| dc.creator | Mohamed Shariff , Abdul Rashid | |
| dc.date | 2019-12-19 | |
| dc.date.accessioned | 2025-03-13T22:29:42Z | |
| dc.date.available | 2025-03-13T22:29:42Z | |
| dc.identifier.uri | https://repositorio.fedepalma.org/handle/123456789/145407 | |
| dc.description | The present method used in determining oil palm parameters required chemical analysis which is destructive, time consuming and expensive. Hence, the purpose of this research is to obtain a non- destructive, easier and faster method in determining oil palm parameters to replace current method. At the same time, to obtain a method to directly distinguish the grades of FFB. Weka software was used to analyze data. Linear regression classification and SMO classification with cross validation of 10 and percentage split of 66% were applied. As a result, combination of Sensor 3(Red Emission, Red Detector), Sensor 2(Dred Emission, Dred Detector), Sensor 2(Fre Emission, Fre Detector), Sensor 4(Blu Emission, Blu Detector) and Sensor 4(NIR Emission, NIR Detector) showed the best overall accuracy to distinguish ripeness of fresh fruit bunch with 79.8% over ripe, 69.4% ripe and 93.3% under ripe. The mean average ROC value is 80.6%. On the other hand, Sensor 2(Fre Emission, Fre Detector) showed the best average accuracy in measuring different parameters values with 59.81% in determining oil to bunch ratio, 73% in determining oil to dry pericarp ratio, 62.57% in determining deterioration of bleaching index, 71.22% in determining carotene, 48.68% in determining peroxide value, 35.76% in determining free fatty acids. Accuracy values to detect free fatty acids increases to 70.94% with addition of average temperature as sensor. | en-US |
| dc.description | El método que se utiliza actualmente para determinar los parámetros del aceite de palma requiere un análisis químico que es destructivo, lento y costoso. Por lo tanto, el objetivo de esta investigación es obtener uno no destructivo, más fácil y más rápido, y reemplazar el método actual. Al mismo tiempo, establecer un procedimiento para distinguir directamente los grados de madurez de RFF. Se utilizó el software Weka para analizar los datos. Se aplicó una clasificación por regresión lineal y una SMO con validación cruzada de 10 y porcentaje dividido de 66 %. Como resultado, una combinación del sensor 3 (Emisión Red, Detector Red), sensor 2 (Emisión Dred, Detector Dred), sensor 2 (Emisión Fre, Detector Fre), sensor 4 (Emisión Blu, Detector Blu) y sensor 4 (Emisión NIR, Detector NIR) mostró la mejor precisión general para distinguir la madurez de racimos de fruta fresca con 79,8 % para sobremaduro, 69,4 % para maduro y 93,3 % para poco maduro (inmaduro). El valor promedio de ROC fue de 80,6 %. Por otra parte, el sensor 2 (Emisión Fre, Detector Fre) mostró la mejor precisión promedio para medir valores de diferentes parámetros, con 59,81 % al determinar la proporción de aceite por racimo, 73 % en la relación de aceite a pericarpio seco, 62,57 % en el índice de deterioro del blanqueo (DOBI), 71,22 % en carotenos, 48,68 % en el valor de peróxido y 35,76 % en los ácidos grasos libres (AGL). Los valores de precisión para la detección de estos últimos aumentaron al 70,94 % con la adición de temperatura promedio como sensor.
| es-ES |
| dc.format | application/pdf | |
| dc.language | spa | |
| dc.publisher | Fedepalma | es-ES |
| dc.relation | https://publicaciones.fedepalma.org/index.php/palmas/article/view/13076/12893 | |
| dc.relation | /*ref*/Abdullah, M.G. (2001). Stepwise Discriminant Analysis for Colour Grading of Oil Palm Using Machine | |
| dc.relation | /*ref*/VisionSystem.FoodandBioproductsProcessing79(4).doi:10.1205/096030801753252298 | |
| dc.relation | /*ref*/Alfatni, M.S., Shariff, A.R., Shafri, H.Z., Saaed, O.M., and Eshanta, O.M. (2008). Oil Palm Fruit Bunch | |
| dc.relation | /*ref*/Grading System Using Red, Green and Blue Digital Number. Journal of Applied Sciences | |
| dc.relation | /*ref*/8(8): 1444-1452. doi:10.3923/jas.2008.1444.1452 | |
| dc.relation | /*ref*/Giovenzana, V., Beghi, R., Civelli, R., and Guidetti, R. (2015). Optical techniques for rapid quality monitoring along minimally processed fruit and vegetable chain. Trends in Food Science & Technology 46(2): 331-338. doi:10.1016/j.tifs.2015.10.006 | |
| dc.relation | /*ref*/Harun, N., Misron, N., Sidek, R., Aris, I., Ahmad, D., Wakiwaka, H., and Tashiro, K. (2013). Investiga- tions on a Novel Inductive Concept Frequency Technique for the Grading of Oil Palm Fresh Fruit Bunches. Sensors 13(2); 2254-2266. doi:10.3390/s130202254 | |
| dc.relation | /*ref*/Ismail, W.I.W., Razali. M.H., Ramli, A.R., Sulaiman, M.N., and Harun, M.H.B. (2009). Development of | |
| dc.relation | /*ref*/Imaging Application for Oil Palm Fruit Maturity Prediction. Engineering e-Transaction 4(2): | |
| dc.relation | /*ref*/56-63.Karp, G., and Pruitt, N.L. (2010). Cell and molecular biology: Concepts and Experi- ments. In: G. Karp, and N.L. Pruitt, Cell and molecular biology: Concepts and Experiments (p. 212). Hoboken, NJ: John Wiley & Sons. | |
| dc.relation | /*ref*/Khan, M., and Quadri, S. (2012). Evaluating Various Learning Techniques for Efficiency. Internation- al Journal of Engineering and Advanced Technology 2(2): 326-331. | |
| dc.relation | /*ref*/Makky, M., and Soni, P. (2014). In situ quality assessment of intact oil palm fresh fruit bunches us- ing rapid portable non-contact and non-destructive approach. Journal of Food Engineering | |
| dc.relation | /*ref*/120; 248-259. doi:10.1016/j.jfoodeng.2013.08.011 | |
| dc.relation | /*ref*/Makky, M., Soni, P., and Salokhe, V. (2014). Automatic non-destructive quality inspection system for oil palm fruits. International Agrophysics 28(3): 319-329. doi:10.2478/intag-2014-0022 | |
| dc.relation | /*ref*/Sankaran, S., Shariff, A.R., Shafri, H.Z., Ehsani, R., Alfatni, M.S., and Hazir, M.A. (2012). Classifi- cation of oil palm fresh fruit bunches based on their maturity using portable four-band sensor system. Computers and Electronics in Agriculture 82: 55-60. doi:10.1016/j.com- pag.2011.12.010 | |
| dc.source | Palmas; Vol. 40 Núm. Especial T (2019); 9-17 | es-ES |
| dc.source | 2744-8266 | |
| dc.subject | oil palm ripenes | en-US |
| dc.subject | oil palm quality | en-US |
| dc.subject | visible light | en-US |
| dc.subject | NIR | en-US |
| dc.subject | temperature | en-US |
| dc.subject | madurez de la palma de aceite | es-ES |
| dc.subject | calidad del aceite de palma | es-ES |
| dc.subject | luz visible | es-ES |
| dc.subject | NIR | es-ES |
| dc.subject | temperatura | es-ES |
| dc.title | Oil Palm Ripeness Detector (OPRID) and Non-Destructive Thermal Method of Palm Oil Quality Estimation | en-US |
| dc.title | Detector de madurez en palma de aceite (OPRID) y método térmico no destructivo para estimar la calidad del aceite de palma | es-ES |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
| dc.identifier.url | https://publicaciones.fedepalma.org/index.php/palmas/article/view/13076 | |
