Unsupervised Spatial–Spectral Feature Learning by 3D Convolutional Autoencoder for Hyperspectral Classification

In recent years, deep learning methods have been widely used in the hyperspectral image (HSI) classification tasks. Among them, spectral-spatial combined methods based on the three-dimensional (3-D) convolution have shown good performance. However, because of the three-dimensional convolution, increasing network depth will result in a dramatic rise in the number of parameters. In addition, the previous methods do not make full use of spectral information. They mostly use the data after dimensionality reduction directly as the input of networks, which result in poor classification ability in some categories with small numbers of samples. To address the above two issues, in this paper, we designed an end-to-end 3D-ResNeXt network which adopts feature fusion and label smoothing strategy further. On the one hand, the residual connections and split-transform-merge strategy can alleviate the declining-accuracy phenomenon and decrease the number of parameters. We can adjust the hyperparameter cardinality instead of the network depth to extract more discriminative features of HSIs and improve the classification accuracy. On the other hand, in order to improve the classification accuracies of classes with small numbers of samples, we enrich the input of the 3D-ResNeXt spectral-spatial feature learning network by additional spectral feature learning, and finally use a loss function modified by label smoothing strategy to solve the imbalance of classes. The experimental results on three popular HSI datasets demonstrate the superiority of our proposed network and an effective improvement in the accuracies especially for the classes with small numbers of training samples.

Download Full-text

A Deep Feature Learning Method for Drill Bits Monitoring Using the Spectral Analysis of the Acoustic Signals

Sensors ◽

10.3390/s18082634 ◽

2018 ◽

Vol 18 (8) ◽

pp. 2634 ◽

Cited By ~ 2

Author(s):

Caleb Vununu ◽

Kwang-Seok Moon ◽

Suk-Hwan Lee ◽

Ki-Ryong Kwon

Keyword(s):

Power Spectrum ◽

Feature Learning ◽

Final Diagnosis ◽

Extraction Process ◽

Drill Bits ◽

High Discrimination ◽

Convolutional Autoencoder ◽

Spectrum Density ◽

High Level ◽

Nonlinear Classifier

Machine fault diagnosis (MFD) has gained an important enthusiasm since the unfolding of the pattern recognition techniques in the last three decades. It refers to all of the studies that aim to automatically detect the faults on the machines using various kinds of signals that they can generate. The present work proposes a MFD system for the drilling machines that is based on the sounds they produce. The first key contribution of this paper is to present a system specifically designed for the drills, by attempting not only to detect the faulty drills but also to detect whether the sounds were generated during the active or the idling stage of the whole machinery system, in order to provide a complete remote control. The second key contribution of the work is to represent the power spectrum of the sounds as images and apply some transformations on them in order to reveal, expose, and emphasize the health patterns that are hidden inside them. The created images, the so-called power spectrum density (PSD)-images, are then given to a deep convolutional autoencoder (DCAE) for a high-level feature extraction process. The final step of the scheme consists of adopting the proposed PSD-images + DCAE features as the final representation of the original sounds and utilize them as the inputs of a nonlinear classifier whose outputs will represent the final diagnosis decision. The results of the experiments demonstrate the high discrimination potential afforded by the proposed PSD-images + DCAE features. They were also tested on a noisy dataset and the results show their robustness against noises.

Download Full-text

A Hybrid Autoencoder Network for Unsupervised Image Clustering

Algorithms ◽

10.3390/a12060122 ◽

2019 ◽

Vol 12 (6) ◽

pp. 122 ◽

Cited By ~ 3

Author(s):

Pei-Yin Chen ◽

Jih-Jeng Huang

Keyword(s):

Feature Learning ◽

Image Data ◽

Image Clustering ◽

Great Success ◽

Distance Metrics ◽

Clustering Methods ◽

Unsupervised Feature Learning ◽

Agglomerative Clustering ◽

Convolutional Autoencoder ◽

Important Field

Image clustering involves the process of mapping an archive image into a cluster such that the set of clusters has the same information. It is an important field of machine learning and computer vision. While traditional clustering methods, such as k-means or the agglomerative clustering method, have been widely used for the task of clustering, it is difficult for them to handle image data due to having no predefined distance metrics and high dimensionality. Recently, deep unsupervised feature learning methods, such as the autoencoder (AE), have been employed for image clustering with great success. However, each model has its specialty and advantages for image clustering. Hence, we combine three AE-based models—the convolutional autoencoder (CAE), adversarial autoencoder (AAE), and stacked autoencoder (SAE)—to form a hybrid autoencoder (BAE) model for image clustering. The MNIST and CIFAR-10 datasets are used to test the result of the proposed models and compare the results with others. The results of the clustering criteria indicate that the proposed models outperform others in the numerical experiment.

Download Full-text

Distinguishable spatial-spectral feature learning neural network framework for motor imagery-based brain computer interface

Journal of Neural Engineering ◽

10.1088/1741-2552/ac1d36 ◽

2021 ◽

Author(s):

Chang Liu ◽

Jing Jin ◽

Ren Xu ◽

Shurui Li ◽

Cili Zuo ◽

...

Keyword(s):

Neural Network ◽

Motor Imagery ◽

Brain Computer Interface ◽

Spectral Feature ◽

Feature Learning ◽

Computer Interface

Download Full-text

Spatial–Spectral Feature Refinement for Hyperspectral Image Classification Based on Attention-Dense 3D-2D-CNN

Sensors ◽

10.3390/s20185191 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5191

Author(s):

Jin Zhang ◽

Fengyuan Wei ◽

Fan Feng ◽

Chunyang Wang

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

Spectral Feature ◽

Small Sample ◽

Training Data ◽

Spectral Features ◽

Training Samples ◽

Proposed Model ◽

Limited Training Samples ◽

Hyperspectral Classification

Convolutional neural networks provide an ideal solution for hyperspectral image (HSI) classification. However, the classification effect is not satisfactory when limited training samples are available. Focused on “small sample” hyperspectral classification, we proposed a novel 3D-2D-convolutional neural network (CNN) model named AD-HybridSN (Attention-Dense-HybridSN). In our proposed model, a dense block was used to reuse shallow features and aimed at better exploiting hierarchical spatial–spectral features. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial–spectral features was realized by the channel attention method and spatial attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer, respectively. Experiment results indicate that our proposed model can learn more discriminative spatial–spectral features using very few training data. In Indian Pines, Salinas and the University of Pavia, AD-HybridSN obtain 97.02%, 99.59% and 98.32% overall accuracy using only 5%, 1% and 1% labeled data for training, respectively, which are far better than all the contrast models.

Download Full-text