Claim Missing Document
Check
Articles

PEMBERI MAKAN OTOMATIS PADA KUCING MENGGUNAKAN RASPBERRY PI BERBASIS ANDROID Uci Rahmalisa; Mardeni Mardeni; Rialtra Helmi; Arie Linarta
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 3 No. 2 (2020): Jurnal Teknologi dan Open Source, December 2020
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v3i2.782

Abstract

Keep a pet at home takes time and effort. For people who have very dense flurry of activity certainly keep a pet such as a cat would be very hard to do. A Raspberry Pi microcontroller is designed for the purpose of automatic feeding so it is easy to use. The workings of the tool are automatic scheduling using an Android-based smartphone so that the servo motor will open and close so that the cat food is taken out into the food container that has been provided. By using an Android-based smartphone, the feeding schedule can be set by the hour for each funnel. Equipped with a buzzer as a reminder of cat owners if the available food stock is low and must be immediately refilled. The programming language used is Python language. Based on testing and performance of "Automatic Cat Feeding Using Raspberry Pi Android Based" has shown results in accordance with the design that is able to open and close the funnel that fills the cat food container with a servo motor automatically by setting a predetermined time.
Automatic Height and Weight Measurement Integrated Database System uci rahmalisa; Yulisman Yulisman
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 4 No. 2 (2021): Jurnal Teknologi dan Open Source, December 2021
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v4i2.1792

Abstract

Measurement of height and weight, it is needed especially for school age 5-15 years old. From the results of monitoring height and weight measurements, we can monitor whether the child is underweight or overweight and obese. We can also monitor the growth of elementary school age children. The problem faced is that monitoring the growth of children in schools cannot be carried out effectively. This is because the process of measuring children's height and weight is done manually and of course it takes time for the process, besides that, data on student height and weight are also recorded still manually, so that data processing and utilization is not optimal. The purpose of making this Automatic Height and Weight Measurement Integrated Database System to process of measuring height and weight can be done effectively and efficiently, so it can produce integrated information in Database. The existence of an integrated database will make it easier for related parties to recap and archive children's data and store history of children's growth as material for evaluating and monitoring child growth. The results of this evaluation can be used as a reference for follow-up to be conducted. The resulting output is information in the form of tables and graphs of children's growth. In this research using the prototyping method which aims to get an overview of the tool to be designed and built, then it will be evaluated by the user. The evaluated prototype will be used as a reference to make a tool as the final product as the output of this research.
Design of Microcontroller Programming Learning KIT Using Scratch for Arduino Yulisman S.Kom; Uci Rahmalisa
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 4 No. 2 (2021): Jurnal Teknologi dan Open Source, December 2021
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v4i2.1793

Abstract

Based on the results of the researcher's observations, the competence of students' skills in the subjects of Microprocessors and Microcontrollers is still lacking. This is due to the fact that the current learning method is still using the conventional method, and still using conventional program code writing model. It is difficult to understand for students who are beginners in the field of programming. The purpose of this research is to produce Learning KIT products to facilitate learning activities of Microcontroller programming with Plug and Play system, in writing program code was made easy with simply compiling instructions in the form of block puzzles. It can make easy for the beginner to understand programming logic and algorithms. The method steps taken refer to prototyping method, it aims to get an overview of the tool’s designed and built to be shown to the user. The evaluation prototype will be used as a reference to make a tool as the final product as the output of this research.
Belangkas Robot As An Effort To Improve Calistung Ability In Early Children Uci Rahmalisa; Arie Linarta; Sri Yulani
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 5 No. 2 (2022): Jurnal Teknologi dan Open Source, December 2022
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v5i2.2678

Abstract

Education in the 4.0 era requires the education sector to be able to compete and utilize computer technology, which is currently developing rapidly as an interesting and interactive learning tool or media for children and to increase children's interest in learning. The first problem that came to the attention of the implementing team was that it was difficult for children to concentrate while studying, and children who entered elementary school without attending kindergarten still had difficulties in the processes of reading, writing, and arithmetic (Calistung), which of course would have an impact on children's delays in understanding learning material. The second problem is that the online teaching and learning process that was carried out previously was not effective in encouraging children's understanding of a lesson because it was difficult for children to focus on the learning being given. The third problem is that children are often exposed to gadgets that will have a negative impact on their gross and fine motor development. The duration of long and frequent use will lead to addiction to gadgets, the child's development will become less than optimal, and the child's emotions will be out of control and trigger early stress. The fourth problem is the absence of interactive learning media in partner schools that can increase children's interest in learning. The output target to overcome the existing problems will be interactive learning media in the form of a robot named BELANGKAS Robot (Concise Learning). The purpose of this research is to develop an alternative learning medium for children using robots by inviting children to collaborate and compiling a series of instructions for the robot to carry out a learning activity (an introduction to numbers, letters, and pictures) that leads to sharpening children's logical thinking and attracting children's interest in learning. reading, writing, and arithmetic. From the results of the research that has been done, the BELANGKAS robot is proven to be able to attract children's learning interest, and of course this interest will improve children's learning abilities, especially CALISTUNG.
The Relationship Between Age, Parity, Ideal Weight, and Blood Pressure in Diagnosing Hypertension in Pregnant Women Using The K-Means Algorithm Hendry Fonda; Uci Rahmalisa
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 6 No. 2 (2023): Jurnal Teknologi dan Open Source, December 2023
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v6i2.3157

Abstract

Hypertension is one of the health problems that often arise during pregnancy and can cause complications in 2-3% of pregnancies. Hypertension In Pregnancy (HDK) is defined as a blood pressure of ≥140/90 mmHg in two or more measurements. Data mining is a combination of a number of computer science disciplines that is defined as the process of discovering new patterns from very large data sets. By looking at records on Age, IMT, Parity / Gravidity, and Blood Pressure and analysis with K-Means clustering, it can be seen that the similarity of values of the above variables ultimately forms patterns related to hypertension in pregnant women. The clustering process using 5 clusters according to the elbow chart analysis. In this study, it was seen that the variable Blood Pressure is the same pattern and often appears in each cluster. While hypertension occurs in 1 cluster out of 5 existing clusters.
Monitoring Water Quality in The Well-Water Processing System to Make Drinkable Water Based on IoT Hendry Ponda; Uci Rahmalisa; Haris Tri Saputra; Rika Melyanti
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 7 No. 2 (2024): Jurnal Teknologi dan Open Source, December 2024
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v7i2.4271

Abstract

Indonesia is also inseparable from problems related to clean water. The city of Pekanbaru is currently experiencing rapid growth. In some big cities, the difficulty of clean water suitable for consumption is commonly felt by some residents, for example in Tuah Karya district – Pekanbaru. Moreover, this area is prone to flooding so the quality is getting worse because it smells and is cloudy. To produce clean water suitable for drinking that can be consumed by all levels of society. Water quality monitoring is also easy to do with IoT-based water quality monitoring tools. The goal of developing this prototype is to improve the healthy standard of living of the community by meeting the clean water needs of the prototype to be built. Seen from the main indicators, TDS and PH = TMS (Not Eligible) were obtained and followed by several other indicators that were still TMS. The results of the sample test showed that the water did not belong to the category of clean water and was suitable for consumption. After the water source of the drilled well is filtered using a tool made (without a manganese filter), the main indicators of TDS and pH are qualified.
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.