Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Hydrophobicity signal analysis for robust SARS-CoV-2 classification
Get PDFRapid and accurate classification of viral pathogens is critical for effective public health interventions. This study introduces a novel approach using convolutional neural networks (CNN) to classify SARS-CoV-2 and non-SARS-CoV-2 viruses via hydrophobicity signal derived from DNA sequences. Conventional machine learning methods grapple with the variability of viral genetic material, requiring fixed-length sequences and extensive preprocessing. The proposed method transforms genetic sequences into image-based representations, enabling CNNs to handle complexity and variability without these constraints. The dataset includes 8,143 DNA sequences from seven coronaviruses, translated into amino acid sequences and evaluated for hydrophobicity. Experimental results demonstrate that the CNN model achieves superior performance, with an accuracy of over 99.84% in the classification task. The model also performs well with extended sequence lengths, showcasing robustness and adaptability. Compared to previous studies, this method offers higher accuracy and computational efficiency, providing a reliable solution for rapid virus detection with potential applications in bioinformatics and clinical settings
Efficient deep learning approach for brain tumor detection and segmentation based on advanced CNN and U-Net
Get PDFIn this paper, we propose an innovative deep learning methodology dedicated to tumor detection and segmentation in medical images using convolutional neural networks (CNNs) and the U-Net architecture. The study emphasizes the importance of improving the quality and relevance of these features by employing advanced preprocessing methods. The subsequent development involves training a CNN model to achieve accurate tumor classification within the medical images. Among the various deep learning techniques proposed for medical image analysis, U-net-based models have gained significant popularity for multimodal medical image segmentation. However, due to the diverse shapes, sizes, and appearances of brain tumors, simple block architectures commonly used in segmentation tasks may not adequately capture the complexity of tumor boundaries and internal structures. The experimental results provide compelling evidence of the proposed approach's efficacy in accurately detecting and segmenting brain tumors. The results highlight the successful performance of the approach and its ability to achieve accurate tumor identification and segmentation
TechTrolley-enhancing the retail experience
Get PDFIn the modern era, convenience and efficiency have become essential aspects of daily life, and grocery shopping is no exception. The traditional shopping experience, characterized by long queues and time-consuming checkout processes, can be frustrating and inefficient. To address these challenges, the TechTrolley has emerged as an innovative solution, leveraging Bluetooth and radio frequency identification (RFID) technology to revolutionize the grocery shopping experience. With the help of TechTrolley, customer can seamlessly complete the shopping by scanning and purchasing the products, controlling the trolley with the use of controller integrated in application, getting details of the products and price in the application and over LCD display embedded on the trolley, complete the checkout process at billing counter. With the need to implement, we need an RFID tag, ESP32, LCD display, L298N motor driver and battery to implement the motion features of a trolley, database for storing the user and product details, a bridge network through router to establish the network between admin, user and the trolley in order to invoke the real time updates
Investigation on OMYA with single superstrate layer
Get PDFThe need for wireless communication technology is increasing rapidly. Many people are already using internet data services offered by providers or using wireless fidelity (Wi-Fi) services. One of the things that must be considered in Wi-Fi technology is that it requires antenna characteristics that have a relatively small shape and light mass. This paper aimed to improve gain and to analyze the performance of octagon microstrip Yagi antenna (OMYA) with a single superstrate layer. The antenna was designed, simulated, and measured. The experimental result presents that this concept is capable to produce a gain of 11.80 dB, a return loss of -23.24 dB, and the bandwidth is up to 800 MHz with total dimensions of 70×75 mm
Communication induced checkpointing based fault tolerance mechanism using deep-learning in IoT applications
Get PDFInternet of things (IoT) is increasingly used in diverse environments such as healthcare, industry and agriculture. They carry a risk of adverse effects if they make decisions based on faulty information. Software faults, especially transient faults are a primary contributor to deficient decision-making. The existing fault tolerant mechanisms often suffer from checkpoint overheads as checkpoints are placed in all the nodes. This paper describes a novel communication induced checkpointing based fault tolerance mechanism (CIC-FTM) designed to efficiently recover from transient faults, while minimizing useless and forced checkpoints. Long short-term memory (LSTM) based deep learning algorithm is used in our approach to predict fault occurrences and strategically place checkpoints. The proposed method also in turn improve system reliability and performance. Experimental results demonstrate the effectiveness of proposed CIC-FTM in IoT environment by minimizing the practicable operating time for checkpointing and back propagation, compared to traditional fault-tolerance mechanisms
An improved WOA of PI control for three phase PWM rectifier
Get PDFIn the empire of electric vehicle (EV) propulsion systems, efficient energy conversion is paramount for extending driving range and enhancing overall performance. Rectifiers play a crucial role in converting AC from the grid into DC for battery charging and motor operation. However, the performance of rectifiers is heavily influenced by the control algorithms employed. This work presents an optimized proportional-integral (PI) controller design for rectifiers in EV applications. The proposed controller aims to achieve high efficiency, fast response, and robustness to variations in load and input voltage. The optimization process incorporated in this work utilized whale optimization topology for tuning the PI controller parameters. The objective is to minimize cost function that represents deviation of rectifier output from desired characteristics under various operating conditions. The outcomes of simulation demonstrate that suggested controller works to provide greater accuracy than traditional control techniques. Moreover, experimental validation verifies the proposed controller's reliability and efficiency in practical EV applications. The optimized PI controller contributes to maximizing energy efficiency, extending battery life, and enhancing the overall reliability of electric vehicle propulsion systems
Implementation of perspective-n-point techniques and YOLOv5 algorithm based on surveillance camera for localization
Get PDFThe technology of processors has advanced significantly, resulting in smaller and more powerful devices with much processing capability. Particularly, camera technology has witnessed extensive research in utilizing images for various applications. Currently, surveillance cameras are widely used for security purposes when abnormal events occur. In this research, the benefits of utilizing data from surveillance cameras are explored to assist in determining the position of a moving robot using the perspective-n-point (PnP) technique. the scale factor, which varies, has been improved by integrating checks with the YOLOv5 algorithm. This algorithm employs a custom model to specifically detect the robot of interest, enabling the determination of its real-world position using multiple surveillance cameras. These cameras have different perspectives within the same area. Considering the deviation caused by determining the position from a single viewpoint, multiple cameras are employed to mitigate this issue
Improvement the cogging torque reduction methods by combining the magnet slotted and gradually inclined surface end in permanent magnet generator
Get PDFCogging torque (CT) in permanent magnet synchronous (PMS) machine, generator or electric motor should be reduced to increase the preperformance in application. Many CT reduction techniques has been proposed in the last few years. This research dealt with the study of techniques for reduction of the CT in PMSG. The PMS generator investigated in this paper is the integral slot number type with 18 slots and 6 poles. The CT has been analyzed to be reduced by employ the slot opening width variation, magnet edges slotting, and gradually inclined surface end. This paper also has analyzed the effect of combination of slot opening width and slotting permanent magnets. The finite element method magnetics (FEMM) is used in this work to perform electromagnetic simulations of the PMSG. Using the FEMM, the CT reduction of permanent magnet synchronous generators studied is analyzed and the CT peak value is compared. It is found that by combining of reduced of slot opening and slotting the permanent magnets can reduce the CT of PMS generator significantly abound 98.55% compared with the base line model
Design of starting a three phase induction motor using direct on-line, variable frequency drive, soft starting, and auto transformer methods
Get PDFThe problem with 3-phase induction motors is that when starting the motor, the motor starting current can reach five to seven times the nominal current. This research compares slip, starting current, bus voltage, acceleration torque, motor torque, energy savings, and kVAR from the direct on-line (DOL), variable frequency drive (VFD), soft starting, and autotransformer starting methods in the electrical transient analyzer program (ETAP) software. This research result shows that the fastest VFD slip reaches a steady state, namely at 11+ seconds. The lowest starting/starting current is owned by the VFD method, namely <20% full load amps (FLA) in the first 2 seconds. The lowest decrease in bus voltage at steady state was experienced by the VFD method, namely 0.8152%. The quickest acceleration torque reaches a steady state in the VFD method, namely in 11+ seconds. The soft starting method owns the lowest starting torque, namely 20.75%. The soft starting method has the largest energy savings, namely 148.02 kW. Of the several variables observed, the best starting method is the VFD method
Job matching analysis by latent semantic indexing enhanced on multilingual word meanings
Get PDFJob matching is a hiring process that involves a thorough understanding of the context and meaning of words in different languages. The updated and expanded latent semantic indexing (LSI) Framework seeks to improve the precision and relevance of job matching analysis of word meanings in multi-languages. Because they only compare related terms, conventional LSIs are often insufficient to address the complexity of context in job matching. Extending the LSI approach can improve the vector representation of words and help you understand the context and semantic relationships in the text. Improved LSI analyzes context more precisely by using word vector representation. Improved LSI focuses on understanding semantic relationships between words in many languages to produce more accurate and relevant job matches. This paper describes the steps involved in improving LSI, such as data collection, pre-processing, linguistic feature extraction, LSI model training, and evaluation of matching results. The results show that the examined classification model has much better performance in terms of word classification. Conventional LSI has an average prediction value of 79%, once the enhanced LSI can accurately predict about 84% of the entire word, it has a reasonable capacity to recognize the actual words in a natural context