Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
A guide for selection of wireless communication technology for effective and robust early forest fire detection system
Get PDFThe world is facing a major ecosystem crisis due to global warming and pollution. Considering the rate at which the temperatures are rising, one must think about the causes and origins of this extreme environmental shift. Today, countries like India, have cities ranked as some of the most polluted cities in the world. Apart from vehicular traffic and industrial wastes, one of the prime components of the entire problem is forest fires. Burning forests emit tons of harmful gases into the atmosphere. This disaster also leaves drastic aftereffects on the economy and society. Therefore, an efficient system should be designed to monitor the forest fires at the earliest. Highlighting the role of wireless sensor networks in the irregular terrains of forests and considering the technical challenges, it is important to identify, first, the best technology for communication among sensors, in such complex terrains. Second, the identification of an optimization algorithm for the deployment of sensors to achieve maximum coverage This work presents an analysis of state-of-the-art wireless sensor networks to identify a reliable communication technique. Further an optimization algorithm is proposed for maximum coverage with a minimum number of sensors. The algorithm outperforms the other state-of-the-art algorithms in simulation results
SentimentLP: unveiling advanced sentiment analysis through Leptotila optimization-based gradient boosting machines
Get PDFSentiment analysis is pivotal in extracting insights from textual data, enabling organizations to understand customer opinions, market trends, and brand perception. This study introduces a novel approach, SentimentLP, which integrates Leptotila optimization (LPO) with gradient boosting machines (GBM) for sentiment analysis tasks. The proposed framework leverages LPO’s dynamic optimization capabilities to enhance GBM models’ performance in sentiment classification. Through iterative refinement and adaptive learning, SentimentLP optimizes feature extraction, model training, and ensemble learning processes, improving sentiment analysis accuracy and efficiency. Results from various evaluation metrics, including precision, recall, classification accuracy, and F-measure, demonstrate the effectiveness of SentimentLP in accurately capturing sentiment expressions in text data. Additionally, the fusion of LPO with GBM ensures scalability, adaptability, and interpretability of sentiment analysis models, making SentimentLP a valuable tool for extracting actionable insights from textual data across diverse domains and applications
A stochastic optimization called split-compete optimization and its utilization on economic load dispatch problem
Get PDFThe economic load dispatch (ELD) problem is one crucial optimization problem in a power system. Metaheuristics has become a standard method to tackle this problem. Ironically, ELD is not popular enough to become a constrained use case in most studies introducing new metaheuristics, where four designs in mechanical engineering have become the most popular ones. This work introduced a new metaheuristic called split-compete optimization (SCO). It contains three serial steps where two directed searches are employed and competed against each other in each step. SCO is then assessed to tackle both unconstrained and constrained problems where 23 classic functions represent the unconstrained problems and two cases in ELD problems represent the constrained ones. Five new metaheuristics are chosen as competitors, including the coati optimization algorithm (COA), language education optimization (LEO), northern goshawk optimization (NGO), Kookaburra optimization algorithm (KOA), and walrus optimization algorithm (WaOA). In the first evaluation, SCO is superior enough by being better than COA, LEO, NGO, KOA, and WaOA in 14, 13, 20, 15, and 10 functions, whereas SCO is dominant in high-dimensional functions. Meanwhile, SCO is competitive in solving both cases of ELD problems
Design and implementation of linear quadratic regulator control for two-wheeled self-balancing robot
Get PDFThis research aimed to develop a control system for a self-balancing robot (SBR) based on the mathematical model of an inverted pendulum on a two-wheeled cart. The linear quadratic regulator (LQR) control was implemented to maintain the SBR’s balance under normal conditions. A linearization approach was used to convert the dynamic model into a linear form, enabling the application of LQR. Testing was conducted through simulations and a physical SBR prototype equipped with an MPU6050 sensor and NEMA 17 motor. The test results demonstrated the effectiveness of the LQR control in maintaining the SBR’s balance and its responsiveness to disturbances. Although there are differences between the simulations and physical implementation, the system successfully maintained the SBR’s balance. In conclusion, the use of the inverted pendulum mathematical model and the implementation of LQR control successfully produced a stable and effective control system for SBR balance. By testing various values of the LQR parameters, optimal robot control parameters can be obtained
Determination analysis of main dimensions of induction motors for railway propulsion system
Get PDFInduction motors are used in industrial production processes. As for its use as a traction motor, it requires special design and manufacture. The type of induction motor that is widely chosen as a traction motor for railways is a squirrel-cage three-phase induction motor. The main consideration for the selection or design of an induction motor as a railway traction motor is the torque requirement to drive the train. Other parameters that are considered in the selection of an induction motor as a traction motor include available spaces for installation. This research is using a three-phase, 2,300 VAC, 480 kW, and 50 Hz induction motor. By using the application program for determining the parameters of the induction motor, it shows that the motor produces a moderate output coefficient (between maximum and minimum) and produces a torque greater than induction motor torque in general. As a result of the analysis, this induction motor is suitable to be used as a motor for the railway, where greater torque is required
Hybrid image encryption using quantum bit-plane scrambling and discrete wavelet transform
Get PDFDigital image security is increasingly vulnerable to sophisticated attacks, underscoring the urgent need for robust encryption techniques. Traditional encryption methods often fall short in defending against advanced threats, highlighting the importance of innovative solutions to protect digital images. This study tackles these challenges by incorporating quantum computing into image encryption, employing techniques such as bit-plane scrambling, pixel permutation, and bit permutation. These strategies enhance security by introducing complex, non-linear transformations that make decryption attempts significantly more difficult without the correct cryptographic keys. A key configuration based on r=44, μ=2024 is employed to achieve this. The integration of quantum bit-plane scrambling and quantum pixel permutation results in a highly secure encryption method. Experimental results show substantial improvements in entropy levels, along with strong unified average changing intensity (UACI) and number of pixels change rate(NPCR) values across various images. Notably, the "Peppers" image achieved the best performance, with UACI values of 33.5572 and NPCR values of 99.8301. The method proves highly effective, as repeated tests with incorrect keys failed to decrypt the plain image accurately. Future research could explore the addition of a discrete quantum wavelet transform to further enhance the security and efficiency of quantum-based image encryption methods
Non-fungible token modeling: the enthusiasm of music fans for the digital-collectible revolution
Get PDFBlockchain technology has become a major focus in data security and reliability. A foundation for innovations such as non-fungible token (NFT), which opens up new opportunities in managing ownership of digital assets. We investigate NFTs in the form of voice, which is digital audio communication. During the COVID-19 pandemic, podcasts have been rampant, creating new business opportunities in digital media such as NFTs, which have explored and evolved in various markets; voice content has gained significant space in sales, promotion, and dissemination/innovation. This research presents a comprehensive analysis of NFTs from 2019 to 2022, focusing on the variable association consisting of the NFT category, the price of each of those NFT categories, NFT editions, and NFT marketplace. We used structural equation modeling (SEM) to clarify the relationship in partial least squares structural equation modeling (PLS-SEM). This study’s findings suggest that music enthusiasts seek NFTs based on the NFT category. Therefore, it is crucial for NFT creators, who are musicians too, to exercise caution when choosing the NFT category that is most popular among music enthusiasts. We suggest that the musicians creating NFTs should consider establishing appealing NFT categories to attract music fans and other collectors
A method for brand image recognition for ordering payment in supermarket
Get PDFThis paper presents a product brand recognition method based on the YOLOv8 algorithm. The performance evaluation of the proposed method is conducted on two datasets consisting of GroZi-120 and GroZi-3.2K. The results show that the proposed method can achieve high accuracy. The precision and F1-score on the GroZi-120 and GroZi-3.2K datasets reach of {74.77%, 80%} and {99.86%, 100%}, respectively. The comparison with previous studies shows that the precision and F1-score obtained by the YOLOv8 method outperform some previous studies. Additionally, the effectiveness of the proposed method is also evaluated on a dataset of 6,170 images for twelve real products collected from supermarkets for use in order payment. The results show that the proposed method can be applied in single-order payment as well as multiple simultaneous orders with high accuracy in product recognition ranging from 94% to 98%. Therefore, the proposed method can be applied in order quick payment at supermarkets
A smart ontology based model to optimize crop decision support
Get PDFEffective crop recommendation systems are crucial for modern agriculture, yet existing models often struggle to adapt to dynamic environmental conditions and incorporate expert knowledge. This paper proposed a novel model that fuses decision tree (DT) algorithms with ontologies, combining robust data analysis with semantic knowledge representation. DT provide transparent, adaptable decision rules that respond to changing environmental factors, while ontologies structure domain expertise to enable deeper reasoning and improve accuracy. This integrated approach achieved a remarkable 99.77% accuracy on an Indian crop recommendation dataset, significantly outperforming previous methods. By merging the strengths of DT and ontologies, this model offers a powerful, adaptable tool for informed decision-making, supporting farmers in today's complex agricultural landscape
Drone-based high-resolution air pollution monitoring: a comprehensive system and field evaluation
Get PDFThis paper presents a novel air pollution monitoring system designed for drone deployment, featuring a specialized payload comprising sensor suites and processing components. The upper half of the payload accommodates MQ series sensors and an SDS011 particulate matter (PM) sensor, strategically positioned to provide comprehensive coverage of various air pollutants. Processing boards, including an Arduino and ESP8266 node micro controller unit (NodeMCU), facilitate data collection, transmission, and connectivity to a designated cloud platform for real-time monitoring and analysis. Additionally, the payload incorporates air pumps for pollution mitigation and relay modules for remote control. Field tests conducted in suburban and industrial areas evaluated the system's efficacy in capturing subtle air quality variations and responding to pollution spikes. Analysis of ground-level and airborne data provided insights into sensor performance and system adaptability across diverse environments. Overall, the proposed system demonstrates promising potential as a comprehensive solution for high-resolution air pollution monitoring, with implications for enhancing public health interventions and environmental management strategies