Jurnal Sains dan Teknologi Informasi

Penerapan Sistem Informasi Geografis pada Pemetaan Coffee Shop Daerah Jakarta Selatan Berbasis Web

Rahayu Noveandini — 2025-12-23

The application of Geographic Information Systems (GIS) for mapping coffee shops in South Jakarta is highly relevant and beneficial. GIS allows the public to easily access more complete and accurate information about the distribution of coffee shops in the area. The problem is that there is currently no system that provides information and locations of coffee shops in South Jakarta for the general public. The development of the South Jakarta coffee shop GIS was carried out to respond to the community's need for more complete and structured location information. This web-based system makes it easier for users to find coffee shops that suit consumer needs through clear and informative spatial data visualization. This system also provides an interactive map that displays the locations of all coffee shops in South Jakarta, equipped with more detailed additional information than conventional map services, making it easier for users to search and determine the appropriate choice. The objective of this research is to develop GIS software that maps the locations of coffee shops. Leaflet.js software is used to map coffee shop locations using the Waterfall approach as the system development method. The process sequence begins with Analysis, Design, Coding, Testing, Implementation, and Maintenance, with testing using the blackbox method, and the results show that all system features function properly. System performance testing was conducted using two browsers, Chrome and Microsoft Edge, with page access speeds of 0.16 seconds for Chrome and 0.91 seconds for Microsoft Edge. For further development of the system, features such as user reviews, ratings, and recommendations based on user preferences can be added to make the system more interactive and informative.

Prediksi Jumlah Pendapatan Bisnis Katring Rumahan Menggunakan Metode Fuzzy Tsukamoto

Iin Parlina — 2025-12-23

Home catering business is a growing business with a system that depends on the number of orders and production costs that are not fixed in each period [1]. This condition makes it difficult for business owners to predict income accurately. Based on this, this study aims to build a revenue prediction system using the Fuzzy Tsukamoto Method that is able to process data on the number of orders and production costs as variables as objects to measure the value of income in a home catering business. The data source for this study was collected based on order production data. The data used in this study is questionnaire data with a simple random sampling technique. The sample of respondents was 50 respondents. The variable used was the number of catering orders produced based on the income value. The method used to solve this case is to utilize data mining techniques with the Fuzzy Tsukamoto method. The data was processed using visual studio software and calculated from 3 variables, namely the order variable (P1) has a Fuzzy set with few and many, the price variable (H) has an affordable and low set, and the income variable (P2) has a low and high set. The predicted revenue of the catering business resulted in orders for 750 boxes at a price of Rp. 25,000, with a predicted weekly revenue of Rp. 25,750,000. This can be used as input for home catering businesses.

Prediksi dan Pencegahan Risiko Burnout pada Pekerja Fleksibel Menggunakan Algoritma Random Forest

Noha Noor Fauziah Mk — 2025-12-24

Flexible workers operating under remote, hybrid, and freelance schemes face burnout risks that are difficult to detect early due to irregular work patterns and blurred work-time boundaries. Conventional burnout monitoring relying on manual surveys is static and lacks sensitivity to the dynamics of workers' psychological changes. This study aims to develop a machine learning-based burnout prediction system for flexible workers capable of providing real-time risk predictions accompanied by personalized prevention recommendations. The method employed is Random Forest Classifier using a dataset from Kaggle titled "Mental Health & Burnout in the Workplace" encompassing 5.000 observations. System development follows the Agile approach and is implemented through a Streamlit-based web application. Preprocessing stages include binary label transformation, data leakage elimination, one-hot encoding, class imbalance handling using SMOTE, and stratified split with a 90:10 ratio. The Random Forest model is configured with 800 trees, max_depth of 20, and other optimal hyperparameters. Evaluation results demonstrate that the model achieves 87% accuracy with precision of 0.89, recall of 0.91, and F1-score of 0.90 for the burnout class. Feature importance analysis identifies CareerGrowthScore, StressLevel, and ProductivityScore as dominant factors. The system provides real-time predictions with latency <2 seconds and prevention recommendations tailored to individual risk profiles. This research contributes a practical solution for self-monitoring mental health among flexible workers and provides organizations with an instrument for monitoring remote workforce well-being. Black-box testing validates that all functionalities operate according to specifications.

Sistem Mobile Deteksi Gangguan Kejiwaan Berbasis Suara Menggunakan Metode Deep Convolutional Neural Network

Kristiawan Nugroho — 2025-12-26

-Mental disorders are a global health problem that often goes undetected early, requiring innovative approaches to their detection. This study aims to develop a mobile system capable of detecting mental disorders based on voice using Deep Convolutional Neural Network technology. The method used in this study is the collection of voice data from individuals experiencing symptoms of mental disorders, followed by voice feature extraction and the application of a Deep Convolutional Neural Network model for the classification of these disorders. The system was tested using a processed voice dataset, which includes various types of mental disorders, including depression and anxiety. The results showed that the Deep Convolutional Neural Network model was able to achieve high detection accuracy, with the ability to recognize mental disorders based on specific voice characteristics. This finding opens new opportunities for faster and more efficient detection of mental disorders using mobile devices, which are accessible to the wider community. This study also demonstrates the great potential of deep learning technology in the field of mental health, particularly in the prevention and diagnosis of mental disorders.

Implementasi Penunjang Keputusan Pemilihan Biji Kopi Robusta dan Arabika Terbaik Menggunakan Metode Promethee pada Perkebunan Kopi

Devani Erik Saputra — 2025-12-31

Coffee beans are one of the most important commodities in the food and beverage industry, where the quality of the beans significantly determines the final product produced. Assessing high-quality coffee beans is a crucial factor in maintaining consumer satisfaction and preserving flavor consistency. This assessment process requires an accurate and objective method, as it involves various complex factors such as size, color, aroma, taste, and moisture level. A Decision Support System (DSS) serves as an effective solution to assist in complex, multi-criteria decision-making processes. The purpose of this study is to develop and implement a DSS based on the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) to objectively assess and determine the best quality Robusta and Arabica coffee beans. The PROMETHEE method was chosen because it is capable of handling multiple evaluation criteria simultaneously and generating alternative rankings based on measurable preference levels. This study includes data collection, analysis of factors affecting coffee bean quality, and the design and implementation of the PROMETHEE method within the developed DSS. The results of the study indicate that the application of the PROMETHEE method in the DSS can provide accurate, consistent, and reliable recommendations in determining coffee bean quality. Therefore, this system can serve as an effective tool for decision-makers in evaluating coffee bean quality in a more systematic and objective manner.