检索结果-内蒙古大学图书馆

Kulla, a container-centric construction model for building infrastructure-agnostic distributed and parallel applications

引用

JOURNAL OF SYSTEMS AND SOFTWARE 2020年 168卷 110665-110665页

作者： Reyes-Anastacio, Hugo G. Gonzalez-Compean, J. L. Sosa-Sosa, Victor J. Carretero, Jesus Garcia-Blas, Javier CINVESTAV Unidad Tamaulipas Km 5-5 Carr Soto la Marina Victoria 87130 Tamaulipas Mexico Univ Carlos III Madrid Comp Sci & Engn Dept Av Univ 30 Madrid 28911 Spain

This paper presents the design, development, and implementation of Kulla, a virtual container-centric construction model that mixes loosely coupled structures with a parallel programming model for building infrastructure-agnostic distributed and parallel applications. In Kulla, applications, dependencies and environment settings, are mapped with construction units called Kulla-Blocks. A parallel programming model enables developers to couple those interoperable structures for creating constructive structures named Kulla-Bricks. In these structures, continuous dataflow and parallel patterns can be created without modifying the code of applications. methods such as Divide&Containerize (data parallelism), Pipe&Blocks (streaming), and Manager/Block (task parallelism) were developed to create Kulla-Bricks. Recursive combinations of Kulla instances can be grouped in deployment structures called Kulla-Boxes, which are encapsulated into VCs to create infrastructure-agnostic parallel and/or distributed applications. Deployment strategies were created for Kulla-Boxes to improve the IT resource profitability. To show the feasibility and flexibility of this model, solutions combining real-world applications were implemented by using Kulla instances to compose parallel and/or distributed system deployed on different IT infrastructures. An experimental evaluation based on use cases solving satellite and medical image processing problems revealed the efficiency of Kulla model in comparison with some traditional state-of-the-art solutions. (C) 2020 Published by Elsevier Inc.

关键词： Infrastructure-agnostic applications Construction model Virtual containers parallel patterns Pipelines

来源：评论

学校读者我要写书评

暂无评论

Edge First: Edge-Guided Geometry for Superior 3D Roof Wireframe Reconstruction*

Edge First: Edge-Guided Geometry for Superior 3D Roof Wirefr...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Qiaoqiao Hao Ting Han Yujun Liu Shangfeng Huang Duxin Zhu Jinhe Su Yundong Wu Guorong Cai School of Computer Engineering Jimei University Xiamen China School of Geospatial Engineering and Science Sun Yat-Sen University Zhuhai China School of Architecture and Urban Planning Shenzhen University Shenzhen China Department of Geomatics Engineering University of Calgary Calgary Canada

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Roof wireframe reconstruction has shown great success in 3D building reconstruction due to its lightweight nature and straightforward representation. However, previous methods consider all roof points, which result in edge redundancy and omissions. In this paper, we propose a novel and streamlined Edge-guided Geometric wireframe reconstruction framework, named EDGE. We find that points distributed along the roof edges make a significant contribution to the precise geometric structure of wireframe. Therefore, we design an edge point extractor (EPE) to capture the spatial relationship between points and edges, filtering out internal plane points. Moreover, we discover that the previous edge detectors rely solely on corner points, leading to error accumulation. To address this, we present the Hybrid Edge Detector (HED) feeding corner points with edge contextual features, which not only enhances edge completeness but also mitigates edge redundancy. Comprehensive experiments demonstrate EDGE outperforms existing wireframe reconstruction methods with 0.86 Corner F 1 -score and 0.71 Edge F 1 -score on Building3D dataset, striking the significant improvement of accuracy between corner and edge. Notably, our EDGE achieves a significant improvement of over 11% in Edge Recall, demonstrating the effectiveness and robustness of the proposed method.

关键词： Three-dimensional displays Accuracy image edge detection Buildings Termination of employment Detectors Reconstruction algorithms Feature extraction Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Scalable Approximation Algorithm for Weighted Longest Common Subsequence 27th

A Scalable Approximation Algorithm for Weighted Longest Comm...

引用

27th International European conference on parallel and distributed Computing (Euro-Par)

作者： Buhler, Jeremy Lavastida, Thomas Lu, Kefu Moseley, Benjamin Washington Univ St Louis MO 63110 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA Washington & Lee Univ Lexington VA 24450 USA

ISBN: (纸本)9783030856656;9783030856649

This work introduces novel parallel methods for weighted longest common subsequence (WLCS) and its generalization, allsubstrings WLCS. Previous work developed efficient algorithms for these problems via Monge matrix multiplication, which is a limiting factor for further improvement. Diverging from these approaches, we relax the algorithm's optimality guarantee in a controlled way, using a different, natural dynamic program which can be sketched and solved in a divideand-conquer manner that is efficient to parallelize. Additionally, to compute the base case of our algorithm, we develop a novel and efficient method for all-substrings WLCS inspired by previous work on unweighted all-substrings LCS, exploiting the typically small range of weights. Our method fits in most parallel models of computation, including the PRAM and the BSP model. To the best of our knowledge this is the fastest (1 -epsilon)-approximation algorithm for all-substrings WLCS and WLCS in BSP. Further, this is the asymptotically fastest parallel algorithm for weighted LCS as the number of processors increases.

关键词： parallel approximation algorithms Weighted LCS

来源：评论

学校读者我要写书评

暂无评论

distributed and parallel Sparse Computing for Very Large Graph Neural Networks

Distributed and Parallel Sparse Computing for Very Large Gra...

引用

IEEE International conference on Big Data

作者： Quentin R. Petit Chong Li Nahid Emad Huawei Paris Research Center & Université Paris-Saclay Boulogne-Billancourt France Distributed and Parallel Software Lab Huawei Paris Research Center Boulogne-Billancourt France Maison de la Simulation & LI-PaRAD Université Versailles Saint-Quentin Saclay France

ISBN: (纸本)9781665480468

Deep learning (DL) requires high-performance processing on big data. Graph Neural Networks, a challenging topic in DL using linear algebra methods, need algorithmic solutions to efficiently assign and process graph data on modern distributed and parallel machines, which are considered with mixed arithmetic and various types of tensor/matrix accelerators. Determining compression techniques for the graph’s sparse data structures is one of the key *** first objective is to design and implement a reusable parallel numerical library to resolve large neural network graphs. Our design strategy is drawn on a component-based approach and targets maximum code reuse in various parallel contexts while allowing for performance optimization. The solution could be later integrated into a DL framework like MindSpore.

关键词： Deep learning distributed databases Linear algebra Big Data parallel machines Graph neural networks Libraries

来源：评论

学校读者我要写书评

暂无评论

Simple-FPN: An image Anomaly Detection and Localization Network based on SimpleNet and Feature Pyramid

Simple-FPN: An Image Anomaly Detection and Localization Netw...

引用

Digital Twins and parallel Intelligence (DTPI), IEEE International conference on

作者： Yiming Zhao Fenghua Zhu Yibo Mi Dewang Chen Gang Xiong School of Future Technology Harbin Institute of Technology Harbin China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China School Transportation Fujian University of Technology Fuzhou China School Transportation Fujian University of Technology Fuzhou

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

We propose a neural network that is simple to understand, easy to implement and deploy, called Simple-FPN. This network is mainly used to detect and locate anomaly in images. The neural network mainly includes the following four parts: (1) a feature extraction part, including a pre-trained feature extraction network and a corresponding feature pyramid structure, (2) a pre-adaptation part, which maps the features obtained by feature extraction to the feature distribution space formed by target image set, (3) an anomaly feature generator adding Gaussian noise to the extracted features, and (4) the anomaly discriminator part is used to distinguish anomaly and normal features. The anomaly feature generator needs to be included during training, but is not required during inference. The design of this neural network mainly relies on three assumptions: (1) mapping common features in the non-target environment to the target environment helps avoid deviations in data distribution, (2) generating anomaly features in the feature domain is more efficient than in the image space, (3) features at different scales in the image can be more effectively extracted through feature pyramid. Simple-FPN has better performance than some previous methods. In the data set MVTec AD, Simple-FPN’s AUROC can reach an average of 99.4%. In addition, Simple-FPN’s inference speed can reach 89 FPS when tested on a 4060 GPU (only calculating inference time). Simple-FPN has excellent performance among many other anomaly detection networks.

关键词： Location awareness Training Gaussian noise Neural networks Graphics processing units Feature extraction Generators Digital twins Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Diffusion priors for variational likelihood estimation and image denoising 24

Diffusion priors for variational likelihood estimation and i...

引用

Proceedings of the 38th International conference on Neural Information processing Systems

作者： Jun Cheng Shan Tan School of Artificial Intelligence and Automation Huazhong University of Science and Technology

ISBN: (纸本)9798331314385

Real-world noise removal is crucial in low-level computer vision. Due to the remarkable generation capabilities of diffusion models, recent attention has shifted towards leveraging diffusion priors for image restoration tasks. However, existing diffusion priors-based methods either consider simple noise types or rely on approximate posterior estimation, limiting their effectiveness in addressing structured and signal-dependent noise commonly found in real-world images. In this paper, we build upon diffusion priors and propose adaptive likelihood estimation and MAP inference during the reverse diffusion process to tackle real-world noise. We introduce an independent, non-identically distributed likelihood combined with the noise precision (inverse variance) prior and dynamically infer the precision posterior using variational Bayes during the generation process. Meanwhile, we rectify the estimated noise variance through local Gaussian convolution. The final denoised image is obtained by propagating intermediate MAP solutions that balance the updated likelihood and diffusion prior. Additionally, we explore the local diffusion prior inherent in low-resolution diffusion models, enabling direct handling of high-resolution noisy images. Extensive experiments and analyses on diverse real-world datasets demonstrate the effectiveness of our method. Code is available at https://***/HUST-Tan/DiffusionVI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

distributed Deep Reinforcement Learning with Graph Neural Networks for Personalized Drug Interaction Analysis

Distributed Deep Reinforcement Learning with Graph Neural Ne...

引用

International conference on image Information processing

作者： Narayan Vyas Nitin N. Jadhav Vaishali V. Raje Chahil Choudhary Department of CSE Chandigarh University Mohali India Department of Medicine Krishna Institute of Medical Sciences Krishna Vishwa Vidyapeeth Karad India Department of PSM Krishna Institute of Medical Sciences Krishna Vishwa Vidyapeeth Karad India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

This research pivots around the intricate domain of personalized drug interaction analysis, harnessing the power of Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL). Emphasizing the need for personalized medicine, the study bridges the gap between static drug interaction data and dynamic patient-specific requirements. The principal purpose is to delve into the amalgamation of GNNs and DRL, targeting precise, adaptive, and safer drug recommendations tailored to individual patient profiles. The significance of this work lies in its potential to revolutionize the pharmaceutical landscape, shifting from a one-size-fits-all model to bespoke drug therapies. Preliminary outcomes have underscored the capability of this integrated approach to outperform traditional methods, illuminating a promising trajectory for future medical interventions and setting a benchmark in patient-centric drug interaction analysis.

关键词： Drugs Q-learning Precision medicine Information processing Benchmark testing Deep reinforcement learning Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms for Breast Cancer Histopathology Classification in H&E-Stained images

Deep Learning Algorithms for Breast Cancer Histopathology Cl...

引用

International conference on Biomedical Engineering (IBIOMED)

作者： Nicky Aulia Arif Iskandar Rose Khasana Dewi Biomedical Engineering Swiss German University Tangerang Indonesia Faculty of Medicine Brawijaya University Malang Indonesia

ISBN: (数字)9798350389265

ISBN: (纸本)9798350389272

Breast cancer is a leading cause of cancer deaths worldwide. Diagnosing breast histological images is challenging due to their complexity, compounded by the limited and unevenly distributed availability of pathology experts. This results in a burdensome and time-consuming diagnostic process, with inconsistencies due to subjectivity and varying expertise levels. Therefore, research on computer-aided diagnosis (CAD) is essential. This study aims to assist in distinguishing H&E-stained smear images from various categories of breast cancer tissues by exploring feature extraction, pre-processing, classifier, and input image strategies. The goal is to alleviate the burden on pathologists and standardize interobserver diagnoses. The method developed aims to classify breast cancer into four states and eight morphological subtypes, using feature extractors such as DenseNet201, InceptionV3, and VGG16. Pre-processing methods include data expansion, on-the-fly augmentation, stain normalization, and CLAHE. Input images and classifiers include single input images with different magnifications and multiple patches with majority voting. Analytical methods used were accuracy and loss curves, and evaluation measures included accuracy, precision, and F1-score. The optimal model for 4-class classification used single input images with multiple magnifications, achieving an accuracy, of 95.35%. For breast cancer state classification, the best model used multiple patches with majority voting, achieving an accuracy and F1-score of 85.3% and 85.3%, which improved to 91.25% with majority voting. Despite limitations, this method shows potential for improving tissue analysis and aiding classification. In the future, it may be adapted to help diagnose breast cancer in Indonesia, enhancing diagnostic accuracy and efficiency.

关键词： Solid modeling Adaptation models Accuracy image analysis Design automation Histopathology Feature extraction Breast cancer Loss measurement Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Big Data-Driven Computational Aptamer Design Framework via parallel Monte Carlo Tree Search

Big Data-Driven Computational Aptamer Design Framework via P...

引用

IEEE International conference on Big Data

作者： Jinglin Jian Zhiheng Jiao Zihan Li Jin Chen School of Information Sciences University of Illinois Urbana-Champaign Champaign US Independent Researcher San Francisco US Cleveland Clinic Cleveland OH

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Computational aptamer design using Monte Carlo Tree Search (MCTS) shows promise in drug discovery but is limited by sequential computing and simulation, which hinders the exploration of vast nucleotide sequence spaces and the integration of high-quality molecular docking techniques. We present a big data-driven parallel MCTS framework that significantly accelerates aptamer discovery while maintaining high accuracy. Our framework addresses these computational bottlenecks by distributing tasks across multiple processing units, enabling simultaneous exploration of diverse sequence regions and efficient incorporation of RNA/ssDNA-protein docking simulations for candidate evaluation. Key designs include a distributed search architecture with molecular docking, a score penalty system for optimized exploration, and comprehensive RNA/ssDNA docking pipelines that combine structure prediction with protein docking simulations. Experimental results targeting human complement component protein (i.e., protein 2A73) demonstrate a 98-fold increase in daily successful candidate discovery and improved binding affinity compared to the baseline, with the successful ratio increasing from 1% to 7.59%. Our approach not only accelerates the aptamer design process but also enhances the quality of generated aptamers, providing a more efficient and effective tool for drug discovery.

关键词： Proteins Monte Carlo methods Accuracy Pipelines Production Transformers Stability analysis Drug discovery Computational efficiency Reliability

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network for processing Fingerprint image Noise

Artificial Neural Network for Processing Fingerprint Image N...

引用

Summer Virtual conference on Software Engineering, Artificial Intelligence, Networking and parallel/distributed Computing (SNPD-Summer), ACIS International

作者： Ke Han Department of Fingerprint Technology Institute of Forensic Science Ministry of Public Security China Beijing China

ISBN: (纸本)9798350396386

Fingerprint images from crime scenes can be used to find and identify suspects in the field of forensic science. Fingerprint images are usually polluted by noise, which affects the visual effect of fingerprint images. It is important to process the noise of fingerprint images. A supervised learning 9-layer artificial neural network besides the input layer and the output layer is designed to remove the noise of fingerprint images in this paper. The first three layers of the neural network are convolutional layers. The purpose of designing convolutional layers is to extract the feature information of the images layer by layer and gradually generate the feature maps. The fourth layer to the sixth layer are fully connected layers. The number of neurons in the fourth layer is the same as that of the sixth layer. The number of neurons in the fourth layer is the number of elements in the vector flattened by the feature maps outputted from the last convolutional layer. The seventh layer to the ninth layer in the neural network are deconvolutional layers. These deconvolutional layers gradually restore the feature maps to the fingerprint image. Finally, the enhanced fingerprint image is outputted from the output layer. As the training samples of fingerprint images is inadequate, this paper provides a way to make training samples. The clear fingerprint image is blurred as the corresponding blurred fingerprint image, which solves the problem of lack of the training samples. The blurred fingerprint image and the corresponding clear fingerprint image are used to establish the training sample set and train the artificial neural network. The mean square error function is used as the loss function to adjust and optimize the parameters of the neural network. The neural network in this paper is evaluated on test fingerprint images. The neural network method is compared with the Gaussian low-pass filtering method and the Wiener filtering method. Experimental results show that the neura

关键词： Training Wiener filters Filtering image matching Neurons Artificial neural networks Fingerprint recognition

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：