Malaysian Agriculture RepositoryThe DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material.http://http://agris.upm.edu.my:8080/dspace2024-03-19T03:09:05Z2024-03-19T03:09:05ZDeep learning to detect and classify the purity level of Luwak coffee green beansHendrawan, YusufWidyaningtyas, ShintaFauzy, Muchammad RizaSucipto, SuciptoDamayanti, RetnoAl Riza, Dimas FirmandaHermanto, Mochamad BagusSandra, Sandrahttp://agris.upm.edu.my:8080/dspace/handle/0/223982023-03-18T08:27:20Z2022-01-01T00:00:00ZTitle: Deep learning to detect and classify the purity level of Luwak coffee green beans
Authors: Hendrawan, Yusuf; Widyaningtyas, Shinta; Fauzy, Muchammad Riza; Sucipto, Sucipto; Damayanti, Retno; Al Riza, Dimas Firmanda; Hermanto, Mochamad Bagus; Sandra, Sandra
Abstract: Luwak coffee (palm civet coffee) is known as one of the most expensive coffee in the world. In order to lower production costs, Indonesian producers and retailers often mix high-priced Luwak coffee with regular coffee green beans. However, the absence of tools and methods to classify Luwak coffee counterfeiting makes the sensing method’s development urgent. The research aimed to detect and classify Luwak coffee green beans purity into the following purity categories, very low (0-25%), low (25-50%), medium (50-75%), and high (75-100%). The classifying method relied on a low-cost commercial visible light camera and the deep learning model method. Then, the research also compared the performance of four pre-trained convolutional neural network (CNN) models consisting of SqueezeNet, GoogLeNet, ResNet-50, and AlexNet. At the same time, the sensitivity analysis was performed by setting the CNN parameters such as optimization technique (SGDm, Adam, RMSProp) and the initial learning rate (0.00005 and 0.0001). The training and validation result obtained the GoogLeNet as the best CNN model with optimizer type Adam and learning rate 0.0001, which resulted in 89.65% accuracy. Furthermore, the testing process using confusion matrix from different sample data obtained the best CNN model using ResNet-50 with optimizer type RMSProp and learning rate 0.0001, providing an accuracy average of up to 85.00%. Later, the CNN model can be used to establish a real-time, non-destructive, rapid, and precise purity detection system.2022-01-01T00:00:00ZPectinase production from banana peel biomass via the optimization of the solid-state fermentation conditions of Aspergillus niger strainNazaitulshila RasitYong, Sin SzeMohd Ali HassanOoi, Chee KuanSofiah HamzahWan Rafizah Wan Abdullah@Wan Abd. RahmanMd. Nurul Islam Siddiquehttp://agris.upm.edu.my:8080/dspace/handle/0/223992023-03-18T08:37:28Z2022-01-01T00:00:00ZTitle: Pectinase production from banana peel biomass via the optimization of the solid-state fermentation conditions of Aspergillus niger strain
Authors: Nazaitulshila Rasit; Yong, Sin Sze; Mohd Ali Hassan; Ooi, Chee Kuan; Sofiah Hamzah; Wan Rafizah Wan Abdullah@Wan Abd. Rahman; Md. Nurul Islam Siddique
Abstract: In this study, the biomass of banana peel was used to produce pectinase via optimization of solid-state fermentation conditions of the filamentous fungi Aspergillus nigeA. niger). The operating conditions of solid-state fermentation were optimized using the method of full factorial design with incubation temperature ranging between 25 °C and 35 °C, moisture content between 40% and 60%, and inoculum size between 1.6 x 106 spores/mL and 1.4 x 107 spores/mL. Optimizing the solid-state fermentation conditions appeared crucial to minimize the sample used in this experimental design and determine the significant correlation between the operating conditions. A relatively high maximal pectinase production of 27 UmL-1 was attained at 35° C of incubation, 60% of moisture content, and 1.6 x 106 spores/mL of inoculum size with a relatively low amount of substrate (5 g). Given that the production of pectinase with other substrates (e.g., pineapple waste, lemon peel, cassava waste, and wheat bran) generally ranges between 3 U/mL and 16 U/mL (Abdullah et al., 2018; Handa et al., 2016; Melnichuk et al., 2020; Thangaratham and Manimegalai, 2014; Salim et al., 2017), thus the yield of pectinase derived from the banana peel in this study (27 U/mL) was considered moderately high. The findings of this study indicated that the biomass of banana peel would be a potential substrate for pectinase production via the solid-state fermentation of A. niger.2022-01-01T00:00:00ZEsterification of free fatty acid in palm oil mill effluent using sulfated carbon-zeolite composite catalystHasanudin, HasanudinPutri, Qodria UtamiAgustina, Tuty EmiliaHadiah, Fitrihttp://agris.upm.edu.my:8080/dspace/handle/0/224002023-03-18T08:44:42Z2022-01-01T00:00:00ZTitle: Esterification of free fatty acid in palm oil mill effluent using sulfated carbon-zeolite composite catalyst
Authors: Hasanudin, Hasanudin; Putri, Qodria Utami; Agustina, Tuty Emilia; Hadiah, Fitri
Abstract: Free fatty acid esterification (FFA) in palm oil mill waste (POME) was carried out using a sulfonated carbon-zeolite composite catalyst. The catalyst is synthesized with carbon precursor obtained from molasses, which is adsorbed on the surface of the zeolite and then carbonized and sulfonated with concentrated H₂SO₄ to form a sulfonated carbon-zeolite catalyst composite, which will be used for the esterification catalyst and the optimization process for the esterification reaction is carried out using the response surface methodology (RSM) and experimental central composite design (CCD). Importantly, the observed independent variables were temperature, catalyst weight, and reaction time to produce fatty acid methyl ester (FAME) products. The catalyst was successfully synthesized, which was shown from the SEM characterization strengthened by the presence of a sulfate group in the FTIR results and the calculation results of high acidity properties. Optimization of FFA esterification with SCZ catalyst obtained optimal conditions with a temperature of 79°C, a catalyst weight of 3.00 g, and a reaction time of 134 minutes with a FAME product of 93.75%, considering that the viscosity of biodiesel is below that required by the API.2022-01-01T00:00:00ZEffect of water absorption on flexural properties of kenaf/glass fibres reinforced unsaturated polyester hybrid composites rodZainudin YahyaMohamed Nainar, Mohamed AnsariNazim Abdul RahimAlaseel, Bassam HamidNoor Afeefah Nordinhttp://agris.upm.edu.my:8080/dspace/handle/0/224012023-03-18T08:51:57Z2022-01-01T00:00:00ZTitle: Effect of water absorption on flexural properties of kenaf/glass fibres reinforced unsaturated polyester hybrid composites rod
Authors: Zainudin Yahya; Mohamed Nainar, Mohamed Ansari; Nazim Abdul Rahim; Alaseel, Bassam Hamid; Noor Afeefah Nordin
Abstract: This study investigates the effect of water absorption on the flexural strength of kenaf/ glass/unsaturated polyester (UPE) hybrid composite solid round rods used for insulating material applications. Three volume fractions of kenaf/glass fibre 20:80 (KGPE20), 30:70 (KGPE30), and 40:60 (KGPE40) with three different fibre arrangement profiles of kenaf fibres were fabricated by using the pultrusion technique and were aimed at studying the effect of kenaf fibres arrangement profile and its content in hybrid composites. The fibre/ resin volume fraction was maintained constant at 60:40. The dispersion morphologies of tested specimens were observed using the scanning electron microscope (SEM). The findings were compared with pure glass fibre-reinforced UPE (control) composite. The water absorption results showed a clear indication of how it influenced the flexural strength of the hybrid and non-hybrid composites. The least affected sample was observed in the 30KGPE composite type, wherein the kenaf fibre was concentrated at the centre of a cross-section of the composite rod. The water absorption reduced the flexural strength by 7%, 40%, 24%, and 38% of glass/UPE (control), 20KGPE, 30KGPE, and 40KGPE composites, respectively. In randomly distributed composite types, the water absorption is directly proportional to the volume fraction of kenaf fibre. At the same time, flexural properties were inversely proportional to the volume fraction of kenaf fibres. Although the influence of water absorption on flexural strength is low, the flexural strength of pultruded hybrid composites was more influenced by the arrangement of kenaf fibre in each composite type than its fibre loading.2022-01-01T00:00:00Z