Claim Missing Document
Check
Articles

Found 4 Documents
Search

Design and Implementation of a Dual-Cloud IoT Air Quality Monitoring System Using Fuzzy Mamdani Method Qodri Ramadani, Fiqih; Ramadhan Nasution, Yusuf
Journal of Information Systems and Technology Research Vol. 4 No. 3 (2025): September 2025
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v4i3.1326

Abstract

Air pollution continues to be a critical environmental issue that negatively impacts human health, ecosystems, and urban sustainability. Therefore, reliable air quality monitoring systems are urgently required to provide real-time and accurate information for both communities and decision-makers. This study presents the design and implementation of an Internet of Things (IoT)-based air quality monitoring system that integrates environmental sensors with an ESP32 microcontroller. A key novelty of this research is the adoption of a dual-cloud architecture, combining ThingSpeak and Blynk, to enhance data accessibility, visualization, and system reliability compared to conventional single-cloud approaches. The Fuzzy Mamdani method is applied to classify air quality levels into three categories: Good, Moderate, and Poor, using input variables of temperature, humidity, and gas concentration. Methodologically, the system was tested under multiple environmental conditions, and fuzzy membership functions and rules were carefully designed to reflect realistic thresholds. The results show that the dual-cloud system enables more robust and flexible monitoring, with faster data synchronization and higher reliability in remote visualization. Quantitatively, the system achieved a 92% expert validation score and demonstrated a 15% improvement in responsiveness compared to previous single-cloud implementations reported in the literature. The discussion highlights that dual-cloud visualization provides an effective solution to overcome downtime risks and single-point failures, while also improving user experience in accessing real-time air quality information. This research contributes to the growing body of work on IoT-based environmental monitoring and can serve as a foundation for future smart city applications.
Implementasi Data Mining dengan K-Means Clustering untuk Memprediksi Pengadaan Obat Pane, Putri Pratiwi; Ramadhan Nasution, Yusuf; Furqan, Mhd.
Journal of Computer System and Informatics (JoSYC) Vol 5 No 2 (2024): February 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i2.4920

Abstract

Community Health Center is one of the institutions that provides healthcare services. To ensure the provision of quality healthcare services, the Community Health Center management must be able to effectively manage medicine inventory to avoid the risks of shortages or excess stock. Therefore, the purpose of this research is to observe and perform clustering of medicine demands at Puskesmas Mandala using the K-Means Clustering technique. The data used includes medicine demand data from January to December 2023 at the health center. In its implementation, the RapidMiner application or software is utilized to perform clustering using the K-Means Clustering algorithm. The available medicine data will be grouped into 3 clusters: cluster 0 for high medicine demands, cluster 1 for moderate medicine demands, and cluster 2 for low medicine demands. Out of the 28 test data used, the results show the first cluster consisting of 24 items, the second cluster consisting of 3 items, and the third cluster consisting of 1 item with a Davies Bouldin Index value of 0.276. From this research, the Puskesmas can continue to procure medicine for the types classified under high-demand clusters to ensure that the medicine needs are consistently met.
Penerapan Algoritma C4.5 Pada Klasifikasi Status Gizi Balita Ramadhan Nasution, Yusuf; Armansyah; Furqan, Mhd; Matondang, Toibatur Rahma
JURNAL FASILKOM Vol. 14 No. 1 (2024): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v14i1.6941

Abstract

The study aims to classify the nutritional status of the child using the C4.5 algorithm. The secondary data used is derived from the assessment of the nutrition status of a child in Puskesmas Promji and Puksesmas Suka Makmur. A classification model is constructed using the C4.5 algorithm based on a number of predictor factors that have been determined. The research methodology includes data collection, data preprocessing, model development with C4.5 algorithms, model evaluation, and results analysis. Model evaluation is done using measurements such as accuracy. In addition, the significance of predictor variables in affecting the nutritional status of infants was also evaluated through data analysis. This research contributed to the development of a method of classifying the nutritional status of infants using the C4.5 algorithm approach. The implication of this study is that the classification model developed can be used as a tool to support early identification and intervention against nutritional problems in infants. Furthermore, based on testing using the confusion matrix technique with the 80:20 data division of a total of 502 datasets, consisting of 402 training data and 100 testing data, an accuracy rate of 80 percent was obtained.
PREDICTING TEA HARVEST PRODUCTION AT BAH BUTONG USING RANDOM FOREST AND HISTORICAL DATA Prayoga, Hafizd; Ramadhan Nasution, Yusuf
JURTEKSI (jurnal Teknologi dan Sistem Informasi) Vol. 12 No. 2 (2026): Maret 2026
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Royal Kisaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v12i2.4455

Abstract

Abstract: Accurate forecasts of tea harvest production are important for workforce planning, factory operations, and marketing decisions, yet conventional estimation in plantations often relies on field experience and can be biased and less adaptive to changing conditions. This study aims to develop a Random Forest Regression model to predict tea harvest production at the Bah Butong tea plantation using historical operational and climate-related data. The dataset consists of 60 monthly records (2020–2024) with six predictor variables: rainfall (mm), number of rainy days, pest level, weed level, number of harvested trees and land area. Data were split into 80% training (48 samples) and 20% testing (12 samples). Model hyperparameters were optimized using RandomizedSearchCV with RepeatedKFold cross-validation (5 folds, 3 repeats). The tuned model achieved MSE of 668,980,524.45, RMSE of 25,864.66 kg, MAE of 19,838.69 kg, and MAPE of 7.59% on the test set. The results indicate that the model can provide practical production estimates, with errors averaging about 7–8% of the actual production. Feature importance analysis shows that the number of harvested tea bushes and cultivated area contribute most to predictions. Future work should extend the historical period and incorporate time-based features (seasonality/lag) for improved forecasting. Keywords: hyperparameter tuning; production prediction; random forest; regression; tea harvest Abstrak: Perkiraan akurat produksi panen teh sangat penting untuk perencanaan tenaga kerja, operasional pabrik, dan keputusan pemasaran, namun estimasi konvensional di perkebunan seringkali bergantung pada pengalaman lapangan dan dapat bias serta kurang adaptif terhadap perubahan kondisi. Studi ini bertujuan untuk mengembangkan model Regresi Random Forest untuk memprediksi produksi panen teh di perkebunan teh Bah Butong menggunakan data operasional dan data terkait iklim historis. Dataset terdiri dari 60 catatan bulanan (2020–2024) dengan enam variabel prediktor: curah hujan (mm), jumlah hari hujan, tingkat hama, tingkat gulma, jumlah pokok panen, dan luas lahan. Data dibagi menjadi 80% data pelatihan (48 sampel) dan 20% data pengujian (12 sampel). Parameter model dioptimalkan menggunakan RandomizedSearchCV dengan validasi silang RepeatedKFold (5 lipatan, 3 pengulangan). Model yang telah disempurnakan mencapai MSE sebesar 668.980.524,45, RMSE sebesar 25.864,66 kg, MAE sebesar 19.838,69 kg, dan MAPE sebesar 7,59% pada set data uji. Hasil tersebut menunjukkan bahwa model dapat memberikan estimasi produksi yang praktis, dengan kesalahan rata-rata sekitar 7–8% dari produksi aktual. Analisis kepentingan fitur menunjukkan bahwa jumlah semak teh yang dipanen dan luas lahan budidaya paling berkontribusi pada prediksi. Pekerjaan selanjutnya harus memperpanjang periode historis dan menggabungkan fitur berbasis waktu (musiman/lag) untuk peramalan yang lebih baik. Kata kunci: panen teh; prediksi produksi; random forest; regresi; tuning parameter