Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Fuzzy Logic Based DTC Control of Synchronous Reluctance Motor
Get PDFThis paper presents the utilization of a fuzzy logic controller (FLC) within the speed control loop of the direct torque control (DTC) algorithm. The aim is to enhance the dynamic performance of a 3-phase synchronous reluctance motor (SynRM) in variable speed applications. The proposed FLC employs the speed error and change of speed error to generate the torque command signal needed for the torque hysteresis comparator within the DTC scheme. The system being analyzed comprises of a synchronous reluctance motor, voltage source converter and the proposed fuzzy logic-based DTC. In order to evaluate the performance of the proposed controller, a comprehensive system model is developed and simulated using MATLAB Simulink. The dynamic response of the entire system is investigated when subjected to various command speeds and loading conditions. It is found that the proposed controller achieves fast and precise dynamic response under all operating conditions. Furthermore, a comparative analysis is conducted between utilizing the FLC and the traditional proportional integral differential (PID) controller in the speed control loop of the DTC, the results demonstrate a significant improvement in the dynamic response when employing FLC compared to the traditional PID controller
Smart Security Solution for Market Shop Using IoT and Deep Learning
Get PDFNowadays, security system in the market shop is an immense concern everywhere. The modern world is leaning towards intelligent, automated security systems instead of the traditional human-based security or CCTV surveillance system because of their limitations. A typical CCTV surveillance system is not intelligent enough to detect intruders or fire. The proposed security system in this paper is an IoT, deep learning, and GSM based innovative security solution specially designed for shops and offices. The objectives of this system are to prevent burglary and fire. For this, the proposed model focuses on fire and intruder detection through both IoT and deep learning approaches. Several IoT sensors have been utilized with a deep learning model to detect fires in shops or offices at an initial stage. The model also utilizes a current sensor for identifying electrical short-circuit to prevent unexpected damages. This system further utilizes GSM technology to send the corresponding notifications to the authorized user and play alarm sounds at the shop as well as the owner's house while detecting suspicious occurrences. The proposed solution has used two pre-trained Convolutional Neural Network (CNN) architecture, namely ResNet50 and Inception V3. This research found an accuracy of 99.49% with ResNet50 architecture in fire detection
Summary on RoF Technologies, Modulations, and Optical Filters: Review
Get PDFIn order to meet the growing need for bandwidth, this article offers a thorough examination of Radio over Fibre (RoF) technology and its integration with wireless communication networks. It starts out by going over the development of wireless networks and the difficulties they encounter, like spectral congestion and RF spectrum operational constraints. An effective way to handle data traffic is to include optical fibre into wireless networks. A detailed analysis is conducted of the technical features of RoF systems, including modulation approaches such as external and direct modulation. While external modulation provides better performance by getting around constraints, direct modulation uses the RF signal to directly modify the brightness of the light source. It is detailed how optical filters, including Fabry-Perot, Fiber-Bragg Grating, and Tunable filters, are used in a variety of applications. They provide an explanation of their functions and importance in optical communication. In addition, a thorough review of relevant literature is included in the study, along with a summary of the main conclusions, approaches, goals, drawbacks, and achievements of academic studies on optical communication and RoF systems. This analysis focuses on the field's problems and achievements. In summary, RoF technology integration of optical and wireless networks holds enormous potential to satisfy the changing needs of high-capacity, high-speed wireless communication. In order to effectively utilise the potential of RoF systems and progress contemporary wireless networks, additional study and development work is yet required
Classification of Cardiovascular Disease Based on Lifestyle Using Random Forest and Logistic Regression Methods
Get PDFCardiovascular disease is a non-communicable disease caused by a disturbance in the function of the heart or blood vessels. According to WHO country profile data released in 2018 regarding non-communicable diseases, cardiovascular disease is the highest cause of death in Indonesia. This study aims to classify cardiovascular disease based on lifestyle using the Random Forest and Logistic Regression methods. In the classification process with the Random Forest and Logistic Regression machine learning methods, a combination of parameters from each machine learning method will be tested to see which parameter combination is the best for processing and classifying cardiovascular disease datasets. The dataset used in this research is obtained from Kaggle called Cardiovascular Disease. The dataset was processed through several pre-processing stages, namely missing value imputation, outlier detection, and extreme data checking. After going through the preprocessing process, the amount of data that entered the classification process was 62478 rows of data with 13 attributes or columns, namely age, height, weight, gender, systolic blood pressure, diastolic blood pressure, cholesterol, glucose, smoking, alcohol intake, physical activity, and cardiovascular disease. Dividing the dataset into different percentage distributions of training data and testing data was also tested to see the difference in classification performance of the two methods. The division of training data was 90% and testing data is 10%. The results obtained from this study were the Logistic Regression method had better accuracy results of 73.07% compared to Random Forest with an accuracy result of 71.87%
The Circulatory System in an Electromagnetic Field
Get PDFThe article deals with the interaction of two electromagnetic fields: the intrinsic electromagnetic field of the elements of circulatory system and the external electromagnetic field of environment. A model of the circulatory system is proposed that allows for a systematic assessment of the impact of electromagnetic fields on the cardiovascular system. The model is based on the biophysical and bioelectrical properties of the elements of the cardiovascular system and the central nervous system. The article considers issues related to the behavior of the vessels of the arterial part of the vascular bed: the capillary network, arterioles and large arteries in an electromagnetic field. The dynamics of myocardial behavior in two phases is clearly illustrated using a two-circuit electrical circuit. The change in the dynamics of the state of an elementary section of the vascular bed over time is estimated using a system of equations based on Hooke's law. The possible mechanism of human behavioral character in unfavorable environmental conditions is analyzed based on the principle of adequate design, which is presented in the diagram of the step-by-step impact of the external environment and its influence on the behavior of the cardiovascular system depending on the intensity of the impact
BERT-BiLSTM model for hierarchical Arabic text classification
Get PDFText classification is a fundamental task in natural language processing (NLP) aimed at categorizing text documents into predefined categories or labels. Leveraging artificial intelligence (AI) tools, particularly deep learning and machine learning, has significantly enhanced text classification capabilities. However, for the Arabic language, which lacks comprehensive resources in this domain, the challenge is even more pronounced. Hierarchical text classification, which organizes categories into a tree-like structure, presents added complexity due to inter-category similarities and connections across different levels. In addressing this challenge, we propose a deep learning model based on BERT (Bidirectional Encoder Representations from Transformers) and BiLSTM (Bidirectional Long Short-Term Memory). Experimental evaluations demonstrate the effectiveness of our approach compared to existing methods, yielding promising results. Our study contributes to advancing text classification methodologies, particularly in the context of Arabic language processing
Comparative Analysis of Hardware Performance for Linear Detection in a Massive MIMO System on FPGA Using the Vivado HLS Tool
No full textThis paper compares the performance of hardware implementation for linear detection in a massive MIMO system. The study focuses on Gram matrix inversion solved using two approaches: direct and indirect matrix inversion. Direct matrix inversion is represented by Cholesky Decomposition, while indirect matrix inversion is represented by the Neumann series and the Gauss-Seidel method. The algorithm for inversions, embedded in a C-based function, is virtually implemented on the FPGA using the Vivado HLS tool. The synthesis report categorizes the performance from the FPGA implementation into three parts: timing (ns), cycle latency, and resource utilization. With the same targeted time limit, indirect matrix inversion such as the Neumann series seems to be the fastest algorithm compared to the direct method due to the matrix-matrix multiplication approach. In terms of latency, NS requires more clock cycles to obtain the output compared to others. Based on the results, the direct inversion method exhibits higher complexity, particularly in timing for clock frequency and resource utilization needed to complete the inversio
Predictive Analysis of Learner’s Performance in Online Environments with LSTM and Attention Mechanism
Get PDFEarly identification and supporting at-risk learners is a key problem in digital learning environment. This paper investigates the use of deep learning methods, namely Long Short-Term Memory (LSTM) neurons with cognitive mechanisms to determine those learners that are most likely to be at risk based upon the involvement of the learners in periodic assessment as well as engagement with the learning components in online learning environments. It also accounts for the relevance of dependencies of temporal elements, which adds a degree of precision in forecasting. The findings show how advanced analysis of data can potentially improve student support strategies with online learning systems, thus ensuring the success and retention of learners in consequence. From the test, result yield information concerning the robustness of the LSTM model in predicting the learner's achievement and provides insight into factors that most importantly have an impact on prediction. That suggests the approach of LSTM with attention mechanism is effective to capture periodic behavior of the learner on virtual platforms and early predictions will be useful for administrators to design timely intervention and improve retention rates of learners
A Twelve-layer Deep Convolution Neural Network for Fast, Efficient and Reliable Identification and Classification of Plant Diseases in Smart Farming
Get PDFSmart farming that uses information and communication technology is developed as a critical technique to address the challenges related to agricultural production, environmental effects (climate change), food security, and supply chain. The recent statistics reveal that the world's population has been increased significantly, which is expected to reach 7.7 billion. It is essential to achieve a significant rise in food output to meet the requirement of such a massive growth of population. However, due to the natural conditions and a variety of plant illnesses, food productivity and farms are reduced. In order to diagnose food diseases in farming, new technologies like the Internet of Things and artificial intelligence are now essential. To this end, the research paper introduces a novel artificial intelligence model represented by a twelve-layer deep convolution neural network to identify and classify plant image diseases. 38 distinct types of plant leaf photos are used for training and testing the suggested model, which are obtained by adjusting different parameters such as (a) hyperparameters; (b) coevolutionary layers; (c) and pooling layers in number. The proposed model consists of an extractor and classifier of functions. The first section involves three phases, i.e., it consists of two convolution layers and a maximum pooling layer for each phase. The second section consists of three levels: flattening, hidden, and output layers. The proposed model is compared with LeNet, VGG16, AlexNet, and Inception v3, which are considered state-of-the-art pre-trained models. The results demonstrate that the accuracy of LeNet, VGG16, AlexNet, and Inception v3 is given as 89%, 93%, 96.11%, and 97.6%, respectively. The findings provided in this research show that the suggested model outperforms state-of-the-art models in terms of training speed and computing time. Also, the results show that the proposed model achieves a considerable improvement in terms of accuracy and the mean square error compared to the state-of-the-art methods. In particular, The outcomes demonstrate that the suggested model achieves a mean square error and prediction accuracy of 98.76% and 0.0580, respectively. The results also depict that the proposed model is more reliable, allows fast convergence time in obtaining the results, and requires only a small number of trained parameters to identify the plant diseases accurately
Deep Learning Techniques for Advanced Drone Detection Systems: A Comprehensive Review of Techniques, Challenges and Future Directions
Get PDFThe widespread use of Unmanned Aerial Vehicles (UAVs), commonly known as drones, across various sectors, such as civilian, commercial, and military operations, has created significant challenges in ensuring security, safety, and privacy. This paper provides a comprehensive review of the latest advancements in drone detection systems leveraging deep learning techniques, covering the period from 2020 to 2024. It critically evaluates both optical (visible light and thermal infrared) and non-optical (radio frequency, radar, and acoustic) detection methodologies. The analysis includes cutting-edge models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs), focusing on their application in drone detection. Key challenges like real-time processing, environmental interference, and differentiation between drones and similar objects are examined. Potential solutions, including sensor fusion, attention mechanisms, and the integration of emerging technologies such as the Internet of Things (IoT) and 5G networks, are discussed in detail. The paper concludes with future research directions to enhance drone detection systems' robustness, scalability, and accuracy, particularly in complex and dynamic environments. This review offers valuable insights for researchers and industry professionals working towards next-generation drone detection technologies