Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Innovative smart showcase design for indoors and eco-friendly hydroponics
Get PDFHydroponics is a unique and fascinating farming technique for producing plants and vegetables. Without having to use a large area of land, people can easily apply the technique to produce fresh and hygienic vegetables. However, the technique cannot be used in apartment environment due to the limited sunlight. Thus, this study introduces an innovative hydroponic system, called as hydroponics smart showcase system that can be implemented indoors, even in the presence of minimal sunlight, and can be monitored online by users. The proposed system consists of a net pot of 4-5 hydroponics cups with a diameter of 50 mm, air temperature and humidity sensors, water level sensors, ultraviolet (UV) lights, indicator displays, and DC fans. Experimental results show that the development of innovative hydroponics using smart showcase has succeeded in stabilizing the air in the showcase according to the specified references. Moreover, UV light intensity settings for photosynthesis can be applied remotely with duration of 24 hours
Automatic urinary bladder detection from medical computed tomography scans using convolutional neural network
Get PDFThis paper introduces a system for detecting and evaluating an algorithm that segments the urinary bladder in medical images obtained from contrast-less computed tomography (CT) scans of patients with bladder tumors. Multiple segmentation methods are needed in situations where tumors in the bladder cause structural changes that appear as irregularities in images, complicating the slicing process. The segmentation process begins with viewing the urinary bladder DICOM in three different perspectives, and then enhancing the image to expand the dataset. Next, the areas of the urinary bladder are pinpointed, with the urinary bladder dataset being split into 70% for training and 30% for testing to distinguish it from the nearby tissues, organs, and bones. The suggested system was evaluated on eight 3D CT images obtained from the cancer imaging archive (TCIA). Results from the experiment show that the designed system is effective in identifying and delineating the urinary bladder
Driving behavior analytics: an intelligent system based on machine learning and data mining techniques
Get PDFOne of the most common causes of road accidents is driver behavior. To reduce abnormal driver behavior, it must be detected early on. Previous research has demonstrated that behavioral and physiological indicators affect drivers' performance. The goal of this study is to consider the feasibility of classifying driver behavior as either aggressive (sudden left or right turns, accelerating and braking), normal (average driving events) or slow (keeping a lower-than-average speed). Innovation in data mining and machine learning (ML) has allowed for the creation of powerful prediction tools. ML techniques have shown potential in predicting driver behavior, with classification being a critical study area. The data set was gathered using the Kaggle platform. This study classifies driver behavior using Orange3 data mining tools and tests several classifiers, including AdaBoost, CN2 rule inducer, and random forest (RF) classifiers. The results showed that AdaBoost was superior in predicting driver behavior, with 100% accuracy, while the classification accuracy in CN2 rule inducer and RF was 99.8% and 95.4%, respectively. These results demonstrate the possibility of early and highly accurate driver behavior prediction and use it to create a ML-based driver behavior detection system
Automatic drowsiness detection system to reduce road accident risks
Get PDFDrowsy driving poses a significant risk to road safety, often equated with impaired driving due to its detrimental effects on cognitive function. This study presents a real-time drowsiness detection system utilizing the YOLOv5 algorithm, enhanced with contrast limited adaptive histogram equalization (CLAHE) technique, to improve detection in low-light conditions. The proposed method analyzes visual cues indicative of drowsiness, such as eye closure and head nodding, leveraging advanced computer vision techniques. A dataset was augmented from 1,056 original images to 2,112 images via CLAHE, resulting in significant improvements in model performance. Experimental results indicate that the model achieves a mean average precision (mAP) of 0.959, with precision and recall values of 0.9529 and 0.9528, respectively, underscoring the effectiveness of CLAHE in enhancing image quality and overall detection performance. The application developed from this model provides timely alerts to drivers, aiming to prevent accidents and promote road safety. This research contributes to the advancement of automated safety systems in vehicles, particularly under challenging lighting conditions
Exploration of digital image tampering detection using CNN with modified particle swarm optimization in deep learning
Get PDFThe field of image processing is crucial for many different applications, including forensic evidence, insurance claims, medical imaging, bioinformatics, artifact collection and more. In many sectors nowadays, digital photographs are regarded as a trustworthy source of information. The manipulation of such photographs leads to a variety of issues. The study presents a method using convolutional neural networks (CNN) combined with modified particle swarm optimization (MPSO) to improve the accuracy of tampering detection. This advancement contributes to improved reliability in fields requiring image authenticity verification, such as forensics and media. The design includes the collection of a dataset comprising both original and tampered images for training and testing the model. A dataset, such as the Media Integration and Communication Center (MICC) dataset, is utilized, which includes various images that have been altered through different tampering techniques. This dataset serves as the foundation for training the CNN and evaluating its performance The findings indicate that the proposed MPSO_CNN method outperforms traditional techniques in terms of precision, accuracy, recall, and F-measure, demonstrating its effectiveness in identifying tampered images. The results highlight the significance of using advanced deep learning techniques for reliable image authenticity verification
Hybrid ANN-PSO MPPT with high-gain boost converter for standalone photovoltaic systems
Get PDFStandalone photovoltaic (SPV) systems play a critical role in delivering clean energy to remote areas; however, maintaining consistent maximum power point tracking (MPPT) under dynamic environmental conditions remains a significant challenge. This paper proposes a hybrid artificial neural network–particle swarm optimization (ANN-PSO) based MPPT algorithm, integrated with a high-gain boost converter (HGBC), to overcome these limitations. The hybrid approach leverages the predictive capacity of ANN and the global optimization strength of PSO to achieve accurate and rapid tracking of the maximum power point under fluctuating irradiance. In addition, the high-gain converter improves voltage amplification and reduces power losses, improving overall system efficiency. The simulation results in MATLAB/Simulink confirm that the proposed system achieves a 99.7% tracking efficiency, faster convergence than conventional MPPT techniques, and significantly reduced power ripple. These results indicate that the proposed strategy can improve energy harvesting and operational stability in SPV applications. In addition, it offers a scalable and cost-effective solution suitable for off-grid electrification, particularly in rural and underdeveloped regions, contributing to global renewable energy goals
Linear algorithm for data retrieval performance optimization in self-encryption hybrid data centers
Get PDFContemporary data centers implement hybrid storage systems that consist of layers from solid-state drives (SSDs) and hard disk drives (HDDs). Due to their high data retrieval speed, SSDs layer is used to store important data blocks that have features like high frequency of access. To boost their security level, many of such systems implement self-encryption algorithms like advanced encryption standard (AES), Blowfish, and triple data encryption standard (3DES) with different key sizes that vary in their complexity and their decryption latency whenever a block is requested for read. Frequently accessed data blocks with increased decryption latencies are better to be migrated to the SSDs layer to decrease their retrieval latency. In this paper, we introduce a linear complexity algorithm hybrid self-encryption storage data migration (HSESM) that migrates important data blocks that requires long decryption latencies from the HDDs layer to the SSDs one. Performance evaluation shows that HSESM data migration process can reduce data blocks read latencies in 13.71%-23.61% under worst-case scenarios
Strategies, characteristics, and research gaps for improving microservices coupling design
Get PDFThe popularity of microservices architecture (MSA) has been pushed by the demand for scalable, maintainable, and efficient applications in the fastchanging digital ecosystem. The objective of this study is to determine strategies for improving service coupling in MSA, analyze the circumstances in which these strategies are successful, and recommend areas of research that need further development for future enhancements. We employed a systematic literature review (SLR) and the seven research gap methodology developed by Müller-Bloch and Kranz to pinpoint 10 essential strategies, such as API gateway and domain-driven design (DDD). The results of our study indicate that the effectiveness of each technique is contingent upon specific design criteria for the microservices, such as the presence of separate read and write operations for command query responsibility segregation (CQRS). To further enhance these techniques, it is crucial to address the research gaps that have been highlighted, particularly the lack of empirical studies on long-term repercussions. This study offers theoretical insights and practical assistance on how to improve the connection between services, thereby enabling the development of more resilient and easily maintainable applications based on MSA
A new deep learning approach for predicting high-frequency short-term cryptocurrency price
Get PDFCryptocurrencies are known for their volatility and instability, making them an attractive but risky investment for traders, analysts, and researchers. As the allure of Bitcoin (BTC) and other cryptocurrencies continues to grow, so does the interest in predicting their prices. To forecast the market rate and sustainability of cryptocurrencies, this study uses machine learning-based time series analysis. The study employs forecast periods ranging from 1 to 10-minutes to categorize the consistency of the market. High-frequency pricing of cryptocurrencies is anticipated with a timestep of up to 10 seconds using various deep learning (DL) models. A hybrid model combining long short-term memory (LSTM) and gated recurrent unit (GRU) is created and compared with standard LSTM and GRU models. Mean squared error (MSE) is the benchmark for estimating the models' performance. The study achieves better results than benchmark models, with MSE values for BTC, Cardano (ADA), and Cosmos (ATOM) in a 5-minute window size being 0.000192, 0.000414, and 0.000451, respectively, and for a 10-minute window size being 0.000212, 0.000197, and 0.000746. Compared to existing models, the suggested model offers a high price predicting accuracy. This study on crypto price prediction using machine learning applications is a preliminary investigation into the topic
Overcurrent effects on copper insulated PVC cables and fire resistance via thermal imaging and macrostructure analysis
Get PDFThis study investigates the effects of overcurrent on copper (Cu) insulated polyvinyl chloride (PVC) cables, focusing on their thermal behavior and fire resistance. We utilized thermal imaging, macrostructural analysis, and Joule heating calculations to evaluate six cable samples subjected to various currents. Results showed that with increasing current, the temperature of the cables rose significantly. For example, the CC0 sample, with no current, had a temperature of 36 °C, while the CC110 sample, subjected to 110 A, reached 1,091 °C. Joule heating calculations indicated energy values ranging from 0 J for the CC0 sample to 7,260,000 J for the CC110 sample. Physical observations included minor deformations at 253 °C and complete insulation loss at 1,091 °C. These findings emphasize the critical need for managing overcurrent to prevent severe cable damage and enhance system safety. This research provides practical insights for optimizing cable design and improving thermal management, offering valuable contributions to electrical engineering practices