Jurnal Informatika dan Rekayasa Perangkat Lunak

Development of an IoT-Based Chicken Manure Management System Prototype for Efficiency and Sustainability

2026-01-09T11:49:29+07:00

Increasing the production scale of laying hen farms results in significant manure waste, thus posing challenges to animal and human health, as well as environmental quality. To address these issues, this study aims to develop a prototype of an Internet of Things (IoT)-based multilevel manure management system to improve operational efficiency and support farm sustainability. The study used a method that included needs analysis, design, implementation, and testing with a blackbox testing approach. The system was designed using the DS3231 RTC module for automatic scheduling, the MQ2 sensor for air quality detection, the ESP8266 microcontroller as the control center, the BTS7960 driver as the current regulator, and the DC motor and conveyor as actuators that drive manure removal, with monitoring results displayed on the LCD. The test results showed that all components functioned as designed: the RTC was able to execute the schedule on time, the MQ2 sensor detected the gas threshold accurately, the ESP8266 processed data and sent instructions properly, the BTS7960 delivered a stable current, the DC motor and conveyor worked according to the set duration. This study provides practical implications for modern farm management through the application of the environmentally friendly smart farming concept.

Determining Strategic Locations for MSMEs in Sario District Using SAW Ranking with AHP Weighting

2026-01-10T20:58:21+07:00

Micro, Small, and Medium Enterprises (MSMEs) play an essential role in the Indonesian economy due to their significant contribution to national economic growth as well as their ability to create jobs for local communities. The long-term success of MSMEs is not only determined by the products or services they offer, but also by the strategic business locations they select. However, identifying strategic locations is challenging due to the lack of structured tools, objective evaluation of multiple criteria, and limited use of integrated decision-support models. This research aims to determine the most strategic location for the development of MSMEs in Sario District, Manado City, by considering several key factors, including accessibility, population density, rental costs, community income levels, and infrastructure availability. These issues highlight the need for a systematic and objective approach to support decision-making in location selection. The problem faced in determining the location is the difficulty of integrating all criteria objectively and systematically. For this reason, the Analytical Hierarchy Process (AHP) method is employed to determine the weight of each criterion. In contrast, the Simple Additive Weighting (SAW) method is utilized to rank the alternative locations. The analysis found Sario Tumpaan (A4) as the most strategic location and Sario (A3) as the least. Data were obtained from surveys, interviews, questionnaires, and agency documents. The AHP–SAW-based Decision Support System effectively provided objective and consistent recommendations, with Sario Tumpaan serving as a benchmark for future evaluations and development.

Comparison of Modern NLP with Classical Machine Learning Algorithms in Evaluating Food Security Programs

2026-02-06T18:39:21+07:00

The success of food security programs faces various challenges. Most of the available data is in the form of unstructured text reports, news, and policy documents. The BERT (Bidirectional Encoder Representations from Transformers) model allows the system to read reports and news by considering the relationship between words in sentences. Compared to Support Vector Machines (SVMs) that rely on numerical data. The dataset is expanded to improve the generalization of the IndoBERT Classifier. There are 6 commodity data and 3 labels used in IndoBERT Modeling, represented by a 768-dimensional feature vector resulting in Accuracy 0.8333 (83.33%) indicating 5 correct predictions, with one misclassification. Tuned Min-Max on Support Vector Machines (SVM) is used in each dimension to find the optimal hyperplane contributing. The feature matrix x with size (39,10) and the target variable y with size (39) show Accuracy 0.92 (92.0%) that the data division process maintains the class proportion consistently. SVM performed better than IndoBERT. Classification evaluation of the models showed IndoBERT with Accuracy 83% and SVM Sccuracy 87%.

Website-Based Running Sports Information System For Communities In North Sulawesi Using Extreme Programming Method

2026-01-20T10:27:58+07:00

The community in North Sulawesi has shown a strong interest in running, as evidenced by the increasing number of running communities and events. However, the absence of an integrated platform that provides information about running routes, communities, and events has become a challenge for runners in accessing information efficiently. This study employs the Extreme Programming method and aims to develop a web-based information system that delivers comprehensive information related to running sports. The website features key components such as community profile pages, a running event calendar, and running route locations, complete with maps, route descriptions, track lengths, difficulty categories, photo galleries, and supporting facilities like toilets and resting spots. The displayed information is sourced from various local communities and is systematically organized to ensure easy access for the public. Additionally, the website includes a contact page that allows users to provide suggestions or feedback to the admin. It also features a function that enables event organizers to directly submit event data and running route locations into the system through the contact page. This system is expected to help the community access information more easily and increase participation in running activities throughout North Sulawesi

Synthetic Data Pattern Simulation of Patient Care Journey Using K-Means Clustering

2026-02-14T06:45:34+07:00

Heterogeneous synthetic data is artificial data that can include many types of features (demographics, examinations, therapies). Complex patients (many procedures & medications) but fast service process and low complications. All patients are divided into 4 clusters, patient segmentation includes cluster 1 including mild patients, Cluster 2 including complex patients, Cluster 3 including high costs, Cluster 4 including high readmission risk. The highest silhouette score is 0.2187, which is obtained when the number of clusters (k) is 2. Based on previous calculations, the Davies-Bouldin Index result for the current clustering solution is 2.33. The Calinski-Harabasz index for the clustering solution with k=4 is 367.72. Clustering results are simply groups, without labels. Further analysis is needed to assign clinical meaning to each cluster.