Hydrophobicity classification of composite insulators based on convolutional neural networks

Kokalis, Christos-Christodoulos A.; Tasakos, Thanos; Kontargyri, Vassiliki T.; Siolas, Georgios; Gonos, Ioannis F.

doi:10.1016/j.engappai.2020.103613

Cited by 32 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is specifically designed for image recognition and detection; it contains many layers of neural network that extracts features of an image and detects which class it belongs to (detection and recognition of an image after it is trained with a set of images). Figure 2 shows the architecture and working of CNN [24,25]. A CNN contains layers of neural nets.…”

Section: Methodsmentioning

confidence: 99%

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Mohammed

Hussain

2021

Computation

View full text Add to dashboard Cite

Accurate, fast, and automatic detection and classification of animal images is challenging, but it is much needed for many real-life applications. This paper presents a hybrid model of Mamdani Type-2 fuzzy rules and convolutional neural networks (CNNs) applied to identify and distinguish various animals using different datasets consisting of about 27,307 images. The proposed system utilizes fuzzy rules to detect the image and then apply the CNN model for the object’s predicate category. The CNN model was trained and tested based on more than 21,846 pictures of animals. The experiments’ results of the proposed method offered high speed and efficiency, which could be a prominent aspect in designing image-processing systems based on Type 2 fuzzy rules characterization for identifying fixed and moving images. The proposed fuzzy method obtained an accuracy rate for identifying and recognizing moving objects of 98% and a mean square error of 0.1183464 less than other studies. It also achieved a very high rate of correctly predicting malicious objects equal to recall = 0.98121 and a precision rate of 1. The test’s accuracy was evaluated using the F1 Score, which obtained a high percentage of 0.99052.

show abstract

Section: Methodsmentioning

confidence: 99%

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Mohammed

Hussain

2021

Computation

View full text Add to dashboard Cite

show abstract

“…It is a challenging task to acquire a certain number of insulators with HC1–HC7. Some researchers proposed that using different percentage of isopropyl alcohol by volume as spraying solution could artificially simulate different HCs [12–17]. Isopropyl alcohol has a lower surface tension than water, spray it on the insulator surface, the droplets formed consistent with weak hydrophobic.…”

Section: Spray Images Collectionmentioning

confidence: 99%

“…Convolutional neural network (CNN) is widely used in intelligent image recognition tasks due to its excellent feature extraction ability. In order to overcome the limitations of the subjective feature extraction, some researchers had applied CNN to HC recognition of composite insulators [16,17], and already verified the feasibility. However, the generalization ability of the CNN model under actual conditions, including various shooting angles and distances, different ambient lighting and surface conditions, is not considered at present, which limits the practical application of this technology.…”

Section: Introductionmentioning

confidence: 99%

Hydrophobicity Classification of Composite Insulators Based on Light‐Weight Convolutional Neural Networks

Qiu

Liu

Liao

et al. 2022

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

To achieve accurate and rapid measurement of the hydrophobicity class (HC) of composite insulators, an intelligent spray image recognition technique based on light‐weight convolutional neural networks (CNN) is proposed in this paper. A spray image data set contains clean, contaminated and aged insulators with various illuminations, shooting angles and distances, about 10 400 images of shed surface were collected by spray tests and data augmentation. Five classification models were established by different CNNs, including GoogLeNet, ResNet101, ShuffleNet 0.5×, ShuffleNet 0.25× and MobileNet V2, while the first four of them were pre‐trained by ImageNet dataset. These models were trained, validated and tested by spray image data set. Six indexes were designed to evaluate each model and the discriminative regions for classification were visualized by gradient weighted class activation mapping (Grad‐CAM) method. The results show that these models can effectively recognize spray images with HC1–HC7 and the light‐weight ShuffleNet 0.5× has the best performance, with the classification accuracy of 97.09% for 2022 test images. The Grad‐CAM visualizations indicate that the results have high reliability. This study can provide reference for on‐line detection and intelligent identification of hydrophobicity levels of composite insulators. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

“…Recently, deep learning has been introduced into insulator detection. The existing insulator detection methods have been successfully applied to the detection of insulator pollution degrees [4], insulator hydrophobicity degrees [17], and insulator icing degrees [18]. The ordinary methods collect samples of various categories and divide them into the train set, validation set, and the test set.…”

Section: Insulator Identificationmentioning

confidence: 99%

Few-shot contrastive learning for image classification and its application to insulator identification

Jin

Huang

2021

Appl Intell

View full text Add to dashboard Cite

This paper presents a novel discriminative Few-shot learning architecture based on batch compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably good performance in image recognition. Most existing CNN methods facilitate classifiers to learn discriminating patterns to identify existing categories trained with large samples. However, learning to recognize novel categories from a few examples is a challenging task. To address this, we propose the Residual Compact Network to train a deep neural network to learn hierarchical nonlinear transformations to project image pairs into the same latent feature space, under which the distance of each positive pair is reduced. To better use the commonality of class-level features for category recognition, we develop a batch compact loss to form robust feature representations relevant to a category. The proposed methods are evaluated on several datasets. Experimental evaluations show that our proposed method achieves acceptable results in Few-shot learning.

show abstract

Hydrophobicity classification of composite insulators based on convolutional neural networks

Cited by 32 publications

References 19 publications

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Hydrophobicity Classification of Composite Insulators Based on Light‐Weight Convolutional Neural Networks

Few-shot contrastive learning for image classification and its application to insulator identification

Contact Info

Product

Resources

About