Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Fuzzy logic control of a hybrid PV/battery/diesel generator system integrated in an electrical network: case study of City of Douala
Get PDFThe control of hybrid systems is a considerable challenge for the energy supply to consumers. For this purpose, this study implemented an intelligent control for a hybrid system connected to the electrical grid to meet the energy demand of a building in the city of Douala, Cameroon. In this work, an intelligent management system using fuzzy logic is proposed to overcome the challenges of this multi-source integration. The proposed method based on a fuzzy logic controller makes it possible to optimize the performance of the energy sources used with a coordination system. Thus, it makes it possible to adjust in real time the system control process based on climatic conditions and the characteristics of the storage devices in order to provide an adequate adaptive control strategy. Furthermore, this system effectively balances the energy supply from all sources. MATLAB/Simulink software and real building data are used to simulate the proposed intelligent management strategy. The results obtained indicate that energy is efficiently supplied to consumers with efficiency of 98% and reduction of fuel consumption of 45% based on the availability of the sources, thus demonstrating the benefits of the control strategy based on fuzzy logic for balanced system operation
Efficient lung disease detection using a hybrid vision transformer and YOLO framework with transfer learning
Get PDFLung diseases are among the most important causes of morbidity and mortality worldwide; it require prompt and accurate diagnosis methods. A novel hybrid deep learning framework for integrating you only look once version 8 (YOLOv8), considering real-time detection and vision transformer (ViT-B/16) for global context-based classification of lung diseases in chest X-ray images, is presented. Based on transfer learning and a two-stage detection-classification pipeline, this proposed model is applicable to dealing with inter-image variability, overlapped disease features and lack of annotated medical examples. Our developed hybrid model achieves the highest classification accuracy of 96.8% and 0.98 AUC-ROC on the National Institutes of Health (NIH) Chest X-ray dataset, which consists of over 112,000 images covering 14 diseases, and outperforms its several current state-of-the-art models. In addition, attention heatmaps and bounding box visualizations highly correlate with clinical variables and enhance interpretability. This paper demonstrates the practicability of hybrid vision driven architectures for better medical image analysis and shows their integration into clinical decision-support systems
Optimizing social issue sentiment analysis with hybrid Chi-square and bayesian-optimized binary coordinate ascent
Get PDFFeature selection aims to reduce the dimensionality of the feature space and prevent overfitting. However, when striving to produce accurate models for sentiment classification, feature selection introduces several challenges, particularly concerning textual content. Consequently, many researchers are exploring hybrid feature selection methods to customize the selection process and develop more advanced automated techniques, recognizing that the performance of these methods depends on hyperparameters. Integrating Bayesian Optimization into binary coordinate ascent (BCA) enhances the search for optimal solutions and improves classification performance in sentiment analysis, explicitly focusing on classifying abortion sentiment using Naïve Bayes. The effectiveness of combining Chi2 feature selection with the hybridized BCA and Bayesian Optimization approach is tested across multiple n-gram configurations. Results demonstrate significant improvements in accuracy and recall compared to Chi2 and BCA hybrid methods. For instance, the Bayesian Optimization-enhanced approach achieved up to 93.80% accuracy (1-gram) and 100% recall (4-gram), outperforming the baseline method. The study highlights trade-offs between computational efficiency and performance, noting that while the Chi2 and BCA hybrid method has lower training time complexity, the Bayesian Optimization-enhanced method excels in accuracy and recall during testing. The findings suggest that integrating Bayesian Optimization into feature selection improves sentiment classification performance and recommend further exploration of this approach with other classification algorithms, especially for social issues like abortion sentiment analysis
Dynamic driver of digital devices for embedded systems design
Get PDFA wide-ranging exploration of the diverse applications of embedded systems (ES) is delved in in this study, tracing their evolution from early industrial control to their current pervasive influence on modern technological landscapes. The study underscores their crucial role in various sectors, including consumer electronics, automotive technology, medical and healthcare, education and research, industrial automation, telecommunications, smart cities, edge computing, and the convergence of 5G and artificial intelligence (AI). It accentuates the versatility and transformative potential of ES. The paper reviews the historical, current, and future contributions and evolution of ES in shaping contemporary technological landscapes. Emphasizing the broad impact of ES, the paper highlights their significance for researchers, practitioners, and enthusiasts navigating the dynamic intersection of technology and diverse disciplines
A novel hybrid model for sentiment analysis in MOOC forums with hybrid word and character-level neural networks
Get PDFSentiment analysis is crucial, in the field of natural language processing (NLP). Has applications in different areas. This study focuses on analyzing sentiments in massive open online course (MOOC) forums highlighting its importance in understanding how users interact and shaping educational strategies. The study presents a novel hybrid neural network model specifically tailored for sentiment analysis in MOOC forums. This innovative model combines word level and character level embeddings to handle the linguistic expressions commonly found in this context. The model architecture integrates bidirectional long short-term memory (BiLSTM) layers for word level embeddings and convolutional neural networks (CNNs) for character level embeddings aiming to harness the strengths of both types of embeddings for a view of the linguistic used in MOOC forum posts. Notably this model achieves an accuracy rate of 93.11% showcasing its effectiveness, in sentiment analysis within MOOC forums. This research contributes to sentiment analysis within the context of online education
Predicting student status using machine learning by analyzing classroom behaviors with X-API data
Get PDFWe explore the emergence and growing significance of educational data mining, a field dedicated to extracting valuable insights from vast datasets gathered from diverse educational environments. Utilizing the experience API (XAPI) and the Kalboard 360 online learning platform, our research presents a novel behaviorally based student performance model that evaluates the influence of student interactions on academic results. We create reliable models for precisely projecting academic success by utilizing machine learning techniques including logistic regression, k-nearest neighbors (KNNs), support vector machines (SVM), decision trees, random forests (RF), and XGBoost. The outcomes show a notable increase in categorization accuracy. Through the personalization of instruction, formative assessment support, and proactive identification of each student's unique needs to maximize their learning experience, this approach holds the potential to improve educational processes
Clustering and routing using spiral exploration mechanism with honey badger optimization in wireless sensor network
Get PDFWireless sensor network (WSN) contains a huge number of spatially distributed sensor nodes that are connected by wireless to monitor and record information from the environment. The WSN nodes are battery-powered, thus reducing energy after a certain period which affects the network lifetime. To overcome this issue, this research proposed a spiral exploration mechanism with honey badger optimization (SEM-HBO) for cluster head (CH) and route path selection in WSN. The objective of this research is to reduce energy consumption and enhance network lifespan in WSN. The distance, communication cost, residual energy and cluster density are considered as fitness functions for selecting CH and route path in WSN. Through the SEM-HBO search behavior, it explores different routes and recognizes best one for reducing energy consumption and delays thereby enhancing network lifetime. The SEM-HBO performance is calculated based on packet delivery ratio (PDR), delay, energy consumption (EC), network lifetime (NL), and throughput for 100-500 nodes. The SEM-HBO performance is efficient and it achieves 99.62% and 99.59% of PDR for 100 and 200 nodes when compared to harmony search algorithm and competitive swarm optimization (HSA-CSO)
Fake review detection using enhanced ensemble support vector machine system on e-commerce platform
Get PDFDue to the quick growth of online marketing transactions, including buying and selling, fake reviews are created to promote the product market and mislead new customers. E-commerce customers can post reviews and comments on the goods or services they obtained. Before making a purchase, new customers frequently read the feedback and comments posted on the website. Nowadays customers find it very difficult to identify whether the reviews are fake or not, but doing so is essential. So, it's very crucial to develop an online spam detection system to help both consumers and producers in their decision-making. The reviewer's behaviour and important review characteristics can help you identify fake reviews. The importance of this study is to develop a fake review detection system on e-commerce platforms using an enhanced ensemble support vector machine system in which the Euclidean distance is replaced with the Mahalanobis distance metric. Review texts collected from Amazon and Yelp were given as input data sets into the constructed model and classified as fake or real
Utilizing logistic regression in machine learning for categorizing social media advertisement
Get PDFThe purpose of this paper is to investigate the use of logistic regression in machine learning to distinguish the types of social media advertisements. Since the logistic regression algorithm is designed to classify data with a target variable that has categorical results, it is the one selected. As a result, this research intends to measure the efficiency of logistic regression for the classification of social media advertisements. This research centers on the social media advertisements dataset and employs logistic regression for classification purposes. The model is evaluated against performance metrics to measure the extent to which it can categorize social media advertisements. As a result, the findings of this study show that logistic regression is fit for classifying social media advertisements. Logistic regression is important for machine learning when it comes to classifying social media advertisements because it supports categorizing advertisements according to their characteristics and precisely predicts the categorical results
Mobile application for distributing information to students at the Sciences and Humanities University
Get PDFCurrently, educational institutions around the world have implemented many standards and rules to ensure teaching quality. Many of these standards and rules are related to the use of technologies that provide students with services and facilities to learn. However, in Peru, a Latin American country, these standards and rules have been recently implemented, and as a result, information systems are required to guarantee teaching quality. This research exposes the implementation of a mobile application for distributing and managing information for students and teachers who require data about courses, grades, absences, and receive news about important university announcements. This work applied both research methods and Scrum methodologies together to demonstrate how the education process benefits from the use of technologies. As a result of these implementations, processes like finding academic information improved by an average of 50%. These results support that the implementation of mobile application technologies in educational environments is beneficial for guaranteeing process improvement and teaching quality