Araştırma Makalesi
BibTex RIS Kaynak Göster

MADENLERİN SINIFLANDIRILMASINA YÖNELİK HİBRİD BİR CNN MODELİN OLUŞTURULMASI

Yıl 2023, , 685 - 693, 03.09.2023

Turab Selçuk

https://doi.org/10.17780/ksujes.1285080

Öz

Madenlerin ülkelerin ekonomisindeki yeri oldukça büyüktür. Bu nedenle madencilikte cevher yataklarının tespiti ve tanımlanması önemli bir araştırma konusudur. Cevher sınıflandırılması işlemlerinde de bilgisayar tabanlı karar destek sistemleri kullanılmaktadır Bu çalışmada yedi farklı cevherin sınıflandırılmasına yönelik dört aşamadan oluşan hibrid bir CNN model oluşturulmuştur. Bu aşamalar, özellik çıkarımı, özellik birleştirme, özellik seçimi ve sınıflandırmadır. Özellik çıkarımı için, sınıflandırma problemlerinde yüksek başarım gösteren ResNet50, MobileNetV2 ve DenseNet201 mimarileri kullanılmıştır. Çıkarılan özellikler birleştirilerek 1x3000 boyutlarında kapsamlı özellik vektörü elde edilmiştir. Sınıflandırma başarımını arttırmak için özellik vektörüne NCA, ReliefF ve mRMR algoritmaları uygulanarak ayırt ediciliği yüksek özellikler belirlenmiştir. Bu özellikler destek vektör makineleri ile sınıflandırılmıştır. Elde edilen sonuçlara göre MRMR için 91.34, NCA için 92.42 ve ReliefF için 93,14 doğruluk değeri göstermiştir. Sonuç olarak önerilen hibrid CNN modelinin cevher sınıflandırılmasında literatürdeki klasik CNN modellere göre daha yüksek başarım sağlamıştır. Önerilen hibrid CNN modelin jeoloji alanında cevher sınıflandırılmasına yönelik çalışmalarda araştırmacılara karar desteği sağlayacağı düşünülmektedir.

Anahtar Kelimeler

Maden Sınıflandırma Hibrid CNN modeli Özellik seçimi

Kaynakça

  • Baraboshkin, E.E., Ismailova, L.S., Orlov, D.M., Zhukovskaya, E.A., Kalmykov, G.A., Khotylev, O. V., Baraboshkin, E.Y., Koroteev, D.A., 2019. Deep convolutions for in-depth automated rock typing. arXiv 135, 104330. https://doi.org/10.1016/j. cageo.2019.104330.
  • Chatterjee, S., 2013. Vision-based rock-type classification of limestone using multi-class support vector machine. Appl. Intell. 39, 14–27. https://doi.org/10.1007/s10489- 012-0391-7.
  • Chaves, D., Fern´andez-Robles, L., Bernal, J., Alegre, E., Trujillo, M., 2018. Automatic characterisation of chars from the combustion of pulverised coals using machine vision. Powder Technol. 338, 110–118. https://doi.org/10.1016/j. powtec.2018.06.035.
  • Chen, J., Pisonero, J., Chen, S., Wang, X., Fan, Q., Duan, Y., 2020a. Convolutional neural network as a novel classification approach for laser-induced breakdown spectroscopy applications in lithological recognition. Spectrochim. Acta – Part B At. Spectrosc. 166, 105801 https://doi.org/10.1016/j.sab.2020.105801.
  • Ebrahimi, M., Abdolshah, M., abdolshah, S., 2016. Developing a computer vision method based on AHP and feature ranking for ores type detection. Appl. Soft Comput. J. 49, 179–188. https://doi.org/10.1016/j.asoc.2016.08.027.
  • Fu, Y., Aldrich, C., 2018. Froth image analysis by use of transfer learning and convolutional neural networks. Miner. Eng. 115, 68–78. https://doi.org/10.1016/j. mineng.2017.10.005.
  • Galdames, A., Mendoza, A., Orueta, M., de Soto García, I.S., S_anchez, M., Virto, I.,Vilas, J.L., 2017. Development of new remediation technologies for contaminated soils based on the application of zero-valent iron nanoparticles and bioremediation with compost. Resource-Efficient Technologies 3, 166e176.
  • Gao, R., Sun, Z., Li, W., Pei, L., Hu, Y., Xiao, L., 2020. Automatic coal and gangue segmentation using U-net based fully convolutional networks. Energies 13, 829. https://doi.org/10.3390/en13040829.
  • Han, S., Li, H., Li, M., Luo, X., 2019. Measuring rock surface strength based on spectrograms with deep convolutional networks. Comput. Geosci. 133, 104312 https://doi.org/10.1016/j.cageo.2019.104312.
  • Iglesias, J.C.´A., Santos, R.B.M., Paciornik, S., 2019. Deep learning discrimination of quartz and resin in optical microscopy images of minerals. Miner. Eng. 138, 79–85. https://doi.org/10.1016/j.mineng.2019.04.032.
  • Imamverdiyev, Y., Sukhostat, L., 2019. Lithological facies classification using deep convolutional neural network. J. Pet. Sci. Eng. 174, 216–228. https://doi.org/ 10.1016/j.petrol.2018.11.023.
  • Izadi, H., Sadri, J., Bayati, M., 2017. An intelligent system for mineral identification in thin sections based on a cascade approach. Comput. Geosci. 99, 37–49. https://doi. org/10.1016/j.cageo.2016.10.010.
  • K. Kira, L.A. Rendell, The feature selection problem: traditional methods and a new algorithm, in: AAAI, vol. 2, 1992a, pp. 129–134.
  • Khorram, F., Morshedy, A.H., Memarian, H., Tokhmechi, B., Zadeh, H.S., 2017. Lithological classification and chemical component estimation based on the visual features of crushed rock samples. Arab. J. Geosci. 10, 1–9. https://doi.org/10.1007/ s12517-017-3116-8.
  • Li BQ, Hu LL, Niu S, Cai YD, Chou KC (2012) Predict and analyze S-nitrosylation modification sites with the mRMR and IFS approaches. J Proteomics 75: 1654.1665
  • Li, J., Su, Z., Geng, J., Yin, Y., 2018. Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network. IFAC-PapersOnLine 51, 76–81. https://doi.org/10.1016/j.ifacol.2018.09.412.
  • Massinaei, M., Jahedsaravani, A., Taheri, E., Khalilpour, J., 2019. Machine vision based monitoring and analysis of a coal column flotation circuit. Powder Technol. 343, 330–341. https://doi.org/10.1016/j.powtec.2018.11.056.
  • Mollajan, A., Ghiasi-Freez, J., Memarian, H., 2016. Improving pore type identification from thin section images using an integrated fuzzy fusion of multiple classifiers. J. Nat. Gas Sci. Eng. 31, 396–404. https://doi.org/10.1016/j.jngse.2016.03.030.
  • Montes-Atenas, G., Seguel, F., Valencia, A., Bhatti, S.M., Khan, M.S., Soto, I., Becerra Yoma, N., 2016. Predicting bubble size and bubble rate data in water and in froth flotation-like slurry from computational fluid dynamics (CFD) by applying deep neural networks (DNN). Int. Commun. Heat Mass Transf. 76, 197–201. https://doi. org/10.1016/j.icheatmasstransfer.2016.05.031.
  • Patel, A.K., Chatterjee, S., Gorai, A.K., 2017. Development of machine vision-based ore classification model using support vector machine (SVM) algorithm. Arab. J. Geosci. 10, 1–16. https://doi.org/10.1007/s12517-017-2909-0.
  • Perez, C.A., Saravia, J., Navarro, C., Castillo, L., Schulz, D., Aravena, C., 2012. Lithological classification based on Gabor texture image analysis, in: 2012 International Symposium on Optomechatronic Technologies, ISOT 2012. IEEE, pp. 1–3. https://doi.org/10.1109/ISOT.2012.6403273.
  • Sadeghiamirshahidi, M., Eslam Kish, T., Doulati Ardejani, F., 2013. Application of artificial neural networks to predict pyrite oxidation in a coal washing refuse pile. Fuel 104, 163–169. https://doi.org/10.1016/j.fuel.2012.10.016.
  • Si, L., Xiong, X., Wang, Z., Tan, C., 2020. A Deep Convolutional Neural Network Model for Intelligent Discrimination between Coal and Rocks in Coal Mining Face. Math. Probl. Eng. 2020, 1–12. https://doi.org/10.1155/2020/2616510.
  • Wang, X., Song, C., Yang, C., Xie, Y., 2018. Process working condition recognition based on the fusion of morphological and pixel set features of froth for froth flotation. Miner. Eng. 128, 17–26. https://doi.org/10.1016/j.mineng.2018.08.017.
  • Xiong, Y., Zuo, R., Carranza, E.J.M., 2018. Mapping mineral prospectivity through big data analytics and a deep learning algorithm. Ore Geol. Rev. 102, 811–817. https:// doi.org/10.1016/j.oregeorev.2018.10.006.
  • Zhang, C., Yue, J., Qin, Q., 2020a. Deep quadruplet network for hyperspectral image classification with a small number of samples. Remote Sens. 12, 647. https://doi. org/10.3390/rs12040647.
  • Zhang, Z., Liu, Ying, Hu, Q., Zhang, Zhiwei, Liu, Yang, 2020c. Competitive Voting-based Multi-class Prediction for Ore Selection, in: IEEE International Conference on Automation Science and Engineering. IEEE, pp. 514–519. https://doi.org/10.1109/ CASE48305.2020.9217017.

CREATING A HYBRID CNN MODEL FOR MINES CLASSIFICATION

Yıl 2023, , 685 - 693, 03.09.2023

Turab Selçuk

https://doi.org/10.17780/ksujes.1285080

Öz

The impact of mines on the economy of countries is quite large. For this reason, the detection and identification of ore deposits in mining is an important research topic. Computer-based decision support systems are also used in ore classification processes. In this study, a hybrid CNN model consisting of four stages was created for the classification of seven different ores. These stages are feature extraction, feature aggregation, feature selection and classification. ResNet50, MobileNetV2 and DenseNet201 architectures were used in feature extraction. By combining the extracted features, a feature vector of 1x3000 dimensions was obtained. In order to increase the classification performance, NCA, ReliefF and mRMR algorithms were applied to the feature vector and features with high distinctiveness were determined. These features are classified by support vector machines. According to the results obtained, it showed an accuracy value of 91.34 for MRMR, 92.42 for NCA and 93.14 for ReliefF. As a result, the proposed hybrid CNN model has higher performance in ore classification than the classical CNN models in the literature. It is thought that the proposed hybrid CNN model will provide decision support to researchers in studies on ore classification in the field of geology

Anahtar Kelimeler

Mines Classification hybrid CNN model feature selection

Kaynakça

  • Baraboshkin, E.E., Ismailova, L.S., Orlov, D.M., Zhukovskaya, E.A., Kalmykov, G.A., Khotylev, O. V., Baraboshkin, E.Y., Koroteev, D.A., 2019. Deep convolutions for in-depth automated rock typing. arXiv 135, 104330. https://doi.org/10.1016/j. cageo.2019.104330.
  • Chatterjee, S., 2013. Vision-based rock-type classification of limestone using multi-class support vector machine. Appl. Intell. 39, 14–27. https://doi.org/10.1007/s10489- 012-0391-7.
  • Chaves, D., Fern´andez-Robles, L., Bernal, J., Alegre, E., Trujillo, M., 2018. Automatic characterisation of chars from the combustion of pulverised coals using machine vision. Powder Technol. 338, 110–118. https://doi.org/10.1016/j. powtec.2018.06.035.
  • Chen, J., Pisonero, J., Chen, S., Wang, X., Fan, Q., Duan, Y., 2020a. Convolutional neural network as a novel classification approach for laser-induced breakdown spectroscopy applications in lithological recognition. Spectrochim. Acta – Part B At. Spectrosc. 166, 105801 https://doi.org/10.1016/j.sab.2020.105801.
  • Ebrahimi, M., Abdolshah, M., abdolshah, S., 2016. Developing a computer vision method based on AHP and feature ranking for ores type detection. Appl. Soft Comput. J. 49, 179–188. https://doi.org/10.1016/j.asoc.2016.08.027.
  • Fu, Y., Aldrich, C., 2018. Froth image analysis by use of transfer learning and convolutional neural networks. Miner. Eng. 115, 68–78. https://doi.org/10.1016/j. mineng.2017.10.005.
  • Galdames, A., Mendoza, A., Orueta, M., de Soto García, I.S., S_anchez, M., Virto, I.,Vilas, J.L., 2017. Development of new remediation technologies for contaminated soils based on the application of zero-valent iron nanoparticles and bioremediation with compost. Resource-Efficient Technologies 3, 166e176.
  • Gao, R., Sun, Z., Li, W., Pei, L., Hu, Y., Xiao, L., 2020. Automatic coal and gangue segmentation using U-net based fully convolutional networks. Energies 13, 829. https://doi.org/10.3390/en13040829.
  • Han, S., Li, H., Li, M., Luo, X., 2019. Measuring rock surface strength based on spectrograms with deep convolutional networks. Comput. Geosci. 133, 104312 https://doi.org/10.1016/j.cageo.2019.104312.
  • Iglesias, J.C.´A., Santos, R.B.M., Paciornik, S., 2019. Deep learning discrimination of quartz and resin in optical microscopy images of minerals. Miner. Eng. 138, 79–85. https://doi.org/10.1016/j.mineng.2019.04.032.
  • Imamverdiyev, Y., Sukhostat, L., 2019. Lithological facies classification using deep convolutional neural network. J. Pet. Sci. Eng. 174, 216–228. https://doi.org/ 10.1016/j.petrol.2018.11.023.
  • Izadi, H., Sadri, J., Bayati, M., 2017. An intelligent system for mineral identification in thin sections based on a cascade approach. Comput. Geosci. 99, 37–49. https://doi. org/10.1016/j.cageo.2016.10.010.
  • K. Kira, L.A. Rendell, The feature selection problem: traditional methods and a new algorithm, in: AAAI, vol. 2, 1992a, pp. 129–134.
  • Khorram, F., Morshedy, A.H., Memarian, H., Tokhmechi, B., Zadeh, H.S., 2017. Lithological classification and chemical component estimation based on the visual features of crushed rock samples. Arab. J. Geosci. 10, 1–9. https://doi.org/10.1007/ s12517-017-3116-8.
  • Li BQ, Hu LL, Niu S, Cai YD, Chou KC (2012) Predict and analyze S-nitrosylation modification sites with the mRMR and IFS approaches. J Proteomics 75: 1654.1665
  • Li, J., Su, Z., Geng, J., Yin, Y., 2018. Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network. IFAC-PapersOnLine 51, 76–81. https://doi.org/10.1016/j.ifacol.2018.09.412.
  • Massinaei, M., Jahedsaravani, A., Taheri, E., Khalilpour, J., 2019. Machine vision based monitoring and analysis of a coal column flotation circuit. Powder Technol. 343, 330–341. https://doi.org/10.1016/j.powtec.2018.11.056.
  • Mollajan, A., Ghiasi-Freez, J., Memarian, H., 2016. Improving pore type identification from thin section images using an integrated fuzzy fusion of multiple classifiers. J. Nat. Gas Sci. Eng. 31, 396–404. https://doi.org/10.1016/j.jngse.2016.03.030.
  • Montes-Atenas, G., Seguel, F., Valencia, A., Bhatti, S.M., Khan, M.S., Soto, I., Becerra Yoma, N., 2016. Predicting bubble size and bubble rate data in water and in froth flotation-like slurry from computational fluid dynamics (CFD) by applying deep neural networks (DNN). Int. Commun. Heat Mass Transf. 76, 197–201. https://doi. org/10.1016/j.icheatmasstransfer.2016.05.031.
  • Patel, A.K., Chatterjee, S., Gorai, A.K., 2017. Development of machine vision-based ore classification model using support vector machine (SVM) algorithm. Arab. J. Geosci. 10, 1–16. https://doi.org/10.1007/s12517-017-2909-0.
  • Perez, C.A., Saravia, J., Navarro, C., Castillo, L., Schulz, D., Aravena, C., 2012. Lithological classification based on Gabor texture image analysis, in: 2012 International Symposium on Optomechatronic Technologies, ISOT 2012. IEEE, pp. 1–3. https://doi.org/10.1109/ISOT.2012.6403273.
  • Sadeghiamirshahidi, M., Eslam Kish, T., Doulati Ardejani, F., 2013. Application of artificial neural networks to predict pyrite oxidation in a coal washing refuse pile. Fuel 104, 163–169. https://doi.org/10.1016/j.fuel.2012.10.016.
  • Si, L., Xiong, X., Wang, Z., Tan, C., 2020. A Deep Convolutional Neural Network Model for Intelligent Discrimination between Coal and Rocks in Coal Mining Face. Math. Probl. Eng. 2020, 1–12. https://doi.org/10.1155/2020/2616510.
  • Wang, X., Song, C., Yang, C., Xie, Y., 2018. Process working condition recognition based on the fusion of morphological and pixel set features of froth for froth flotation. Miner. Eng. 128, 17–26. https://doi.org/10.1016/j.mineng.2018.08.017.
  • Xiong, Y., Zuo, R., Carranza, E.J.M., 2018. Mapping mineral prospectivity through big data analytics and a deep learning algorithm. Ore Geol. Rev. 102, 811–817. https:// doi.org/10.1016/j.oregeorev.2018.10.006.
  • Zhang, C., Yue, J., Qin, Q., 2020a. Deep quadruplet network for hyperspectral image classification with a small number of samples. Remote Sens. 12, 647. https://doi. org/10.3390/rs12040647.
  • Zhang, Z., Liu, Ying, Hu, Q., Zhang, Zhiwei, Liu, Yang, 2020c. Competitive Voting-based Multi-class Prediction for Ore Selection, in: IEEE International Conference on Automation Science and Engineering. IEEE, pp. 514–519. https://doi.org/10.1109/ CASE48305.2020.9217017.
Toplam 27 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Elektrik Mühendisliği
Bölüm Elektrik Elektronik Mühendisliği
Yazarlar

Turab Selçuk 0000-0002-8445-2105

Yayımlanma Tarihi 3 Eylül 2023
Gönderilme Tarihi 18 Nisan 2023
Yayımlandığı Sayı Yıl 2023

Kaynak Göster

APA Selçuk, T. (2023). MADENLERİN SINIFLANDIRILMASINA YÖNELİK HİBRİD BİR CNN MODELİN OLUŞTURULMASI. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(3), 685-693. https://doi.org/10.17780/ksujes.1285080