Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Computer System and Informatics (JoSYC) KLIK: Kajian Ilmiah Informatika dan Komputer
I Made Gede Sunarya
Universitas Pendidikan Ganesha, Singaraja
Computer Science & IT Decision Sciences, Operations Research & Management Industrial & Manufacturing Engineering

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

Found 2 Documents
Search

 1 
Analisis Usability Pada Sistem Informasi LAPORBUP Menggunakan Performance Measurement, Retrospective Think Aloud dan User Experience Questionnaire Mohamad Ariansidi; I Made Candiasa; I Made Gede Sunarya
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 3 No. 6 (2023): Juni 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v3i6.807

Abstract

Since 5 years of its use until now there has never been an evaluation at LAPORBUP and it is not yet known how high the level of user satisfaction is in using LAPORBUP. In addition, several problems were found in LAPORBUP which were felt by users related to the interface and system functionality. These problems indicate that LAPORBUP is still not in accordance with the needs, it is necessary to carry out an evaluation analysis of the overall usability of the system by measuring the effectiveness and efficiency as well as the level of user satisfaction. The LAPORBUP evaluation involved 54 respondents obtained from OPD representatives and active users of LAPORBUP. Processing of this evaluation data is carried out using the Performance Measurement technique to measure system effectiveness and efficiency, as well as Retrospective Think Aloud and User Experience Questionnaire to measure aspects of user satisfaction. The results of the Performance Measurement evaluation show that the LAPORBUP application has not been effective because several problems were found when the respondents worked on the task scenarios. Furthermore, UEQ data analysis was carried out using the UEQ Data Analysis Tool by comparing the value of each aspect with the available product data set. Based on the analysis conducted, the attractiveness aspect is included in the good category with a value of 1.72. The clarity aspect is included in the category above the average with a value of 1.48. The efficiency aspect is included in the category above the average with a value of 1.18. The aspect of accuracy is included in the good category with a value of 1.55. The stimulation aspect is included in the very good category with a value of 2.13. The novelty aspect is included in the Very Good category with a value of 1.64. The recommendations generated from Retrospective Think Aloud consist of 7 recommendations on the complaints page, 14 recommendations on the management page, 10 recommendations on the regent's page, and 9 recommendations on the OPD page. The results of the analysis show that improvements can be made to aspects of clarity and efficiency so as to improve the quality of LAPORBUP services
Klasifikasi Tingkat Kematangan Roasting Biji Kopi Berbasis Ekstraksi Fitur Warna HSV Menggunakan Metode Naïve Bayes Gusti Ayu Devani Zelvia; I Made Gede Sunarya; I Gde Made Hanura; Ida Bagus Gede Putra Kenaka
Journal of Computer System and Informatics (JoSYC) Vol 7 No 3 (2026): May 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v7i3.9777

Abstract

Manual determination of coffee bean roasting levels through visual inspection has limitations, particularly in terms of subjectivity and human error. To address this, the present study develops an automatic classification system based on digital images to identify the roasting maturity level of coffee beans. The system uses six-dimensional HSV (Hue, Saturation, Value) color features — specifically the mean and standard deviation of each channel classified using the Naive Bayes Classifier (NBC) algorithm. Primary data (145 images) were collected only for the medium and dark classes, as these are the most common roasting levels in the local industry and were underrepresented in the secondary dataset from Kaggle (1,600 images), covering four classes: green, light, medium, and dark. A pixel normalization step was applied prior to HSV conversion to mitigate sensor bias between the primary (smartphone) and secondary (Kaggle) data sources. The images underwent size normalization to 224×224 pixels, then split into training data (75%) and test data (25%). Performance evaluation was carried out using a confusion matrix and metrics such as accuracy, precision, recall, and F1-score. The classification results show that the model achieves an accuracy of 83.48% (compared to 79.82% using only mean features), with the best performance in the light class (F1-score: 0.97) and medium class (F1-score: 0.90). The dark class had the lowest performance (recall: 0.61) due to spectral similarity with adjacent classes. These findings establish a lightweight baseline (inference time: 2.3 ms/image, model size: <1 KB) suitable for embedded and IoT implementations in small-scale coffee processing industries.
Co-Authors Gusti Ayu Devani Zelvia I Gde Made Hanura I Made Candiasa Ida Bagus Gede Putra Kenaka Mohamad Ariansidi