Article Per Year (5 Year)
p-Index From 2021 - 2026
0.92
P-Index
This Author published in this journals
All Journal Jurnal Sistem Informasi dan Informatika (SIMIKA) Journal of Applied Data Sciences SAINSTEK Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer
Helda Yenni
Universitas Sains Dan Teknologi Indonesia
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Materials Science & Nanotechnology Mechanical Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
MODEL PREDIKSI PRODUKTIVITAS PADI MENGGUNAKAN XGBOOST DAN RANDOM FOREST Yoga Safitra Anugraha; Helda Yenni; Wirta Agustin; Hadi Asnal
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 9 No. 1 (2026): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v9i1.4169

Abstract

Rice is a strategic commodity in ensuring national food security in Indonesia. Predicting rice productivity is a critical issue due to the decreasing harvest area and fluctuating production. This study aims to develop and compare the performance of two machine learning algorithms, namely Extreme Gradient Boosting (XGBoost) and Random Forest, in predicting rice productivity based on harvest area and total production data. The dataset consists of rice productivity data from 38 provinces in Indonesia over the period 2018 to 2024. The models were evaluated using three data splitting ratios (70:30, 80:20, and 90:10) and four evaluation metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²). The results show that both models perform well, with Random Forest achieving the highest R² value of 0.887 and the lowest RMSE of 2.939 on the 90:10 split, indicating higher accuracy. XGBoost, while slightly lower in accuracy (R² = 0.781), produced more stable predictions across varying input scales. When tested on new data, both models showed consistent performance, demonstrating generalization capabilities. These findings indicate that machine learning models are effective in modeling and forecasting agricultural productivity and can serve as decision-support tools for policymakers and agricultural stakeholders. The models can be utilized for strategic planning, resource allocation, and improving agricultural productivity in the future.
Implementasi Algoritma Regresi Linear Untuk Memprediksi Harga Laptop Risky Harahap; Karpen,; Helda Yenni; Muhamad Jamaris
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/rnnp7x70

Abstract

The development of laptop technology has driven the need for accurate price predictions to assist consumers in making purchasing decisions appropriately and efficiently. This study implements a Linear Regression algorithm to predict laptop prices based on 4 main features including Brand, Processor, RAM, and GPU. The dataset used consists of 11,768 data obtained from the Kaggle platform which is processed through preprocessing, feature transformation, and model evaluation stages with various performance metrics. The analysis results show that the RAM feature has the most significant influence on laptop prices, followed by Processor, Brand, and GPU. The developed Linear Regression model successfully achieved an R-squared value of 0.6453, which indicates that the model is able to explain 64.53% of the variation in laptop prices based on the analyzed features. This study contributes to the development of an accurate laptop price prediction system and provides a practical tool to support data-based purchasing decisions effectively and efficiently.
Prediksi Jumlah Titik Ruang Terbuka Hijau (RTH) Menggunakan Metode Regresi Linier dan Model Random Forest M. Azzuhri Dinata; Helda Yenni; Wirta Agustin; Aguston
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/d81adt50

Abstract

The development and preservation of Green Open Space (GOS) is an important part of maintaining environmental balance, especially in the Sumatra Ecoregion. This study aims to predict the number of GOS points using a linear regression approach and the Random Forest algorithm. The data used include variables such as area and forest area from several provinces in Sumatra. Model performance evaluation was carried out using MAE, RMSE, and coefficient of determination (R²) metrics. The analysis results show that the Random Forest model has superior performance compared to linear regression, with an MAE value of 5.52, RMSE of 5.88, and R² of 0.74. Meanwhile, linear regression was only able to achieve an R² of 0.45. These findings indicate that Random Forest is more effective in capturing non-linear data patterns and more accurate in predicting the number of GOS points. This study contributes to the use of data science technology to support sustainable environmental planning, as well as becoming a basis for data-based spatial planning policy making
Desain Dashboard Web Real-Time untuk Kendali Lampu Neon Box dengan ESP8266 dan Panel Surya Rometdo Muzawi; Helda Yenni; Irwansyah Sidabutar; Windy Fahrurozi
SAINSTEK Vol. 13 No. 2 (2025)
Publisher : Sekolah Tinggi Teknologi Pekanbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35583/js.v13i2.369

Abstract

Perkembangan teknologi Internet of Things (IoT) mendorong terciptanya sistem otomasi pintar yang efisien dan hemat energi, termasuk pada pengendalian pencahayaan ruang publik seperti neon box. Penelitian ini bertujuan untuk merancang dan mengimplementasikan antarmuka pengguna berbasis web yang terintegrasi dengan sistem kendali lampu neon box menggunakan mikrokontroler ESP8266 dan sumber daya panel surya. Sistem mencakup dua sensor utama, yaitu INA219 untuk pemantauan tegangan dan arus baterai serta DS18B20 untuk pengukuran suhu baterai. ESP8266 berperan sebagai unit pengendali pusat yang mengakuisisi data dari sensor melalui antarmuka I²C dan OneWire, mengatur status lampu neon melalui relay atau MOSFET, serta mengirimkan data ke server secara nirkabel menggunakan protokol HTTP atau MQTT melalui koneksi Wi-Fi. Pada sisi server, data diterima dan disimpan dalam basis data MySQL melalui layanan web berbasis PHP, yang sekaligus menyediakan endpoint API untuk keperluan monitoring. Antarmuka dashboard dikembangkan dengan menggunakan Chart.js guna menampilkan visualisasi real-time dari tegangan, arus, suhu baterai, serta status lampu. Sistem juga memungkinkan kontrol manual lampu secara jarak jauh melalui dashboard tersebut. Hasil pengujian menunjukkan bahwa sistem mampu memberikan respons kendali yang andal, visualisasi data yang informatif, serta konsumsi daya yang rendah. Integrasi antara panel surya, IoT, dan antarmuka web ini menjadikan sistem sebagai solusi mandiri yang efisien untuk manajemen pencahayaan luar ruang, khususnya di lokasi yang minim akses listrik konvensional.
MYCD: Integration of YOLO-CNN and DenseNet for Real-Time Road Damage Detection Based on Field Images Helda Yenni; Rometdo Muzawi; Karpen Karpen; M. Khairul Anam; Michel Kasaf; Tjut Rizqi Maysyarah Hadi; Dewi Sari Wahyuni
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1040

Abstract

Road damage such as cracks, potholes, and uneven surfaces poses serious risks to transportation safety, logistics efficiency, and maintenance budgeting in Indonesia. Manual inspection is time consuming, labor intensive, and prone to error, motivating the use of reliable computer vision solutions. This study proposes MYCD, a hybrid and mobile ready architecture that combines the fast detection ability of YOLO with the dense feature reuse of DenseNet, enhanced by the Convolutional Block Attention Module (CBAM) for spatial and channel focus and Spatial Pyramid Pooling (SPP) for multi scale context understanding. The system detects and classifies the severity of road damage into minor, moderate, and severe categories using images captured by standard cameras. MYCD was trained and validated on 1,120 field images using an 80/20 split to simulate realistic deployment. Validation achieved 64 percent accuracy, with the highest per class precision of 0.72 for minor damage and mAP@0.5 = 0.677. The confusion matrix showed that most errors occurred in the moderate category because of visual similarity with minor and severe damage. Unlike earlier studies that extended YOLO with heavy backbones such as ResNet or EfficientNet, MYCD focuses on feature propagation (DenseNet), attention precision (CBAM), and multi scale fusion (SPP) optimized for real time operation on standard hardware. Efficiency profiling confirmed its deployability. After compression, the model size is 46.8 MB and it requires 3.7 GFLOPs per inference at 640×640 resolution. On a mid-range Android device (Snapdragon 778G, 8 GB RAM), MYCD runs at 19 frames per second with 1.2 GB peak memory. Compared with YOLOv8 WD (68 MB; 5.2 GFLOPs), MYCD reduces computation by 31 percent while maintaining similar accuracy. Overall, MYCD achieves a practical balance of speed, accuracy, and efficiency, providing a deployable and reproducible framework for real time road damage detection in resource limited settings.
Co-Authors Aguston Anam, M Khairul Dewi Sari Wahyuni Hadi Asnal Irwansyah Sidabutar Karpen Karpen Karpen, M. Azzuhri Dinata Michel Kasaf Muhamad Jamaris Risky Harahap Rometdo Muzawi Tjut Rizqi Maysyarah Hadi Windy Fahrurozi Wirta Agustin Yoga Safitra Anugraha