Unsupervised Convolutional Autoencoder-Based Feature Learning for Automatic Detection of Plant Diseases

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

Image Processing Technique for Automatic Detection of Plant Diseases and Alerting System in Agricultural Farms

2020 International Conference on Communication and Signal Processing (ICCSP) ◽

10.1109/iccsp48568.2020.9182065 ◽

2020 ◽

Author(s):

Pradeep Kumar Mugithe ◽

Rohit Varma Mudunuri ◽

B Rajasekar ◽

S Karthikeyan

Keyword(s):

Image Processing ◽

Automatic Detection ◽

Processing Technique ◽

Plant Diseases ◽

Image Processing Technique ◽

Alerting System

Download Full-text

A Review on Digital Image Processing Techniques for Automatic Detection, Quantification and Identification of Plant Diseases

International Journal of Computer Applications ◽

10.5120/ijca2017915373 ◽

2017 ◽

Vol 173 (8) ◽

pp. 14-19 ◽

Cited By ~ 1

Author(s):

Madhu Jadon ◽

Rashi Agarwal ◽

Raghuraj Singh ◽

Shilpa D.

Keyword(s):

Image Processing ◽

Digital Image Processing ◽

Digital Image ◽

Automatic Detection ◽

Plant Diseases ◽

Image Processing Techniques ◽

Processing Techniques

Download Full-text

An Unsupervised Deep Feature Learning Model Based on Parallel Convolutional Autoencoder for Intelligent Fault Diagnosis of Main Reducer

Computational Intelligence and Neuroscience ◽

10.1155/2021/8922656 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Qing Ye ◽

Changhua Liu

Keyword(s):

Fault Diagnosis ◽

Deep Structure ◽

Feature Learning ◽

Unsupervised Feature Learning ◽

Feature Generation ◽

Model Based ◽

Deep Feature ◽

Convolutional Autoencoder ◽

Diagnostic Framework ◽

Sample Set

Traditional diagnostic framework consists of three parts: data acquisition, feature generation, and fault classification. However, manual feature extraction utilized signal processing technologies heavily depending on subjectivity and prior knowledge which affect the effectiveness and efficiency. To tackle these problems, an unsupervised deep feature learning model based on parallel convolutional autoencoder (PCAE) is proposed and applied in the stage of feature generation of diagnostic framework. Firstly, raw vibration signals are normalized and segmented into sample set by sliding window. Secondly, deep features are, respectively, extracted from reshaped form of raw sample set and spectrogram in time-frequency domain by two parallel unsupervised feature learning branches based on convolutional autoencoder (CAE). During the training process, dropout regularization and batch normalization are utilized to prevent over fitting. Finally, extracted representative features are feed into the classification model based on deep structure of neural network (DNN) with softmax. The effectiveness of the proposed approach is evaluated in fault diagnosis of automobile main reducer. The results produced in contrastive analysis demonstrate that the diagnostic framework based on parallel unsupervised feature learning and deep structure of classification can effectively enhance the robustness and enhance the identification accuracy of operation conditions by nearly 8%.

Download Full-text