Garuda - Garba Rujukan Digital

Automatic Floor Cleaning Robot Using Arduino and Ultrasonic Sensor Yuda Irawan; Muhardi Muhardi; Rian Ordila; Roni Diandra
Journal of Robotics and Control (JRC) Vol 2, No 4 (2021): July
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.2485

The entire floor cleaning robot is divided into several parts, namely consisting of an Ultrasonic Sensor, Motor Shield L298, Arduino Uno microcontroller, Servo, and Dc Motor. This tool works when the Arduino Uno microcontroller processes the ultrasonic sensor as a distance detector and a DC motor as a robot driver, then the DC motor is driven by the Motor Shield L298. When an ultrasonic sensor detects a barrier in front of it, the robot will automatically look for a direction that is not a barrier to the floor cleaning robot. The distance value on the sensor has been determined, that is, when the distance read by the ultrasonic sensor is below 15 cm. The results of testing the value of the ultrasonic sensor distance found different conditions that occur. In a distance of 15 cm, the condition of the prototype cleaning robot for the road floor cleaning is obtained, while the distance 15 cm, the condition for the prototype of the street floor cleaning robot has stopped.

Efficiency Of STMIK Hang Tuah Pekanbaru Stationery Inventory Office Using Monte Carlo Method Rian Ordila
Journal of Applied Engineering and Technological Science (JAETS) Vol. 1 No. 2 (2020): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Inventory management in Office Stationery needs (ATK) is instrumental in supporting administrative activities. Not terinvetaris well, resulting in the use of goods is not optimal and increase spending on this ATK. For that required a system that can manage this ATK supplies. so that in the prediction of ATK inventory can coordinate and minimize expenditure of STMIK Hang Tuah Pekanbaru expenditure. The data obtained in this research is ATK At High School of Information and Computer Management (STMIK) Hang Tuah Pekanbaru sourced from Head of Equipment Section such as paper type A4 and F4, Paperclip, Map and Printer Ink. ATK is always experiencing shortage or also excess needs. With the Monte Carlo Method, STMIK Hang Tuah Pekanbaru will be able to determine the Pattern of ATK Supplies requirement in STMIK Hang Tuah Pekanbaru and the method can give a decision in determining the pattern of ATK request that will be requested to the employee. The result of the experiment of this method is to obtain the average number of procurement requests and the average number of procurement. Estimates of the Monte Carlo simulation strategic plan that has been done will yield an estimated information on the average amount of procurement as 16 packs and the estimated average monthly expenditure of Rp 21,333.- With the amount of calculations obtained then the Office Stationery to be purchased can be estimated and inventory can be provided to meet the demand for campus needs in 2018

PENGALAMAN DOSEN DALAM MENGAJARKAN ANATOMI PADA MAHASISWA KESEHATAN SELAMA MASA PANDEMI COVID-19: STUDI FENOMENOLOGI Siska Mayang Sari; Wahyu Praba Yudha; Susi Erianti; Raja Fitrina Lestari; Dian Roza Adila; Rani Lisa Indra; Rian Ordila
Jurnal Kesehatan Medika Saintika Vol 13, No 2 (2022): Desember 2022
Publisher : Stikes Syedza Saintika Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30633/jkms.v13i2.1475

Kondisi pandemi akibat COVID-19 menyebabkan terjadinya perubahan dalam dunia pendidikan. Penerapan protokol kesehatan menuntut diminimalkan bahkan ditiadakannya pembelajaran secara tatap muka. Tujuan dari penelitian ini adalah menggali berbagai hal tentang pengalaman dosen dalam mengajarkan anatomi pada mahasiswa selama terjadinya pandemi COVID-19. Penelitian ini merupakan penelitian kualitatif dengan pendekatan studi fenomenologi. Partisipan berjumlah 4 orang yang merupakan dosen yang mengajar anatomi di Universitas Hang Tuah Pekanbaru dan Universitas Awal Bros Pekanbaru. Pengumpulan data dilakukan dengan cara wawancara mendalam dan analisis data dengan teknik collaizi. Penelitian ini menemukan empat tema yaitu 1) Hambatan dosen dalam memaparkan materi anatomi tubuh manusia, 2) Masalah yang dihadapi dosen dalam mengajarkan anatomi tubuh manusia, 3) Teknik dosen dalam mengajar anatomi seperti media dan metode, dan 4) Penggunaan teknologi untuk mengajar anatomi tubuh manusia. Partisipan berharap adanya aplikasi yang interaktif tentang anatomi tubuh manusia sehingga memudahkan partisipan dalam mengajarkan topik tersebut pada masa pandemi COVID-19, kepada institusi pendidikan diharapkan untuk mengembangkan aplikasi digital guna menunjang proses pembelajaran tentang anatomi tubuh manusia.

Expert system for selection of saving products using the backward chaining method at PT. State saving bank (persero) tbk. Pekanbaru branch office Rian Ordila; Hendry Fonda; Hasti Rizki
Journal of Telecommunication Control and Intelligent System Vol. 1 No. 3 (2021): Monograph Book of Intellegent System
Publisher : PTTI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/jtcis.v1i3.63

Bank is a business entity engaged in finance, especially providing services in payment traffic and money circulation. Each bank has savings products with their respective advantages. Prospective customers who want to save definitely want quality and profitable savings. PT. Bank Tabungan Negara (Persero) Tbk. Pekanbaru Branch Office is one of the banks that has many deposit products. There are several factors that influence the decision of prospective customers in choosing a deposit product, such as administrative fees, interest offered, minimum balance, and ease of transacting through e-channel services. A web-based expert system can be a solution to these problems because it has the same functions and knowledge as someone who must have, experience, to solve a problem and make decisions. The method used in this system is backward chaining. The basis of knowledge that contains facts and rules from this research is the name of the product and the criteria for the deposit product. This system uses the PHP programming language and uses a MySQL database as data storage. This system begins by asking several questions, analyzing customer needs according to the criteria for the deposit product and providing output product according to customer needs. With this system, it can make it easier for customers to determine what savings product choices are suitable for their needs and help BTN KC Pekanbaru customer service to make the account.

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

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.

An Explainable Multimodal Hybrid Deep Learning Framework for Real-Time IoT-Based Fish Freshness Classification Rian Ordila; Miratu Megasari; Yulanda Yulanda; Yuda Irawan; Refni Wahyuni
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7844

Reliable assessment of fish freshness supports product quality, food safety, and consumer acceptance throughout fisheries supply chains. Sensory inspection remains common, but reliance on individual judgment can produce inconsistent assessments and limit monitoring efficiency. Here, a multimodal framework combines Computer Vision, IoT sensing, and Deep Learning to monitor Nile tilapia freshness in realtime. Its visual branch uses YOLO26 to locate fish eyes and EfficientNet B3 with CBAM to classify the extracted regions. A BiLSTM network learns temporal patterns from MQ136 and MQ137 measurements of H₂S and NH₃ associated with spoilage. An MLP then combines the class probabilities from both branches to assign the final freshness category. In the detection experiment, YOLO26 recorded 0.930 precision and 0.953 mAP@0.5. Visual classification with EfficientNet B3 plus CBAM reached 92% accuracy, whereas sensor classification with BiLSTM reached 93%, with AUC values as high as 0.99. Combining the modalities yielded 97% accuracy and a macro average F1 score of 0.97, exceeding the performance of either branch alone. Grad CAM maps located the main visual responses within eye regions relevant to freshness deterioration. These results support the framework's interpretability and its potential use for intelligent fish freshness assessment under near realtime monitoring conditions.

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

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.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search