of Informatics Satellite Communication and Remote Sensing Program Istanbul Technical University ITU Ayazaga Campus Institute of Informatics Building Sariyer Istanbul34469 Turkey Istanbul34469 Turkey Faculty of Engineering and Built Environment Universiti Sains Islam Malaysia Negeri Sembilan Bandar BaruNilai71800 Malaysia Department of Computer Engineering College of Computer Science and Engineering University of Ha'il Saudi Arabia Advance Informatics Department Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia

For dealing with traffic bottlenecks at airports, aircraft object detection is insufficient. Every airport generally has a variety of planes with various physical and technological requirements as well as diverse service requirements. Detecting the presence of new planes will not address all traffic congestion issues. Identifying the type of airplane, on the other hand, will entirely fix the problem because it will offer important information about the plane's technical specifications (i.e., the time it needs to be served and its appropriate place in the airport). Several studies have provided various contributions to address airport traffic jams;however, their ultimate goal was to determine the existence of airplane objects. This paper provides a practical approach to identify the type of airplane in airports depending on the results provided by the airplane detection process using mask region convolution neural network. The key feature employed to identify the type of airplane is the surface area calculated based on the results of airplane detection. The surface area is used to assess the estimated cabin length which is considered as an additional key feature for identifying the airplane type. The length of any detected plane may be calculated by measuring the distance between the detected plane's two furthest points. The suggested approach's performance is assessed using average accuracies and a confusion matrix. The findings show that this method is dependable. This method will greatly aid in the management of airport traffic congestion. Copyright © 2021, The Authors. All rights reserved.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Inferring spatial transcriptomics markers from whole slide images to characterize metastasis-related spatial heterogeneity of colorectal tumors: A pilot study

引用

Journal of Pathology informatics 2023年 14卷 100308-100308页

作者： Fatemi, Michael Feng, Eric Sharma, Cyril Azher, Zarif Goel, Tarushii Ramwala, Ojas Palisoul, Scott M. Barney, Rachael E. Perreard, Laurent Kolling, Fred W. Salas, Lucas A. Christensen, Brock C. Tsongalis, Gregory J. Vaickus, Louis J. Levy, Joshua J. Department of Computer Science University of Virginia Charlottesville VA United States Thomas Jefferson High School for Science and Technology Alexandria VA United States Department of Computer Science Purdue University West Lafayette IN United States Department of Computer Science Massachusetts Institute of Technology Cambridge MA United States Department of Biomedical Informatics and Medical Education University of Washington Seattle WA United States Emerging Diagnostic and Investigative Technologies Department of Pathology and Laboratory Medicine Dartmouth Health NH United States Dartmouth Cancer Center NH United States Department of Epidemiology Dartmouth College Geisel School of Medicine Hanover NH United States Department of Molecular and Systems Biology Dartmouth College Geisel School of Medicine Hanover NH United States Integrative Neuroscience at Dartmouth (IND) graduate program Dartmouth College Geisel School of Medicine Hanover NH United States Department of Community and Family Medicine Dartmouth College Geisel School of Medicine Hanover NH United States Department of Dermatology Dartmouth Health NH United States Program in Quantitative Biomedical Sciences Dartmouth College Geisel School of Medicine Hanover NH United States

Over 150 000 Americans are diagnosed with colorectal cancer (CRC) every year, and annually over 50 000 individuals will die from CRC, necessitating improvements in screening, prognostication, disease management, and therapeutic options. Tumor metastasis is the primary factor related to the risk of recurrence and mortality. Yet, screening for nodal and distant metastasis is costly, and invasive and incomplete resection may hamper adequate assessment. Signatures of the tumor-immune microenvironment (TIME) at the primary site can provide valuable insights into the aggressiveness of the tumor and the effectiveness of various treatment options. Spatially resolved transcriptomics technologies offer an unprecedented characterization of TIME through high multiplexing, yet their scope is constrained by cost. Meanwhile, it has long been suspected that histological, cytological, and macroarchitectural tissue characteristics correlate well with molecular information (e.g., gene expression). Thus, a method for predicting transcriptomics data through inference of RNA patterns from whole slide images (WSI) is a key step in studying metastasis at scale. In this work, we collected tissue from 4 stage-III (pT3) matched colorectal cancer patients for spatial transcriptomics profiling. The Visium spatial transcriptomics (ST) assay was used to measure transcript abundance for 17 943 genes at up to 5000 55-micron (i.e., 1–10 cells) spots per patient sampled in a honeycomb pattern, co-registered with hematoxylin and eosin (H&E) stained WSI. The Visium ST assay can measure expression at these spots through tissue permeabilization of mRNAs, which are captured through spatially (i.e., x–y positional coordinates) barcoded, gene specific oligo probes. WSI subimages were extracted around each co-registered Visium spot and were used to predict the expression at these spots using machine learning models. We prototyped and compared several convolutional, transformer, and graph convolutional neural

关键词： Colorectal cancer Deep learning Graph neural network Histomorphology Spatial transcriptomics Transformers

来源：评论

学校读者我要写书评

暂无评论

TOWARDS AUDITABILITY REQUIREMENTS SPECIFICATION USING AN AGENT-BASED APPROACH

arXiv

引用

arXiv 2020年

作者： de Albuquerque, Denis J.S. Nunes, Vanessa Tavares Cappelli, Claudia Ralha, Célia Ghedini Department of Computer Science University of Brasilia Brazil Informatics Graduate Program Federal University of Rio de Janeiro Brazil

Transparency is an important factor in democratic societies composed of characteristics such as accessibility, usability, informativeness, understandability and auditability. In this research we focus on auditability since it plays an important role for citizens that need to understand and audit public information. Although auditability has been a subject of discussion when designing systems, there is a lack of systematization in its specification. We propose an approach to systematically add auditability requirements specification during the goal-oriented agent-based Tropos methodology. We used the Transparency Softgoal Interdependency Graph that captures the different facets of transparency while considering their operationalization. An empirical evaluation was conducted through the design and implementation of LawDisTrA system that distributes lawsuits among judges in an appellate court. Experiments included the distribution of over 300,000 lawsuits at the Brazilian Superior Labor Court. We theorize that the presented approach for auditability provides adequate techniques to address the cross-organizational nature of transparency. Copyright © 2020, The Authors. All rights reserved.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Comparison heuristics method for solving two echelon vehicle routing problem

引用

AIP Conference Proceedings 2024年第1期3029卷

作者： Muhammad Khahfi Zuhanda Saib Suwilo Opim Salim Sitompul Mardiningsih Informatics Engineering Study Program Faculty Engineering Universitas Medan Area Medan Indonesia Department of Mathematics Universitas Sumatera Utara Medan Indonesia Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

Today, almost everyone has done online shopping activities. The presence of e-commerce makes it easier for humans to do shopping. E-commerce companies compete to provide the best service to the community. One of them is in the delivery within the city. In terms of city delivery, the 2E-VRP model has been discussed a lot lately in terms of consolidating shipments. This study aims to present the 2E-VRP mathematical model and work in two stages to find a solution. In this article, the author also compares solutions with several heuristic models including 2-opt, repetitive nearest neighbor, nearest neighbor, farthest insertion, cheapest insertion, arbitrary insertion, and nearest insertion. From the results of research conducted by the 2-opt method, farthest insertion, cheapest insertion, and nearest insertion, the total distance is the best, all three get the same distance, then followed by the nearest insertion, arbitrary insertion, and nearest insertion methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： de Franca, F.O. Virgolin, M. Kommenda, M. Majumder, M.S. Cranmer, M. Espada, G. Ingelse, L. Fonseca, A. Landajuela, M. Petersen, B. Glatt, R. Mundhenk, N. Lee, C.S. Hochhalter, J.D. Randall, D.L. Kamienny, P. Zhang, H. Dick, G. Simon, A. Burlacu, B. Kasak, Jaan Machado, Meera Wilstrup, Casper Cavaz, W.G.L. Federal University of ABC Santo Andre Brazil Evolutionary Intelligence group Centrum Wiskunde and Informatica Science Park Amsterdam Netherlands University of Applied Sciences Upper Austria Hagenberg Austria Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School Boston USA Center for Computational Astrophysics Flatiron Institute and Department of Astrophysical Sciences of Princeton University USA LASIGE Faculdade de Ciências Universidade de Lisboa Lisboa Portugal Computational Engineering Division Lawrence Livermore National Laboratory Livermore USA Department of Mechanical Engineering University of Utah Utah USA Meta FAIR France Victoria University of Wellington School of Engineering and Computer Science New Zealand University of otago Department of Information Science New Zealand Institut für Angewandte Physik Universität TübingenMax Planck Institute for Intelligent Systems Tübingen Germany Abzu AI Orient Plads 1 Nordhavn Denmark

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main promise of this approach is that it may return an interpretable model that can be insightful to users, while maintaining high accuracy. The current standard for benchmarking these algorithms is SRBench, which evaluates methods on hundreds of datasets that are a mix of real-world and simulated processes spanning multiple domains. At present, the ability of SRBench to evaluate interpretability is limited to measuring the size of expressions on real-world data, and the exactness of model forms on synthetic data. In practice, model size is only one of many factors used by subject experts to determine how interpretable a model truly is. Furthermore, SRBench does not characterize algorithm performance on specific, challenging sub-tasks of regression such as feature selection and evasion of local minima. In this work, we propose and evaluate an approach to benchmarking SR algorithms that addresses these limitations of SRBench by 1) incorporating expert evaluations of interpretability on a domain-specific task, and 2) evaluating algorithms over distinct properties of data science tasks. We evaluate 12 modern symbolic regression algorithms on these benchmarks and present an in-depth analysis of the results, discuss current challenges of symbolic regression algorithms and highlight possible improvements for the benchmark itself. Authors

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review

引用

The Lancet Digital Health 2024年第5期6卷 e367-e373页

作者： Han, Ryan Acosta, Julián N Shakeri, Zahra Ioannidis, John P A Topol, Eric J Rajpurkar, Pranav Department of Biomedical Informatics Harvard Medical School BostonMA United States Department of Computer Science Stanford University StanfordCA United States University of California Los Angeles–Caltech Medical Scientist Training Program Los AngelesCA United States Department of Neurology Yale School of Medicine New HavenCT United States Rad AI San FranciscoCA United States Institute of Health Policy Management and Evaluation Dalla Lana School of Public Health University of Toronto TorontoON Canada Stanford Prevention Research Center Department of Medicine Stanford University StanfordCA United States Meta-Research Innovation Center at Stanford Stanford University StanfordCA United States Scripps Research Translational Institute Scripps Research La JollaCA United States

This scoping review of randomised controlled trials on artificial intelligence (AI) in clinical practice reveals an expanding interest in AI across clinical specialties and locations. The USA and China are leading in the number of trials, with a focus on deep learning systems for medical imaging, particularly in gastroenterology and radiology. A majority of trials (70 [81%] of 86) report positive primary endpoints, primarily related to diagnostic yield or performance;however, the predominance of single-centre trials, little demographic reporting, and varying reports of operational efficiency raise concerns about the generalisability and practicality of these results. Despite the promising outcomes, considering the likelihood of publication bias and the need for more comprehensive research including multicentre trials, diverse outcome measures, and improved reporting standards is crucial. Future AI trials should prioritise patient-relevant outcomes to fully understand AI's true effects and limitations in health care. © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Investigation and Incident Response in Internet of Things (IoT-DFIR): Challenges and Models

Digital Forensics Investigation and Incident Response in Int...

引用

International Conference on Wireless and Telematics (ICWT)

作者： Syaiful Ahdan Eki Ahmad Zaki Hamidi Sampurna Dadi Riskiono Ridha Muldina Negara Ratna Mayasari Suci Ramadona Ade Nurhayati Adi Sucipto Jupriyadi Galih Nugraha Nurkahfi Dzata Farahiyah Muchammad Naseer Faculty of Engineering & Computer Science Universitas Teknokrat Indonesia Lampung Indonesia Electrical Engineering Department UIN Sunan Gunung Djati Bandung Bandung Indonesia School of Electrical Engineering Telkom University Bandung Indonesia Elearical Engineering Study Program Politeknik Caltex Riau Riau Indonesia Faculty of Engineering Institut Teknologi Telkom Jakarta Jakarta Indonesia National Research and Innovation Agency (BRIN) Bandung Indonesia Faculty of Industrial Technology Universitas Islam Indonesia Yogyakarta Yogyakarta Indonesia Informatics Department Sekolah Tinggi Teknologi Bandung Bandung Indonesia

Many different industries are currently making substantial use of the Internet of Things (IoT). IoT is the process through which electronic devices communicate with their surrounding virtual environment by continuously exchanging data via sensors. Due to increased IoT security concerns, digital forensic investigators now possess greater knowledge and abilities to investigate IoT devices. IoT-DigFor are required in terms of cybercrime due to the rapid growth in the number of electronic devices and the collection and consumption of enormous amounts of data. IoT systems with billions of devices have produced a significant amount of evidence, which presents a significant challenge to digital investigators and practitioners who must connect with IoT devices to conduct fast and thorough investigations into cybercrimes. This article presents detailed information about forensics in the IoT environment. The IoT forensic paradigm and the challenges that design-based security requirements and IoT system security offer for IoT-DigFor are covered in great detail at the beginning of the article.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of Information Technology Investment (a case study of ODOO ERP: Project Management Module Implementation in Indonesia Based Company) 10

Feasibility study of Information Technology Investment (a ca...

引用

10th International Conference on ICT for Smart Society, ICISS 2019

作者： Jingga, Fredy Kosala, Raymond Supangkat, Suhono Harso Ranti, Benny School of Information Systems Bina Nusantara University Computer Science Department BINUS Graduate Program-Doctor of Computer Science Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program-Doctor of Computer Science Jakarta11480 Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9781728148809

IT Governance are one of the needs in managing Enterprise Level IT. This study shows part of the decision domain of IT Governance Help, which are IT Investment and Prioritization. The purpose of this study is to determine feasibility of implementation open source ERP system Odoo project management module that replaces current system based on operational, economic, and technical aspects. The method used are Fit/Gap Analysis and Cost Benefit model using economic impact worksheet. The analysis is done by comparing the requirement with features owned by current system and Odoo ERP system. This research resulted that Odoo ERP System is feasible in the 3 aspects, the operational feasibility Odoo reaching 72% Fit, the economic feasibility with ROI of 84%, and technical feasibility indicating the technical requirement can be fulfilled by leasing AWS server. The conclusion is the open source ERP system Odoo project management module is feasible to be applied in terms of 3 aspects that have been studied, those are operational, economic, and technical. © 2019 IEEE.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Applying mobility business intelligence concept in analyzing oil palm plantation productivity

引用

AIP Conference Proceedings 2024年第1期3026卷

作者： Andreas Wahyu Krisdiarto Irya Wisnubhadra Anzaludin Samsinga Perbangsa Teddy Suparyanto Bens Pardamean Faculty of Agricultural Technology STIPER Institute of Agriculture Yogyakarta Indonesia Informatics Engineering Department Atma Jaya Yogyakarta University Yogyakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia BDSRC Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

The palm oil business employs almost 20 million people, generates USD 21 billion in revenue, and plays a vital role in Indonesia’s social economy. The Fresh Fruit Bunches (FFB) to Palm Oil Mills (POM) distribution system is one important aspect of fruit quality. Three steps are involved in getting Oil Palm FFB from the plantation to the POM. The first part of the procedure involves cutting FFB from the tree, the second stage involves gathering the fruit at a fruit collection point (FCP), and the third stage involves transporting the fruit to the palm oil mill (POM). As of now, the cost of the FFB transportation is still considerable, accounting for roughly 15% to 20% of the FFB pricing. The use of the Business Intelligence (BI) idea in the oil palm harvesting system is presented in this study as a foundation for creating web-based applications.

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：