Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Bulletin of Computer Science Research
Esti Wijayanti
Universitas Muria Kudus, Kudus
Computer Science & IT Decision Sciences, Operations Research & Management

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Klasifikasi Mutu Tomat dan Potensi Umur Simpan Berdasarkan Fitur Warna-Tekstur Menggunakan Random Forest Intan Noviyanti; Esti Wijayanti; Evanita Evanita
Journal of Information System Research (JOSH) Vol 7 No 4 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i4.10295

Abstract

Postharvest tomato deterioration remains a major challenge due to manual and subjective quality assessment, which may lead to inconsistent sorting results and inaccurate shelf-life estimation. This study aims to develop a tomato quality classification system and predict potential shelf life based on digital image processing using the Random Forest algorithm. The study employed 936 tomato images and 450 non-tomato images collected independently. The extracted features consisted of Red Green Blue (RGB) and Hue Saturation Value (HSV) color features, as well as Gray Level Co-occurrence Matrix (GLCM) texture features. Tomato quality was classified into three categories, namely Poor, Medium, and Good, using a Random Forest Classifier, while shelf-life prediction was performed using a Random Forest Regressor. The classification model achieved an accuracy of 96.81%, precision of 96.82%, recall of 96.81%, and an F1-score of 96.81%. The regression model produced a Mean Absolute Error (MAE) of 0.0621, a Root Mean Square Error (RMSE) of 0.1152, and an R² value of 0.8752, while cross-validation yielded an average accuracy of 95.83% ± 1.24%, indicating stable model performance. Feature importance analysis revealed that color features contributed the most to both models, with g_mean identified as the most influential feature for tomato quality classification and shelf-life prediction. This study contributes to the development of a tomato quality assessment system capable of simultaneously classifying tomato quality and predicting shelf-life potential based on digital image processing using the Random Forest algorithm. In addition, feature importance analysis is employed to identify the visual characteristics that have the greatest influence on model performance. The results demonstrate that the proposed approach has the potential to support tomato sorting and postharvest management processes in a more objective and efficient manner.
Penerapan NLP Pada Chatbot Telegram Untuk Informasi Seputar Handphone Arfiyan Khusnul Umam; Esti Wijayanti; Ahmad Abdul Chamid
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.540

Abstract

This research develops a chatbot based on the Telegram platform that integrates Natural Language Processing (NLP) technology to provide information about mobile phones quickly, accurately, and efficiently. With the increasing need for users to access data regarding specifications, prices, reviews, and device damage diagnosis interactively, this chatbot becomes a relevant solution in supporting digital literacy and improving user experience. The system was developed using Agile methodology through stages of needs analysis, interface design, Telegram API implementation, and NLP integration with BERT architecture for intent recognition and named entity recognition. Data was collected through web scraping from e-commerce platforms, technology review websites, and community forums, then structured in a MongoDB database. Main features include product specification searches, damage identification, latest news, and interactive guides that support device problem-solving. White Box Testing showed satisfactory results with Statement Coverage 92%, Branch Coverage 88%, Intent Recognition accuracy 87%, Response Time 2.1 seconds, and Query Success Rate 97.5%. Evaluation results confirm that the chatbot is able to perform its functions responsively and practically, ready for deployment, and has potential to be expanded to other digital platforms to increase information technology competitiveness in the digital era.
Sistem Informasi Sidang Seminar Proposal dan Skripsi Berbasis Web dengan Pendekatan Metode Waterfall Muhammad Farid Arshal Afandi; Ahmad Jazuli; Esti Wijayanti
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): July 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7575

Abstract

The scheduling of proposal seminars and thesis defenses is a crucial process completely of student studies in the informatics engineering study program. However, this process often faces several challenges, such as delayed information, manual data accumulation, and a lack of transparency in schedule and examiner selection. To address these issues, the Laravel framework was chosen for the design of this web-based system, aiming to simplify the administration and scheduling processes for proposal seminars and thesis defenses. Laravel was selected due to its support for structured, secure, and efficient system development. This web-based system utilizes PHP and SQL for database management. The development methodology used is Waterfall, which adopts a sequential and systematic approach, starting from the requirement, design, implementation, verification, and maintenance stages. Each stage is done in a structured manner to ensure that all needs have been met before moving on to the next stage. System implementation using the Laravel framework as the backend foundation with responsive interface design. The case study was conducted at the Informatics Engineering Study Program of Universitas Muria Kudus. The results of testing indicate that the system improves data processing efficiency, accelerates information delivery, and minimizes errors in the registration and scheduling processes. With implementation of this system, academic procedures are expected to become more orderly, transparent, and well-structured. The test results show that the system is able to improve efficiency, as well as reduce administrative errors in the registration and scheduling process. All users are already interrelated in this registration process, starting from students, lecturers, coordinators, operators.
Co-Authors Ahmad Abdul Chamid Ahmad Jazuli Arfiyan Khusnul Umam Evanita Evanita Intan Noviyanti Muhammad Farid Arshal Afandi