Hierarchical broad learning system for hyperspectral image classification

Xiao, Guangrun; Wei, Yantao; Yao, Hongxun; Deng, Wei; Xu, Jiajun; Pan, Donghui

doi:10.1049/ipr2.12371

Cited by 4 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BLS has been applied in many fields. Xiao [5] proposed a hierarchical broad learning system, which combines wavelet transform and filter with broad learning system to form a hierarchical structure. The wavelet transform is used to observe noise, and broad learning system is used to obtain pixel probability maps.…”

Section: Iintroductionmentioning

confidence: 99%

Broad learning system based on adaptive lasso

Zhang

Liang

2023

Preprint

View full text Add to dashboard Cite

Broad learning system is an emerging method, which has achieved outstanding performance in regression and classification problems. This paper proposes a novel algorithm called Broad Learning System based on adaptive lasso (AdL1-BLS) to reduce model size and improve model generalization performance. The proposed AdL1-BLS introduces the weighted L1-norm penalty into BLS, adaptive lasso is used to assign different adaptive coefficients to each output weight of BLS. Because of the effect of adaptive coefficients, the output weight of BLS gets varying degrees of compression rates, which avoids the problem of over-sparse network structure and reduces the prediction error of the network, which better solve the BLS over-fitting problem, and improves the generalization of BLS under the premise of ensuring the sparseness of the network. Finally, the experiments on several commonly used regression data sets are carried out to verify the feasibility of the proposed AdL1-BLS. The experiment results indicate that AdL1-BLS can reduce model complexity without loss of prediction accuracy and improve the model interpretability.

show abstract

Section: Iintroductionmentioning

confidence: 99%

Broad learning system based on adaptive lasso

Zhang

Liang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Only the connection weights between the input layer and the output layer need to be calculated, which greatly improves the training speed of the model. Recently, BLS has been widely used in HSI classification [16][17][18][19][20][21] once it was proposed. Ma et al [17] proposed a novel Multiscale Random Convolution Broad Learning System (MRC-BLS).…”

Section: Introductionmentioning

confidence: 99%

Local Discriminative Embedding Broad Learning System With Graph Convolutional for Hyperspectral Image Classification

Wei

Shi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Broad learning system has attracted increasing attention in the hyperspectral image (HSI) classification, due to its universal approximation capability and high efficiency. However, two main challenges remained. One is that the mapping from the original BLS input to the mapped feature (MF) is linear, which is difficult to fully represent the complex spatial-spectral features of HSI. The other is that BLS fails to explore the local geometric structure relationship between samples within HSI. To overcome the limitations mentioned above, we propose a local discriminative embedding broad learning system with graph convolutional (GDEBLS). To address the first challenge, GDEBLS utilizes the graph convolution operation to aggregate the node information in the adjacent graph to learn the context and obtain the rich nonlinear spatial-spectral features in HSI. To deal with the second challenge, our method utilizes a neighborhood selection approach based on manifold structure to calculate the true distances between samples in the manifold space, overcoming the limitations of Euclidean distance measurement. Next, We introduce local manifold structure and discriminative information into BLS. The experimental results show that the proposed method significantly surpasses other state-of-the-art methods.INDEX TERMS broad learning system; hyperspectral image; local geometric structure; graph convolutional.

show abstract