检索结果-内蒙古大学图书馆

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Singh, Abhishek Bruzzone, Lorenzo Univ Trento Dept Informat Engn & Comp Sci Remote Sensing Lab RSLab Trento Italy

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Availability of limited training remote sensing datasets is one of the problems in deep learning, as deep architectures require a large number of training samples for proper training. In this paper, we present a technique for data augmentation based on a spectral indexed generative adversarial network to train deep convolutional neural networks. This technique uses the spectral characteristic of multispectral (MS) images to support data augmentation in order to generate realistic training samples with respect to each land-use and land-cover class. The impact of multispectral remote sensing data generated through the spectral indexed GAN are evaluated through classification experiments. Experimental results obtained on the classification of the Sentinel-2 Eurosatallband datasets show that data augmentation through spectral indexed GAN enhances the main accuracy metrics.

关键词： Training data data Augmentation Generative Model Remote Sensing Image analysis Classification Accuracy

来源：评论

学校读者我要写书评

暂无评论

Author Index

Author Index

引用

ieee symposium on large data analysis and visualization (LDAV)

Presents the author index for the conference.

ISBN: (数字)9781665491563

ISBN: (纸本)9781665491570

Presents the author index for the conference.

关键词： Moon Indexes data visualization data analysis

来源：评论

学校读者我要写书评

暂无评论

CommentVis: Unveiling Comment Insights Through Interactive visualization Tool

CommentVis: Unveiling Comment Insights Through Interactive V...

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Guangjing Yan Jinhwa Jang Jinwook Seo Seoul National University Samsung Electronics

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

Recently, online forums have emerged as a stage for consumers to comment and share their reviews. These user comments serve as a valuable data source for marketing professionals and analysts. Nevertheless, conventional user interfaces often present an overwhelming volume of comments in a linear-structured list, significantly impeding the efficiency of marketing professionals in analyzing the feedback. In response to this challenge, we introduce CommentVis, an interactive visualization tool that helps users grasp the skeleton of comments’ semantic distribution. Using the tool, analysts gain detailed information about comments with profound insights. The tool leverages state-of-the-art large-scale language models, optimizing the speed and depth of analysis of substantial text data that may take a long time for marketers. To illustrate the practical application of CommentVis, we present a usage scenario that demonstrates its effectiveness in real-world marketing analysis. The tool’s impact and utility were further validated through a user study involving three marketing professionals in a global manufacturing company.

关键词： Reviews Soft sensors Semantics data visualization Feature extraction data processing Skeleton

来源：评论

学校读者我要写书评

暂无评论

SparkFlow: Towards High-Performance data Analytics for Spark-based Genome analysis 22

SparkFlow: Towards High-Performance Data Analytics for Spark...

引用

22nd ieee/ACM International symposium on Cluster, Cloud and Internet Computing (CCGrid)

作者： Filgueira, Rosa Awaysheh, Feras M. Carter, Adam White, Darren J. Rana, Omer Univ St Andrews Sch Comp Sci St Andrews Fife Scotland Univ Tartu Inst Comp Sci Delta Ctr Tartu Estonia Univ Edinburgh Edinburgh Parallel Comp Ctr Edinburgh Midlothian Scotland Cardiff Univ Phys Sci & Engn Coll Cardiff Wales

ISBN: (纸本)9781665499569

The recent advances in DNA sequencing technology triggered next-generation sequencing (NGS) research in full scale. Big data (BD) is becoming the main driver in analyzing these large-scale bioinformatics data. However, this complicated process has become the system bottleneck, requiring an amalgamation of scalable approaches to deliver the needed performance and hide the deployment complexity. Utilizing cutting-edge scientific workflows can robustly address these challenges. This paper presents a Spark-based alignment workflow called SparkFlow for massive NGS analysis over singularity containers. SparkFlow is highly scalable, reproducible, and capable of parallelizing computation by utilizing data-level parallelism and load balancing techniques in HPC and Cloud environments. The proposed workflow capitalizes on benchmarking two state-of-art NGS workflows, i.e., BaseRecalibrator and ApplyBQSR. SparkFlow realizes the ability to accelerate large-scale cancer genomic analysis by scaling vertically (HyperThreading) and horizontally (provisions on-demand). Our result demonstrates a trade-off inevitably between the targeted applications and processor architecture. SparkFlow achieves a decisive improvement in NGS computation performance, throughput, and scalability while maintaining deployment complexity. The paper's findings aim to pave the way for a wide range of revolutionary enhancements and future trends within the High-performance data Analytics (HPDA) genome analysis realm.

关键词： Big data High-performance data Analytics Apache Spark Genome analysis HPC Scientific Workflow

来源：评论

学校读者我要写书评

暂无评论

AFALog: A General Augmentation Framework for Log-based Anomaly Detection with Active Learning 34

AFALog: A General Augmentation Framework for Log-based Anoma...

引用

34th ieee International symposium on Software Reliability Engineering (ISSRE)

作者： Duan, Chiming Jia, Tong Cai, Huaqian Li, Ying Huang, Gang Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ Inst Artificial Intelligence Beijing Peoples R China Peking Univ Sch Comp Sci Beijing Peoples R China Peking Univ Natl Engn Res Ctr Software Engn Beijing Peoples R China

ISBN: (纸本)9798350315943

Log-based anomaly detection is becoming more and more important for maintaining the availability of modern microservice systems. Existing supervised/semi-supervised log anomaly detection models require a large amount of human-labeled logs for training which are hard to collect in realworld systems. Unsupervised models often perform poorly without explicit anomaly labels. To improve the performance of unsupervised models, in this paper, we first make an empirical study of existing unsupervised models to tackle the reason why they often produce unsatisfied results. We find that anomaly detection results produced by existing unsupervised models are significantly affected by two key problems including Not-Cover (NC) problem and Suspicious-Noise (SN) problem. To solve these problems, we propose a novel augmentation framework called AFALog. AFALog leverages the idea of active learning to incorporate human knowledge so as to augment data quality. It can support almost all existing unsupervised models and improve their performance. Our experiments on two open datasets and one dataset collected from a real-world microservice system demonstrate that DALog improves the F1-score by an average of 6.61%, with only 5.9% labeled training data.

关键词： Anomaly Detection Augmentation Log analysis Active Learning Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Off-Road Path-Planning Based on large Scale OpenStreetMap and DSM data 9

Off-Road Path-Planning Based on Large Scale OpenStreetMap an...

引用

9th International Conference on Big data and Information Analytics, BigDIA 2023

作者： Ren, Shaoxuan Zhang, Maojun Liu, Yan Wang, Jingyi Zhou, Wen National University of Defense Technology College of Systems and Engineering Changsha China Hangzhou Dianzi University School of Computer Science and Technology Changsha China

ISBN: (纸本)9798350330076

In order to plan collision-free and shortest routes for vehicles in large-scale off-road scenarios, it is necessary to have a sufficient understanding and utilization of scene information. This paper proposes an off-road path planning method based on large scale OpenStreetMap (OSM) and Digital Surface Model (DSM). Our method comprehensively utilizes the terrain information from OpenStreetMap, slope information from DSM to analysis the traversability of the scene. We conduct experiments with a 2.5 km ∗ 3.5 km area surrounding the Federal Institute of Technology in Lausanne, Switzerland. In order to more intuitively display the results of path planning in the terrain, we conducted a three-dimensional visualization of the results. The experimental results verify the effectiveness of the method and the collision-free and the shortest routes can be planned in the large scale off-road scenarios. © 2023 ieee.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Exploiting Functional Connectivity Inference for Efficient Root Cause analysis

Exploiting Functional Connectivity Inference for Efficient R...

引用

ieee/IFIP Network Operations and Management symposium

作者： Winchester, Giles Parisis, George Berthouze, Luc Univ Sussex Dept Informat Brighton E Sussex England

ISBN: (纸本)9781665406017

A crucial step in remedying faults within network infrastructure is to determine their root cause. However, the large-scale, complex and dynamic nature of modern architecture makes root cause analysis challenging. Statistical approaches for causal inference are promising, however, their deployment has been historically limited due to their high time complexity. In this paper we propose a general framework for leveraging the concept of functional connectivity to reduce the computational overhead of causal inference algorithms. We demonstrate on synthetic data that our approach can achieve substantial speedups when combined with state-of-the-art causal discovery algorithms, with only a small cost in terms of loss of causal information in some cases.

关键词： Network management root cause analysis functional connectivity inference

来源：评论

学校读者我要写书评

暂无评论

How to Trust Unlabeled data? Instance Credibility Inference for Few-Shot Learning

引用

ieee TRANSACTIONS ON PATTERN analysis AND MACHINE INTELLIGENCE 2022年第10期44卷 6240-6253页

作者： Wang, Yikai Zhang, Li Yao, Yuan Fu, Yanwei Fudan Univ Sch Data Sci Shanghai 200433 Peoples R China Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Hong Kong Univ Sci & Technol Dept Math Hong Kong Peoples R China Hong Kong Univ Sci & Technol Dept Chem & Biol Engn Hong Kong Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Shanghai 200433 Peoples R China

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories, some of which are with a large number of instances, but with only a few manually annotated. Learning from such extremely limited labeled examples is known as Few-Shot Learning (FSL). Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm to predict pseudo-labels of unlabeled instances with an initial classifier trained from the few shot and then select the most confident ones to augment the training set to re-train the classifier. This is achieved by constructing a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of the corresponding pseudo-labeled instance. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances. This process is repeated until all the unlabeled samples are included in the expanded training set. Theoretically, under the conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show the effe

关键词： Training data models Noise measurement Task analysis Feature extraction visualization Standards Few-shot learning incidental parameters regularization path semi-supervised learning self-taught learning

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network based Root Cause analysis Using Multivariate Time-series KPIs for Wireless Networks

Graph Neural Network based Root Cause Analysis Using Multiva...

引用

ieee/IFIP Network Operations and Management symposium

作者： Yen, Chia-Cheng Sun, Wenting Purmehdi, Hakimeh Park, Won Deshmukh, Kunal Rajan Thakrar, Nishank Nassef, Omar Jacobs, Adam Ericsson Inc Santa Clara CA 95054 USA Kings Coll London Dept Engn London England

ISBN: (纸本)9781665406017

Due to the rapid adoption of SG networks and the increasing number of devices and base stations (gNBs) connected to it, manually identifying malfunctioning machines or devices that cause a part of the networks to fail becomes more challenging. Furthermore, data collected from the networks are not always sufficient. To overcome these two issues, we proposed a novel root cause analysis (RCA) framework that integrates graph neural networks (GNNs) with graph structure learning (GSL) to infer hidden dependencies from available data. The learned dependencies are the graph structure utilized to predict the root cause machines or devices. We found that despite the fact that the data is often incomplete, the GSL model can infer fairly accurate hidden dependencies from data with a large number of nodes and generate informative graph representation for GNNs to identify the root cause. Our experimental results showed that higher accuracy of identifying a root cause and victim nodes can be achieved when the number of nodes in an environment is increased.

关键词： 5G networks anomaly detection fault localization root cause analysis graph neural networks

来源：评论

学校读者我要写书评

暂无评论

AUGMENTED AERIAL REALITY: ON FUSING SYNTHETIC AND REAL AIRBORNE IMAGERY FOR OBJECT DETECTION

AUGMENTED AERIAL REALITY: ON FUSING SYNTHETIC AND REAL AIRBO...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Weber, Immanuel Bongartz, Jens Roscher, Ribana PLEdoc AB EX Gladbecker Str 404 D-45326 Essen Germany Univ Appl Sci Koblenz AMLS Joseph Rovan Allee 2 D-53424 Remagen Germany Univ Bonn Inst Geodesy & Geoinformat Niebuhrstr 1a D-53121 Bonn Germany

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Object detection is a core task for image analysis and interpretation and is broadly applied in applications relying on space- and airborne imagery. Like all supervised deep learning methods, training an object detector generally requires a large amount of representative annotated data, which can be hard to acquire in practice. To overcome this challenge, generating synthetic data can be an option to alleviate a lack of real-world annotated data. One key influential factor for the quality of the synthetic data is the background. We show that the detectors' classifier especially depends severely on the background and has a large impact on the detection precision. Using real background is a natural option, however, we show that this naive approach has drawbacks such as a significant drop in recall. In this paper, we demonstrate that by using style transfer to match the synthetic foreground to the real background, the detector can mitigate these drawbacks and achieve a more balanced result in terms of precision and recall.

关键词： deep learning object detection synthetic data data fusion

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：