检索结果-内蒙古大学图书馆

International Conference on High Performance computing

作者： Henrique R. A. Freitas Celso L. Mendes Aleksandar Ilic Graduate Program in Applied Computing National Institute for Space Research São José dos Campos Brazil Associate Laboratory of Computing National Institute for Space Research São José dos Campos Brazil INESC-ID Instituto Superior Técnico University of Lisbon Lisbon Portugal

Hydrological models are extensively used in applications such as water resources, climate change, land use, and forecast systems. The focus of this paper is performance optimization of the MGB hydrological model, which is widely employed to simulate water flows in large-scale watersheds. The optimization strategies that we selected include AVX-512 vectorization, thread-parallelism on multi-core CPUs (OpenMP), and data-parallelism on many-core GPUs (CUDA). We conducted experiments for real-world input datasets on state-of-the-art HPC systems based on Intel's Skylake CPUs and NVIDIA GPUs. In addition, a Roofline model characterization for these datasets confirmed performance improvements of up to 37.5x on the most time-consuming part of the code and 8.6x on the full MGB model. The work proposed herein shows that careful optimizations are needed for hydrological models to achieve a significant fraction of the performance potential in modern processors.

关键词： Analytical models Computational modeling Scalability High performance computing Conferences Graphics processing units Predictive models

来源：评论

学校读者我要写书评

暂无评论

Experience sharing between cooperative reinforcement learning agents

arXiv

引用

arXiv 2019年

作者： Souza, Lucas Oliveira de Oliveira Ramos, Gabriel Ralha, Celia Ghedini Numenta Redwood City United States Graduate Program in Applied Computing Universidade do Vale do Rio dos Sinos São Leopoldo Brazil Computer Science Department University of Brasilia Brasilia Brazil

The idea of experience sharing between cooperative agents naturally emerges from our understanding of how humans learn. Our evolution as a species is tightly linked to the ability to exchange learned knowledge with one another. It follows that experience sharing (ES) between autonomous and independent agents could become the key to accelerate learning in cooperative multiagent settings. We investigate if randomly selecting experiences to share can increase the performance of deep reinforcement learning agents, and propose three new methods for selecting experiences to accelerate the learning process. Firstly, we introduce Focused ES, which prioritizes unexplored regions of the state space. Secondly, we present Prioritized ES, in which temporal-difference error is used as a measure of priority. Finally, we devise Focused Prioritized ES, which combines both previous approaches. The methods are empirically validated in a control problem. While sharing randomly selected experiences between two Deep Q-Network agents shows no improvement over a single agent baseline, we show that the proposed ES methods can successfully outperform the baseline. In particular, the Focused ES accelerates learning by a factor of 2, reducing by 51% the number of episodes required to complete the task. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Blending Lossy and Lossless Data Compression Methods to Support Health Data Streaming in Smart Cities

SSRN

引用

SSRN 2024年

作者： Andrade, Alexandre da Costa, Cristiano André Roehrs, Alex Muchaluat-Saade, Debora Christina Righi, Rodrigo da Rosa Applied Computing Program Universidade do Rio dos Sinos RS São Leopoldo Brazil Computer Science Department Universidade Federal Fluminense RJ Niterói Brazil Software Innovation Laboratory - SOFTWARELAB

The digital transformation process has significantly boosted the widespread adoption of telemedicine and the utilization of wearable devices for monitoring vital signs. However, implementing a system for continuous monitoring of the population's vital signs, with data being streamed from various locations within a smart city context, faces significant challenges. These challenges are related to bandwidth, latency, and storage capacity due to the large volume of data. To overcome these challenges, a common practice consists in modeling an edge-fog-cloud layered architecture. The literature lacks software solutions capable of managing the simultaneous transmission of various vital signs data, coming from individuals geographically distributed, while maintaining the ability to promptly issue alerts and generate health notifications. In this context, we propose the VSAC (Vital Sign Adaptive Compressor) model, which combines lossy and lossless data compression algorithms in a layered architecture to support healthcare demands in a smart city. The main contribution is how we blend both strategies: we first use lossy compression to collect only valuable vital sign data for each individual, applying lossless algorithms afterwards to reduce the number of bytes before sending it to higher layers. We provide a protocol that facilitates the collection of heterogeneous data distributed across different city regions, providing real-time processing. A prototype was developed to evaluate the model and its performance in various load scenarios. The results indicate that orchestrating two data compression algorithms is more efficient than conventional data reduction methods, showing gains up to 46\% when measuring the compression rate metric. © 2024, The Authors. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Stroke Lesion Detection Using Convolutional Neural Networks

Stroke Lesion Detection Using Convolutional Neural Networks

引用

International Joint Conference on Neural Networks

作者： Danillo Roberto Pereira Pedro P. Reboucas Filho Gustavo Henrique de Rosa Joao Paulo Papa Victor Hugo C. de Albuquerque Department of Computing São Paulo State University Bauru SP Brazil Federal Institute of Education Science and Technology of Ceará CE Brazil Graduate Program in Applied Informatics University of Fortaleza Fortaleza CE Brazil

Stroke is an injury that affects the brain tissue, mainly caused by changes in the blood supply to a particular region of the brain. As consequence, some specific functions related to that affected region can be reduced, decreasing the quality of life of the patient. In this work, we deal with the problem of stroke detection in Computed Tomography (CT) images using Convolutional Neural Networks (CNN) optimized by Particle Swarm Optimization (PSO). We considered two different kinds of strokes, ischemic and hemorrhagic, as well as making available a public dataset to foster the research related to stroke detection in the human brain. The dataset comprises three different types of images for each case, i.e., the original CT image, one with the segmented cranium and an additional one with the radiological density's map. The results evidenced that CNN's are suitable to deal with stroke detection, obtaining promising results.

关键词： Computed tomography Hemorrhaging Brain Attenuation Blood Image segmentation Cranium

来源：评论

学校读者我要写书评

暂无评论

Multi-Instance Task in Swarm Robotics: Sorting Groups of Robots or Objects into Clusters with Minimalist Controllers

Multi-Instance Task in Swarm Robotics: Sorting Groups of Rob...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Adilson Krischanski Yuri K. Lopes Andre B. Leal Ricardo F. Martins Roberto S.U. Rosso Department of Computer Science Santa Catarina State University (UDESC) Joinville Brazil Graduate Program in Applied Computing (PPGCAP) UDESC Brazil Department of Electrical Engineering Santa Catarina State University (UDESC) Joinville Brazil

Relying only on behaviors that emerge from simple responsive controllers; swarms of robots have been shown capable of autonomously aggregate themselves or objects into clusters without any form of communication. We push these controllers to the limit, requiring robots to sort themselves or objects into different clusters. Based on a responsive controller that maps the current reading of a line-of-sight sensor to a pair of speeds for the robots' differential wheels, we demonstrate how multiple tasks instances can be accomplished by a robotic swarm. Using the dividing rectangles approach and physics simulation, a training step optimizes the parameters of the controller guided by a fitness function. We conducted a series of systematic trials in physics-based simulation and evaluate the performance in terms of dispersion and the ratio of clustered robots/objects. Across 20 trials where 30 robots cluster themselves into 3 groups, an average of 99.83% of them were correctly clustered into their group after 300 s. Across 50 trials where 15 robots cluster 30 objects into 3 groups, an average of 61.20%, 82.87%, and 97.73% of objects were correctly clustered into their group after 600 s, 900 s, and 1800 s, respectively. The object cluster behavior scales well while the aggregation does not, the latter due to the requirement of control tuning based on the number of robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Quantitative Analysis on Different Carbonate Indicators Based on Spaceborne Data in a Controlled Karst Area

A Quantitative Analysis on Different Carbonate Indicators Ba...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： M. Muller V. F. Sales D. C. Zanotta A. Marques T. T. Guimarães L. Bachi E. M. Souza D. Brum L. Gonzaga M. R. Veronez C. L. Cazarin Vizlab X-Reality & GeoInformatics Lab - Graduate Program in Applied Computing UNISINOS University Rio Grande do Sul Brazil State University of Maringa Parana Brazil CENPES - PETROBRAS Rio de Janeiro Brazil

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

New sensors aboard recently launched satellites have induced the development of several measures aimed to indicate the presence of many materials over the Earth. Karsts are places rich in carbonate rocks and present large economic and environmental importance. This paper aimed at assessing the performance and consistency of different carbonate estimators derived from orbital images acquired over a controlled karst area. Experiments were assisted by a multi-scaled reference data built through a high spatial resolution Unmanned Aerial Vehicle (UAV) image acquired over the selected area. Results show a considerable unconformity among selected measures and better performance presented by indices exploiting measures along visible and infrared spectral regions.

关键词： Rocks Remote sensing Earth Indexes Artificial satellites Thermal sensors Sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

Preconditioners for regularized image superresolution

Preconditioners for regularized image superresolution

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： N. Nguyan G. Golub P. Milanfar Sci. Comput. & Comput. Math. Program Stanford Univ. CA USA Scientific Computing and Computational Mathematics Program University of Stanford Stanford CA USA Applied Electromagnetics Lab SRI International Inc. Menlo Park CA USA

Superresolution reconstruction produces a high resolution image from a set of low resolution images. Previous work on superresolution had not adequately addressed the computational issues for this problem. In this paper, we propose efficient block circulant preconditioners for solving the regularized superresolution problem by conjugate gradients. The effectiveness of the preconditioners is demonstrated with superresolution results for a simulated image sequence and a FLIR image sequence.

关键词： Image resolution Layout Spatial resolution Pixel Image reconstruction Image sequences Motion estimation Solids Equations Scientific computing

来源：评论

学校读者我要写书评

暂无评论

Quantum Wrapper Networking: Investigating the Noise Impact of Classical Headers on the Quantum Payload

Quantum Wrapper Networking: Investigating the Noise Impact o...

引用

2024 Frontiers in Optics, FiO 2024

作者： Gül, Gamze On, Mehmet Berkay Tan, Shannon G. Proietti, Roberto Kanter, Gregory S. Yoo, S.J. Ben Kumar, Prem Graduate Program in Applied Physics Northwestern University 2145 Sheridan Road EvanstonIL60208 United States Department of Electrical and Computer Engineering University of California Davis DavisCA95616 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States Department of Electronics and Telecommunications Engineering Politecnico di Torino Italy

We study the impact in time and frequency domains of classical headers on quantum payloads in quantum wrapper networking. We identify and characterize in-fiber scattering processes that produce noise photons degrading...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monitoring Heat Waves and Their Impacts on Summer Crop Development in Southern Brazil

引用

Agricultural Sciences 2014年第4期5卷 353-364页

作者： Anibal Gusso Jorge Ricardo Ducati Mauricio Roberto Veronez Victor Sommer Luiz Gonzaga da Silveira Junior Environmental Engineering Vale do Rio dos Sinos University(UNISINOS)Sao LeopoldoBrazil Center for Remote Sensing and Meteorological Research Federal University of Rio Grande do Sul(UFRGS)Porto AlegreBrazil VizLab-Advanced Visualization Laboratory Vale do Rio dos Sinos University(UNISINOS)Sao LeopoldoBrazil Astronomy Department Federal University of Rio Grande do Sul(UFRGS)Porto AlegreBrazil Graduate Program in Geology Vale do Rio dos Sinos University(UNISINOS)Sao LeopoldoBrazil Crop Breeding Foundation(Fundacao Pró-Sementes) Passo FundoBrazil Graduate Program in Applied Computing Vale do Rio dos Sinos University(UNISINOS)São LeopoldoBrazil

Periods in the soybean summer cycle that are sensitive to the occurrence of high temperatures were studied. An analysis was performed on the variability of soybean yields associated with crop canopy temperatures during key development periods. A land surface temperature (LST) data series from MODIS (Moderate Resolution Imaging Spectroradiometer) on the Aqua satellite was processed between 2003 and 2012 that covered the entire state of Rio Grande do Sul, in Brazil. Enhanced vegetation index (EVI) data from MODIS on the Terra satellite were used to monitor the LST during different phenological stages. Spatially interpolated maps of soybean yield distributions were generated using data obtained from Instituto Brasileiro de Geografia e Estatística (IBGE) at state and municipality levels. The results indicate that canopy-LST occurrence in mid-February, during the grain filling, is most correlated to yield reduction (R2 = 0.82 and RMSD = 14.4%). At the state level, the average yield is 2003 kg·ha-1 with a standard deviation of 308 kg·ha-1. The overall average of the canopy-LST is 305.0 K (31.8°C) with a standard deviation of 1.9 K. The slope of the downward linear relationship between canopy-LST and yield was -28.7%. These results indicate that monitoring heat wave events can provide important information for characterising agriculture vulnerability.

关键词： Land Surface Temperature Soybean Remote Sensing Canopy Vegetation Index MODIS Data

来源：评论

学校读者我要写书评

暂无评论

A New Method Based on Deep Learning to Detect Lesions in Retinal Images using YOLOv5

A New Method Based on Deep Learning to Detect Lesions in Ret...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Carlos Santos Marilton Aguiar Daniel Welfer Bruno Belloni Federal Institute of Education Science and Technology Farroupilha Alegrete Brazil Postgraduate Program in Computing (PPGC) Federal University of Pelotas Pelotas Brazil Departament of Applied Computing Federal University of Santa Maria Santa Maria Brazil Federal Institute of Education Science and Technology Sul-Rio-Grandense Passo Fundo Brazil

ISBN: (纸本)9781665429825

Diabetic Retinopathy is one of the leading causes of vision loss and presents in its initial phase retinal lesions, such as microaneurysms, hemorrhages, and hard and soft exudates. Therefore, computational models capable of detecting these lesions can help in the early diagnosis of the disease and prevent the manifestation of more severe forms of lesions, helping define the best form of treatment. This work proposes a method based on deep neural network models that perform one-stage object detection, using state-of-the-art data augmentation and transfer learning techniques to present a model that aids in the medical diagnosis of fundus lesions. The model was trained, adjusted, and evaluated using the DDR Diabetic Retinopathy Dataset, and implemented based on the YOLOv5 architecture and the PyTorch framework, achieving values for mAP of 0.1040 and 0.0283 for IoU threshold of 0.5 and 0.5:0.95 respectively, in the validation set. The results obtained in the experiments demonstrate that the proposed method presented superior results to equivalent works found in the literature.

关键词： Deep learning Training Retinopathy Neural networks Computer architecture Retina Data models

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：