Deteksi Pulpitis Menggunakan Machine Learning Convolutional Neural Network Berbasis CNN1D dan MFCC
Abstract
Tulisan ini membahas isu krusial dalam upaya menjaga kesehatan gigi masyarakat, khususnya yang berkaitan dengan pulpitis, sebuah kondisi peradangan pada pulpa gigi yang dapat dipengaruhi oleh beberapa variable seperti infeksi bakteri, trauma, atau kerusakan gigi. Penulis memperkenalkan sebuah solusi inovatif untuk mendeteksi dan membedakan gigi yang terkena pulpitis dari gigi yang sehat. Solusi ini diharapkan dapat membantu dokter gigi dalam proses diagnosis dan perawatan pulpitis agar lebih efektif dan juga efisien. Untuk mencapai tujuan tersebut, penulis mengembangkan sebuah sistem berbasis pembelajaran mesin yang menggunakan deteksi pulpitis melalui analisis sinyal audio. Dalam penelitian ini, model Convolutional Neural Network 1D (CNN1D) digunakan bersama dengan proses ekstraksi fitur Mel-Frequency Cepstral Coefficients (MFCC). Model CNN1D dioptimalkan menggunakan optimizer Adam dengan tingkat pembelajaran sebesar 0.001, ukuran batch 32, dan proporsi data uji sebesar 20%. Evaluasi model dilakukan dengan confusion matrix untuk menganalisis akurasi prediksi berdasarkan sinyal audio. Metode pembelajaran mesin yang diusulkan ini menunjukkan potensi besar dalam membantu tenaga kesehatan, terutama dokter gigi, untuk mendiagnosis pulpitis dengan tingkat akurasi yang tinggi, sehingga dapat meningkatkan kualitas perawatan dan hasil pengobatan bagi pasien.
Kata kunci—CNN1D, Confusion matrix, Data, Ekstraksi ciri, Gigi, Machine learning, MFCC, Pulpitis.
References
H. Jayakodi, S. Kailasam, K. Kumaravadivel, B. Thangavelu, and S. Mathew, “Clinical and pharmacological management of endodontic flare-up,” Journal of Pharmacy and Bioallied Sciences, vol. 4, no. 6, p. 294, Jan. 2012, doi: 10.4103/0975-7406.100277.
I. a. E. Karim, P. R. Cooper, I. About, P. L. Tomson, F. T. Lundy, and H. F. Duncan, “Deciphering reparative processes in the inflamed dental pulp,” Frontiers in Dental Medicine, vol. 2, Mar. 2021, doi: 10.3389/fdmed.2021.651219.
Y. -l. Ng, V. Mann, and K. Gulabivala, “A prospective study of the factors affecting outcomes of nonsurgical root canal treatment: part 1: periapical health,” International Endodontic Journal, vol. 44, no. 7, pp. 583–609, Mar. 2011, doi: 10.1111/j.1365-2591.2011.01872.x.
F. Lorencetti-Silva et al., “Effects of inflammation in dental pulp cell differentiation and reparative response,” Frontiers in Dental Medicine, vol. 3, Aug. 2022, doi: 10.3389/fdmed.2022.942714.
M. F. Amanda, “Deteksi Pulpitis Reversibel Melalui Sinyal Wicara Dengan Metode Linear Predictive Coding (Lpc) Dan Klasifikasi K-Nearest Neighbor (K-Nn),” Repository, May 03, 2019. https://repository.telkomuniversity.ac.id/home/catalog/id/149651/slug/deteksi-pulpitis-reversibel-melalui-sinyal-wicara-dengan-metode-linear-predictive-coding-lpc-dan-klasifikasi-k-nearest-neighbor-k-nn-.html
K. Das and R. N. Behera, “A survey on Machine Learning: Concept,Algorithms and Applications,” International Journal of Innovative Research in Computer and Communication Engineering, vol. 5, no. 2, Jan. 2017, [Online]. Available: https://www.rroij.com/open-access/a-survey-on-machine-learning-conceptalgorithms-and-applications-.pdf
S. Kiranyaz, T. Ince, and M. Gabbouj, “Real-Time Patient-Specific ECG classification by 1-D convolutional neural networks,” IEEE Transactions on Biomedical Engineering, vol. 63, no. 3, pp. 664–675, Mar. 2016, doi: 10.1109/tbme.2015.2468589.
Z. Wang, W. Yan and T. Oates, "Time series classification from scratch with deep neural networks: A strong baseline," 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 2017, pp. 1578-1585, doi: 10.1109/IJCNN.2017.7966039.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Neural Information Processing Systems, vol. 25, pp. 1097–1105, Dec. 2012, [Online]. Available: http://books.nips.cc/papers/files/nips25/NIPS2012_0534.pdf
K. Simonyan and A. Zisserman, “Very deep convolutional networks for Large-Scale image recognition,” Computer Vision and Pattern Recognition, Sep. 2014, [Online]. Available: http://export.arxiv.org/pdf/1409.1556
R. Gomez, K. Nakamura, T. Mizumoto and K. Nakadai, "Improved hands-free automatic speech recognition in reverberant environment condition," 2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), Villers-les-Nancy, France, 2014, pp. 67-71, doi: 10.1109/HSCMA.2014.6843253.Al-Khowarizmi and H. Maulana, "The Utilization of Gaussian Filter Method on Voice Record Frequency Noise," 2020 2nd International Conference on Cybernetics and Intelligent System (ICORIS), Manado, Indonesia, 2020, pp. 1-5, doi.
C. Cowan, J. Arthur, J. Mavor and P. Denyer, "CCD based adaptive filters: Realization and analysis," in IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 29, no. 2, pp. 220-229, April 1981, doi: 10.1109/TASSP.1981.1163538Y. Religia, A. Rusdi, I. Romli, and A. Mazid, “Feature Extraction Untuk Klasifikasi Pengenalan Wajah Menggunakan Support Vector Machine Dan K-Nearest Neighbor,” jurnal.pelitabangsa.ac.id, Sep. 2019, doi: 10.37366/pelitatekno.v14i2.233.
A. V. Oppenheim and R. W. Schafer, Discrete-Time signal Processing. 1989. [Online]. Available: http://ci.nii.ac.jp/ncid/BA06610540.
L. Rabiner and B.-H. Juang, Fundamentals of speech recognition. 1993. [Online]. Available: https://ci.nii.ac.jp/naid/10016946567/
D. O’Shaughnessy, Speech Communications: human and machine. 2012. [Online]. Available: https://cds.cern.ch/record/1480800
J. W. Cooley, P. a. W. Lewis, and P. D. Welch, “The Fast Fourier Transform and its applications,” IEEE Transactions on Education, vol. 12, no. 1, pp. 27–34, Jan. 1969, doi: 10.1109/te.1969.4320436.
S. S. Stevens, J. Volkmann, and E. B. Newman, “A scale for the measurement of the psychological magnitude pitch,” The Journal of the Acoustical Society of America, vol. 8, no. 3, pp. 185–190, Jan. 1937, doi: 10.1121/1.1915893.
N. Ahmed, T. Natarajan and K. R. Rao, "Discrete Cosine Transform," in IEEE Transactions on Computers, vol. C-23, no. 1, pp. 90-93, Jan. 1974, doi: 10.1109/T-C.1974.223784.
Z. Wang, W. Yan and T. Oates, "Time series classification from scratch with deep neural networks: A strong baseline," 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 2017, pp. 1578-1585, doi: 10.1109/IJCNN.2017.7966039.
D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, Jan. 2020, doi: 10.1186/s12864-019-6413-7.
