Multiple Kernel Feature Line Embedding for Hyperspectral Image Classification

Chen, Ying Nong

doi:10.3390/rs11242892

Cited by 7 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Imani et al used a combination of median-mean line (MML) and feature line (FL) metrics to eliminate the negative impact of outliers on the class mean and improve the efficiency of the algorithm dimensional reduction [25]. In addition, scholars have also proposed extended versions of feature spacebased algorithms, such as orthogonal nearest neighbor feature line embedding (ONNFLE) [26], fuzzy kernel NFLE (FKN-FLE) [27], multiple kernel feature line embedding (MKFLE) [28], space-to-space (S2S)-based metric learning (FSDML) [29], support vector machine (SVMFLE)-based feature line embedding [30], and other methods.…”

Section: Introductionmentioning

confidence: 99%

Dimensionality reduction method based on multiple feature-space collaborative discriminative projection for rotor fault diagnosis

Dong¹,

Zhao²,

Yuan³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

At present, the trend of complex and intelligent rotating machinery and equipment is becoming more and more obvious, which generates a large amount of high-dimensional and nonlinear fault monitoring data that is difficult to handle. This makes the traditional dimensionality reduction algorithms based on point-to-point metrics or a small number of graph embedding structures lose their utility. To solve this problem, a multiple feature-spaces collaborative discriminative projection (MFSCDP) algorithm for rotor fault dataset dimensionality reduction is proposed. The algorithm first improves the projection metric from sample point to feature space into the median metric in order to achieve the effect of weakening the extrapolation error of the algorithm, and based on this, we propose a sample point-to-point guided nearest-neighbor feature space selection method to improve the construction efficiency of the feature space embedding graph. Then, by using Relief F to indirectly construct the reduced dimensional projection matrix with multiple feature spaces of collaboration. Finally, the proposed MFSCDP algorithm is used for the dimensionality reduction process of the rotor fault dataset. The algorithm's performance was verified using experimental information from rotor failure simulations of two different structural types. The result shows that the algorithm can reduce the difficulty of fault classification and improve the accuracy of identification.

show abstract

Section: Introductionmentioning

confidence: 99%

Dimensionality reduction method based on multiple feature-space collaborative discriminative projection for rotor fault diagnosis

Dong¹,

Zhao²,

Yuan³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Algorithms that rely on sample point-to-point (P2P) metric learning have restricted generalization capabilities and are incapable of extracting more discriminative information for subsequent fault classification. Hence, nearest feature space embedding (NFSE) [6], weighted feature line embedding (WFLE) [1], multiple kernel feature line embedding (MKFLE) [4], and others based on point-to-space (P2S) metrics have been introduced. These algorithms utilize the P2S metric, which not only compresses the feature space dimension but also enables the extraction of additional information for fault identification.…”

Section: Introductionmentioning

confidence: 99%

Dimensionality reduction of rotor fault dataset based on joint embedding of multi-class graphs

Zhang,

Wang,

Zhao

et al. 2023

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

Traditional dimensionality reduction techniques usually rely on a single or a limited number of similar graphs for graph embedding, which limits their ability to extract more information about the internal structure of the data. To address this problem, this study proposes a rotor fault dataset dimensionality reduction algorithm based on multi-class graph joint embedding (MCGJE). The algorithm first overcomes the defect that the traditional feature space cannot take both local and global information into account by constructing local and global median feature line graphs; secondly, based on the graph embedding framework, the algorithm also constructs a hypergraph structure for inscribing complex multivariate relationships between high-dimensional data in the feature space, which in turn enables it to contain more fault information. Finally, we conducted two different rotor fault simulation experiments. The results show that the MCGJE-based algorithm has robust dimensionality reduction capability and can significantly improve the accuracy of fault identification.

show abstract

“…To perceive the relationships among the graph node and its neighbors, graph embedding is employed, which learns to represent graph nodes with n-dimensional vectors. Graph embedding has a close connection with methods of the representation-based classification (e.g., some up-to-date works, such as LMRKNN [24], TPCRC [25], the novel DCRC method via l2 regularizations [26] and MKFLE [27]). Inspired by the representation learning, graph embedding methods on graph domain (e.g., DeepWalk [28], node2vec [29], LINE [30] and SDNE [31]) and some specific methods like those seen in [32] and [15] are proposed, which accomplish information aggregation based on the adjacent relationships among nodes on graphs.…”

Section: Introductionmentioning

confidence: 99%

A Spatial Adaptive Algorithm Framework for Building Pattern Recognition Using Graph Convolutional Networks

Bei

Guo

Huang³

2019

Sensors

View full text Add to dashboard Cite

Graph learning methods, especially graph convolutional networks, have been investigated for their potential applicability in many fields of study based on topological data. Their topological data processing capabilities have proven to be powerful. However, the relationships among separate entities include not only topological adjacency, but also correlation in vision, for example, the spatial vector data of buildings. In this study, we propose a spatial adaptive algorithm framework with a data-driven design to accomplish building group division and building group pattern recognition tasks, which is not sensitive to the difference in the spatial distribution of the buildings in various geographical regions. In addition, the algorithm framework has a multi-stage design, and processes the building group data from whole to parts, since the objective is closely related to multi-object detection on topological data. By using the graph convolution method and a deep neural network (DNN), the multitask model in this study can learn human thoughts through supervised training, and the whole process only depends upon the descriptive vector data of buildings without any ancillary data for building group partition. Experiments confirmed that the method for expressing buildings and the effect of the algorithm framework proposed are satisfactory. In summary, using deep learning methods to complete the tasks of building group division and building group pattern recognition is potentially effective, and the algorithm framework is worth further research.

show abstract

Multiple Kernel Feature Line Embedding for Hyperspectral Image Classification

Cited by 7 publications

References 22 publications

Dimensionality reduction method based on multiple feature-space collaborative discriminative projection for rotor fault diagnosis

Dimensionality reduction method based on multiple feature-space collaborative discriminative projection for rotor fault diagnosis

Dimensionality reduction of rotor fault dataset based on joint embedding of multi-class graphs

A Spatial Adaptive Algorithm Framework for Building Pattern Recognition Using Graph Convolutional Networks

Contact Info

Product

Resources

About