Penerapan Internet of Things (IoT) Untuk Monitoring Kondisi Tanah Gembur Pada Tanaman Hias Pucuk Merah Secara Real-Time

2026-05-01T21:36:48+00:00

This research aims to develop a real-time Internet of Things (IoT) based loose soil pH monitoring system for application to red shoots ornamental plants. The system designed in this research combines a soil pH sensor to measure soil acidity levels, a NodeMCU ESP32 microcontroller as a data processor, a 16x2 I2C LCD to display local information, and provides real-time data to users through the Blynk application. The purpose of developing this system is that users can easily monitor soil conditions in real-time and take necessary actions to increase plant productivity, especially red shoots ornamental plants that require special attention to their soil conditions. This research is expected to be a continuation of previous research which is still in the design stage of a soil pH monitoring system. This development is focused on a different research object, namely loose soil pH in red shoots ornamental plants, so it is expected to be able to produce a more practical, applicable loose soil pH monitoring system, and provide a real contribution to the management of red shoots ornamental plants effectively and efficiently.

Optimasi Kinerja Algoritma Random Forest dengan SMOTE untuk Prediksi Kinerja Akademik Siswa

2026-07-12T15:52:28+00:00

Student academic performance prediction is an essential component of Educational Data Mining (EDM) for the early identification of at-risk students. This approach aims to improve prediction accuracy and support decision-making for the early identification of at-risk students. This study proposes an optimized prediction pipeline that integrates feature engineering, Pearson Correlation-based Feature Filtering (PCFF), the Synthetic Minority Over-sampling Technique (SMOTE), and Random Forest (RF) to predict student academic performance. The Portuguese Student Performance Dataset (1,043 clean records; Pass = 814, Fail = 230) was used for evaluation. Four engineered features were constructed, reducing the feature space to 15 features through PCFF (threshold |r| ? 0.1). SMOTE was applied exclusively within each training fold to prevent data leakage. Two primary models were evaluated: a baseline Naïve Bayes model (Accuracy = 90.43%) and the proposed RF Default + SMOTE model (Accuracy = 93.78%, Recall = 95.09%, F1-score = 95.98%). Ten-fold stratified cross-validation achieved an accuracy of 90.89% ± 2.08%. The engineered feature G_avg obtained the highest feature importance score (0.285), outperforming the original grade features. The results demonstrate that integrating SMOTE and feature engineering significantly improves minority class detection, reducing False Negatives from 15 (baseline) to 8 (RF + SMOTE), representing a 46.7% improvement in identifying at-risk students.

Journal of Informatics Management and Information Technology

Penerapan Internet of Things (IoT) Untuk Monitoring Kondisi Tanah Gembur Pada Tanaman Hias Pucuk Merah Secara Real-Time

Optimasi Kinerja Algoritma Random Forest dengan SMOTE untuk Prediksi Kinerja Akademik Siswa