Oil palm fruit grading using a hyperspectral device and machine learning algorithm

Bensaeed, O M; Shariff, Abdul Rashid Mohamed; Mahmud, Asif; Shafri, Helmi Zulhaidi Mohd; Alfatni, Meftah Salem M.

doi:10.1088/1755-1315/20/1/012017

Cited by 38 publications

(29 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dengan menggunakan metode ini, tingkat kematangan buah dapat dideteksi melalui warna TBS kelapa sawit, karena terdapat perbedaan warna antara TBS mentah, matang, dan busuk yang terjadi sebagai akibat dari proses kimia yang terjadi di dalam buah kelapa sawit. Metode lain yang diusulkan adalah dengan menggunakan kamera hiperspektrum (Junkwon, 2009), (Bensaeed, 2014).…”

Section: Pendahuluanunclassified

“…Berdasarkan beberapa hasil penelitian sebelumnya, kedua panjang gelombang ini dapat digunakan untuk melakukan prediksi tingkat kematangan TBS kelapa sawit. Pada panjang gelombang 670 -680 nm, terdapat hubungan antara tingkat kematangan TBS kelapa sawit dengan jumlah kandungan klorofil di dalam TBS (Thoriq, 2016), (Bensaeed, 2014), (Utom, 2018). Pada penelitian lain, parameter yang diamati adalah rasio klorofil dengan beta karoten menggunakan panjang gelombang 750 nm (Junkwon, 2009).…”

Section: Metodeunclassified

“…Oleh karena itu, akurasi sistem yang diperoleh pada penelitian masih mencapai 57,14%. Hasil ini relatif lebih kecil apabila dibandingkan dengan penelitian sebelumnya (Bensaeed, 2014) sebesar 94,54%. Disamping jenis TBS, faktor lain yang berpengaruh terhadap hasil penelitian ini, jumlah data yang digunakan.…”

Section: Data Ujiunclassified

See 2 more Smart Citations

Pengembangan Sistem Penilaian Kematangan Tandan Buah Segar Kelapa Sawit menggunakan Citra 680 dan 750 NM

Setiawan¹,

Ananda²

2020

JTIIK

View full text Add to dashboard Cite

Salah satu permasalahan utama dalam industri kelapa sawit adalah proses sortasi Tandan Buah Segar (TBS) di pabrik kelapa sawit. Parameter yang digunakan dalam sortasi TBS adalah jumlah brondolan kelapa sawit. Pada saat ini, sortasi dilakukan oleh grader yang bersifat subyektif dan sering kali tidak konsisten. Hal ini terjadi karena keterbatasan penglihatan dan kemampuan manusia untuk mengolah informasi jumlah brondolan setiap TBS dalam waktu yang terbatas. Oleh karena itu, pada penelitian ini dikembangkan sistem penilaian kematangan TBS kelapa sawit berbasis spektroskopi dan nilai kontras citras. Sumber cahaya yang digunakan pada penelitian ini adalah lampu berjenis Light-emitting Diode (LED) dengan panjang gelombang 680 dan 750 nm. Akuisisi citra TBS dilakukan dengan menggunakan kamera DSLR yang telah dimodifikasi. sehingga diperoleh dua citra TBS pada panjang gelombang 680 dan 750 nm. Kemudian, dilakukan perhitungan nilai kontras kedua citra tersebut. Dalam penelitian ini, terdapat 24 TBS yang digunakan sebagai data latih, dengan komposisi 10 TBS matang dan 14 TBS mentah. Data uji yang digunakan berjumlah 77 TBS yang terdiri dari 38 matang dan 39 mentah. Pada penelitian ini, Support Vector Machine (SVM) digunakan sebagai metode klasifikasi. Akurasi data latih yang diperoleh adalah 66,67%. Sedangkan akurasi data uji dari sistem yang dikembangkan dalam penelitian ini adalah 57,14%. Hasil yang diperoleh ini masih perlu diperbaiki untuk meningkatkan akurasi sistem dengan cara menambah jumlah data, baik data latih maupun uji, serta menggunakan pembelajaran mesin. AbstractOne of the main problems in the palm oil industry is the grading of Fresh Fruit Bunches (FFB) in the palm oil mills. The parameter used for the process is the number of fruitlets detached from the bunch. Nowadays, the FFB grading is conducted by graders which is subjective and often inconsistent due to the limitation of human vision and ability to process information on the number of fruitlets detached per FFB in a very limited time. Therefore, this study developed a grading system to assess and estimate the FFB maturity based on spectroscopy and image contrast value. From the literature review, visible light and NIR spectrum in 680 and 780 nm can be used as light sources to detect the maturity level of FFB. DSLR camera is used to acquire the FFB image. Using this scheme, two FFB images in 680 and 750 nm are obtained. The next process is to calculate the image contrast. In this research, there are 24 FFB that are used as training data that consists of 10 ripe and 14 unripe. A total of 77 FFB are used as test data that consists of 38 ripe and 39 unripe. Support Vector Machine (SVM) is used in this research to classify the maturity level of FFB. The accuracy of the training dataset is 66.67%. Meanwhile, the accuracy of the test data is 57.14%. Future works will focus on enhancing accuracy of the system through increasing the number of training and testing data using machine learning.

show abstract

Section: Pendahuluanunclassified

Section: Metodeunclassified

See 1 more Smart Citation

Pengembangan Sistem Penilaian Kematangan Tandan Buah Segar Kelapa Sawit menggunakan Citra 680 dan 750 NM

Setiawan¹,

Ananda²

2020

JTIIK

View full text Add to dashboard Cite

show abstract

“…You et al [ 16 ] introduced a microwave technique to monitor the oil palm ripeness in Malaysia. Another study of oil palm ripeness determination uses a hyperspectral device and machine learning algorithm by Bensaeed et al [ 17 ]. The different wavelengths from different types of oil palm grading are classified by an artificial neural network.…”

Section: Introductionmentioning

confidence: 99%

Effect of Charging Parameter on Fruit Battery-Based Oil Palm Maturity Sensor

et al. 2020

View full text Add to dashboard Cite

Oil palm is one of the key industries highly observed in Malaysia, due to its high demand both whether locally or internationally. The oil extraction rate (OER) in palm oil production is used as an element to identify the performance of the mills, estates and producers. In view of this, there are specific instrument or sensor needs to be implemented at the mills especially during the reception of fresh fruit bunches (FFB) transported from the field for oil content processing. This paper aims to study and propose the use of a fruit battery-based oil palm maturity sensor to analyse the effect of the sensor to various parameters. The study utilizes a charging method with different parameters, including a moisture content test on the palm oil samples. Three types of parameters are tested along with the different grades of oil palm fruit from different bunches, such as the load resistance, charging voltage and charging time. The repeatability data of the samples are obtained with the used list of values in each parameter. The results show that the parameters tested for the unripe, under ripe and ripe samples can affect the sensor sensitivity.

show abstract

“…Some problems in computer vision include image classification, object detection, movement tracking, action recognition and segmentation estimation. Researchers today are very active in developing accreditation and application of deep learning, such as research in the field of Regression [2], classification [3] (Vincent et al, 2008), dimension reduction [4], motion modeling [5],information retrieval [6] Because of the deep learning general application, deep learning has the potential to apply in many areas of human life. This paper intended to review deep learning application in agriculture and specially its application opportunity on oil palm fresh fruith bunch (FFB) grading.…”

Section: Introductionmentioning

confidence: 99%

A Study of Deep Learning Method Opportunity on Palm Oil FFB (Fresh Fruit Bunch) Grading Methods

Aji¹,

Hawari²

2019

Proceedings of the 2019 Ahmad Dahlan International Conference Series on Engineering and Science (ADICS-ES 2019)

View full text Add to dashboard Cite

The deep learning method is a state of the art in technological developments in various fields, including in agriculture. Deep learning applications in agriculture include many things including the application of fruit grading, including the fruit of palm or palm oil FFB (Fresh Fruit Bunch). Deep learning implementation opportunity in palm oil FFB grading is open because one aspect of fresh fruit grading is based on the number of sockets (fruitless) contained in FFB. Deep learning has the ability to recognize objects, so the determination of FFB grading can be developed based on calculating sockets (fruitless) by utilizing deep learning. So far no researcher has used the number of sockets for grading FFB using deep learning.

show abstract

Oil palm fruit grading using a hyperspectral device and machine learning algorithm

Cited by 38 publications

References 21 publications

Pengembangan Sistem Penilaian Kematangan Tandan Buah Segar Kelapa Sawit menggunakan Citra 680 dan 750 NM

Pengembangan Sistem Penilaian Kematangan Tandan Buah Segar Kelapa Sawit menggunakan Citra 680 dan 750 NM

Effect of Charging Parameter on Fruit Battery-Based Oil Palm Maturity Sensor

A Study of Deep Learning Method Opportunity on Palm Oil FFB (Fresh Fruit Bunch) Grading Methods

Contact Info

Product

Resources

About