Peningkatan Kinerja Pengklasifikasi Objek Bawah Laut dengan Deep Learning

Aris Tjahyanto; Faisal Johan Atletiko

doi:10.30812/matrik.v21i3.1466

Aris Tjahyanto Institut Teknologi Sepuluh Nopember
Faisal Johan Atletiko Institut Teknologi Sepuluh Nopember

DOI: https://doi.org/10.30812/matrik.v21i3.1466

Keywords: Deep learning, Pembangkit gema, Pembelajaran mesin, SONAR, Sorot-tunggal

Abstract

Pengenalan objek bawah laut dapat dilakukan berdasarkan pola hamburan SONAR, seperti untuk deteksi ranjau dan deteksi batu yang terletak di dasar laut. Kesulitan yang dihadapi pada pengenalan objek bawah laut antara lain adalah pemilihan metode ekstraksi fitur, adanya rotasi objek yang menghasilkan pola hamburan yang berbeda, lingkungan atau latar belakang bervariasi, dan kemampuan pengklasifikasi yang berbeda untuk lingkungan yang lebih kompleks. Pada penelitian ini, kami menggunakan deep learning neural network untuk meningkatkan kinerja klasifikasi dua buah objek bawah laut. Secara khusus, dibandingkan jumlah neuron pada lapisan tersembunyi dan fungsi aktivasi yang dapat menghasilkan kinerja yang lebih tinggi dari penelitian sebelumnya. Pada penelitian sebelumnya, proses klasifikasi dilakukan dengan menggunakan neural network dengan 12 buah lapisan tersembunyi, dan menghasilkan akurasi maksimal sebesar 90.4%. Dilakukan percobaan pada struktur jaringan syaraf tiruan berupa multilayer perceptron dengan 2 buah lapisan tersembunyi dan 7 macam fungsi aktivasi. Dari percobaan yang dilakukan diperoleh
bahwa deep learning neural network memberikan rata-rata akurasi terbaik sebesar 85,9% dengan akurasi maksimal sebesar 96,15% lebih baik dibandingkan hasil penelitian sebelumnya. Akurasi terbaik tersebut diperoleh dengan memanfaatkan jumlah neuron pada lapisan tersembunyi sebanyak 140 buah, dan fungsi aktivasi reLU untuk lapisan tersembunyi fungsi aktivasi Linear untuk lapisan output.

Downloads

Download data is not yet available.

References

[1] L. Lu, H. Ni,W.Wang, L. Ma, J. Huang, and Q. Ren, “Experimental Results of Sediment Characterization by Processing Backscatter
Envelope of Single-beam Sonar*,” in OCEANS 2019 - Marseille, 2019, pp. 1–5.
[2] H. Li, F. Yin, and C. Li, “A High-accuracy Target Tracking Method and Its Application in Acoustic Engineering,” in 2019 IEEE 4th
International Conference on Signal and Image Processing (ICSIP), 2019, pp. 690–694.
[3] D. Cook, K. Middlemiss, P. Jaksons, W. Davison, and A. Jerrett, “Validation of fish length estimations from a high frequency multibeam
sonar (ARIS) and its utilisation as a field-based measurement technique,” Fisheries Research, vol. 218, pp. 59–68, 2019.
[4] J. Helminen and T. Linnansaari, “Object and behavior differentiation for improved automated counts of migrating river fish using
imaging sonar data,” Fisheries Research, vol. 237, p. 105883, 2021.
[5] Y. Seo, B. Jang, and S. Im, “A Comparison of Machine Learning Schemes for Moving Direction Estimation with Acoustic Data,” in
2019 International Conference on Electronics, Information, and Communication (ICEIC), 2019, pp. 1–3.
[6] D. Einsidler, M. Dhanak, and P.-P. Beaujean, “A Deep Learning Approach to Target Recognition in Side-Scan Sonar Imagery,” in
OCEANS 2018 MTS/IEEE Charleston, 2018, pp. 1–4.
[7] Y. Steiniger, J. Stoppe, T. Meisen, and D. Kraus, “DealingWith Highly Unbalanced Sidescan Sonar Image Datasets for Deep Learning
Classification Tasks,” in Global Oceans 2020: Singapore U.S. Gulf Coast, 2020, pp. 1–7.
[8] R. Ghosh, “Sonar Target Classification Problem : Machine Learning Models,” vol. 9, no. 1, pp. 247–248, 2020.
[9] Z. Wei, Y. Ju, and M. Song, “A Method of Underwater Acoustic Signal Classification Based on Deep Neural Network,” in 2018 5th
International Conference on Information Science and Control Engineering (ICISCE), 2018, pp. 46–50.
[10] J. H. Christensen, L. V. Mogensen, and O. Ravn, “Deep Learning based Segmentation of Fish in Noisy Forward Looking MBES
Images,” IFAC-PapersOnLine, vol. 53, no. 2, pp. 14 546–14 551, 2020.
[11] G. Xu, Q. Chen, T. Yoshida, K. Teravama, Y. Mizukami, Q. Li, and D. Kitazawa, “Detection of Bluefin Tuna by Cascade Classifier
and Deep Learning for Monitoring Fish Resources,” in Global Oceans 2020: Singapore U.S. Gulf Coast, 2020, pp. 1–4.
[12] B. V. Deep and R. Dash, “Underwater Fish Species Recognition Using Deep Learning Techniques,” in 2019 6th International Conference
on Signal Processing and Integrated Networks (SPIN), 2019, pp. 665–669.
[13] J. Seok, “Active sonar target classification using multi-aspect sensing and deep belief networks,” International Journal of Engineering
Research and Technology, vol. 11, pp. 1999–2008, 2018.
Peningkatan Kinerja Pengklasifikasi . . . (Aris Tjahyanto)
760 r ISSN: 2476-9843
[14] L. J. Ziomek, An Introduction to Sonar Systems Engineering, 1st ed. Boca Raton: CRC Press, 2017.
[15] X. Wu, V. Kumar, Q. J. Ross, J. Ghosh, Q. Yang, H. Motoda, G. J. McLachlan, A. Ng, B. Liu, P. S. Yu, Z. H. Zhou, M. Steinbach,
D. J. Hand, and D. Steinberg, Top 10 algorithms in data mining. Chapman and Hall/CRC, dec 2009.
[16] H. Rahman, M. U. Ahmed, S. Begum, M. Fridberg, and A. Hoflin, “Deep Learning in Remote Sensing: An Application to Detect
Snow and Water in Construction Sites,” in 2021 4th International Conference on Artificial Intelligence for Industries (AI4I), 2021,
pp. 52–56.
[17] L. Deng and D. Yu, Deep Learning: Methods and Applications. Now Foundations and Trends, 2014.
[18] T. Arif, Introduction to Deep Learning for Engineers: Using Python and Google Cloud Platform. Morgan & Claypool, 2020, vol. 5.
[19] R. Vang-Mata, Multilayer Perceptrons: Theory and Applications. Nova Science, 2020.
Matrik: Jurnal