Geniş Frekans Bantlı Anten Sistemleriyle Gömülü Nesnelerin Türünün Tespitinde Yapay Zeka Tabanlı Hibrit Bir Yaklaşım

Abstract

Kazı öncesinde gömülü nesnenin cinsinin bilinmesi gereksiz kazı yapılmasını önler. Üstelik zamandan ve paradan tasarruf sağlar. Bu çalışmada gömülü nesnelerin tespiti için bir deney seti hazırlandı. Deney seti, geniş frekans bandında elektromanyetik dalgalar gönderip alan bir anten, yansımaları kaydeden ve işleyen bir yazılımdan ve kum havuzundan oluşturuldu. Çalışmada bu kum havuzuna farklı derinlik, boyut ve şekillerde metalik ve metalik olmayan nesneler gömülerek bir profil boyunca ölçümler alındı. Yapılan ölçümlerden 2 boyutlu görüntüler oluşturuldu ve bu görüntülere görüntü işleme teknikleri uygulandı. İşlenmiş görüntülerden nesnenin türünü tespit etmek için sınıflandırma algoritmaları kullanıldı. Algoritmaların başarısını artırmak için, nitelik seçme teknikleri olarak korelasyona dayalı öznitelik seçimi (CFS) ve Temel Bileşen Analizi (PCA) kullanılmıştır. CFS ile öznitelik seçiminde arama yöntemleri olarak metasezgisel optimizasyon algoritmalarından genetik algoritma (GA), Parçacık Sürü Optimizasyonu (PSO), Harmony arama (HA) ve Evrimsel arama (EA) tercih edildi. Algoritmaların performansı 10 kat çapraz doğrulama yöntemi kullanılarak analiz edildi. Sonuç olarak PCA algoritmasının öznitelik seçiminde kullanımının metasezgisel algoritmalara göre sınıflandırma başarısını daha fazla arttırdığı anlaşıldı. Kullanılan sınıflandırma algoritmaları arasında en başarılı olanı Rastgele ağaç algoritması oldu. PCA sonrasında bu algoritmanın doğruluk değeri %95,8’e ulaşıldı. Bu nedenle ölçüm sistemine gömülü yazılımda PCA ve Rastgele ağaç algoritmalarının kullanıldığı hibrit bir yaklaşım önerilmektedir.

Keywords

• Yapay Zeka
• Gömülü nesne
• Metasezgisel optimizasyon algoritmaları
• PCA
• Görüntü işleme.

An Artificial Intelligence-Based Hybrid Approach to Detect the Type of Buried Objects with Broad Frequency Band Antenna Systems

Abstract

Knowing the type of buried object before excavation prevents unnecessary excavation. Moreover, it saves time and money. In this study, an experiment set was prepared for the detection of buried objects. The experimental set was composed of an antenna that sends and receives electromagnetic waves in a wide frequency band, software that records and processes reflections, and a sandbox. In the study, metallic and non-metallic objects with different depths, sizes and shapes were buried in this sand pool and measurements were taken along a profile. 2D images were created from the measurements and image processing techniques were applied to these images. Classification algorithms were used to detect the type of bruied object from processed images. To increase the success of the algorithms, correlation-based attribute selection (CFS) and Principal Component Analysis (PCA) were used as attribute selection techniques. Genetic algorithm (GA), Particle Swarm Optimization (PSO), Harmony search (HA), and Evolutionary search (EA), which are among the metaheuristic optimization algorithms, were preferred as search methods in attribute selection with CFS. The performance of the algorithms was analyzed using the 10-fold cross-validation method. As a result, it was understood that the use of the PCA algorithm in attribute selection increases the classification success more than metaheuristic algorithms. The most successful among the classification algorithms used is the Random tree algorithm. After PCA, the accuracy value of this algorithm was 95.8 Therefore, a hybrid approach is proposed in which PCA and Random tree algorithms are used in the software embedded in the measurement system.

Keywords

• Artificial Intelligence
• Buried object
• Metaheuristic optimization algorithms
• PCA
• Image processing.

References

1. G. Grandjean and D. Leparoux, "The potential of seismic methods for detecting cavities and buried objects: experimentation at a test site," Jour. of App. Geoph., vol. 56, no. 2, pp. 93-106, 2004.
2. J. D. Ducut et al., "A review of electrical resistivity tomography applications in underground imaging and object detection," Disply., vol. 73, p. 102208, 2022.
3. S. Jazayeri, A. Klotzsche, and S. Kruse, "Improved resolution of pipes with full waveform inversion," 2017.
4. W. Van Verre, L. A. Marsh, J. L. Davidson, E. Cheadle, F. J. Podd, and A. J. Peyton, "Detection of metallic objects in mineralized soil using magnetic induction spectroscopy," IEEE Trans. on Geosc. and Rem. Sens., vol. 59, no. 1, pp. 27-36, 2020.
5. K. Ho, P. D. Gader, and J. N. Wilson, "Improving landmine detection using frequency domain features from ground penetrating radar," in IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium, vol. 3, IEEE, pp. 1617-1620, 2004.
6. D. J. Daniels, Ground penetrating radar. Iet, 2004.
7. L. E. Besaw and P. J. Stimac, "Deep convolutional neural networks for classifying GPR B-scans," in Detection and sensing of mines, explosive objects, and obscured targets, vol. 9454, SPIE, pp. 385-394, 2015.
8. S. Lameri, F. Lombardi, P. Bestagini, M. Lualdi, and S. Tubaro, "Landmine detection from GPR data using convolutional neural networks," 25th European Signal Processing Conference (EUSIPCO), IEEE, pp. 508-512, 2017.

9. H. M. Alshamy, J. W. A. Sadah, T. R. Saeed, S. A. Mohammed, G. M. Hatem, and A. H. Gatan, "Evaluation of GPR Detection for buried objects material with different depths and scanning angles," in IOP Conference Series: Materials Science and Engineering, vol. 1090, no. 1, IOP Publishing, p. 012042, 2021.
10. H. A. Gaber, A. M. Abudeif, M. A. Mohammed, G. Z. AbdelAal, and K. K. Mansour, "Archaeological prospecting on the site of Osirion-Abydos using High Resolution Ground Penetrating Radar Technique, Sohag District, Egypt," Sohag Jour. of Scie., vol. 7, no. 2, pp. 115-122, 2022.
11. S. Saleh et al., "Detection of archaeological ruins using integrated geophysical surveys at the Pyramid of Senusret II, Lahun, Fayoum, Egypt," Pure and Appl. Geophy., vol. 179, no. 5, pp. 1981-1993, 2022.
12. X. Liang, D. Hu, Y. Li, Y. Zhang, and X. Yang, "Application of GPR underground pipeline detection technology in urban complex geological environments," Geofl., 2022.
13. A. Dell'Acqua, A. Sarti, S. Tubaro, and L. Zanzi, "Detection of linear objects in GPR data," Signal Proce., vol. 84, no. 4, pp. 785-799, 2004.
14. Z. Hui-lin, T. Mao, and C. Xiao-li, "Feature extraction and classification of echo signal of ground penetrating radar," *Wuhan University Jour. of Natural Scie., vol. 10, no. 6, pp. 1009-1012, 2005.
15. C. G. Windsor, L. Capineri, and P. Falorni, "The estimation of buried pipe diameters by generalized hough transform of radar data," Piers Online, vol. 1, pp. 345-349, 2005.
16. S. K. Sinha and P. W. Fieguth, "Automated detection of cracks in buried concrete pipe images," Autom. in Constr., vol. 15, no. 1, pp. 58-72, 2006.
17. X. Zhou, Q. Chen, S. Lyu, and H. Chen, "Estimating the Direction and Radius of Pipe from GPR Image by Ellipse Inversion Model," arXiv preprint arXiv:2201.10184, 2022.
18. L. C. M. Amaral, A. Roshan, and A. Bayat, "Review of machine learning algorithms for automatic detection of underground objects in GPR images," Journal of Pipel. Systems Eng. and Pract., vol. 13, no. 2, p. 04021082, 2022. S. Li, J. Zhao, H. Zhang, and Y. Zhang, "Automatic detection of pipelines from sub-bottom profiler sonar images," IEEE Journal of Oceanic Eng., vol. 47, no. 2, pp. 417-432, 2021.
19. T. S. Brandes, B. Ballard, S. Ramakrishnan, E. Lockhart, B. Marchand, and P. Rabenold, "Environmentally adaptive automated recognition of underwater mines with synthetic aperture sonar imagery," The Journ. of the Acoust. Socie. of America, vol. 150, no. 2, pp. 851-863, 2021.
20. A. Abhinaya, "Using Machine Learning to detect voids in an underground pipeline using in-pipe Ground Penetrating Radar," University of Twente, 2021.
21. X. Yin, Y. Chen, A. Bouferguene, H. Zaman, M. Al-Hussein, and L. Kurach, "A deep learning-based framework for an automated defect detection system for sewer pipes," Autom. in Constr., vol. 109, p. 102967, 2020.
22. M. Salucci, L. Tenuti, L. Poli, and A. Massa, "Buried object detection and imaging through innovative processing of GPR data," in 11th European Conference on Antennas and Propagation (EUCAP): IEEE, pp. 1703-1706, 2017.
23. E. Pasolli, F. Melgani, M. Donelli, R. Attoui, and M. De Vos, "Automatic detection and classification of buried objects in GPR images using genetic algorithms and support vector machines," in IGARSS 2008-2008 IEEE International Geoscience and Remote Sensing Symposium, vol. 2: IEEE, pp. II-525-II-528, 2008.
24. H. Qin, D. Zhang, Y. Tang, and Y. Wang, "Automatic recognition of tunnel lining elements from GPR images using deep convolutional networks with data augmentation," Autom. in Constr., vol. 130, p. 103830, 2021.
25. M. Dash and H. Liu, "Feature selection for classification," Intelligent Data Analy., vol. 1, no. 1-4, pp. 131-156, 1997.
26. M. A. Hall, "Correlation-based feature subset selection for machine learning," Ph.D. Thesis, University of Waikato, 1988.
27. R. Eberhart and J. Kennedy, "A new optimizer using particle swarm theory," in MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science: IEEE, pp. 39-43, 1995.
28. D. Goldenberg, Genetic Algorithms in Search, Optimization and Machine Learning, Reading: Addison Wesley, 1989.
29. L. M. Schmitt, "Theory of genetic algorithms," Theor. Comp. Scie., vol. 259, no. 1-2, pp. 1-61, 2001.
30. Z. W. Geem, C.-L. Tseng, and Y. Park, "Harmony search for generalized orienteering problem: best touring in China," in International Conference on Natural Computation*, Springer, pp. 741-750, 2005.
31. S. Fong, R. P. Biuk-Aghai, and R. C. Millham, "Swarm search methods in weka for data mining," in Proceedings of the 2018 10th International Conference on Machine Learning and Computing, pp. 122-127, 2018.
32. L. KPFRS, "On lines and planes of closest fit to systems of points in space," in Proceedings of the 17th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (SIGMOD). 19, 1901.
33. G. Holmes, B. Pfahringer, R. Kirkby, E. Frank, and M. Hall, "Multiclass alternating decision trees," in Machine Learning: ECML, 13th European Conference on Machine Learning Helsinki, Finland, August 19–23, Proceedings, Springer, pp. 161-172, 2002.
34. H. Shi, "Best-first decision tree learning," University of Waikato, 2007.
35. B. Pfahringer, "Random model trees: an effective and scalable regression method," University of Waikato, New Zealand, 1995.
36. C. Tan, H. Chen, and C. Xia, "The prediction of cardiovascular disease based on trace element contents in hair and a classifier of boosting decision stumps," Biolog. Trace Element Res., vol. 129, pp. 9-19, 2009.
37. N. Landwehr, M. Hall, and E. Frank, "Logistic model trees," Machine Lear., vol. 59, pp. 161-205, 2005.
38. M. N. Adnan and M. Z. Islam, "Optimizing the number of trees in a decision forest to discover a subforest with high ensemble accuracy using a genetic algorithm," Knowledge-Based Syst., vol. 110, pp. 86-97, 2016.
39. P. Pradham, N. H. Younan, and R. L. King, "Concepts of image fusion in remote sensing applications," in *Image Fusion: Algorit. and Applic., pp. 391-428, 2008.
40. R. Joshi, "Accuracy, precision, recall & f1 score: Interpretation of performance measures," Retrieved April, vol. 1, no. 2018, p. 2016, 2016.