检索结果-内蒙古大学图书馆

Detecting Hydronephrosis Through Ultrasound Images Using State-of-the-Art Deep Learning Models

Ultrasound in Medicine and Biology 2023年第3期49卷 723-733页

作者： Lien, Wan-Ching Chang, Yi-Chung Chou, Hsin-Hung Lin, Lung-Chun Liu, Yueh-Ping Liu, Li Chan, Yen-Ting Kuan, Feng-Sen Department of Emergency Medicine National Taiwan University Hospital Taipei Taiwan Department of Emergency Medicine College of Medicine National Taiwan University Taipei Taiwan Department of Computer Science and Engineering National Chi Nan University Nantou Taiwan Department of Medical Affairs Ministry of Health and Welfare Taipei Taiwan Show Chwan Health Care System Taipei Taiwan Department of Research Planning of Omni Health Group Inc. Taipei Taiwan Department of Business Development Huasin H. T. Limited Taipei Taiwan

The goal of this study was to assess the feasibility of three models for detecting hydronephrosis through ultrasound images using state-of-the-art deep learning algorithms. The diagnosis of hydronephrosis is challenging because of varying and non-specific presentations. With the characteristics of ready accessibility, no radiation exposure and repeated assessments, point-of-care ultrasound becomes a complementary diagnostic tool for hydronephrosis;however, inter-observer variability still exists after time-consuming training. Artificial intelligence has the potential to overcome the human limitations. A total of 3462 ultrasound frames for 97 patients with hydronephrosis confirmed by the expert nephrologists were included. One thousand six hundred twenty-eight ultrasound frames were also extracted from the 265 controls who had normal renal ultrasonography. We built three deep learning models based on U-Net, Res-UNet and UNet++ and compared their performance. We applied pre-processing techniques including wiping the background to lessen interference by YOLOv4 and standardizing image sizes. Also, post-processing techniques such as adding filter for filtering the small effusion areas were used. The Res-UNet algorithm had the best performance with an accuracy of 94.6% for moderate/severe hydronephrosis with substantial recall rate, specificity, precision, F1 measure and intersection over union. The Res-UNet algorithm has the best performance in detection of moderate/severe hydronephrosis. It would decrease variability among sonographers and improve efficiency under clinical conditions. © 2022 World Federation for Ultrasound in Medicine & Biology

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

The Frontier of Geospatial AI Deep Learning Applications in Data Mining and Spatial Analysis

The Frontier of Geospatial AI Deep Learning Applications in ...

引用

2024 IEEE International Conference on Intelligent systems and Advanced Applications, ICISAA 2024

作者： Mishra, Ajit Kumar Verma, Vikash Manivannan, R. Kumar, N. Krishna Srividya, Mudunuru Sharma, Sanskriti IES College of Technology Department of Electrical & Electronics Engineering M.P Bhopal462044 India GGITS Dept of Artificial Intelligence & Machine Learning M.P Jabalpur India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology School of Computing Computer Science & Engineering TN Chennai India Guru Nanak Institutions Technical Campus Ibrahimpatam Dept.of CSE Telangana Hyderabad India MLR Institute of Technology Dept. of CSE Telangana Hyderabad India GGITS Dept of Computer Science & Business System M.P Jabalpur India

ISBN: (纸本)9798331539948

Modern artificial intelligence uses geographical data mining and regional analysis to analyze large datasets. Deep learning is a new geographic AI method. Example: Geographic Deep Mining Network (GDMN). The Spatial Feature Extractor (SFE), Temporal Geospatial Attention Mechanism (TGAM), and Geospatial Data Fusion Module (GDFM) comprise this technique. We examined six popular approaches and found GDMN performed best. It worked successfully for several reasons. GDMN always outperforms its competitors in memory, F1 score, IoU, training time, and inference time. This is always true. These findings suggest that GDMN might boost geospatial AI's data mining and location analysis abilities. After all the effort, we have developed a solid basis for location intelligence, making it useful in various subject areas. Because it's versatile, mapping specialists may use GDMN for better environmental monitoring or city development. Deep learning helps GDMN make better space choices and uncover insights in large, challenging data sets that no one knew about. GDMN's cutting-edge approaches make space and time research and prediction simpler. This wide perspective offers a more full and all-encompassing picture of today's challenges than previous techniques. This makes it impossible to overstate how significant this work is to location intelligence. Its unmatched research and insights usher in a new era. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Developing an Automatic Approach to Generate Brick Model from Building Information Modelling

SSRN

引用

SSRN 2024年

作者： Li, Mingchen Wang, Zhe Fierro, Gabe Cecil, Man Chi Hou Patrick, So Pok Man Calvin, Leung Kin Fung Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computer Science Colorado School of Mines GoldenCO United States Hensen System Engineering Ltd. Hong Kong Electrical and Mechanical Services Department Government of the HKSAR Hong Kong

In the AECO (Architecture, engineering, Construction, and Operations) sector, addressing information silos for efficient building operation and maintenance is crucial. The Graph-based BIM (Building Information Modeling) supports information sharing and digital twin implementation but struggles to integrate operational data. The Brick ontology overcomes this by standardizing metadata for building assets and their relationships. However, errors in human-generated BIM models hinder widespread application. This paper introduces a novel BIM-to-Brick methodology that corrects IFC (Industry Foundation Classes) models, enabling the creation of high-quality Brick models from imperfect BIM ones. This method facilitates end-to-end digital twin creation with operational data integration, significantly reducing the effort by managing real-world BIM inaccuracies. Our case study confirms the method's effectiveness in generating compliant Brick models, showcasing its potential to improve information reusability and reduce information silos in construction. © 2024, The Authors. All rights reserved.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

Study of the Software Development Life Cycle and the Function of Testing

Study of the Software Development Life Cycle and the Functio...

引用

Interdisciplinary Humanitarian Conference for Sustainability (IIHC), International

作者： Sunil Gupta N Gayathri Department of Computer & System Sciences School of Computer & System Sciences Jaipur National University Jaipur India Department of Computer Science and Engineering Galgotias University Greater Noida Uttar Pradesh India

A construction investigation and configuration process that is imposed on the development of a software item is known as the software development life cycle. Testing is now an important and crucial phase in the software development life cycle in every organisation. Fundamentally important to the software development cycle is testing. Testing should begin early in the software development process to prevent potential bugs, reduce costs, and aid in determining requirements. Software testing is done with the intention of strengthening software and preventing problems. The testing phase of the software development life cycle is critical and vital. However, the manner in which it is finished varies from one association to the next. Software testing has evolved into a component of development, and it is wiser to start testing in the early phases in order to avoid problems by fixing bugs at the end. Additionally, the purpose of testing in the software development life cycle is to improve steadfast quality, execution, and other crucial components that may be characterized as SRS. The SDLC consist an explanatory plan that described to create, schedule, and maintain specific software. The organizational framework that explains the tasks carried out at each level of the software development procedure.

关键词： Software testing Schedules Costs computer bugs Windings Software Encoding

来源：评论

学校读者我要写书评

暂无评论

DeepCell: Multiview Representation Learning for Post-Mapping Netlists

arXiv

引用

arXiv 2025年

作者： Shi, Zhengyuan Ma, Chengyu Zheng, Ziyang Zhou, Lingfeng Pan, Hongyang Jiang, Wentao Yang, Fan Yang, Xiaoyan Chu, Zhufei Xu, Qiang Department of Computer Science and Engineering The Chinese University of Hong Kong Sha Tin Hong Kong Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China School of Computer Science Hangzhou Dianzi University Hangzhou China School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University Shanghai China National Center of Technology Innovation for EDA Nanjing China

Representation learning for post-mapping (PM) netlists is a critical challenge in Electronic Design Automation (EDA), driven by the diverse and complex nature of modern circuit designs. Existing approaches focus on intermediate representations like And-Inverter Graphs (AIGs), limiting their applicability to post-synthesis stages. We introduce DeepCell, a multiview representation learning framework that integrates structural and functional insights from both PM netlists and AIGs to learn rich, generalizable embeddings. At its core, DeepCell employs the novel Mask Circuit Modeling (MCM) mechanism, which refines PM netlist representations in a self-supervised manner using pretrained AIG encoders. DeepCell sets a new benchmark in PM netlist representation, outperforming existing methods in predictive accuracy and reconstruction fidelity. To validate its efficacy, we apply DeepCell to functional engineering Change Orders (ECO), achieving significant reductions in patch generation costs and runtime while improving patch quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Smart Manhole Management system for Real-time Status, Water Level, and Gas Detection

IoT-Enabled Smart Manhole Management System for Real-time St...

引用

Intelligent systems for Cybersecurity (ISCS), International Conference on

作者： Md Asif Imran S M Masfequier Rahman Swapno Gunjan Chhabra Keshav KaushiK Md. Arif Anzum Mahi Md Babul Islam Rezaul Haque Dept. of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Department of CSE Graphic Era Hill University Dehradun Uttarakhand India Adjunct Professor Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science University of Petroleum and Energy Studies Dehradun Uttarakhand India Dept. of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Applied Bahari Big Data Research House Dhaka Bangladesh Department of Computer Modeling Electronic and System Engineering UNICAL Rende Italy

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

Regular monitoring of the maintenance manhole system is imperative to uphold the city's health and cleanliness standards. Our study offers an intelligent manhole that monitors the manhole's condition, water level, and gases. We tested the status, gas, and water levels of our revolutionary, innovative manhole in several places. Our system's Blink app position tracking of our smart manhole is critical. This capability improves monitoring efficiency and speeds up issue resolution. Our work revolutionizes municipal utility maintenance and safety by optimizing manhole performance. Integrating a Node MCU, GPS module, gas sensor, ultrasonic sensor, and Android Blynk software creates a complete real-time monitoring and data-collecting system. Combining these technologies, our Manhole Monitoring system improves safety and streamlines maintenance, making municipal infrastructure more robust and efficient. This paper highlights the promising features of IoT and shows how it may be used to improve the smart manhole. In the future, this creative method may result in a more durable and better intelligent city.

关键词： Surveillance Urban areas Robot vision systems Transforms Cameras Real-time systems Maintenance

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Based Stochastic Dynamical Model to Measure Community Resilience

引用

Journal of Social Computing 2022年第3期3卷 262-286页

作者： Jaber Valinejad Lamine Mili C.Natalie Van Der Wal Data and System Science Lab Harvard Medical SchoolHarvard UniversityCambridgeMA 02138USA Bradley Department of Electrical and Computer Engineering Virginia TechNorthern Virginia CenterFalls ChurchVA 22043USA Department of Multi-Actor Systems Faculty of TechnologyPolicy and ManagementDelft University of TechnologyDelft2600 AAthe Netherlands.

Emergency services and utilities need appropriate planning tools to analyze and improve infrastructure and community resilience to *** as a key metric of community resilience is the social well-being of a community during a disaster,which is made up of mental and physical social *** factors influencing community resilience directly or indirectly are emotional health,emergency services,and the availability of critical infrastructures services,such as food,agriculture,water,transportation,electric power,and communications *** turns out that in computational social science literature dealing with community resilience,the role of these critical infrastructures along with some important social characteristics is not *** address these weaknesses,we develop a new multi-agent based stochastic dynamical model,standardized by overview,design concepts,details,and decision(ODD+D)protocol and derived from neuro-science,psychological and social sciences,to measure community resilience in terms of mental and physical *** this model,we analyze the micro-macro level dependence between the emergency services and power systems and social characteristics such as fear,risk perception,informationseeking behaviour,cooperation,flexibility,empathy,and experience,in an artificial ***,we simulate this model in two case studies and show that a high level of flexibility,experience,and cooperation enhances community *** for both theory and practice are discussed.

关键词： community resilience collective behavior emergency services power systems critical infrastructures artificial society overview,design concepts,details,and decision(ODD+D) cyber-physical-social system

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Software Development Life Cycle Model with Value of Testing and Quality Control

Evaluation of the Software Development Life Cycle Model with...

引用

Interdisciplinary Humanitarian Conference for Sustainability (IIHC), International

作者： Vikram Singh S Annamalai Department of Computer & System Sciences School of Computer & System Sciences Jaipur National University Jaipur India Department of Computer Science and Engineering Galgotias University Greater Noida Uttar Pradesh India

One of the most noteworthy, essential, and important issues in the PC world is software project development. It is a portion of the life cycle for developing frameworks (SDLC). The goal of the SDLC is to reduce the likelihood of failure and disappointment while improving the quality of the software product. The structure that includes multiple tasks and assignments to be completed during the software development process is known as the SDLC. In order to examine existing models, have included five of these SDLC models in this paper: the cascade model, the angular model, the twisting model, and the iterative model. As a result, support and upgrades for the software should be based on current requirements for long-term and stable usage. This study illustrates the concept of testing and its role in quality assurance, experimentation and test levels, and the ongoing planning, execution, and observation of tests. This outline was created with the intention of focusing on the current SDLC sequence.. Approx 300 circulations were selected in addition to the crucial accentuation carried out with embeddings inquiry toward the open-source data collections.

关键词： Software testing Quality assurance Windings Process control Quality control Software Planning

来源：评论

学校读者我要写书评

暂无评论

Darcy-Forchheimer mangetized flow based on differential type nanoliquid capturing Ohmic dissipation effects

引用

Propulsion and Power Research 2023年第3期12卷 443-455页

作者： M.Waqas Yunjie Xu M.Nasir Md Mottahir Alam Amjad Ali Pasha Kashif Irshad Bandar M.Fadhl M.S.Kausar NUTECH School of Applied Science and Humanities National University of TechnologyIslamabad 44000Pakistan Department of Mechanical Engineeing Lebanese American UniversityBeirutLebanon School of Engineering Huzhou UniversityHuzhou 313000China Faculty of Informatics and Computing University Sultan Zainal AbidinBesut Campus22200 BesutTereng-ganuMalaysia Department of Electrical and Computer Engineering King Abdulaziz UniversityJeddah 21589Saudi Arabia Aerospace Engineering Department King Abdulaziz UniversityJeddah 21589Saudi Arabia Interdisciplinary Research Centre for Renewable Energy and Power System(IRC-REPS) Research InstituteKing Fahd University of Petroleum and Minerals(KFUPM)Dhahran 31261Saudi Arabia Mechanical Engineering Department College of Engineering and Islamic ArchitectureUmm Al-Qura UniversityP.O.Box 5555Makkah 21955Saudi Arabia

Hydromagnetic nanoliquid establish an extraordinary category of nanoliquids that unveil both liquid and magnetic *** interest in the utilization of hydromagnetic nanoliquids as a heat transporting medium stem from a likelihood of regulating its flow along with heat transportation process subjected to an externally imposed magnetic *** analysis reports the hydromagnetic nanoliquid impact on differential type(second-grade)liquid from a convectively heated extending *** well-known Darcy-Forchheimer aspect capturing porosity characteristics is introduced for nonlinear *** conditions elaborating heat-mass transportation effect are *** addition,Ohmic dissipation and suction/injection aspects are also a part of this *** analysis is done by implementing the basic relations of fluid *** modeled physical problem is simplified through order *** resulting systems(partial differential expressions)are rendered to the ordinary ones by utilizing the apposite *** solutions are constructed employing homotopy *** and numeric result are addressed comprehensively to elaborate the nature of sundry parameters against physical *** velocity profile is suppressed with increasing Hartmann number(magnetic parameter)whereas it is enhanced with increment in material parameter(second-grade).With the elevation in thermophoresis parameter,temperature and concentration of nanoparticles are accelerated.

关键词： Darcy-Forchheimer magnetized flow Differential type nanoliquid Ohimc dissipation Robin conditions Homotopy algorithm

来源：评论

学校读者我要写书评

暂无评论

Analyses of Software Testing Approaches

Analyses of Software Testing Approaches

引用

Interdisciplinary Humanitarian Conference for Sustainability (IIHC), International

作者： Shalini Joshi Indra Kumari Department of Computer & System Sciences School of Computer & System Sciences Jaipur National University Jaipur India Department of Computer Science and Engineering Galgotias University Greater Noida Uttar Pradesh India

Software testing is an essential part of the Software Development Lifecycle because of its importance both before and after code is written. As such, it necessitates the use of well-developed, well-executed processes and procedures. This article attempts to discuss both existing testing techniques and possible enhancements to those procedures in the sake of higher quality assurance. Extensive testing, including validation and verification, is required to guarantee that the software satisfies all clients' requirements. As a result, software development processes and testing strategies are made. However, software testing strategies provide a well-thought-out sequence of actions that should reliably yield results, as opposed to software testing approaches, which focus on how to test a specific feature or function. In this analysis, the advantages and disadvantages of various software testing strategies are explored. Furthermore, it specifies the basic life cycles that must be observed throughout quality assurance testing.

关键词： Software testing Quality assurance Costs computer bugs Process control Quality control Software

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：