![]() The second factor was the addition of Saccharomyces cerevisiae culture consisting of three levels, without the addition of culture (S0), addition of 1% S. The first factor is was the coffee fermentation time (T) consisting of four levels, 12(T1), 24(T2), 36(T3) and 48(T4) hours. This research was conducted using a complete randomized block design factorial with two factors. This study aims to determine the interaction between the addition of Saccharomyces cerevisiae and fermentation time on the chemical and sensory properties of the coffee produced. Saccharomyces cerevisiae an excellent hydrolytic enzyme producer has important role in food fermentation. High levels of caffeine in Robusta coffee beans can be reduced by Wet coffee fermentation. Test results show that Smart Greenhouse can reduce the water content of coffee cherries 7.4 days more efficiently than conventional drying methods. The integrated Sugeno Fuzzy algorithm keeps the greenhouse at the ideal drying temperature. The results show that Smart Greenhouse can be controlled remotely via the website. With this, the drying of coffee cherries will be optimal and get the water content of the Indonesian National Standard to increase the quality and selling price of the coffee beans. The system can also calculate estimated days based on moisture content. Data on average temperature and humidity per day will be recorded and calculated to determine when the coffee cherries are ready for the next stage. The perfect drying temperature enables coffee cherries to achieve a moisture content of 12.55% within 14 days. Actuators use the fuzzy output results to control the temperature and humidity of the greenhouse to reach the ideal drying conditions. Temperature and humidity data in the greenhouse will be analyzed using a fuzzy algorithm. The Internet of Things is used to allow it to be monitored remotely in real-time. Based on these problems, the researchers made a Smart Greenhouse dryer using the Internet of Things Platform. The undried coffee cherries can damage the quality of coffee beans. This is because traditional farmers still use conventional methods for drying. One of Indonesia's lack of competitiveness in the international market is the low quality of coffee beans. ![]() In testing, it can be concluded that the MultilayerPerceptron method is better than other methods for the coffee bean classification process.Ĭoffee is a major commodity of the Indonesian plantation industry. The HCL color type has an accuracy of 65% split ratio 90:10 and LCH has an accuracy of 78% split ratio 90:10. ![]() Furthermore, the HSI color type has an accuracy of 42% split ratio 90:10. The YUV type has an accuracy of 58% split ratio 90:10. LAB has a 58% curation split ratio of 90:10. CMYK has an accuracy of 63% split ratio 90:10. HSV has an accuracy of 57% split ratio 90:10. From the results obtained, it shows that MultilayerPerceptron is better starting with RGB color with an accuracy of 38% split ratio 90:10. Therefore, this study aims to improve the performance of coffee bean quality classification using four machine learning methods and 7 color features. However, the results carried out in the study only had an accuracy value of up to 47%. In previous studies, coffee bean quality research has been carried out using the ANN method using color features. Coffee is one of Indonesia's foreign exchange earners and plays an important role in the development of the plantation industry. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |