Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Development of frequency modulated continuous wave radar antenna to detect palm fruit ripeness
Get PDFOil palm fruits farmers in Indonesia have determined the ripeness of oil palm fruits in the traditional way, namely using human eye visuals, which have the weakness of inconsistent levels of accuracy and are prone to errors. The development of increasingly sophisticated technology will help oil palm fruits farmers recognize the characteristics of fruit maturity. Advanced technology, such as frequency modulated continuous wave (FMCW) radar, can assist farmers in accurately identifying fruit maturity. To ensure high accuracy and sensitivity, an antenna with low side lobe level (SLL), high gain, and wide bandwidth in the 23-26 GHz range is required. Using CST Microwave Studio 2023, a designed and simulated antenna achieved an SLL of 24 dB, a gain of 15 dBi, and a bandwidth of 2.5 GHz. These results indicate that higher gain enhances energy directionality and overall antenna performance. Additionally, a smaller angular value improves the antenna’s radiation focus, making it more effective for precision sensing in oil palm fruit ripeness detection
Breast cancer detection and classification using deep learning techniques based on ultrasound image
Get PDFBreast cancer ranks as the most prevalent form of cancer diagnosed in women. Diagnosis faces several challenges, such as changes in the size, shape, and appearance of the breast, dense breast tissue, and lumps or thickening, especially if present in only one breast. The major challenge in the deep learning (DL) diagnosis of breast cancer is its non-uniform shape, size, and position, particularly with malignant tumors. Researchers strive through computer-aided diagnosis (CAD) systems and other methods to assist in detecting and classifying tumor types. This work proposes a DL system for analyzing medical images that improves the accuracy of breast cancer detection and classification from ultrasound (US) images. It reaches an accuracy of 99.29%, exceeding previous work. First, image processing is applied to enhance the quality of input images. Second, image segmentation is performed using the U-Net architecture. Third, many features are extracted using Mobilenet. Finally, classification is performed using visual geometry group 16 (VGG16). The accuracy of detection and classification using the proposed system was evaluated
Public health challenges in the Cuzco region: a decade of anemia in vulnerable populations applying data mining
Get PDFThe objective of the research is to carry out an exhaustive analysis of anemia in the province of Cusco using the Rapid Miner Studio tool that allows an analysis of the number of most concurrent cases in each district of the province of Cusco. Different sources of information were consulted to take as a reference the impact of the disease in different parts of the world. Likewise, information was introduced about how information technologies manifest positive responses in certain diseases around the world. The knowledge discovery in databases (KDD) methodology was used, which consists of several phases proposed in the project, such as data selection, data preprocessing, data mining and evaluation of results. Consequently, this research will help to recognize the most abundant cases in the districts of the province of Cusco. The results obtained were that 348 confirmed cases of anemia occurred in the district of Espinar, being the most affected district. Finally, it was concluded that in different provinces, not only in Cusco, there is a high prevalence of the disease due to factors associated with its treatment
Enhancing 3D building visualization and real-time monitoring in construction through IFC and IoT integration
Get PDFThe integration of industry foundation classes (IFC) and internet of thing (IoT) addresses a key challenge in construction: real-time data visualization on specific building storeys. Traditional methods often struggle with data integration and timely monitoring. This study introduces a web-based platform that combines three-dimensional (3D) technology, IFC models, and IoT sensors to enhance visualization and monitoring in construction projects. Unlike prior approaches that focus on static visualization or lack real-time IoT integration, this platform delivers dynamic, storey -specific updates, enabling real-time monitoring of critical building parameters. A case study showed that file size significantly impacted loading speed, ranging from 0.17 kB/ms (97.3 kB model in 572 ms) to 11.72 kB/ms (7.2 MB model in 629 ms). Despite a slight drop in frame rate from 60 to 55 frames per second (FPS), the system maintained smooth user interactions. Memory usage increased from 180 MB to 314 MB to handle complex 3D models and IoT data in real time. These findings demonstrate that integrating IFC with IoT enhances data visualization, providing more efficient decision-making tools for construction stakeholders and improving on-site coordination and resource management
Comparison of multilayer perceptron and nonlinear autoregressive models for wind speed prediction
Get PDFWind energy is a critical component of the global shift to renewable energy sources, with significant growth driven by the need to reduce carbon emissions. Accurate wind speed prediction is crucial for increasing wind energy output since it directly influences wind farm design and performance. The purpose of this study is to compare two artificial neural network (ANN) models for predicting wind speed in Dakhla City, a place with a high wind energy potential. The first model is a multilayer perceptron (MLP) trained with the backpropagation algorithm, while the second is a nonlinear autoregressive with exogenous inputs (NARX) model, a form of recurrent neural network (RNN) noted for its ability to handle time-series data more well. The comparative analysis results show that the NARX model outperforms the MLP model in terms of wind speed forecast accuracy. The NARX model achieved a near-perfect regression coefficient (R) of 0.9998 and a root mean square error (RMSE) of 1.02899, indicating that it can represent complex, nonlinear wind speed patterns. These findings indicate that the NARX model could be a beneficial tool for increasing the efficiency of Dakhla City’s wind energy infrastructure, assisting the region in meeting its renewable energy ambitions
A systematic literature review to address overlapping laws in Indonesia
Get PDFThe vast number of laws often result in legal uncertainty due to overlapping, conflicting, and inconsistent regulations. Identifying and resolving these overlaps is essential for ensuring legal clarity and coherence. This systematic literature review (SLR) explores technologies that have the potential to address the issue of overlapping laws in Indonesia. This study reviews numerous works on knowledge graphs (KGs) and graph mining, focusing on their potential to automate the detection of overlapping laws, thereby streamlining the process of legal harmonization. The review identifies several key research opportunities, such as refining KG construction, exploring semantic similarity measures, enhancing the interlinking of legal information, and ensuring explainability and interpretability. These opportunities promise to enhance the efficiency and effectiveness of detecting overlapping laws and contribute to a more consistent legal system in Indonesia
Metaheuristic algorithm for optimal allocation of electric vehicles and photovoltaics in distribution grid
Get PDFSince electric vehicles (EVs) emit less carbon dioxide, their number is rapidly increasing. As the number of EVs grow, these added loads strain the distribution grid, introducing new challenges. Key concerns for network operators include voltage fluctuations and increased power losses. Properly deploying throughout the grid, photovoltaic (PV) systems and electric vehicle charging stations (EVCS) can assist in lowering power losses and improving the bus voltage profile. A MATLAB implementation of the metaheuristic algorithm called Harris Hawk optimization (HHO) algorithm is developed to select the best locations for integrating EVCSs and PVs, with the goals of enhancing the voltage profile and reducing power losses across buses. IEEE 12-bus and 14-bus systems and real-time distribution grid data were used to test the method. For the 26-bus real-time system, the results demonstrated a notable 24% decrease in overall power loss as compared to the base case and improved voltage regulation, as indicated by a lower average voltage deviation index (AVDI) value of 0.0929. A comparative analysis was performed between optimized and random placements of EVCSs and PVs, as well as against the grey wolf optimization (GWO) algorithm. The results provide a framework for implementing solar-powered EV charging infrastructure. This can reduce costs, enhance energy reliability, and contribute to a cleaner environment
New model for emotion detecting from French text using bidirectional long short-term memory
Get PDFDue to the fast growth of social networks, humans have transformed from being general users to creators of network information’s by providing reviews, evaluations, and thoughts on social websites expressing their feelings on various topics. Recently, feedback analysis has become important not only for business owners to improve their products based on user feedback, but also for users to help them select the most suitable products by benefiting from other's experiences. Extracting and identifying human emotional states such as happiness, anger, and worry in texts are targets of emotion analysis due to their importance in providing suggestions for companies and users according to their needs. Although, there has been a lot of work on emotion detection in English text, there is currently lack of research on French text that is because of not existing of French emotion dataset. This paper presents an emotion detection model that integrates the Camembert tokenizer with bidirectional long short-term memory (Bi-LSTM) for emotion detection in French text. The proposed model is trained and validated using a dataset that has been annotated for emotions in French. The proposed model achieved accuracy and an F1-score of 98.66% and 98.66%, respectively, outperforming previous work by 26.36%
PMU-data assisted state estimation of distribution network with integrated renewables: a comprehensive review
Get PDFThe variability and distributed nature of renewable energy sources (RES) pose challenges to real-time monitoring and control in distribution networks. Phasor measurement units (PMUs) provide high-precision, time-synchronized measurements, significantly improving state estimation (SE) accuracy in complex grids. This paper reviews SE in distribution systems using PMU data, focusing on challenges introduced by high-RES integration. Traditional techniques, such as weighted least squares (WLS), are analyzed, revealing limitations like reduced observability and accuracy due to RES intermittency. To address these challenges, advanced methods such as robust optimization, dynamic network reconfiguration, and decentralized control are explored, showing improved network reliability and adaptability under RES variability. Furthermore, innovative approaches like Bayesian non-parametric modelling are discussed, offering solutions to mitigate uncertainties and enhance grid flexibility. Case studies highlight the scalability and effectiveness of PMUs in extensive networks, showcasing their role in improving both SE precision and system stability. These findings underline the critical need for precise and integrated SE techniques to develop resilient, adaptable smart grids capable of accommodating the increasing penetration of RES, setting a foundation for future technological advancements
Revving up insights: machine learning-based classification of OBD II data and driving behavior analysis using g-force metrics
Get PDFThis research work uses machine learning (ML) approaches to classify on-board diagnostics II (OBD II) data and g-force measures to provide a thorough analysis of driving behavior. The research paper effectively demonstrates the classification of driving behaviours using OBD II and g-force data. Driving behaviours are analyzed by using ML algorithms such as random forest (RF), AdaBoost, and K-nearest neighbors (KNN). The analysis goes beyond a summary by discussing how OBD II data, g-force metrics, and the algorithms interrelate to classify ten distinct driving behaviors (e.g., weaving, swerving, and sideslipping). The RF classifier achieved the highest accuracy, which reinforces the strength of the chosen models. The inclusion of comparisons with other techniques supports arguments about the model's performance. The related works section connects the references to the central topic by highlighting prior approaches and research studies related to OBD II and driver behaviour analysis. The goals of this study are improving the accuracy of driving behaviour classification, with implications for traffic safety, driver education, and insurance sectors