scholarly journals A 3D Cascaded Spectral–Spatial Element Attention Network for Hyperspectral Image Classification

2021 ◽  
Vol 13 (13) ◽  
pp. 2451
Author(s):  
Huaiping Yan ◽  
Jun Wang ◽  
Lei Tang ◽  
Erlei Zhang ◽  
Kun Yan ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
Training Sample ◽  
Small Sample ◽  
Data Sets ◽  
Attention Network ◽  
Deep Network ◽  
Public Data ◽  
Comparable Performance ◽  
And Performance ◽  
Spatial Element

Most traditional hyperspectral image (HSI) classification methods relied on hand-crafted or shallow-based descriptors, which limits their applicability and performance. Recently, deep learning has gradually become the mainstream method of HSI classification, because it can automatically extract deep abstract features for classification. However, it remains a challenge to learn more meaningful features for HSI classification from a small training sample set. In this paper, a 3D cascaded spectral–spatial element attention network (3D-CSSEAN) is proposed to solve this issue. The 3D-CSSEAN integrates the spectral–spatial feature extraction and attention area extraction for HSI classification. Two element attention modules in the 3D-CSSEAN enable the deep network to focus on primary spectral features and meaningful spatial features. All attention modules are implemented though several simple activation operations and elementwise multiplication operations. In this way, the training parameters of the network are not added too much, which also makes the network structure suitable for small sample learning. The adopted module cascading pattern not only reduces the computational burden in the deep network but can also be easily operated via plug–expand–play. Experimental results on three public data sets show that the proposed 3D-CSSEAN achieved comparable performance with the state-of-the-art methods.

A Reliability-Based Approach to Assess Fatigue Behaviour Based on Small Incomplete Data Sets

2008 ◽  
Vol 44-46 ◽  
pp. 871-878 ◽  
Author(s):  
Chu Yang Luo ◽  
Jun Jiang Xiong ◽  
R.A. Shenoi
Keyword(s):  
Incomplete Data ◽  
Standard Procedure ◽  
Fatigue Behaviour ◽  
Fatigue Tests ◽  
Small Sample ◽  
Data Sets ◽  
Safe Life ◽  
A New Technique ◽  
And Performance

This paper outlines a new technique to address the paucity of data in determining fatigue life and performance based on reliability concepts. Two new randomized models are presented for estimating the safe life and pS-N curve, by using the standard procedure for statistical analysis and dealing with small sample numbers of incomplete data. The confidence level formulations for the safe and p-S-N curve are also given. The concepts are then applied for the determination of the safe life and p-S-N curve. Two sets of fatigue tests for the safe life and p-S-N curve are conducted to validate the presented method, demonstrating the practical use of the proposed technique.

scholarly journals ramr: an R package for detection of rare aberrantly methylated regions

2020 ◽  
Author(s):  
Oleksii Nikolaienko ◽  
Per Eystein Lønning ◽  
Stian Knappskog
Keyword(s):  
Performance Metrics ◽  
Developmental Stages ◽  
R Package ◽  
Data Sets ◽  
Bioinformatic Tools ◽  
Public Data ◽  
Risk Of Disease ◽  
Low Incidence ◽  
And Performance ◽  
Risk Of Cancer

AbstractMotivationWith recent advances in the field of epigenetics, the focus is widening from large and frequent disease- or phenotype-related methylation signatures to rare alterations transmitted mitotically or transgenerationally (constitutional epimutations). Merging evidence indicate that such constitutional alterations, albeit occurring at a low mosaic level, may confer risk of disease later in life. Given their inherently low incidence rate and mosaic nature, there is a need for bioinformatic tools specifically designed to analyse such events.ResultsWe have developed a method (ramr) to identify aberrantly methylated DNA regions (AMRs). ramr can be applied to methylation data obtained by array or next-generation sequencing techniques to discover AMRs being associated with elevated risk of cancer as well as other diseases. We assessed accuracy and performance metrics of ramr and confirmed its applicability for analysis of large public data sets. Using ramr we identified aberrantly methylated regions that are known or may potentially be associated with development of colorectal cancer and provided functional annotation of AMRs that arise at early developmental stages.Availability and implementationThe R package is freely available at https://github.com/BBCG/ramr

scholarly journals JL-GFDN: A Novel Gabor Filter-Based Deep Network Using Joint Spectral-Spatial Local Binary Pattern for Hyperspectral Image Classification

2020 ◽  
Vol 12 (12) ◽  
pp. 2016 ◽  
Author(s):  
Tao Zhang ◽  
Puzhao Zhang ◽  
Weilin Zhong ◽  
Zhen Yang ◽  
Fan Yang
Keyword(s):  
Local Binary Pattern ◽  
Hyperspectral Image ◽  
Gabor Filter ◽  
Spectral Characteristics ◽  
Three Dimensional ◽  
Real Data ◽  
Hyperspectral Data ◽  
Data Cube ◽  
Data Sets ◽  
Deep Network

The traditional local binary pattern (LBP, hereinafter we also call it a two-dimensional local binary pattern 2D-LBP) is unable to depict the spectral characteristics of a hyperspectral image (HSI). To cure this deficiency, this paper develops a joint spectral-spatial 2D-LBP feature (J2D-LBP) by averaging three different 2D-LBP features in a three-dimensional hyperspectral data cube. Subsequently, J2D-LBP is added into the Gabor filter-based deep network (GFDN), and then a novel classification method JL-GFDN is proposed. Different from the original GFDN framework, JL-GFDN further fuses the spectral and spatial features together for HSI classification. Three real data sets are adopted to evaluate the effectiveness of JL-GFDN, and the experimental results verify that (i) JL-GFDN has a better classification accuracy than the original GFDN; (ii) J2D-LBP is more effective in HSI classification in comparison with the traditional 2D-LBP.

scholarly journals Hyperspectral Image Classification Based on Improved Rotation Forest Algorithm

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3601 ◽  
Author(s):  
Fei Lv ◽  
Min Han
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Image Data ◽  
Classification Method ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Rotation Forest ◽  
Public Data ◽  
Learning Machine ◽  
Q Statistic

Hyperspectral image classification is a hot issue in the field of remote sensing. It is possible to achieve high accuracy and strong generalization through a good classification method that is used to process image data. In this paper, an efficient hyperspectral image classification method based on improved Rotation Forest (ROF) is proposed. It is named ROF-KELM. Firstly, Non-negative matrix factorization( NMF) is used to do feature segmentation in order to get more effective data. Secondly, kernel extreme learning machine (KELM) is chosen as base classifier to improve the classification efficiency. The proposed method inherits the advantages of KELM and has an analytic solution to directly implement the multiclass classification. Then, Q-statistic is used to select base classifiers. Finally, the results are obtained by using the voting method. Three simulation examples, classification of AVIRIS image, ROSIS image and the UCI public data sets respectively, are conducted to demonstrate the effectiveness of the proposed method.

scholarly journals Analysis of Enterprise Shared Resource Invocation Scheme based on Hadoop and R

2021 ◽  
Vol 12 (1) ◽  
pp. 55-69
Author(s):  
Hong Xiong
Keyword(s):  
User Experience ◽  
Relevant Information ◽  
Data Sets ◽  
Shared Resources ◽  
Shared Resource ◽  
Public Data ◽  
Resource Storage ◽  
The Difference ◽  
And Performance ◽  
Feasible Solutions

The response rate and performance indicators of enterprise resource calls have become an important part of measuring the difference in enterprise user experience. An efficient corporate shared resource calling system can significantly improve the office efficiency of corporate users and significantly improve the fluency of corporate users' resource calling. Hadoop has powerful data integration and analysis capabilities in resource extraction, while R has excellent statistical capabilities and resource personalized decomposition and display capabilities in data calling. This article will propose an integration plan for enterprise shared resource invocation based on Hadoop and R to further improve the efficiency of enterprise users' shared resource utilization, improve the efficiency of system operation, and bring enterprise users a higher level of user experience. First, we use Hadoop to extract the corporate shared resources required by corporate users from the nearby resource storage computer room and terminal equipment to increase the call rate, and use the R function attribute to convert the user’s search results into linear correlations, according to the correlation The strong and weak principles are displayed in order to improve the corresponding speed and experience. This article proposes feasible solutions to the shortcomings in the current enterprise shared resource invocation. We can use public data sets to perform personalized regression analysis on user needs, and optimize and integrate most relevant information.

scholarly journals Research on recommendation algorithm of Graph attention Network based on Knowledge graph

2021 ◽  
Vol 2113 (1) ◽  
pp. 012085
Author(s):  
Yiping Zeng ◽  
Shumin Liu
Keyword(s):  
Recommendation System ◽  
Auxiliary Information ◽  
Experimental Comparison ◽  
Knowledge Graph ◽  
Data Sets ◽  
User Interest ◽  
Attention Network ◽  
Model Combining ◽  
Public Data ◽  
New Research

Abstract The introduction of knowledge graph as the auxiliary information of recommendation system provides a new research idea for personalized intelligent recommendation. However, most of the existing knowledge graph recommendation algorithms fail to effectively solve the problem of unrelated entities, leading to inaccurate prediction of potential preferences of users. To solve this problem, this paper proposes a KG-IGAT model combining knowledge graph and graph attention network, and adds an interest evolution module to graph attention network to capture user interest changes and generate top-N recommendations. Finally, experimental comparison between the proposed model and other algorithms using public data sets shows that KG-IGAT has better recommendation performance.

scholarly journals VIRTUAL TRAINING SAMPLE GENERATION BY GENERATIVE ADVERSARIAL NETWORKS FOR HYPERSPECTRAL IMAGES CLASSIFICATION

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 63-69 ◽  
Author(s):  
T. Alipourfard ◽  
H. Arefi
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Training Sample ◽  
Small Sample ◽  
Hyperspectral Images ◽  
Generative Adversarial Networks ◽  
Hyperspectral Image Classification ◽  
Virtual Training ◽  
Adversarial Networks ◽  
Training Samples

Abstract. Convolutional Neural Networks (CNNs) as a well-known deep learning technique has shown a remarkable performance in visual recognition applications. However, using such networks in the area of hyperspectral image classification is a challenging and time-consuming process due to the high dimensionality and the insufficient training samples. In addition, Generative Adversarial Networks (GANs) has attracted a lot of attentions in order to generate virtual training samples. In this paper, we present a new classification framework based on integration of multi-channel CNNs and new architecture for generator and discriminator of GANs to overcome Small Sample Size (SSS) problem in hyperspectral image classification. Further, in order to reduce the computational cost, the methods related to the reduction of subspace dimension were proposed to obtain the dominant feature around the training sample to generate meaningful training samples from the original one. The proposed framework overcomes SSS and overfitting problem in classifying hyperspectral images. Based on the experimental results on real and well-known hyperspectral benchmark images, our proposed strategy improves the performance compared to standard CNNs and conventional data augmentation strategy. The overall classification accuracy in Pavia University and Indian Pines datasets was 99.8% and 94.9%, respectively.

MULFE: Multi-Label Learning via Label-Specific Feature Space Ensemble

2021 ◽  
Vol 16 (1) ◽  
pp. 1-24
Author(s):  
Yaojin Lin ◽  
Qinghua Hu ◽  
Jinghua Liu ◽  
Xingquan Zhu ◽  
Xindong Wu
Keyword(s):  
Empirical Studies ◽  
Feature Space ◽  
Training Data ◽  
Data Sets ◽  
Learning Framework ◽  
Feature Spaces ◽  
Public Data ◽  
Margin Distribution ◽  
Label Correlations ◽  
Label Correlation

In multi-label learning, label correlations commonly exist in the data. Such correlation not only provides useful information, but also imposes significant challenges for multi-label learning. Recently, label-specific feature embedding has been proposed to explore label-specific features from the training data, and uses feature highly customized to the multi-label set for learning. While such feature embedding methods have demonstrated good performance, the creation of the feature embedding space is only based on a single label, without considering label correlations in the data. In this article, we propose to combine multiple label-specific feature spaces, using label correlation, for multi-label learning. The proposed algorithm, mu lti- l abel-specific f eature space e nsemble (MULFE), takes consideration label-specific features, label correlation, and weighted ensemble principle to form a learning framework. By conducting clustering analysis on each label’s negative and positive instances, MULFE first creates features customized to each label. After that, MULFE utilizes the label correlation to optimize the margin distribution of the base classifiers which are induced by the related label-specific feature spaces. By combining multiple label-specific features, label correlation based weighting, and ensemble learning, MULFE achieves maximum margin multi-label classification goal through the underlying optimization framework. Empirical studies on 10 public data sets manifest the effectiveness of MULFE.

Sign in / Sign up

Export Citation Format

Share Document