The Deep Belief and Self-Organizing Neural Network as a Semi-Supervised Classification Method for Hyperspectral Data

Applied Sciences

Nan Yu¹  Quanxin Wang¹  Qingjian Li¹  Ke Li¹  Suling Jia²  Wei Lan² 

[1] Fundamental Science on Ergonomics and Environment Control Laboratory, School of Aeronautics Science and Engineering, Beihang University, Beijing 100191, China;School of Economics and Management, Beihang University, Beijing 100191, China;

关键词: DBN;    data compression;    hyperspectral;    SOM;    pattern classification;   

DOI  :  10.3390/app7121212

来源: DOAJ

【 摘 要 】

Hyperspectral data is not linearly separable, and it has a high characteristic dimension. This paper proposes a new algorithm that combines a deep belief network based on the Boltzmann machine with a self-organizing neural network. The primary features of the hyperspectral image are extracted with a deep belief network. The weights of the network are fine-tuned using the labeled sample. Feature vectors extracted by the deep belief network are classified by a self-organizing neural network. The method reduces the spectral dimension of the data while preserving the large amount of original information in the data. The method overcomes the long training time required when using self-organizing neural networks for clustering, as well as the training difficulties of Deep Belief Networks (DBN) when the labeled sample size is small, thereby improving the accuracy and robustness of the semi-supervised classification. Simulation results show that the structure of the network can achieve higher classification accuracy when the labeled sample is deficient.

【 授权许可】

Unknown