Green Intelligent Systems and Applications

Preprocessing and Adaptive Parsing of Unstructured Voter Turnout Data with Spatial Feature Enrichment

2026-08-06T06:54:19+00:00

The raw input data exhibited severe structural heterogeneity, manifesting as seven distinct structural formats (Formats A–G) characterized by inconsistent header placement, nested merged cells, variable string representations, and missing values. To address these challenges without relying on static rule-based scripts, an intelligent adaptive parser was developed using dynamic regular expressions (regex) and token-density schema mapping based on normalized Levenshtein distance. The adaptive pipeline automatically identified table structures and standardized heterogeneous column definitions into a unified relational database, achieving a data-cleaning accuracy of 99.4%. To enhance the analytical value of conventional demographic data, a spatial feature enrichment pipeline was implemented by integrating three external Application Programming Interfaces (APIs): OpenStreetMap Nominatim for high-precision geocoding, the Google Maps Distance Matrix API for calculating actual road-network distances and travel times, and the Open-Meteo Elevation API for extracting elevation data. This study contributed to public sector data engineering by demonstrating that the integration of automated adaptive parsing with geospatial multi-API enrichment successfully transformed fragmented public documents into a high-fidelity, multidimensional data repository suitable for robust spatial–demographic policy analysis.

Performance Analysis of the Multivariate Multiple Linear Regression Algorithm for Economic Growth Based on Oil Palm Plantation Land Expansion in North Sumatra Province

2026-08-06T06:54:18+00:00

Oil palm plantations are one of the main sectors contributing to regional economic development in North Sumatra Province. This study aimed to analyze the performance of the Multivariate Multiple Linear Regression (MMLR) algorithm in modeling the relationship between oil palm plantation expansion and regional economic indicators. Secondary data from five oil palm-producing regencies covering the period 2013–2023 were obtained from the Central Statistics Agency (BPS). The independent variables consisted of plantation area and oil palm production, whereas the dependent variables were Gross Regional Domestic Product (GRDP) and per capita income. The dataset was divided into training (2013–2019) and testing (2020–2023) subsets. Model performance was evaluated using the coefficient of determination (R²), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results showed that the MMLR model was able to capture the relationship between oil palm plantation expansion and regional economic indicators, although its predictive performance varied across regencies. These findings indicated that the model provided useful insights into the contribution of the oil palm plantation sector to regional economic development in North Sumatra.

Validation of a Portable Resistive-Sensor Corn Moisture Meter against a Standard Grain Meter

2026-08-23T15:12:42+00:00

Measuring the moisture content of corn kernels was a critical aspect of post-harvest handling, as moisture content directly affected product quality and shelf life. This study validated a portable resistive-sensor-based instrument for measuring corn kernel moisture content by comparing its readings with those obtained using a standard grain moisture meter. The validation involved ten corn kernel samples with moisture contents ranging from 12% to 14% on a wet basis. Each sample was measured using both the standard moisture meter and the portable resistive-sensor instrument under identical conditions. Measurements obtained from the two devices were compared to evaluate their agreement using the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results showed that the portable resistive-sensor instrument achieved an MAE of 0.42% and an RMSE of 0.44% relative to the standard device. These low error values demonstrated that the developed instrument produced consistent measurements and accurately tracked variations in corn kernel moisture content. In addition to its measurement accuracy, the instrument offered several practical advantages, including a simple design, relatively low implementation cost, portability, rapid measurement, and suitability for on-site corn quality assessment. Overall, the resistive-sensor-based instrument provided an economical, practical, and readily implementable alternative for moisture measurement, with potential applications in supporting the drying and storage of agricultural commodities.

Analysis of the Effect of Attributes on Single Tuition Fee Grouping Using Multiple Linear Regression and Extreme Gradient Boosting

2026-08-20T23:39:43+00:00

Objectively determining the Single Tuition Fee (UKT) level was essential for aligning educational costs with students’ socioeconomic conditions. This study compared Multiple Linear Regression (MLR) and Extreme Gradient Boosting (XGBoost) for predicting the final (Pleno) UKT level using data from 12,355 students, including socioeconomic, school-related, and administrative attributes. Data preprocessing involved cleaning, handling missing values and duplicates, transforming categorical variables, and splitting the dataset into training and testing sets (80:20). Models were evaluated under “operational” and “strict” scenarios using accuracy, precision, recall, F1-score, confusion matrices, and AUC. In the operational scenario, XGBoost achieved 93.42% training and 90.15% testing accuracy, outperforming MLR, which achieved 84.10% testing accuracy. Under the strict scenario, XGBoost accuracy decreased to 63.27–63.54%, compared with 49.74–49.86% for MLR. These findings demonstrated XGBoost’s greater ability to capture nonlinear relationships and complex attribute interactions. Permutation importance identified Coordinator- and Verifier-assigned UKT as the dominant predictors, while SHAP analysis identified per capita income as the most influential socioeconomic factor. Overall, XGBoost showed superior predictive performance but should be used as a decision-support tool rather than as the sole determinant of student tuition fees.