Article Per Year (5 Year)
p-Index From 2020 - 2025
1.285
P-Index
This Author published in this journals
All Journal U-NET Jurnal Teknik Informatika Journal of Applied Data Sciences
Subagio, S
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
A Hybrid LSTM–Stacking–SMOTE Model for Weather-Aware Palm Oil Price Prediction Addressing Data Imbalance and Forecast Accuracy Kusmanto, Kusmanto; Subagio, S; Manja, Erni
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.922

Abstract

Accurate forecasting of palm oil prices is crucial for agribusiness decision-making due to high market volatility influenced by dynamic weather conditions. This study proposes a novel hybrid deep learning model combining Long Short-Term Memory (LSTM), Stacking Ensemble, and Synthetic Minority Over-sampling Technique (SMOTE) to improve predictive accuracy and handle class imbalance in price trend classification. The model was trained using a multivariate time-series dataset sourced from Kaggle, consisting of daily records of temperature, humidity, rainfall, and palm oil prices. A binary classification scheme was applied by labeling instances as either price increase (class 1) or price stable/decrease (class 0), based on a 0% price change threshold. Four experimental configurations were evaluated: standard LSTM, LSTM + SMOTE, LSTM + Stacking, and the proposed LSTM + SMOTE + Stacking. The proposed model outperformed all baselines, achieving the highest accuracy of 83.12%, an F1-score of 0.8466, MAE of 0.1688, RMSE of 0.4109, and a perfect recall of 1.0000, indicating excellent sensitivity to minority class trends. In contrast, the standard LSTM achieved only 77.32% accuracy and an F1-score of 0.7224, showing limited ability in handling imbalanced data. Visualization of loss curves and confusion matrices confirmed the model’s learning stability and classification effectiveness. This study contributes a novel integration of ensemble learning and oversampling in time-series commodity forecasting and demonstrates the effectiveness of this approach in capturing weather-driven price patterns, offering a robust framework for predictive analytics in agriculture.
SISTEM PENDUKUNG KEPUTUSAN PENENTUAN PEMILIHAN DOSEN PEMBIMBING SKRIPSI FAKULTAS ILMU KOMPUTER UNIVERSITAS AL WASHLIYAH (UNIVA) LABUHANBATU BERDASARKAN MINAT MAHASISWA DENGAN METODE AHP Sahbudin Ritonga, Desi Deliyanti Ritonga; Subagio, S; Aditya, Rahmad
U-NET Jurnal Teknik Informatika Vol. 8 No. 2 (2024): U-NET Jurnal Teknik Informatika | Agustus
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52332/u-net.v8i2.813

Abstract

Determination of the thesis supervisor at the Faculty of Computer science, Al Washliyah University (UNIVA) Labuhanbtu is currently carried out by determining directly by determining the thesis supervisor to direct and assist in completing the thesis. The main objective of this research is to determine the thesis supervisor of the Faculty Computer science, University of Al Washliyah (UNIVA) Labuhanbatu, the method used in determining the supervisor is using the AHP (Analytical Hierarchy Process) method. The creation of this system begins. Observing and searching for data, analyzing and collecting data, designing, programming, and the application uses the visual basic programming language, source code and access database for its database. The final result of this research is to produce a decision support system for determining thesis supervisor using the AHP (Analytical Hierarchy Process) method.
Journal Sistem Pakar Deteksi Jenis Penyakit Gangguan Kejiwaan Menggunakan Metode Demster Shafer wanda noor afrida; Samsir; Subagio, S
U-NET Jurnal Teknik Informatika Vol. 9 No. 1 (2025): U-NET Jurnal Teknik Informatika | Februari
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52332/u-net.v9i1.838

Abstract

An Expert System can be interpreted as a composition of data and information obtained from an expert or experts which is then processed by a system to be able to solve a problem according to the method used by experts or experts. One of the applications of expert systems is in the medical field, namely in the diagnosis of disease. In the research carried out, the design and creation of an expert system was created as problem solving to help diagnose mental disordersschizophrenia which begins with determining the symptoms to determine the type of mental disorder. In its design, this expert system uses the Simple Additive Weighting algorithm to determine the weight of each symptom experienced by the patient. Then the algorithmDempster Shafer to calculate the confidence value for the symptoms experienced by the patient.
Implementation of NodeMCU ESP8266 Microcontroller for Teacher Attendance System at SMK Swasta Pemda Rantauprapat Mulia, Ahmad; Subagio, S; Ritonga, Wahyu Azhar
U-NET Jurnal Teknik Informatika Vol. 8 No. 2 (2024): U-NET Jurnal Teknik Informatika | Agustus
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52332/u-net.v8i2.848

Abstract

NodeMCU is an open source IoT platform, NodeMCU ESP8266 can be used for Internet of Things (IOT) because the facilities are equipped with Wi-Fi, RFID is a process of identifying objects or objects using radio frequency, this device is widely sold in stores online at a very low price. The type of research used in this research is qualitative research, while the data collection method used is observation andto study, the design method uses the method postage type. This system tests every piece of hardware used and tests the software from a specific functional perspective. The result of this study is the teacher attendance system using Microcontroller NodeMCU ESP8266 replace the manual attendance recording model in the attendance book by writing the entry and rturn hours and filling in the teacher's signature with id card attached to the device RFID connected to microcontroller NodeMCU ESP8266. Thus, reducing the occurrence human error when recap attendance, and reduce paper use.
Sistem Pendukung Keputusan Penentuan Guru Bidang Studi Pada Sekolah SMK Siti Banun Rantauprapat Menggunakan Metode Simple Additive Weighting (SAW) Hsb, Heri Faysal; Ritonga, Wahyu Azhar; Subagio, S
U-NET Jurnal Teknik Informatika Vol. 8 No. 1 (2024): U-NET Jurnal Teknik Informatika | Februari
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52332/u-net.v8i1.850

Abstract

Teachers are one of the most important components owned by schools in sustaining life, which is a challenge for the management of educational institutions to be able to provide an appropriate, effective and efficient decision in managing data in an increasingly competitive business world that encourages schools to work harder. in improving the quality of their schools. The Decision Support System or SPK for determining subject teachers with the (SAW) method produces a system that can determine an option that can assist the head in making decisions. The simple additive weighting (SAW) method applies a weighted average to calculate the amount of production as the final result.
Sistem pakar deteksi penyakit jagung dengan metode forward chaining di kelompok tani lestari desa bandar kumbul Muliadong pane, Siti rahma pane; Subagio, S; Ritonga, Wahyu Azhar
U-NET Jurnal Teknik Informatika Vol. 8 No. 1 (2024): U-NET Jurnal Teknik Informatika | Februari
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52332/u-net.v8i1.871

Abstract

One of the causes of the failure of hybrid corn cultivation activities is pests and diseases which are the result of complex or unbalanced interactions between the three components in weak aquatic ecosystems, ferocious pathogens and deteriorating environmental quality. With that, it is necessary to have an application that can help farmers to take care of corn plants so that they are not attacked by pests and diseases. The application system created in this study is an expert system that can analyze the types of diseases in corn. The expert system in this study uses the Forward Changing method. This expert system is expected to be able to assist farmers in solving farmer problems in detecting corn disease by making applications using WEB, with MySQL and Xampp databases.
EXPERT SYSTEM TO DIAGNOSE DISEASES IN THE HUMAN DIGESTIVE SYSTEM USING THE FORWARD CHAINING METHOD CASE STUDY OF PUSKESMAS HUTAGODANG HEALTH CENTER Daulay, Siti Aisyah; Subagio, S; Ritonga, Wahyu Azhar
U-NET Jurnal Teknik Informatika Vol. 8 No. 2 (2024): U-NET Jurnal Teknik Informatika | Agustus
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52332/u-net.v8i2.883

Abstract

The era that is increasingly developing requires that we have to keep up with the times that are increasingly developing. Meant in medical science, in detecting disease must also follow the current developments. Digestion is one of the organs that exist in humans created by God. The digestive system is present in the body, it is difficult to detect any disease that is in the digestive tract. With this expert system, it is able to make it easier to detect digestive diseases with the help of information technology. And the data makes it easier for medicine to detect this disease. By making applications using WEB, with MySQL and XAmpp databases. By using the Forward Chaining method.
EXPERT SYSTEM FOR DIAGNOSIS OF DISEASES OF celery plants WITH FORWARD CHAINING METHOD IN GROUP SIMPORIK VILLAGE FARMER Pasaribu, Putri Delvina; Subagio, S
U-NET Jurnal Teknik Informatika Vol. 8 No. 1 (2024): U-NET Jurnal Teknik Informatika | Februari
Publisher : LPPM Universitas Al Washliyah Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research is motivated by problems in Siamporik Village who have good celery planting skills, but lack knowledge about this celery plant disease. In the village of Siamporik, the skill of growing celery is due to the lack of detecting celery disease which makes the harvest unsatisfactory. To reduce yield losses, an expert system for diagnosing sop leaves (celery) was created so that it can detect plant diseases, using the Forward Channeling method, using the Web as an application, and using MySQL and Xampp databases.
Co-Authors Daulay, Siti Aisyah Hsb, Heri Faysal Kusmanto Kusmanto Manja, Erni Mulia, Ahmad Muliadong pane, Siti rahma pane Pasaribu, Putri Delvina Rahmad Aditya Sahbudin Ritonga, Desi Deliyanti Ritonga Samsir Wahyu Azhar Ritonga wanda noor afrida