Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal JOURNAL OF SCIENCE AND SOCIAL RESEARCH Journal of Applied Data Sciences
Arie Linarta
Universitas Dumai
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Social Sciences

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
An IoT-Driven Hybrid Stacking Ensemble with Deep Meta-Learning for Vending Machine Sales Forecasting Yulisman Yulisman; Zupri Henra Hartomi; Rian Ordila; Uci Rahmalisa; Arie Linarta; Yuda Irawan
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1395

Abstract

Accurate sales prediction is essential for optimizing inventory management and supporting dynamic pricing strategies in the retail industry, particularly for vending machines (VMs) integrated with IoT technologies. The availability of real-time transactional and environmental data from IoT sensors provides opportunities to improve forecasting accuracy by capturing complex temporal patterns and external influences on consumer behavior. However, traditional time series models and single machine learning approaches often struggle to model nonlinear relationships and long-term dependencies in such data. This study proposes a hybrid stacking ensemble model that integrates machine learning and deep learning techniques to enhance the prediction of daily sales volume per Stock Keeping Unit (SKU) in IoT-enabled vending machines. The proposed framework employs Random Forest Regressor (RF), Support Vector Regression (SVR), and XGBoost Regressor (XGB) as Level-0 base learners. Their predictions, along with corresponding residuals, are utilized as meta-features for a Long Short-Term Memory (LSTM)-based meta-learner, enabling effective modeling of both nonlinear and temporal characteristics. The model incorporates diverse features derived from IoT data, including lagged sales, rolling statistics, temporal attributes (day of week and weekend indicators), and environmental variables such as temperature and humidity collected from IoT sensors. Hyperparameter optimization of the LSTM meta-model is performed using Optuna to improve model stability and generalization. The proposed approach is evaluated using 10-Fold Time Series Cross-Validation to preserve temporal data structure. Experimental results show that the proposed model achieves an R² of 0.9967 and an RMSE of 0.0899, outperforming the best individual base model, XGBoost (R² = 0.9946, RMSE = 0.1121). Although the improvement is marginal, it consistently demonstrates the advantage of combining machine learning and deep learning through a stacking ensemble strategy. These findings indicate that integrating meta-features, residual learning, and IoT-based feature engineering can improve predictive performance and support adaptive decision-making in real-time vending machine operations.
RANCANG BANGUN PROTOTIPE SMART BUOY BERBASIS IOT UNTUK SISTEM PERINGATAN DINI CUACA EKSTREM DI PERAIRAN KOTA DUMAI Nur Rubiati; Amat Sofiyan; Ade Saputra; Arie Linarta
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 4 (2026): August 2026 (1)
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i4.7040

Abstract

Abstract: This study involved the design and construction of an Internet of Things (IoT)-based Smart Buoy prototype to serve as an early warning system for extreme weather in the waters of Dumai City. The research employed a Research and Development (R&D) approach, encompassing hardware and software design, system integration, and performance testing. Weather data—including air temperature, atmospheric pressure, rainfall, and wind speed—are collected via sensors, processed by a microcontroller, and transmitted in real-time over the internet to a monitoring platform. The study yielded the following results: (1) the Smart Buoy prototype is capable of measuring and monitoring weather parameters in real-time; (2) the IoT system successfully transmits measurement data to the monitoring platform, enabling remote weather monitoring; and (3) the integration of air temperature, atmospheric pressure, rainfall, and wind speed data serves as a basis for identifying potentially extreme weather conditions and issuing early warnings to users. Consequently, this IoT-based Smart Buoy prototype offers an effective alternative for weather monitoring and extreme weather early warning, thereby supporting the safety of fishermen and maritime transport users in the waters of Dumai City. Keywords: Smart Buoy, Internet of Things (IoT), Extreme Weather Monitoring   Abstrak: Penelitian ini merancang dan membangun prototipe Smart Buoy berbasis Internet of Things (IoT) sebagai sistem peringatan dini cuaca ekstrem di perairan Kota Dumai. Penelitian menggunakan metode metode penelitian menggunakan pendekatan research and development (R&D) dengan tahapan perancangan perangkat keras, perangkat lunak, integrasi sistem, serta pengujian kinerja alat. Data kondisi cuaca diperoleh melalui sensor yang mengukur suhu udara, tekanan atmosfer, curah hujan, dan kecepatan angin, kemudian diproses oleh mikrokontroler dan dikirimkan secara real-time melalui jaringan internet ke platform pemantauan. Hasil penelitian bertujuan yaitu: (1) prototipe Smart Buoy mampu melakukan pengukuran dan pemantauan parameter cuaca secara real-time; (2) sistem IoT mampu mengirimkan data hasil pengukuran ke platform pemantauan sehingga kondisi cuaca dapat dipantau dari jarak jauh; dan (3) integrasi parameter suhu udara, tekanan atmosfer, curah hujan, dan kecepatan angin dapat digunakan sebagai dasar dalam menentukan kondisi cuaca yang berpotensi ekstrem serta memberikan peringatan dini kepada pengguna. Dengan demikian, prototipe Smart Buoy berbasis IoT dapat menjadi salah satu alternatif sistem pemantauan dan peringatan dini cuaca ekstrem yang efektif dalam mendukung keselamatan nelayan dan pengguna transportasi laut di perairan Kota Dumai. Kata kunci: Smart_Buoy, Internet_of_Things (IoT),  Pemantauan_Cuaca_Ekstrem
An IoT-Driven Hybrid Stacking Ensemble with Deep Meta-Learning for Vending Machine Sales Forecasting Yulisman Yulisman; Zupri Henra Hartomi; Rian Ordila; Uci Rahmalisa; Arie Linarta; Yuda Irawan
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1395

Abstract

Accurate sales prediction is essential for optimizing inventory management and supporting dynamic pricing strategies in the retail industry, particularly for vending machines (VMs) integrated with IoT technologies. The availability of real-time transactional and environmental data from IoT sensors provides opportunities to improve forecasting accuracy by capturing complex temporal patterns and external influences on consumer behavior. However, traditional time series models and single machine learning approaches often struggle to model nonlinear relationships and long-term dependencies in such data. This study proposes a hybrid stacking ensemble model that integrates machine learning and deep learning techniques to enhance the prediction of daily sales volume per Stock Keeping Unit (SKU) in IoT-enabled vending machines. The proposed framework employs Random Forest Regressor (RF), Support Vector Regression (SVR), and XGBoost Regressor (XGB) as Level-0 base learners. Their predictions, along with corresponding residuals, are utilized as meta-features for a Long Short-Term Memory (LSTM)-based meta-learner, enabling effective modeling of both nonlinear and temporal characteristics. The model incorporates diverse features derived from IoT data, including lagged sales, rolling statistics, temporal attributes (day of week and weekend indicators), and environmental variables such as temperature and humidity collected from IoT sensors. Hyperparameter optimization of the LSTM meta-model is performed using Optuna to improve model stability and generalization. The proposed approach is evaluated using 10-Fold Time Series Cross-Validation to preserve temporal data structure. Experimental results show that the proposed model achieves an R² of 0.9967 and an RMSE of 0.0899, outperforming the best individual base model, XGBoost (R² = 0.9946, RMSE = 0.1121). Although the improvement is marginal, it consistently demonstrates the advantage of combining machine learning and deep learning through a stacking ensemble strategy. These findings indicate that integrating meta-features, residual learning, and IoT-based feature engineering can improve predictive performance and support adaptive decision-making in real-time vending machine operations.
Co-Authors Ade Saputra Amat Sofiyan Rahmalisa, Uci Rian Ordila Rubiati, Nur Yuda Irawan Zupri Henra Hartomi