Maturity classification of cacao through spectrogram and convolutional neural network

Abstract

Cacao pod's ideal harvesting time is when it is about to be ripe. Immature harvest would result in hard cacao beans not suitable for fermentation, while overripe cacao pods lead to fungal-infected, defective, and poor-quality yields. The demand for high-quality cacao products is expected to rise due to advancing technology in the present. Pre-harvesting needs to provide optimal identification of which amongst the pods are ripened enough and ready for the next stage of the cacao process. This paper recommends a technique to determine the ripeness of cacao. Nine hundred thirty-three cacao samples were used to collect thumping audio data at five different pod's exocarp locations. Each sound file is 1 second long, creating 4665 cacao sound file datasets at 16kHz sample rate and 16-bit audio bit depth. The process of the Mel-Frequency Cepstral Coefficient Spectogram was then applied to extract recognizable features for the training process. The deep learning method integrated was a convolutional neural network (CNN) to classify the cacao sound successfully. The experimental design model's output exhibits an accuracy of 97.50 % for the training data and 97.13 % for the validation data. While the overall accuracy mean of the classification system is 97.46 %, whether the cacao is unripe or ripe.

Acoustic Sensing for Quality Edible Evaluation of Sriracha Pineapple Using Convolutional Neural Network

“…Bueno et al [3] presented research techniques for determining the ripeness of cacao. A total of 933 cacao samples were classified in the determination of the ripeness of cacao.…”

“…A convolutional neural network (CNN) is used after the input sound signal has been converted into an image [3]. In this research, the feature vector of the spectrogram image is assigned to different input nodes.…”

“…Several researchers have studied how to classify the maturity of agricultural products such as cacao [3], pineapple [1], pineapple ripeness [4], durian ripeness [5], and described optimal pineapple harvesting [6]. Furthermore, researchers have adapted the structure of pre-trained convolutional neural networks (CNNs), using transfer learning, to pre-train AlexNet and VGGNet networks for apple mealiness detection [7].…”

Optimasi Pasca Panen untuk Peningkatan Kualitas Biji Kakao : Review

“…Panen buah yang terlalu tua akan menurunkan rendemen lemak dan menambah persentase biji cacat (berkecambah). Panen buah muda akan menghasilkan biji kakao bercitarasa khas cokelat tidak maksimal, rendemen yang rendah, persentase biji pipih tinggi (Bueno et al, 2020;Hu et al, 2016). Menurut (Saputro, dan Helbawanti, 2020) umur panen kakao berkisar 4.5-6 bulan setelah bunga mekar, dengan ciri-ciri warna sesuai varietas.…”

“…Untuk itu harus dilakukan dengan cara lebih modern, berdasarkan ciri konvensional. Ciri bunyi secara kenvensional tersebut yang mendasari penelitian Bueno et al, (2020). Bueno et al, (2020) Parameter warna (L*, a* dan b*; main tone) dan indeks kematangan (SS/TA) untuk masing-masing klon yang diteliti dan tahapan kematangan digambarkan pada tabel 1.…”