Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Tropical Plantation Journal
Isran Mohamad Pakaya
Universitas Gadjah Mada
Agriculture, Biological Sciences & Forestry Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparison of Agricultural Machine Tool Needs in Food Crop Farming on Direct Surveys and Integrated Planting Calendar Information Systems Isran Mohamad Pakaya; Hermantoro Hermantoro; Eka Suhartanto
Tropical Plantation Journal Vol 2, No 2 (2023): TROPICAL PLANTATION JOURNAL
Publisher : Akademi Komunitas Perkebunan Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56125/tpj.v2i2.24

Abstract

This study aims to compare the needs of agricultural machinery in rice farming through direct surveys and integrated Planting calendar information systems. This research was conducted in July-September 2020 in Boalemo Regency.   The number of respondents in the study was 54 farmers. Based on the study's results, it is known that agricultural machinery is very necessary. This is stated by 91% of respondents stating they always use agricultural machinery in their farming business. Agricultural machinery, hand tractors, power theresors, and combine harvesters are included in the high category that farmers often use with percentages of 9,  8.15%, 85.19%, and 72.22%. Rice transplanters are still in the low category 40.74%, due to small land ownership and lack of socialization. The use of agricultural machinery can save costs, reduce labour, and speed up work. Based on the calculation of the adequacy status of the hand tractor, rice transplanter, and power thereser is appropriate. However, in the  combine harvester there is a difference in a calculation, manually, the status is less, and in the interactive application the status is saturated. This is due to differences in available tools, and delays in updating data on the planting calendar. So it is necessary to regularly input and repair existing data on the word. Analysis of the B/C ratio of hand tractor, rice transplanter and power thereser is 1. 0, will the business of agricultural machinery is profitable and feasible. While the combine harvester value B/C ratio 1. 0, the exploitation of agricultural machinery is detrimental and not feasible.
Classification of Roasting Level of Coffee Beans Using Convolutional Neural Network with MobileNet Architecture for Android Implementation Isran Mohamad Pakaya; Radi Radi; Bambang Purwantana
Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Vol 13, No 3 (2024): September 2024
Publisher : The University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtep-l.v13i3.924-932

Abstract

The roasting process has a significant impact on the aroma profile and taste of coffee making it an essential stage in the coffee processing. Currently, the classification of coffee bean roasting levels still relies on subjective human visual assessment, which can lead to errors due to fatigue or negligence. To overcome this problem, a classification system was developed using computer vision technology with a deep learning approach. The present study designed a coffee bean roasting level classification system based on image analysis integrated within an Android application. The Convolutional Neural Network (CNN) model with the MobileNet architecture was used to identify and classify coffee beans based on their roasting level. Two CNN models, namely CNN Alpha and CNN Beta were used in this study. The dataset included 1.600 coffee bean images, with 1.200 images used to train the model and 400 images used to test the accuracy. In this experiment, the input image had an optimal size of 70x70 pixels, a learning rate of 0.0001, and 100 epochs for both models. The model training and testing results in the highest accuracy of 98-88% in 6.40-0.0012 minutes.The application test results obtained 93.55% accuracy, 97.06% precision, and 96.67% recall. These results indicate that this model and application function optimally in classifying coffee bean roasting levels accurately. Overall, this study reveals the potential of integrating CNN with the MobileNet architecture into an Android-based application to change the way of roasting level classification, as well as to improve efficiency and accuracy. Keywords: Coffee, Roasting, Convolutional Neural Network, MobileNet, Android.
Co-Authors Bambang Purwantana Eka Suhartanto Hermantoro . Radi Radi