Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Fuzzy logic: a novel approach to compound noun extraction
Get PDFCompound noun extraction from textual documents presents a unique challenge due to the inherent complexity and variability in linguistic structures. Traditional approaches often struggle to accurately capture the nuanced semantics of compound nouns, primarily due to their rigid reliance on exact matches. In response, this research underscores the pivotal role of fuzzy logic in addressing the challenges associated with ambiguity and imprecision within compound noun extraction. Leveraging the inherent flexibility of fuzzy logic, we propose a novel approach that surpasses the limitations of traditional methods. Our method embraces the adaptability of fuzzy logic, providing a powerful and context-aware solution for compound noun extraction. Empirical evaluation demonstrates superior performance, with a macro precision of 0.572, recall of 0.607, and F-measure of 0.589, compared to traditional approaches. By incorporating fuzzy logic, our approach excels in handling variations and uncertainties present in natural language, ultimately offering a more accurate and nuanced representation of compound nouns within textual documents. This research not only advances the field of compound noun extraction but also underscores the efficacy of fuzzy logic in overcoming challenges associated with linguistic intricacies in information extraction tasks
Enhancing solar panel efficiency through dual-axis tracking and fresnel lens concentration: an image processing approach
Get PDFSolar energy is currently utilized as an inexhaustible renewable energy source. Solar panels can convert solar energy into electrical energy that humans can use. The drawback of solar panels is that they cannot always be perpendicular to the sun, causing a decrease in the intensity of incoming light. Therefore, in this research, a solar tracking system with a fresnel lens was designed using image processing to increase the output of solar panels. In this research, programming was done using Python software for image processing using the hue, saturation, value (HSV) color, and space model, which was then connected with Arduino using the PyFirmata library to move the motor. In this research, solar panels with a fresnel lens and solar tracking were implemented. Data collection was performed on the output voltage of the solar panel. The research concludes that solar panels with solar tracker and fresnel lens have a higher average output voltage of 7.53 V than passive solar panels with an average output voltage of 6.38 V. Also, the average output voltage increased by 18.02% after implementing the solar tracking system and adding the fresnel lens
Arrhythmia classification using CMF-AFF based on electrocardiogram in field programmable gate array device
Get PDFArrhythmia classification is categorization of irregular heart rhythms depending on patterns detected in electrocardiogram (ECG) signals assist in treatment and diagnosis of cardiac conditions. ECG evaluates heart’s electrical activity to diagnose various heart conditions, but it is affected by interference or noise. ECG’s signal filtering is essential pre-processing stage that minimizes noise and highlights wave characteristics in ECG data. However, digital filters are normally constructed by multiplying coefficient and then multiplying value given as feedback which leads to more power and area consumption. To solve these issues, coefficient memory compression (CMC) technique is proposed with an adaptive FIR filter (AFF) to achieve low area and low power dissipation by compressing memory requirements in a field programmable gate array (FPGA). An adaptive FIR filter is employed to effectively minimize noise like baseline noise, muscle contraction noise, and low-frequency noise. The performance of CMC-AFF is analyzed in terms of look up table (LUT), register, digital signal processing (DSP), power, and global buffer (BufG). The proposed approach achieves a low power consumption of 0.012 W in Zed Board Zynq7000 AP system on chip (SoC) FPGA device compared to existing techniques like collateral and sequence approaches using Bartlet filter and low-power ECG processor using Bartlet filter respectively
Internet of things-based fuzzy controller for automatic irrigation and NPK nutrient monitoring of grapes
Get PDFGrape cultivation has gained increasing attention due to its short growing period and the high market value of its sweet, refreshing fruits. However, achieving optimal growth requires precise environmental and nutrient management, which can be challenging under conventional farming practices. This research aims to develop an automatic watering system that integrates soil moisture and nutrient monitoring to optimize grape cultivation. The system utilizes Nitrogen Phosphorus Potassium (NPK) sensors, soil moisture sensors, and a camera for growth observation, all connected through the internet of things (IoT) for remote monitoring via Android devices. A fuzzy logic controller is implemented to regulate watering duration based on environmental conditions such as temperature and humidity. Experimental results show that the system effectively adjusts watering duration to approximately six seconds when the temperature is between 25–32 °C and humidity is around 60%. The DS18B20 temperature sensor achieved an average error rate of only 0.12%, while the humidity sensor demonstrated 0.2% error, indicating high accuracy levels of 99.8%. Despite minor limitations related to internet stability and sensor calibration, the system demonstrates strong potential for commercial-scale smart farming applications, promoting resource-efficient and data-driven grape cultivation
Enabling SECS/GEM in legacy equipment: a proof of concept
Get PDFThe rapid adoption of Industry 4.0 (I4.0) has driven the need for automated machine-to-machine (M2M) communication in manufacturing. However, legacy equipment remains a challenge due to its incompatibility with modern protocols like semiconductor equipment and materials international (SEMI) equipment communication standard/generic equipment model (SECS/GEM). Replacing these machines is costly, making retrofitting a more viable solution. This paper proposes a modular automation software framework that enables SECS/GEM integration for legacy machines without extensive hardware modifications. The system is implemented using Raspberry Pi and Arduino, acting as an intermediary between legacy equipment and modern factory networks. The framework facilitates real-time data exchange, remote monitoring, and enhanced automation while ensuring scalability and cost-effectiveness. Experimental evaluation demonstrates improved interoperability and reduced manual intervention. This solution provides a practical and adaptable approach to integrating legacy systems into (I4.0) environments
3D mapping for unmanned aerial vehicle combining LiDAR and depth camera in indoor environments
Get PDFIndoor reconnaissance missions for unmanned aerial vehicles (UAVs) pose significant challenges in scene reconstruction, mapping, and environmental feature extraction. Relying on a single type of sensor often results in limited accuracy, increased susceptibility to environmental noise, and a lack of comprehensive spatial information. To address these issues, this study proposes a mapping method that combines light detection and ranging (LiDAR) and depth camera data. The method collects data from both LiDAR and a depth camera integrated on the UAV, then performs preprocessing on both data sources to construct local 3D maps using the real-time appearance-based mapping (RTAB-Map) algorithm. Subsequently, the local maps are merged using a filtering method to generate a detailed and complete global map. Real-time experiments conducted on Ubuntu 20.04 using the robot operating system (ROS) Noetic libraries demonstrate that this multi-sensor fusion approach provides richer and more comprehensive environmental information, thereby enhancing the effectiveness of mapping tasks in unknown indoor environments
An optimized deep learning framework based on LEE for real time student performance prediction in educational data
Get PDFPredicting student performance in real-time remains a critical challenge in educational data mining (EDM), especially with large, noisy, and high-dimensional datasets. This study proposes an advanced deep learning framework that integrates learning entropy estimation (LEE) with models such as support vector machines (SVM), you only look once (YOLO), recurrent convolutional neural networks (RCNN), and artificial neural networks (ANN) to enhance feature selection and classification accuracy. The framework follows a systematic pipeline involving data preprocessing, LEE-based feature extraction, and model training on a real-time academic dataset comprising student demographics, attendance, and performance metrics. Among the proposed models, the LEE-based YOLO (LBYOLO) achieved the highest testing accuracy of 93% and the fastest execution time of 1.84 seconds, while the LEE-based ANN (LBANN) demonstrated consistent performance across precision, recall, and F1-score. The results confirm the superiority of deep learning methods over traditional machine learning techniques for educational prediction tasks. This approach enables early detection of at-risk students and supports timely, data-driven educational interventions. Future work will focus on adaptive learning systems and multi-platform student behavior analysis to support personalized education strategies
Real-time vehicle detection and speed estimation system using Raspberry Pi and camera module
Get PDFIn the era of intelligent transportation systems, real-time vehicle detection and distance estimation play a crucial role in enhancing road safety and traffic efficiency. This study proposes a low-cost, real-time system that integrates you only look once–version 8 (YOLOv8)-based deep learning for vehicle detection with monocular vision techniques for distance estimation, implemented on a Raspberry Pi embedded platform. The objective is to provide a scalable, affordable solution for traffic monitoring and collision avoidance in resource-constrained environments. The methodology involves using a camera module connected to Raspberry Pi for live video capture, YOLOv8 for object detection, and a calibrated monocular distance estimation algorithm based on bounding box dimensions and known vehicle sizes. Experimental results show that the system achieves over 90% detection accuracy under standard lighting conditions and maintains a distance estimation error below 10% for vehicles within 15 meters. The model processes video frames in real time (~0.17 seconds per frame), proving its effectiveness for embedded deployment. In conclusion, the proposed system offers a robust, power-efficient alternative to high-cost light detection and ranging (LiDAR) or stereo vision systems. Its modular design supports future enhancements such as speed estimation or multi-camera integration, making it highly relevant for smart city applications and low-cost vehicular safety systems
Optimized electric vehicle charging: solar-driven wireless power transfer system
Get PDFWireless power transfer (WPT) is emerging as a transformative solution to overcome the limitations of conventional plug-in charging for electric vehicles (EVs). This study aims to design and implement an efficient and reliable wireless charging system using inductive coupling with low requirements on the primary circuit. The proposed system integrates an Arduino-controlled high-frequency converter along with sensors and relays to optimize power flow, ensure safety, and reduce energy wastage. The methodology involves experimental rearrangement of transformers and frequency elements to achieve maximum efficiency while maintaining compact circuit design. Results demonstrate that the system can achieve efficient energy transfer suitable for short charging intervals, particularly beneficial for shuttle buses at stations and rental taxis at parking hubs. The findings highlight that wireless charging not only reduces total charging time but also supports cost-effective battery sizing, enabling improved vehicle turnaround and operational efficiency. In conclusion, this work contributes a weather-resistant, safe, and economically viable charging approach that sets new standards for EV infrastructure. Its implications lie in redefining charging stations along predetermined routes and stops, ultimately advancing sustainable and user-friendly electric transportation
Equilibrium optimizer-based double integral sliding mode maximum power point tracking for wind energy
Get PDFWind energy is an effective renewable energy source. However, when it comes to harnessing its power because of its variability and nonlinearity, traditional controllers have limitations. This work proposes the design of two nonlinear maximum power point tracking (MPPT) methods to track the maximum power point for stochastic wind in the below-rated wind speed zone. These methods are the sliding mode controller (SMC) and the double integral sliding mode controller (DISMC). A benchmark model of a 4.8 MW wind turbine (WT) is subjected to random wind profiles in the MATLAB/Simulink environment. The equilibrium optimizer (EO) is used here and contrasted with particle swarm optimization (PSO) and grey wolf optimizer to achieve a good design of the controller in the sliding plane and change the switching control in sliding mode. The proposed optimization methodology and DISMC improved the smoothening of the control of angular speed, and specifically, the EO outperformed the rest of the techniques