Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Mechatronics, Electrical Power, and Vehicular Technology Journal of Mechatronics and Artificial Intelligence
Rizky Hamdani Sakti
Universitas Pendidikan Indonesia
Electrical & Electronics Engineering

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

Found 3 Documents
Search

 1 
An evaluation of stereo vision for distance estimation using the SGBM algorithm in the CARLA simulator Rizky Hamdani Sakti; Liptia Venica; Dewi Indriati Hadi Putri; Shinta Rohmatika Kosmaga; Estiko Rijanto
Journal of Mechatronics, Electrical Power, and Vehicular Technology Vol 16, No 2 (2025)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/j.mev.2025.1284

Abstract

This paper presents an evaluation of stereo vision based on the semi-global block matching (SGBM) algorithm for distance estimation in an autonomous parking scenario using the CARLA simulator. Distance-disparity regression functions are explored to enhance distance estimation accuracy. The proposed distance estimation model was evaluated using the design science research methodology (DSRM) framework, with experimental validation conducted in CARLA’s promenade environment. The evaluation employed root mean square error (RMSE) and relative error metrics to assess performance. Experiments were performed within a range of 40-350 cm, which is relevant for autonomous parking applications. The experimental results show that the algorithm achieves an overall RMSE of 1.69 cm and an average relative error of 1.1 %. The findings contribute to the advancement of perception systems for autonomous vehicles, particularly in challenging environments.
Analyzing Loss Components in DC Generator for Wind Turbine Applications Elysa Nensy Irawan; Kai Shibuya; Nguyen Hoang Minh Giang; Rizky Hamdani Sakti
Journal of Mechatronics and Artificial Intelligence Vol. 1 No. 1 (2024): JMAI: June 2024
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jmai.v1i1.69864

Abstract

Direct current (DC) generators have gained attention for their simplicity and reliability in wind turbine applications. However, DC generators are subject to energy losses, including ohmic, magnetic core, and mechanical losses, which impact system performance. This research investigates these losses in DC generators used in wind turbines through experimental testing. The methodology integrates laboratory experiments with simulations to quantify and understand loss mechanisms. Findings offer insights for optimizing wind turbine efficiency and reliability. Results show significant total power loss of 99%, emphasizing the need for meticulous loss assessments. Friction, copper, and iron loss coefficients are analyzed with the value of 0.217 and 0.709, respectively. However, with the rise in input voltage levels, a noticeable pattern becomes evident, where the significance of iron loss decreases relative to other influencing factors. Understanding these dynamics is crucial for enhancing wind turbine performance and advancing sustainable energy solutions.
Air Quality Classification System using Random Forest Algorithm using MQ-7 and MQ-135 Sensors with IoT-based Aisyah Aira Putri Maharani; Rizky Hamdani Sakti; Muhamad Fajar Imanul Haq; Muhamad Ajis; Abdu Malikh Silaban
Journal of Mechatronics and Artificial Intelligence Vol. 1 No. 2 (2024): JMAI: December 2024
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jmai.v1i2.75591

Abstract

Air is one of the essential elements in human life besides water and soil. However, currently the air quality in Indonesia is getting worse. Therefore, an air quality classification system using Random Forest algorithm based on CO and CO2 levels using IoT-based MQ7 and MQ13 sensors is needed as a smart solution. The workflow of this system begins with detecting air quality using the MQ-7 sensor for CO gas and the MQ-135 sensor for CO2 gas. Then, the classification process is carried out with the Machine Learning Random Forest algorithm by utilizing a number of training data that has been stored in the program to classify the gas sensor detection results into three types of classes, namely “Good”, “Bad”, or “Toxic”. The final output of this system is a website display that can be accessed on a PC/Laptop monitor in real time. From the results of the Random Forest machine learning algorithm classification testing process, 1 unsuitable data was found from a total of 100 trials that have been carried out. Therefore, the Random Forest machine learning algorithm can be said to be successful in detecting air levels in the surrounding environment well because it provides an accuracy value of 99%.
Co-Authors Abdu Malikh Silaban Aisyah Aira Putri Maharani Elysa Nensy Irawan Estiko Rijanto Hadi Putri, Dewi Indriati Kai Shibuya Liptia Venica Muhamad Ajis Muhamad Fajar Imanul Haq Nguyen Hoang Minh Giang Shinta Rohmatika Kosmaga