Search

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. [ABSTRACT FROM AUTHOR]

Gated spiking neural P (GSNP) model is a recently developed recurrent-like network, which is abstracted by nonlinear spiking mechanism of nonlinear spiking neural P systems. In this study, a modification of GSNP is combined with attention mechanism to develop a novel model for sentiment classification, called attention-enabled GSNP model or termed as AGSNP model. The AGSNP model has two channels that process content words and aspect item respectively, where two modified GSNPs are used to obtain dependencies between content words and between aspect words. Moreover, two attention components are used to establish semantic correlation between content words and aspect item. Comparative experiments on three real data sets and several baseline models are conducted to verify the effectiveness of the AGSNP model. The comparison results demonstrate that the AGSNP model is competent for aspect-level sentiment classification tasks. • We propose a modification of gated spiking neural P systems. • We propose a new model for sentiment classification, termed as AGSNP model. • We design a sentiment classification framework based on AGSNP. [ABSTRACT FROM AUTHOR]

Aspect-level sentiment classification still remains a challenge: how to capture contextual semantic correlation between aspect word and content words more effectively. LSTM-SNP is a variant of long short-term memory (LSTM), inspired from nonlinear spiking mechanisms in nonlinear spiking neural P systems. To address the challenge, we develop a modification of LSTM-SNP and design a bidirectional LSTM-SNP based on the modification, termed as BiLSTM-SNP. Based on BiLSTM-SNP and attention mechanism, we propose a novel method for aspect-level sentiment classification. BiLSTM-SNP is used to capture semantic correlation between aspect word and content words, while attention mechanism is utilized to generate appropriate attention weights for hidden states of BiLSTM-SNP. Experiments on English and Chinese data sets are conducted on the proposed model and several baseline models. Experiment results on English and Chinese data sets demonstrate the effectiveness of the proposed model for aspect-level sentiment classification. [ABSTRACT FROM AUTHOR]