检索结果-内蒙古大学图书馆

Denoising Medical Images Using Deep Learning in IoT Environment

computers, Materials & Continua 2021年第12期69卷 3127-3143页

作者： Sujeet More Jimmy Singla Oh-Young Song Usman Tariq Sharaf Malebary School of Computer Science and Engineering Lovely Professional UniversityJalandharIndia Software Department Sejong UniversitySeoulKorea College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology in RabighKing Abdulaziz UniversityJeddah21911Saudi Arabia

Medical Resonance Imaging(MRI)is a noninvasive,nonradioactive,and meticulous diagnostic modality capability in the field of medical ***,the efficiency of MR image reconstruction is affected by its bulky image sets and slow process ***,to obtain a high-quality reconstructed image we presented a sparse aware noise removal technique that uses convolution neural network(SANR_CNN)for eliminating noise and improving the MR image reconstruction *** proposed noise removal or denoising technique adopts a fast CNN architecture that aids in training larger datasets with improved quality,and SARN algorithm is used for building a dictionary learning technique for denoising large image *** proposed SANR_CNN model also preserves the details and edges in the image during *** experiment was conducted to analyze the performance of SANR_CNN in a few existing models in regard with peak signal-to-noise ratio(PSNR),structural similarity index(SSIM),and mean squared error(MSE).The proposed SANR_CNN model achieved higher PSNR,SSIM,and MSE efficiency than the other noise removal *** proposed architecture also provides transmission of these denoised medical images through secured IoT architecture.

关键词： Medical resonance imaging convolutional neural network denoising contrast enhancement internet of things rheumatoid arthritis

来源：评论

学校读者我要写书评

暂无评论

An Architectural Extension for Digital Twin Platforms to Leverage Behavioral ModelsBehaviors

An Architectural Extension for Digital Twin Platforms to Lev...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Daniel Lehner Santiago Gil Peter H. Mikkelsen Peter G. Larsen Manuel Wimmer CDL-MINT Institute of Business Informatics - Software Engineering Johannes Kepler University Linz Austria Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark

To reduce the work effort for developing and managing Digital Twin (DT)-based services, so-called DT platforms have emerged recently. These DT platforms make it easier to collect, store, and manage data from physical devices, but often they do not provide means for running behavioral models or synchronizing these with runtime data from the physical devices. These aspects are however crucial for developing many DT-based services. As a result, the implementation of a DT that uses behavioral models still requires a lot of implementation effort, which hinders the adoption of DTs for many applications, in particular for small and medium-sized enterprises that often do not have the resources to implement such complex systems. In this paper, we propose an extension to existing DT platforms that simplifies the incorporation of behavioral models. We base this extended platform on requirements derived from two particular use case examples that require behavioral modeling to run their DT services. We discuss the interfaces offered by the extended DT platform, demonstrate its applicability and evaluate the implementation and adaptation effort of our proposed solution in comparison to a baseline implementation. Based on the case studies, the evaluation shows that the extended DT platform reduces the implementation effort by 56% and the effort for adapting DT services across DTs by 39%, compared to existing DT platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving PEM Hydrogen Electrolyser Efficiency using AC Excitation

Improving PEM Hydrogen Electrolyser Efficiency using AC Exci...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Thea Larsen Seho Kim John Kennedy Jingjing Liu Department of Electrical Computer and Software Engineering University of Auckland Auckland New Zealand Earth Resources and Materials Geological and Nuclear Science Wellington New Zealand Department of Chemical and Materials Engineering The University of Auckland Auckland New Zealand

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

Hydrogen is a potential clean energy source that minimises environmental impacts but is currently economically prohibitive due to the low energy conversion efficiency. In order to improve the economic viability, this paper investigates improving the efficiency of hydrogen electrolysis. The prototype power electronics presented in this paper provide low-frequency AC or pulsed current to a proton exchange membrane (PEM) electrolyser to improve the operational efficiency up to 4.2% in contrast to the typical constant current or voltage excitation.

关键词： Green energy Protons Electric potential Buck converters Power supplies Hydrogen Prototypes Voltage Energy conversion Electrochemical processes

来源：评论

学校读者我要写书评

暂无评论

Design, Testing, and Implementation of a Microgrid Controller Using IEC 61131-3

Design, Testing, and Implementation of a Microgrid Controlle...

引用

2022 IEEE Power and Energy Society General Meeting, PESGM 2022

作者： Kabalan, Mahmoud Masui, Ian Gamit, Himanshu University of St. Thomas Department of Electrical and Computer Engineering St Paul United States Graduate Programs in Software University of St. Thomas St Paul United States

ISBN: (数字)9781665408233

ISBN: (纸本)9781665408233

This paper presents a microgrid controller that was designed and implemented using the IEC 61131-3 standard. IEC 61131-3 is a standardized programming language for industrial automation and controllers. The microgrid controller is capable of essential microgrid functionalities such as blackstart, island-mode operation, grid-mode operation, and transitions from island to grid and vice versa. The controller was programmed and implemented using a Schweitzer engineering Laboratories SEL real-time automation controller RTAC 3555. The design and testing phase included a controller-hardware-in-the-loop testbed. The controller was field-tested on an industry-grade microgrid at real-scale. Experimental results show the performance of the microgrid controller under various operating conditions. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Everything you wanted to know about ChatGPT: Components, capabilities, applications, and opportunities

引用

Internet Technology Letters 2024年第6期7卷

作者： Heidari, Arash Navimipour, Nima Jafari Zeadally, Sherali Chamola, Vinay Department of Software Engineering Haliç University Istanbul Turkey Department of Computer Engineering Faculty of Engineering and Natural Science İstanbul Atlas University Istanbul Turkey Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou Taiwan College of Communication and Information University of Kentucky LexingtonKY United States Pilani India

Conversational Artificial Intelligence (AI) and Natural Language Processing have advanced significantly with the creation of a Generative Pre-trained Transformer (ChatGPT) by OpenAI. ChatGPT uses deep learning techniques like transformer architecture and self-attention mechanisms to replicate human speech and provide coherent and appropriate replies to the situation. The model mainly depends on the patterns discovered in the training data, which might result in incorrect or illogical conclusions. In the context of open-domain chats, we investigate the components, capabilities constraints, and potential applications of ChatGPT along with future opportunities. We begin by describing the components of ChatGPT followed by a definition of chatbots. We present a new taxonomy to classify them. Our taxonomy includes rule-based chatbots, retrieval-based chatbots, generative chatbots, and hybrid chatbots. Next, we describe the capabilities and constraints of ChatGPT. Finally, we present potential applications of ChatGPT and future research opportunities. The results showed that ChatGPT, a transformer-based chatbot model, utilizes encoders to produce coherent responses. © 2024 John Wiley & Sons Ltd.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Nusec and Midesec: Datasets for Histopathological Image Analysis

SSRN

引用

SSRN 2024年

作者： Nemati, Nooshin Samet, Refik Sak, Serpil Hancer, Emrah Kirmizi, Bilge Ayca Yildirim, Zeynep Traoré, Mohamed Department of Computer Engineering Ankara University Ankara06830 Turkey Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand Department of Software Engineering Mehmet Akif Ersoy University Burdur15039 Turkey Department of Pathology Faculty of Medicine Ankara University Ankara06080 Turkey

Hematoxylin and Eosin (H&E) staining stands as the gold standard protocol for the preparationof histopathology tissue samples in breast cancer research. This staining technique facilitates theidentification and differentiation of various cell types within the tissue, providing crucial informationfor pathologists. While deep learning algorithms have shown promise in automating the analysis ofH&E images, their effectiveness relies on extensive datasets for training. Unfortunately, there is ascarcity of publicly available datasets specifically tailored for nuclei and mitosis detection. To addressthis gap, this paper introduces two publicly available datasets, namely NuSeC (Nuclei Segmentationand Classification) and MiDeSeC (Mitosis Detection, Segmentation, and Classification) to serve asvaluable resources for building deep learning models for histopathological image analysis. The NuSeCdataset comprises 75 images for training and an additional 25 images for testing, encompassing around6000 nuclei structures, and the MiDeSeC dataset involves 35 training and 15 test image sets with morethan 500 mitoses. In both datasets, the QuPath tool as a pixel-level annotator is utilized to generatemask images. Moreover, we design two deep learning-based methodologies to conduct experimentalanalysis on the NuSeC and MiDeSeC datasets. The results indicate the potential to achieve substantialperformance on these datasets, facilitating the construction of new models or analysis of existing ones © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multitasking With Adaptive Knowledge Transfer for Expensive Multiobjective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Wu, Xunfeng Liu, Songbai Lin, Qiuzhen Tan, Kay Chen Leung, Victor C. M. The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence Hong Kong Hong Kong Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Surrogate-assisted evolutionary algorithms (SAEAs) have shown promising performance in tackling expensive multiobjective optimization problems (EMOPs). However, existing SAEAs solve EMOPs separately, which ignore their optimization experiences earned before. Inspired by multitasking optimization paradigm for multitasking multiobjective optimization problems (MTMOPs), this article designs the first SAEA for tackling expensive MTMOPs (EMTMOPs) with adaptive knowledge transfer. First, a competitive surrogate selection is proposed to improve the generalization ability of approximating various EMOP tasks, where two types of surrogate models are trained and then compete for use to replace real expensive evaluations. Then, an adaptive solution selection is designed, which identifies promising transfer solutions to accelerate the solving of target task and selects promising infill solutions for real expensive evaluations to refine the surrogate models. The performance of our algorithm is validated on three commonly used benchmark suites and some real-world EMTMOPs. The experiments vali-date our superiority over several state-of-the-art SAEAs on most test cases. © 1997-2012 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Integration of Digital Twins in the Metaverse: software engineering Perspectives

Dynamic Integration of Digital Twins in the Metaverse: Softw...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Nedal Nwasra Khalil Omar Ahmed Alsalemi Software Engineering Department University of Petra Amman Jordan Computer Science Department University of Petra Amman Jordan Information Technology Department Al-Madinah College of Technology Madinah Saudi Arabia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

The paper presents an exploratory perspective of the seamless dynamic integration of the Digital Twin within the Metaverse from the software engineering viewpoint. Since the inception of Digital Twins as virtual counterparts of real-world entities, they have portrayed great promises of improving operational efficiency, especially in healthcare, smart manufacturing, and urban planning. However, their more and more seamless integration into such shared virtual environments as the Metaverse, dependent on immersive technologies, brings its specific software engineering challenges: real-time data synchronization, interoperability, scalability, and security. To cope with these challenges, this paper has proposed a layered software architecture belonging to data ingestion, processing, visualization, and user interaction. The key contributions take the form of a comprehensive literature review towards (1) identifying gaps in existing approaches in which this conceptual model and system architecture can facilitate modular and scalable integration of Digital Twins into the Metaverse and (2) practical implementation and benefits of such integration including real-time patient monitoring and interactive therapy simulations in which a healthcare use case can be demonstrated. This work addresses the technical and architectural challenges step by step and lays down the fundamental basis that will allow the integration of Digital Twins in real-time, secure, and user-centric immersive environments across a wide range of industries. Future research should be oriented towards standardization, improved data governance, and adaptive interaction paradigms.

关键词： Industries Metaverse Systems architecture Medical services Real-time systems Digital twins Security Synchronization software engineering Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Predicting Pre-Owned Bike Values with Machine Learning Techniques in Bangladesh

Predicting Pre-Owned Bike Values with Machine Learning Techn...

引用

Data Science and Network Security (ICDSNS), International Conference on

作者： Kazi Hassanul Ferdous Md.Shohel Arman Kazi Rifat Ahmed Nusrat Tasnim Imran Mahmud P. Revathi Department of Software Engineering DIU Data Science Lab Daffodil International University Dhaka Bangladesh Department of Computer Science Holy Cross College Tiruchirapalli Tamilnadu India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

As the importance of sustainable practices in the automobile sector grows, it's critical to anticipate motorcycle prices and offerings. With so many variables to consider when buying a secondhand motorcycle-condition, mileage, brand reputation, model characteristics, etc.-accurate pricing prediction is essential for both customers looking for good values and sellers hoping to maximize profits. This study investigates the effectiveness of four machine learning techniques Decision Tree models, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), and Stochastic Gradient Descent (SGD) Regressions-in predicting motorcycle prices using a dataset obtained from motorcycle merchants. It's noteworthy that these methods are used with a hybrid architecture to improve prediction accuracy. Different approaches are compared and contrasted to find the best fit for the given dataset, and the difficulties and roadblocks that come with them are also discussed. After extensive testing, the decision tree model's effectiveness is shown with an amazing 97% accuracy rate, providing accurate price estimates that are essential for encouraging sustainable habits in the ever-changing Internet of Things environment. With an impressive accuracy rate, this methodology provides precise pricing estimations, which are critical for supporting sustainable practices in the automotive industry.

关键词： Support vector machines Industries Accuracy Motorcycles Stochastic processes Pricing Predictive models Nearest neighbor methods Data models Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

Polarization Correction using Physics-guided Foundation Model for Photon-Counting CT

Polarization Correction using Physics-guided Foundation Mode...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： X. Yu W. Qin T. Zhong Q. Wu M. Su W. Wang X. Ji G. Quan Y. Chen X. Lai School of Biomedical Engineering ShanghaiTech University Shanghai China School of Computer Science and Engineering Southeast University Nanjing China College of Software Engineering Southeast University Nanjing China CT RPA Department United Imaging Healthcare Shanghai China

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

Photon-counting computed tomography (PCCT) represents a paradigm-shift advancement in CT technology. However, a significant challenge in PCCT is the polarization effect in photon-counting detectors (PCDs), especially in cadmium-based PCDs, which generate instable counting rate and inaccurate material decomposition results. In this paper, we introduce a polarization spectrum response model and propose a polarization correction method based on a physics-guided foundation model for photon-counting CT. Our approach is designed to accurately address the complexities of time-varying and dose-dependent polarization in PCDs. Preliminary results demonstrate accurate material decomposition that is free of significant band artifacts with proper polarization correction, underscoring the potential benefits in PCCT image quality.

关键词： Image quality Polarization Microwave integrated circuits Accuracy Semiconductor detectors Computed tomography Computational modeling

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：