Recognition of gangues from color images using convolutional neural networks with attention mechanism

Liu, Huajie; Xu, Ke

doi:10.1016/j.measurement.2022.112273

Cited by 9 publications

(4 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dari hasil kompilasi data yang dilakukan terhadap review studi ini, sumber data yang digunakan untuk identifikasi Batubara dan gangue dapat dikategorikan menjadi 5 sumber data, yaitu data optik, data multispectral, data thermal, sinar X & Gamma dan data dielectric. Data optik adalah kategori data citra yang bersumber dari spektrum cahaya tampak dan dapat berupa data grayscale (Hou, W., 2019;Liu, K., 2018), data warna (Liu, H., 2023), tekstur dan geometri (Li, M. et al, 2020). Data multispectral adalah data yang diambil dari beberapa spektrum yang berbeda (Hu, F. et al, 2022).…”

Section: Sumber Dataunclassified

Review: Identifikasi Batubara dan Gangue Menggunakan Machine Learning dan Deep Learning

Bohari,

Hidayat,

Andianingsari

2024

imtech

View full text Add to dashboard Cite

Abstrak - Pemisahan gangue dari batubara adalah hal yang cukup penting dalam dunia industri pertambangan batubara. Berbagai upaya telah dilakukan oleh para peneliti dalam mencari cara yang lebih efektif dan efisien untuk identifikasi gangue dan batubara. Diantara metode yang cukup banyak diminati oleh para peneliti dalam satu dekade terkahir ini adalah penggunaan teknologi machine learning dan deep learning. Studi review ini bertujuan untuk melihat tren penelitian terkait klasifikasi batubara dan gangue yang menggunakan metode machine learning dan deep learning. Studi ini juga memotret perkembangan metode classifier yang digunakan beserta perkembangan penggunaan berbagai jenis sumber data citra yang menjadi masukan pada classifier. Berdasarkan hasil tabulasi dan analisa dari data-data yang dikumpulkan melalui studi ini diketahui bahwa jumlah penelitian terkait klasifikasi batubara dan gangue mengalami peningkatan dalam beberapa tahun terkahir yang disertai dengan penggunaan berbagai jenis metode classifier dan sumber data citra yang juga cukup bervariasi. Metode classifier yang cukup banyak digunakan adalah Convolutionary Neural Networks, dimana penggunaannya cukup dominan dengan angka lebih dari 60% diantara metode classifier lainnya. Sedangkan data citra optik menduduki peringkat atas sebagai sumber data citra yang paling banyak digunakan yaitu di level sekitar 60%. Di sisi lain, tren penggunaan data citra multispectral dan data citra thermal juga meningkat sebagai alternatif terhadap data citra optik yang cukup sensitif terhadap faktor lingkungan.

show abstract

Section: Sumber Dataunclassified

Review: Identifikasi Batubara dan Gangue Menggunakan Machine Learning dan Deep Learning

Bohari,

Hidayat,

Andianingsari

2024

imtech

View full text Add to dashboard Cite

show abstract

“…In contrast, a convolutional neural network can automatically extract high-level features of images and respond quickly. This method is least affected by external unfavorable factors and is more conducive to achieving accurate and rapid coal gangue recognition. − …”

Section: Introductionmentioning

confidence: 99%

“…This method is least affected by external unfavorable factors and is more conducive to achieving accurate and rapid coal gangue recognition. 21 − 23 …”

Section: Introductionmentioning

confidence: 99%

Research on the Strong Generalization of Coal Gangue Recognition Technology Based on the Image and Convolutional Neural Network under Complex Conditions

Xun,

Yang,

Liu

2023

ACS Omega

View full text Add to dashboard Cite

A coal gangue image recognition method based on complex conditions is proposed to address the current issue of image-based coal gangue recognition being greatly affected by complex conditions. First, complex conditions such as different shooting backgrounds, shooting distances, and lighting intensities are set to simulate the underground coal mining environment. Then, based on three convolutional neural network algorithms, the coal gangue recognition model is established, and the influence of different complex conditions on coal gangue image recognition is analyzed. At the same time, a network model with a strong generalization ability is determined. The results show that the accuracy of coal gangue image recognition has no obvious regularity under different shooting background conditions, and complex environments should be the primary factor affecting the accuracy of coal gangue image recognition. The accuracy of coal gangue image recognition is negatively correlated with the increase in shooting distance, and strong light conditions are conducive to improving the accuracy of coal gangue image recognition. The LeNet network model has the strongest generalization ability, which can meet the requirements of recognition accuracy and respond quickly. The accuracy of coal gangue image recognition under different complex conditions can reach more than 0.99, and the average single image recognition time is only 177 ms. This article studies the influence law of different complex conditions on the recognition of coal and gangue images and confirms that the LeNet network has strong generalization ability, achieving accurate and fast recognition of coal gangue images under complex conditions and providing a reference basis for the deployment of underground coal gangue sorting.

show abstract

“…The study found that in most cases, channel attention contributes more to the model's performance than spatial attention. Reference [10] introduced a novel attention mechanism inspired by the human visual system, named Patch Attention, and used this attention mechanism to improve convolutional neural networks, significantly enhancing the model's recognition performance on color images. The superiority and effectiveness of the above two improvement methods have been validated in the research achievements of many scholars.…”

mentioning

confidence: 99%

The Immune Depth Presentation Convolutional Neural Network Used for Oil and Gas Pipeline Fault Diagnosis

Xu,

2024

IEEE Access

View full text Add to dashboard Cite

In recent years, deep learning has been widely applied in the diagnosis of oil and gas pipeline failures due to its powerful feature representation capabilities. However, in practical applications, the diagnostic accuracy falls short of meeting actual requirements due to complex environmental interference, coupled with existing methods that focus solely on spatial feature relationships. To improve diagnostic performance, this paper eliminates the influence of complex backgrounds through optimal neural-immune domain in the image preprocessing stage. Subsequently, an Immune Depth Presentation Network capable of effectively capturing inter-feature correlations in the channel dimension is proposed, and it is integrated with a conventional convolutional neural network to construct the Immune Depth Presentation Convolutional Neural Network model. To validate the effectiveness and stability of the model, we compared the proposed algorithm in this paper with classic algorithms such as BPNN, KNN, VGG16, VGG19, Resnet34, and Resnet50. We conducted multiple experiments, and the results indicate that the proposed algorithm achieved the highest average testing accuracy, demonstrating stable performance. INDEX TERMSImmune depth presentation, convolutional neural network, oil and gas pipeline, image classification, fault diagnosis I.INTRODUCTION

show abstract

Recognition of gangues from color images using convolutional neural networks with attention mechanism

Cited by 9 publications

References 57 publications

Review: Identifikasi Batubara dan Gangue Menggunakan Machine Learning dan Deep Learning

Review: Identifikasi Batubara dan Gangue Menggunakan Machine Learning dan Deep Learning

Research on the Strong Generalization of Coal Gangue Recognition Technology Based on the Image and Convolutional Neural Network under Complex Conditions

The Immune Depth Presentation Convolutional Neural Network Used for Oil and Gas Pipeline Fault Diagnosis

Contact Info

Product

Resources

About