Mendeteksi Jenis Burung Berdasarkan Pola Suaranya

Penulis

  • Budi Darma Setiawan Universitas Brawijaya
  • Imam Cholissodin Universitas Brawijaya
  • Rekyan Regasari Mardi Putri Universitas Brawijaya

DOI:

https://doi.org/10.25126/jtiik.201632183

Abstrak

Abstrak

Ilmuwan biologi terutama di bidang biodifersitas, terus melakukan penelitian tentang spesies hewan yang ada di dunia. salah satu hewan yang spesiesnya memiliki banyak variasi adalah burung. Tiap jenis burung memiliki perbedaan-perbedaan, mulai dari bentuk anggota tubuhnya, prilakunya, makanannya hingga suaranya. Ilmuwan sering juga mengalami kesulitan untuk melakukan pengamatan di alam. Misalnya, untuk mengetahui spesies burung apa saja yang ada di suatu daerah, mereka harus hadir di suatu wilayah, dan menelusuri setiap pelosok. kadang kala kehadiran mereka di tempat tersebut dalam jangka waktu lama, malah mengusik burung yang ada, dan burung-burung malah pergi meninggalkan tempat, sebelum berhasil diamati. Salah satu cara untuk mendeteksi burung apa saja yang ada di suatu wilayah, tanpa harus mengusik keberadaan burung adalah dengan menggunakan alat bantu. Bisa dengan menggunakan kamera video untuk mengambil gambar lingkungan sekitar, atau dengan perekam suara, untuk merekam suara burung yang ada di sana. Untuk itu penelitian ini ditujukan untuk membuat sebuah pengklasifikasi suara burung secara otomatis. Fitur yang digunakan adalah rhythm, pitch, mean, varian, min, max, dan delta  dari suara burungnya. dari hasil klasifikasi 4 jenis burung, didapatkan hasil rata-rata akurasi terbaik sebesar 88.82%.

 

Kata Kunci : suara burung, klasifikasi, rhythm, pitch

Abstract

Many of Biologi scientist, especially in the field of biodiversity, conduct research on the animal species that exist in the world. One of the animal which is largely diverse in species is bird. Each species of birds have differences, from the shape of his body, his behavior, his food to it's voice. Scientists often find it difficult to make observations in nature. For example, to determine which species of birds present in an area, they should be present in an area, and explore every corner. sometimes their presence in that place for a long time, even disturb the bird, and they leaving the place, before been observed. One way to detect any bird that is in an area, without having to disturb the presence of birds is to use the automatic tools. For example to use a video camera to take pictures of the surrounding environment, or with voice recorders to record the sound of the birds that were there. This study is aimed to create a classifier bird sound automatically. Features used are rhythm, pitch, mean, variance, min, max, and delta of the bird sound samples. of the results of the classification of four types of birds, showed the best average of accuracy is 88.82%.

 

Key Word : bird song, classification, rhythm, pitch.

Downloads

Download data is not yet available.

Referensi

Birds, A. A. (2015). The Cornell lab of Ornithology - All About Birds. Retrieved March 1, 2015, from http://www.allaboutbirds.org/page.aspx ?pid =1059

Catchpole, C. K., & Slater, P. J. (1995). Bird Song: Biological Themes and Variations. Cambridge: Cambridge Univ. Press.

Chen, S.-s., & Li, y. (2013). Automatic Recognition of Bird Songs Using Time-Frequency Texture. Mathura: 5th International Conference on Computational Intelligence and Communication Networks (CICN).

Chu, W., & Blumstein, D. T. (2011). Noise robust bird song detection using syllable pattern-based hidden Markov models. Prague: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Huang, G.B., Zhu, Q.Y., dan Siew, C.K. (2004). Extreme Learning Machine : A New Learning Scheme of Feddforward neural Networks. Proceeding of International Joint Conference on Neural Networks. Hungary, 25-29 Juli.

Huang, G.B., Zhu, Q.Y., dan Siew, C.K. (2005). Extreme Learning Machine : Theory and applications. Elsevier science : Neurocomputing 70 (2006) 489-501.

Neal, L., Brigs, F., Raich, R., & Fern, X. Z. (2011). Time-frequency segmentation of bird song in noisy acoustic environments. Prague: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Somervuo, P., & Harma, A. (2004). Bird song recognition based on syllable pair histograms. IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. (ICASSP '04).

Somervuo, P., Harma, A., & Fagerlund, S. (2006). Parametric Representations of Bird Sounds for Automatic Species Recognition. IEEE Transaction on Audio, Speech, and Language Processing, 14(6).

Sun, Z.L., Choi, T.M., Au, K.F., dan Yu, Y. (2008). Sales Forecasting using Extreme Learning Machine with Application in Fashion Retailing.Elsevier Decision Support Systems 46 (2008) 411-419.

Wang, N.-C., Hudson, R. E., Tan, L. N., Taylor, C. E., Alwan, A., & Yao, K. (2013). Change point detection methodology used for segmenting bird songs. Beijing: IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP).

Unduhan

Diterbitkan

20-06-2016

Terbitan

Bagian

Teknologi Informasi

Cara Mengutip

Mendeteksi Jenis Burung Berdasarkan Pola Suaranya. (2016). Jurnal Teknologi Informasi Dan Ilmu Komputer, 3(2), 126-132. https://doi.org/10.25126/jtiik.201632183