Electronics and Informatics Journal

Development of an Energy Model-Based A-Star Algorithm for Energy Efficient Path Planning of Underwater Robots in Ship Hull Cleaning

Rajwa Umi Salsabila — 2026-01-31

This study presents the development of an energy-based A-Star algorithm for efficient path planning of underwater robots used in ship hull cleaning, motivated by the growing need for energy-efficient autonomous systems operating under complex hydrodynamic conditions such as fluid drag, pressure, and varying underwater currents. The proposed method integrates a physical energy consumption model into the conventional A-Star cost function and is evaluated through numerical simulations in a two-dimensional grid environment representing a ship hull surface, where key parameters including travel distance, drag force, and directional changes are considered to estimate total energy usage. The simulation results demonstrate that the proposed algorithm successfully generates collision-free paths with smoother and more stable trajectories compared to the conventional approach, with recorded energy consumption ranging from 88.73 to 115.99 joules across five scenarios and an average computation time of approximately 0.02 seconds. These findings indicate that incorporating hydrodynamic considerations significantly improves navigation performance while maintaining computational efficiency. In conclusion, the study confirms that the shortest geometric path is not always the most energy-efficient in underwater environments, and the proposed energy-based A-Star algorithm provides a realistic and practical framework for enhancing the sustainability and effectiveness of future autonomous ship hull cleaning systems.

Design and Simulation of an IoT-Based Library Noise Monitoring System Using ESP32 and ThingSpeak

Mutia Hikmah — 2026-01-31

This research details the creation and simulation of a noise monitoring system for libraries that is based on the Internet of Things (IoT), making use of an ESP32 microcontroller, a KY-037 sound detection device, the ThingSpeak cloud service, and a Mamdani fuzzy inference system. The main aim of this study is to constantly keep track of how loud it is and sort the levels into different noise conditions described in words, so that library supervisors can assess the acoustic setting and any possible disruptions in the areas where people read. In the designed system, the ESP32 acts as an IoT point that takes analog signals from the KY-037 sensor, changes these signals into decibel (dB) values, and sends the data to a safe ThingSpeak channel using a way of sending data that depends on events, which happens when noise levels go over certain set limits. Old noise data is taken out in CSV format and handled in MATLAB, where a Mamdani fuzzy model with three types of input (quiet, moderate, and noisy) and three levels of output (low, medium, and high) is put in place to make a noise index that goes from 0 to 100. The simulation results show that the ESP32–KY-037 setup sends noise data to ThingSpeak in a trustworthy manner without any breaks in communication, and the fuzzy output tracks the general pattern of the sensor data, giving a smoother way to sort noise. The suggested system can tell the difference between calm and potentially disruptive conditions, which backs up the idea of a smart library space with abilities for remote monitoring. This research shows that it is doable to put together ESP32, ThingSpeak, and fuzzy logic for noise monitoring that adjusts itself, and it lays the groundwork for future work that includes more sensor points and warning systems that work in real time.

Underwater Detection of Ship Hull Biofouling Using Computer Vision

Nabil Al Buqari Jufri — 2026-01-31

This study proposes a simulation-based approach for biofouling detection on ship hulls using YOLOv8-Nano. The integration of deep learning-based object detection for real-time biofouling detection demonstrates potential in reducing maintenance costs and improving ship performance. YOLOv8-Nano effectively detects biofouling organisms such as barnacles, mussels, and algae in underwater environments, even with challenges like varying visibility and object sizes. The research highlights the feasibility of using automated detection for biofouling management, offering a scalable solution compared to traditional methods like dry-docking and manual cleaning. However, the study is based on a simulated environment, and real-world testing is required to validate the system’s operational effectiveness. While the model performs well for larger organisms, challenges remain in detecting smaller or partially obscured biofouling due to environmental factors such as lighting and water clarity. The findings suggest future improvements, including enhancing model accuracy with multispectral imaging, refining the detection capabilities, and integrating AI-driven predictive analytics for proactive biofouling management. This work lays the foundation for the development of an efficient and scalable biofouling management system, contributing to sustainable maritime maintenance practices.

Classification of Shallot Leaf Health Based on RGB Images Using Machine Learning Algorithms

Fradilla — 2026-01-31

Agricultural productivity often declines due to plant diseases that reduce yield and quality. Shallot (Allium ascalonicum L.) is one of Indonesia’s key horticultural commodities, yet it is highly vulnerable to leaf diseases such as purple blotch and Fusarium-induced moler. This study aims to develop a shallot leaf health classification model using RGB images and machine learning algorithms. The proposed system employs an experimental approach based on a publicly available image dataset consisting of three categories: healthy, purple blotch, and moler-infected leaves. Preprocessing stages include image resizing, noise reduction, and contrast enhancement to improve visual clarity. Feature extraction combines RGB color histograms and Gray-Level Co-occurrence Matrix (GLCM) texture descriptors to obtain informative features. Two algorithms Support Vector Machine (SVM) and Random Forest (RF) were trained and evaluated using accuracy, precision, recall, and F1-score metrics. The results show that both models achieved perfect classification performance, with RF demonstrating slightly higher stability and robustness. These findings confirm that the integration of RGB imagery and lightweight machine learning algorithms provides a reliable, low-cost, and computationally efficient solution for early detection of shallot leaf diseases. The proposed approach contributes to precision agriculture development and offers potential deployment for smallholder farmers through simple, camera-based monitoring systems.

Design and Implementation of an IoT-Based Roadside Air Quality Monitoring System Using ESP32 Multi-Sensor and Mamdani Fuzzy Logic Integrated with Blynk

Dessy Dwi Sulistiyawati — 2026-01-31

Increased volume of road transportation can worsen air quality and negatively impact the health of road users. The project aims to develop and implement a highway air quality monitoring system that leverages the Internet of Things (IoT), with multi-sensor integration and Mamdani's fuzzy logic for air quality evaluation. The system consists of an ESP32 microcontroller integrated with a BME280 sensor to measure temperature, humidity, and pressure, an MQ-135 sensor to detect gaseous pollutants, and a GP2Y1010AU0F dust sensor to assess particle concentration. Sensor data is sent in real-time to Blynk's IoT platform over Wi-Fi and displayed as numerical values, graphs, and time-series graphs. Gas and dust measurements are further processed through Mamdani's fuzzy logic system to generate a Fuzzy Air Quality (Fuzzy AQ) score, which ranges from 0 to 100 and is categorized into three levels: low, medium, and high. The experimental results showed that the system could consistently monitor air quality parameters and present up-to-date air quality status through the Blynk app, with fuzzy outputs that correspond to sensor fluctuations and open up opportunities for expansion to other roadside monitoring locations in the future.