检索结果-内蒙古大学图书馆

CINDERELLA Trial: validation of an artificial-intelligence cloud-based platform to improve the shared decision-making process and outcomes in breast cancer patients proposed for locoregional treatment

引用

European Journal of Surgical Oncology 2024年第2期50卷 107916-107916页

作者： Bonci, Eduard-Alexandru Kaidar-Person, Orit Antunes, Marilia Ciani, Oriana Cruz, Helena Di Micco, Rosa Gentilini, Oreste Gouveia, Pedro Heil, Jörg Kabata, Pawel Freitas, Nuno Gonçalves, Tiago Romariz, Miguel Martins, Henrique Mavioso, Carlos Mika, Martin Pfob, André Schinköthe, Timo Silva, Giovani Cardoso, Maria-João Champalimaud Foundation Champalimaud Research and Clinical Centre Lisbon Portugal Iuliu Hatieganu University of Medicine and Pharmacy Surgical Oncology and Gynecologic Oncology Department Cluj-Napoca Romania Sheba Medical Center Breast Cancer Radiation Therapy Unit Ramat Gan Israel Tel-Aviv University Sackler School of Medicine Tel-Aviv Israel University of Lisbon Faculty of Sciences Lisbon Portugal University of Lisbon Instituto Superior Técnico Lisbon Portugal SDA Bocconi University Center for Research on Health and Social Care Management Milan Italy San Raffaele University and Research Hospital Breast Surgery Unit Milan Italy University of Lisbon Faculty of Medicine Lisbon Portugal Heidelberg University Hospital Department of Obstetrics & Gynecology Heidelberg Germany Medical University of Gdańsk Faculty of Medicine - Department of Surgical Oncology Gdańsk Poland INESC TEC - Institute for Systems and Computer Engineering- Technology and Science Networked Intelligent Systems Porto Portugal University of Porto Faculty of Sciences Porto Portugal University of Porto Faculty of Engineering Porto Portugal ISCTE - University Institute of Lisbon Social and Enterprise Sciences Lisbon Portugal CANKADO GmbH Ottobrunn Germany

来源：评论

学校读者我要写书评

暂无评论

Residential DER Cooperative Investments

Residential DER Cooperative Investments

引用

International Conference on European Electricity Market, EEM

作者： María de Almansa Fco. Alberto Campos Salvador Doménech José Villar Fco. Alberto Campos Salvador Doménech Instituto de Investigación Tecnológica IIT ICAI Universidad Pontificia Comillas Madrid Spain Instituto de Investigación Tecnológica IIT ICAI Universidad Pontificia Comillas Madrid Spain INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal

This paper aims to model collaborative behaviours related to distributed generation investments in a residential neighbourhood, by means of Cooperative Game Theory (CGT). The main objective is to analyse the economic impact of the installation of photovoltaic solar panels and batteries, and the assessment of the potential energy savings due to the cooperation among residential households. In this regard, both the purchase of needed energy from the grid and the sale of the spare energy from the households' self-generation to the grid are considered. The comparison between cooperative and non-cooperative behaviours in the investments and energy management decisions is analysed based on the Shapley value, a cost sharing method from CGT, concluding that cooperation among prosumers to share energy in a residential energy community is in general more efficient than prosumers making individual decisions.

关键词： Batteries Investment State of charge Collaboration Indexes Resource management Economics

来源：评论

学校读者我要写书评

暂无评论

DR|GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images

arXiv

引用

arXiv 2019年

作者： Araújo, Teresa Aresta, Guilherme Mendonça, Luís Penas, Susana Maia, Carolina Carneiro, Ângela Mendonça, Ana Maria Campilho, Aurélio INESC TEC Institute for Systems and Computer Engineering Technology and Science Porto4200-465 Portugal Faculty of Engineering of University of Porto Porto4200-465 Portugal Department of Ophthalmology of Hospital de Braga Braga Portugal Department of Ophthalmology of Centro Hospitalar São João Porto Portugal Department of Surgery and Physiology Faculty of Medicine University of Porto Porto Portugal

Diabetic retinopathy (DR) grading is crucial in determining the patients' adequate treatment and follow up, but the screening process can be tiresome and prone to errors. Deep learning approaches have shown promising performance as computer-aided diagnosis (CAD) systems, but their black-box behaviour hinders the clinical application. We propose DR|GRADUATE, a novel deep learning-based DR grading CAD system that supports its decision by providing a medically interpretable explanation and an estimation of how uncertain that prediction is, allowing the ophthalmologist to measure how much that decision should be trusted. We designed DR|GRADUATE taking into account the ordinal nature of the DR grading problem. A novel Gaussian-sampling approach built upon a Multiple Instance Learning framework allow DR|GRADUATE to infer an image grade associated with an explanation map and a prediction uncertainty while being trained only with image-wise labels. DR|GRADUATE was trained on the Kaggle training set and evaluated across multiple datasets. In DR grading, a quadratic-weighted Cohen's kappa (QWK) between 0.71 and 0.84 was achieved in five different datasets. We show that high QWK values occur for images with low prediction uncertainty, thus indicating that this uncertainty is a valid measure of the predictions' quality. Further, bad quality images are generally associated with higher uncertainties, showing that images not suitable for diagnosis indeed lead to less trustworthy predictions. Additionally, tests on unfamiliar medical image data types suggest that DR|GRADUATE allows outlier detection. The attention maps generally highlight regions of interest for diagnosis. These results show the great potential of DR|GRADUATE as a second-opinion system in DR severity grading. Copyright © 2019, The Authors. All rights reserved.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

UOLO - automatic object detection and segmentation in biomedical images

arXiv

引用

arXiv 2018年

作者： Araújo, Teresa Aresta, Guilherme Galdran, Adrian Costa, Pedro Mendonça, Ana Maria Campilho, Aurélio INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal Faculdade de Engenharia da Universidade do Porto Porto Portugal

We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneously for detecting a class of objects and segmenting an optionally different class of structures. UOLO is trained on a set of bounding boxes enclosing the objects to detect, as well as pixel-wise segmentation information, when available. A new loss function is devised, taking into account whether a reference segmentation is accessible for each training image, in order to suitably backpropagate the error. We validate UOLO on the task of simultaneous optic disc (OD) detection, fovea detection, and OD segmentation from retinal images, achieving state-of-the-art performance on public datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Smart transformer control strategies for multi-microgrid islanding operation

Smart transformer control strategies for multi-microgrid isl...

引用

Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion (MEDPOWER 2018)

作者： Mário Couto João A. Peças Lopes Carlos L. Moreira Faculdade de Engenharia da Universidade do Porto Porto Portugal Institute for Systems and Computer Engineering Technology and Science (INESC TEC) Porto Portugal

ISBN: (纸本)9781839531330

In a framework with an increased number of small-scale generators connected to the distribution grid by inverters, the replacement of the electromagnetic transformers by Smart Transformers (ST) in secondary substations brings new opportunities to improve the grid flexibility. In this research, they are exploited in the context of Multi-Microgrids (MMG) allowing their operation in islanding mode, through the development of control functionalities to be incorporated in the converters of ST. The possibility to connect a storage device in the DC link, provided by a three-stage configuration (AC/DC/AC), fully decouples the control possibilities between Medium Voltage (MV) and Low Voltages (LV) grid sides. Even though energy storage cannot be considered, the frequency control of the LV grid can be also decoupled from the MV grid. In order to illustrate these set of possible approaches, two different configurations are addressed in the paper and their control strategies properly described: 1) with storage — the ST operates as grid-forming for both sides; 2) without storage — the ST just operating as a grid-forming unit for the LV side.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Optimization Model for the Design of Additive Manufacturing Supply Chains

An Optimization Model for the Design of Additive Manufacturi...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Filipe M. de Brito Gélson da Cruz Júnior Enzo M. Frazzon João P. Basto Symone G. S. Alcalá School of Electrical Mechanical and Computer Engineering Federal University of Goiás Goiânia Goiás Brazil Industrial and Systems Engineering Department Federal University of Santa Catarina Florianópolis Brazil INESC TEC - Technology and Science Faculty of Engineering University of Porto Porto Portugal Faculty of Science and Technologies Federal University of Goiás Aparecida de Goiânia Goiás Brazil

The continuous adoption of Additive Manufacturing (AM) can enhance Supply Chain's (SC) effectiveness, adaptability and competitiveness. AM allows for a decentralized SC, bringing production centres nearer to customers, increasing products availability and decreasing inventory level and lead time. However, the integration of SC and AM brings difficulties, leading to the need of a completely new SC design. This paper proposes an optimization model supporting the design of spare parts SCs operating under a Make-To-Order (MTO) strategy. The proposed approach considers the decision of deploying productive resources (3D printers) in locations of a spare parts SC. The problem is represented as a combination of the p-median and location-allocation optimization models, which are solved using a Mixed Integer Linear Programming (MILP). The approach is tested in two scenarios from a real-world use case of an elevator maintenance service provider. Obtained results demonstrated the promising capabilities of the proposed approach for handling the new design challenges arising from the forthcoming widespread use of 3D printers in manufacturing SCs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

108TiP CINDERELLA clinical trial: Using artificial intelligence-driven healthcare to enhance breast cancer locoregional treatment decisions

引用

ESMO Open 2024年 9卷 103179-103179页

作者： A. Pfob E-A. Bonci O. Kaidar-Person M. Antunes O. Ciani H. Cruz R. Di Micco O.D. Gentilini J. Heil P. Kabata M. Romariz T. Gonçalves H.G. Martins L. Borsoi M. Mika N. Romem T. Schinköthe G. Silva M. Bobowicz M.J. Cardoso Department of Obstetrics & Gynecology Heidelberg University Hospital Heidelberg Germany Breast Unit Champalimaud Research and Clinical Centre Champalimaud Foundation Lisbon Portugal Breast Cancer Radiation Therapy Unit Sheba Medical Center Ramat Gan Israel CEAUL - Centro de Estatística e Aplicações Faculdade de Ciências Universidade de Lisboa Lisbon Portugal Center for Research on Health and Social Care Management (CERGAS) SDA Bocconi University Milan Italy Breast Surgery Unit San Raffaele University and Research Hospital Milan Italy Department of General Surgery Copernicus Mamma Centrum Wojewodzkie Centrum Onkologii Copernicus Podmiot Leczniczy Gdańsk Poland Telecommunications and Multimedia INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal ISCTE - Instituto Universitário de Lisboa Lisbon Portugal CANKADO GmbH Ottobrunn Germany Surgical Oncology Medical University of Gdansk Gdansk Poland

来源：评论

学校读者我要写书评

暂无评论

Joint Centralized and Distributed Electricity Generation Expansion in a Decarbonized Scenario: The Spanish Case

Joint Centralized and Distributed Electricity Generation Exp...

引用

International Conference on European Electricity Market, EEM

作者： Salvador Domenech Martinez Fco. Alberto Campos Fernandez Michel Rivier Abbad Jose villar Collado Instituto de Investigacion Tecnologica lIT ICAI Universidad Pontificia Comillas Madrid Spain Technology and Science Porto INESC TEC - Institute for Systems and Computer Engineering Portugal

Power systems of most EU countries will face substantial changes driven mainly by the EU Clean Energy Package and the expected increasing role of customers making use of demand response and distributed self-generation and self-storage resources (self-DG&S). This work aims to analyze the impact of these two factors on the long term evolution of both utility scale centralized generation and storage (CG&S), and self-DG&S. An hourly-resolution generation expansion model based on cost minimization for CG&S and expenses' minimization for self-DG&S is used. Four case studies covering the period 2018-2047 for a real sized system (the Spanish one) are presented. Results highlight a strong synergy between battery costs and solar photovoltaic investments, while wind power seems to be better complemented by peaker thermal units.

关键词： Investment Batteries Wind power generation Minimization Mathematical model

来源：评论

学校读者我要写书评

暂无评论

An Electricity Generation Expansion Model with ICEV and PEV Investments

An Electricity Generation Expansion Model with ICEV and PEV ...

引用

International Conference on European Electricity Market, EEM

作者： Rosendo Castanon Fco. Alberto Campos Fernandez Salvador Domenech Martinez Jose Villar Collado Instituto de Investigación Tecnológica IIT ICAI Universidad Pontificia Comillas Madrid Spain INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal

Environmental policies could accelerate the replacement of Internal Combustion Engine Vehicles (ICEV) by Plug-in-Electric Vehicles (PEV) in many countries. However, in countries where these policies are still not implemented (for example those with no significant PEV subsidies like Spain), technical and economic criteria can also be relevant to assess the future PEV penetration. This work develops a new long-term expansion model that computes the share of PEV and ICEV based on economic criteria, including the impact of PEV on the electricity price and generation mix. The model minimizes the power and transport system costs (investment, operation and maintenance costs, etc.) considering electricity and private transportation needs. Results provide insight on the combined evolution of the renewable generation and of the PEV and ICEV future fleets in Spain, considering environmental constraints such as those imposed by the European Commission.

关键词： Investment Europe Power systems Economics Computational modeling Transportation Acceleration

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the performance of a photovoltaic power plant installed in a building in the north of Portugal

引用

Energy Procedia 2018年 153卷 42-47页

作者： Gustavo Pinto Monteiro Ana I. Palmero-Marrero Carlos Moreira Armando C. Oliveira University of Porto Mechanical Engineering Department Rua Dr. Roberto Frias 4200-465 Porto Portugal Institute of Systems and Computers Engineering Technology and Science (INESC TEC) Rua Dr. Roberto Frias 4200-465 Porto Portugal

In this work, the evaluation of the performance of a small-size photovoltaic plant, with 15 kWp of capacity, is made and some proposals for its optimization are presented. The plant consists of a grid-connected centralized system, where the output power is consumed in the same building. The PV plant production data of the last couple of years are analysed, filtering the periods of inoperation. To obtain an accurate prediction of the efficiency and power output, the characteristics of all plant components were introduced in SAM software. The results obtained through the simulations and the measured output power values were compared.

关键词： Photovoltaics solar energy power plant grid-connected SAM 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：