KARAKTERISTIK FITUR SUARA KETUKAN BUAH KELAPA BERDASARKAN DOMAIN WAKTU DAN DOMAIN FREKUENSI
DOI:
https://doi.org/10.21009/03.1201.FA02Abstract
Abstrak
Pada penelitian ini dilakukan untuk menganalisis karakteristik suara akustik hasil ketukan buah kelapa dengan tingkat kematangan pada buah kelapa yang berbeda yaitu muda, setengah tua, dan tua. Analisis suara ketukan buah kelapa dilakukan untuk menentukan apakah perbedaan respons akustik dapat membantu meningkatkan diferensiasi buah pada tingkat kematangan yang berbeda. Dalam pendekatan ini analisis suara akan dilakukan dengan mengekstraksi beberapa fitur seperti Mel Frequency Cepstral Coefficients (MFCC), Mel spectrogram, centroid, zero crossing rate (ZCR), spectral rolloff, dan contrast. Fitur yang diekstraksi kemudian direduksi dimensinya dengan teknik Principal Componen Analysis (PCA). Efektivitas pendekatan ini dievaluasi dengan menganalisis representasi fitur yang dihasilkan. Hasil percobaan menunjukkan kemampuan metode yang diusulkan dalam menangkap informasi penting yang berkaitan dengan tingkat kematangan kelapa.
Kata-kata kunci: analisis suara, kematangan buah kelapa, ekstraksi fitur
Abstract
This research was conducted to analyze the characteristics of the acoustic sound produced by tapping coconuts with different levels of maturity on coconuts, namely young, fairly mature, and mature. The Analysis of coconut sound-tapping was conducted to determine whether differences in acoustic responses can aid in improving fruit differentiation at various maturity levels. In this approach, sound analysis is performed by extracting several features, including Mel Frequency Cepstral Coefficients (MFCC), Mel spectrogram, centroid, zero crossing rate (ZCR), spectral rolloff, and contrast. The extracted features are then subjected to dimensionality reduction using Principal Component Analysis (PCA). The effectiveness of this approach needs to be evaluated by analyzing the resulting feature representation. The experimental results demonstrate the capability of the proposed method in capturing essential information related to coconut maturity levels.
Keywords: suara analysis, coconut maturity, feature extraction
References
[2] R. Child, “the coconut,” 1954.
[3] D. Rahmawati, H. Haryanto, F. Sakariya, “the Design of Coconut Maturity Prediction Device With Acoustic Frequency Detection Using Naive Bayes Method Based Microcontroller,” JEEMECS (Journal Electr. Eng. Mechatron. Comput. Sci, vol. 2, no. 1, 2019, doi: 10.26905/jeemecs.v2i1.2806.
[4] W. Afiatun, Nafi’ah, “Deteksi Frekuensi Akustik pada Buah Kelapa Magelang (Cocos nucifera) Menggunakan Software Spectra PLUS-DT,” Jurnal Fisika Indonesia, vol. 19, no. 57, pp. 51-54, 2017, doi: 10.22146/jfi.27277.
[5] J. A. Caladcad et al., “Determining Philippine coconut maturity level using machine learning algorithms based on acoustic signal,” Computers and electronics in agriculture, vol. 172, p. 105327, 2020, doi: 10.1016/j.compag.2020.105327.
[6] N. A. Fadchar, J. C. D. Cruz, “A Non-Destructive Approach of Young Coconut Maturity Detection using Acoustic Vibration and Neural Network,” 16th IEEE International Colloquium on Signal Processing & Its Applications (CSPA), pp. 136-140, 2020, doi: 10.1109/CSPA48992.2020.9068723.
[7] M. M. Gatchalian, S. Y. De Leon, T. Yano, “Measurement of young coconut (Cocos nucifera, L.) maturity by sound waves,” Journal Food Engineering, vol. 23, no. 3, pp. 253-276, 1994, doi: 10.1016/0260-8774(94)90053-1
[8] D. Halliday, R. Resnick, J. Walker, “Fundamentals of physics,” John Wiley \& Sons, 2013.
[9] T. Theodorou, I. Mporas, N. Fakotakis, “An Overview of Automatic Audio Segmentation,” International Journal of Information Technology and Computer Science (IJITCS), vol. 6, no. 11, pp. 1-9, 2014, doi: 10.5815/ijitcs.2014.11.01.
[10] F. Cohen Tenoudji, “Analog and Digital Signal Analysis From Basics to Applications,” Springer International Publishing Switzerland, 2016.
[11] A. G. Jondya, B. H. Iswanto, “Indonesian’s Traditional Music Clustering Based on Audio Features,” Procedia Computer Science, vol. 116, pp. 174-181, 2017, doi: 10.1016/j.procs.2017.10.019.
