Penerapan Metode Formant Analysis Dalam Sistem Analisis Pola Suara Untuk Deteksi Dini Penyakit Parkinson
Kata Kunci:
Parkinson, Formant Analysis, CNN, Raspberry Pi 4 Model BAbstrak
Penyakit Parkinson adalah kondisi degeneratif yang berkembang secara bertahap dan mempengaruhi gerakan tubuh, menyebabkan gejala seperti tremor, kekakuan, dan gangguan bicara. Deteksi dini penyakit ini sangat penting untuk memungkinkan intervensi medis yang lebih efektif dan manajemen gejala yang lebih baik. Penelitian ini bertujuan untuk mengembangkan sistem deteksi dini penyakit Parkinson yang memiliki sifat portabel dan dapat digunakan kapan saja dan dimana saja. Sistem tersebut dirancang dengan menggunakan metode Formant Analysis yang diimplementasikan pada Raspberry Pi 4 Model B. Penelitian ini menggunakan dataset dari IEEE DataPort yang bernama Italian Parkinson’s Voice and Speech, kemudian dimodifikasi sehingga hanya berdurasi sebanyak 4 detik per data sampel agar pengolahan data menjadi lebih akurat. Setelah ekstraksi selesai, setiap kelas akan diklasifikasikan menggunakan Convolutional Neural Network (CNN). Alat ini kemudian akan dioperasikan melalui layar LCD dan Graphical User Interface (GUI). Penerapan metode Formant Analysis dalam menganalisis frekuensi formant telah berhasil menunjukkan bahwa model CNN yang dibuat dapat mendeteksi penyakit Parkinson dengan tingkat akurasi sebesar 96%. Sementara itu akurasi yang dihasilkan sistem adalah 85% dari 20 pengujian dimana kelas Non-Parkinson mendapatkan akurasi 100% dan kelas Parkinson mendapatkan akurasi 70%. Dengan hasil ini, sistem yang dikembangkan menunjukkan potensi besar dalam mendukung diagnosa awal penyakit Parkinson, serta membuka peluang untuk pengembangan lebih lanjut guna meningkatkan akurasi dan fungsionalitasnya di masa mendatang.
Referensi
Alia, S., Hidayati, H.B., Hamdan, M., Nugraha, P., Fahmi, A., Turchan, A. and Haryono, Y., 2022. Penyakit Parkinson: Tinjauan Tentang Salah Satu Penyakit Neurodegeneratif yang Paling Umum. Aksona, 1(2), pp.95–99. https://doi.org/10.20473/aksona.v1i2.145.
Anand, A., Haque, M.A., Alex, J.S.R. and Venkatesan, N., 2018. Evaluation of Machine learning and Deep learning algorithms combined with dimentionality reduction techniques for classification of Parkinson’s Disease. 2018 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2018, pp.342–347. https://doi.org/10.1109/ISSPIT.2018.8642776.
Blesa, J. and Przedborski, S., 2014. Parkinson’s disease: Animal models and dopaminergic cell vulnerability. Frontiers in Neuroanatomy, 8(DEC), pp.1–12. https://doi.org/10.3389/fnana.2014.00155.
DeMaagd, G. and Philip, A., 2015. Parkinson’s Disease and its Management Part 1: Disease Entity, Risk Factors, Pathophysiology, Clinical Presentation, and Diagnosis. P&T, 40(8), pp.504–532. https://doi.org/10.1136/bmj.308.6923.281.
Ng, S.I., Ng, C.W.Y. and Lee, T., 2023. A Study on Using Duration and Formant Features in Automatic Detection of Speech Sound Disorder in Children. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2023-Augus(August), pp.4643–4647. https://doi.org/10.21437/Interspeech.2023-937.
Ramezani, H., Khaki, H., Erzin, E. and Akan, O.B., 2017. Speech features for telemonitoring of Parkinson’s disease symptoms. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp.3801–3805. https://doi.org/10.1109/EMBC.2017.8037685.
Ranny, R., Suwardi, I.S., Rajab, T.L.E. and Lestari, D.P., 2019. Kajian Penelitian Pemrosesan Bunyi dan Aplikasinya pada Teknologi Informasi. JUITA : Jurnal Informatika, 7(1), p.1. https://doi.org/10.30595/juita.v7i1.3491.
Rizek, P., Kumar, N. and Jog, M.S., 2016. An update on the diagnosis and treatment of Parkinson Disease. CMAJ, 188(16), pp.1157–1165. https://doi.org/10.1097/MED.0000000000000782.
Safitri, I., Hidayati, H.B., Turchan, A., Suhartati and Khaerunnisa, S., 2019. Solanum betaceum improves cognitive function by decreasing N-Methyl-D-aspartate on Alzheimer rats model. International Journal of Applied Pharmaceutics, 11(Special Issue 5), pp.167–170. https://doi.org/10.22159/ijap.2019.v11s5.T1015.
Suartika E. P, I.W., 2016. Klasifikasi Citra Menggunakan Convolutional Neural Network (Cnn) Pada Caltech 101. Jurnal Teknik ITS, [online] 5(1), p.76. Available at: <http://repository.its.ac.id/48842/>.
Upadhya, S.S., Cheeran, A.N. and Nirmal, J.H., 2017. Statistical comparison of Jitter and Shimmer voice features for healthy and Parkinson affected persons. Proceedings of the 2017 2nd IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2017, pp.1–6. https://doi.org/10.1109/ICECCT.2017.8117853.
Wahyuningtyas, V., 2021. Implementasi Ekstraksi Fitur untuk Klasifikasi Suara Urban Menggunakan Deep Learning. Sains, Aplikasi, Komputasi dan Teknologi Informasi, 3(1), pp.10–17.
Xie, Xiaoping and Cai, Hao and Li, Can and Ding, F., 2023. A Voice Disease Detection System Based on MFCCs and Single-Layer CNN. arXiv preprint arXiv:2304.08708, [online] pp.1–9. Available at: <https://arxiv.org/ftp/arxiv/papers/2304/2304.08708.pdf>.
Alia, S., Hidayati, H.B., Hamdan, M., Nugraha, P., Fahmi, A., Turchan, A. and Haryono, Y., 2022. Penyakit Parkinson: Tinjauan Tentang Salah Satu Penyakit Neurodegeneratif yang Paling Umum. Aksona, 1(2), pp.95–99. https://doi.org/10.20473/aksona.v1i2.145.
Anand, A., Haque, M.A., Alex, J.S.R. and Venkatesan, N., 2018. Evaluation of Machine learning and Deep learning algorithms combined with dimentionality reduction techniques for classification of Parkinson’s Disease. 2018 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2018, pp.342–347. https://doi.org/10.1109/ISSPIT.2018.8642776.
Blesa, J. and Przedborski, S., 2014. Parkinson’s disease: Animal models and dopaminergic cell vulnerability. Frontiers in Neuroanatomy, 8(DEC), pp.1–12. https://doi.org/10.3389/fnana.2014.00155.
DeMaagd, G. and Philip, A., 2015. Parkinson’s Disease and its Management Part 1: Disease Entity, Risk Factors, Pathophysiology, Clinical Presentation, and Diagnosis. P&T, 40(8), pp.504–532. https://doi.org/10.1136/bmj.308.6923.281.
Ng, S.I., Ng, C.W.Y. and Lee, T., 2023. A Study on Using Duration and Formant Features in Automatic Detection of Speech Sound Disorder in Children. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2023-Augus(August), pp.4643–4647. https://doi.org/10.21437/Interspeech.2023-937.
Ramezani, H., Khaki, H., Erzin, E. and Akan, O.B., 2017. Speech features for telemonitoring of Parkinson’s disease symptoms. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp.3801–3805. https://doi.org/10.1109/EMBC.2017.8037685.
Ranny, R., Suwardi, I.S., Rajab, T.L.E. and Lestari, D.P., 2019. Kajian Penelitian Pemrosesan Bunyi dan Aplikasinya pada Teknologi Informasi. JUITA : Jurnal Informatika, 7(1), p.1. https://doi.org/10.30595/juita.v7i1.3491.
Rizek, P., Kumar, N. and Jog, M.S., 2016. An update on the diagnosis and treatment of Parkinson Disease. CMAJ, 188(16), pp.1157–1165. https://doi.org/10.1097/MED.0000000000000782.
Safitri, I., Hidayati, H.B., Turchan, A., Suhartati and Khaerunnisa, S., 2019. Solanum betaceum improves cognitive function by decreasing N-Methyl-D-aspartate on Alzheimer rats model. International Journal of Applied Pharmaceutics, 11(Special Issue 5), pp.167–170. https://doi.org/10.22159/ijap.2019.v11s5.T1015.
Suartika E. P, I.W., 2016. Klasifikasi Citra Menggunakan Convolutional Neural Network (Cnn) Pada Caltech 101. Jurnal Teknik ITS, [online] 5(1), p.76. Available at: <http://repository.its.ac.id/48842/>.
Upadhya, S.S., Cheeran, A.N. and Nirmal, J.H., 2017. Statistical comparison of Jitter and Shimmer voice features for healthy and Parkinson affected persons. Proceedings of the 2017 2nd IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2017, pp.1–6. https://doi.org/10.1109/ICECCT.2017.8117853.
Wahyuningtyas, V., 2021. Implementasi Ekstraksi Fitur untuk Klasifikasi Suara Urban Menggunakan Deep Learning. Sains, Aplikasi, Komputasi dan Teknologi Informasi, 3(1), pp.10–17.
Xie, Xiaoping and Cai, Hao and Li, Can and Ding, F., 2023. A Voice Disease Detection System Based on MFCCs and Single-Layer CNN. arXiv preprint arXiv:2304.08708, [online] pp.1–9. Available at: <https://arxiv.org/ftp/arxiv/papers/2304/2304.08708.pdf>.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
