Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Intrusion detection in clustering wireless network by applying extreme learning machine with deep neural network algorithm
Get PDFNowadays, intrusion detection systems (IDSs) have growingly come to be considered as an important method owing to their possible to expand into a key factor, which is crucial for the security of wireless networks. In wireless network, when there is a thousand times more traffic, the effectiveness of normal IDS to identify hostile network intrusions is decreased by an average factor. This is because of the exponential growth in network traffic. This is due to the decreased number of possibilities to discover the intrusions. This is because there are fewer opportunities to see possible risks. We intend an extreme learning machine with deep neural network (DNN) algorithm-based intrusion detection in clustering (EIDC) wireless network. The main objective of this article is to detect the intrusion efficiently and minimize the false alarm rate. This mechanism utilizes the extreme learning machine (ELM) with a deep neural network algorithm for optimizing the weights of input and hidden node biases to deduce the network output weights. Simulation outcomes illustrate that the EIDC mechanism not only assures a better accuracy for detection, considerably minimizes an intrusion detection time, and shortens the false alarm rate
Advancements and challenges in deep learning techniques for lung disease diagnosis
Get PDFThis study explores the application of deep learning (DL) techniques in diagnosing lung diseases using screening methods such as Chest X-Rays (CXRs) and computed-tomography (CT) scans. The motivation for this research stems from the need for advanced diagnostic tools in healthcare, with DL showing significant potential in medical image analysis. Despite advancements, challenges such as high costs of CT scans, processing time constraints, image noise, and variability persist. To address these issues, the study conducts a thorough literature survey to identify diverse preprocessing techniques, detection algorithms, and classification models designed for CXR analysis. In conclusion, this work contributes to the advancement of medical imaging technologies by offering innovative solutions, acknowledging existing limitations, and addressing the challenges in lung disease diagnosis. Future research should focus on further refining these techniques and exploring their application in broader clinical settings
Evolution of the optical add/drop multiplexer in dense wavelength division multiplexing optical networks
Get PDFMobile network operators are facing ever-increasing traffic demands because of the numerous data-hungry applications used by subscribers nowadays. As a result, technologies that support high bandwidth and network availability have become essential. One such technology is dense wavelength division multiplexing (DWDM). This study investigated the evolution of an optical add/drop multiplexer (OADM), which is one of the key components of DWDM technology. The goal of this research was to investigate how the evolution of an OADM has contributed to network survivability and bandwidth enhancement in DWDM optical networks. A thorough search of the literature on an OADM was undertaken using data sources like Google Scholar, Elsevier, ResearchGate, ScienceDirect, Springer, and DWDM vendor manuals. The study found that in order to address present and future DWDM optical network demands, a reconfigurable optical add/drop multiplexer (ROADM) deployed over flexgrid spectrum is essential. The most advanced iteration of a ROADM supports colorless, directionless, contentionless, and flex-grid functionalities, resulting in the most robust, flexible, and future-proof DWDM optical network. The study further found that flex-grid technology supports uplinks with high line rates and has superior spectral efficiency
Detection of COVID-19 based on cough sound and accompanying symptom using LightGBM algorithm
Get PDFCoronavirus disease 19 (COVID-19) is an infectious disease whose diagnosis is carried out using antigen-antibody tests and reverse transcription polymerase chain reaction (RT-PCR). Apart from these two methods, several alternative early detection methods using machine learning have been developed. However, it still has limitations in accessibility, is invasive, and its implementation involves many parties, which could potentially even increase the risk of spreading COVID-19. Therefore, this research aims to develop an alternative early detection method that is non-invasive by utilizing the LightGBM algorithm to detect COVID-19 based on the results of feature extraction from cough sounds and accompanying symptoms that can be identified independently. This research uses cough sound samples and symptom data from the Coswara dataset, and cough sound’s features were extracted using the log mel-spectrogram, mel frequency cepstrum coefficient (MFCC), chroma, zero crossing rate (ZCR), and root mean square (RMS) methods. Next, the cough sound features are combined with symptom data to train the LightGBM. The model trained using cough sound features and patient symptoms obtained the best performance with 95.61% accuracy, 93.33% area under curve (AUC), 88.74% sensitivity, 97.91% specificity, 93.17% positive prediction value (PPV), and 96.33% negative prediction value (NPV). It can be concluded that the trained model has excellent classification capabilities based on the AUC values obtained
Integrating gamification to increase users’ engagement to adhere COVID-19 interventions using extended TAM
Get PDFGamification has shown potential for enhancing motivation and engagement, yet its effectiveness in promoting adherence to COVID-19 preventive measures remains underexplored. With decreasing public attentiveness, this study examines the role of gamification in encouraging compliance with health protocols through an extended technology acceptance model (TAM) and structural equation modeling (SEM). A gamified mobile application was developed, incorporating features such as points, badges, and progress tracking, and was designed to appeal to younger audiences. Data collected from 150 secondary school students in Sarawak, Malaysia, indicated that perceived usefulness, perceived ease of use, and attitude toward the app significantly influenced engagement with COVID-19 preventive measures. Among these factors, perceived usefulness demonstrated the strongest effect on engagement (β = 0.424, t = 4.812, p < 0.001). The findings highlight the potential of gamification to enhance compliance with COVID-19 protocols
Seeking best performance: a comparative evaluation of machine learning models in the prediction of hepatitis C
Get PDFHepatitis C is a disease that affects millions of people worldwide. It is spread through contact with contaminated blood through injections, transfusions, or other means. It is estimated that with early detection patients have a higher rate of recovery. The objective of this study is to perform a comparative evaluation of different models focused on the prediction of hepatitis C, to determine which of the models offers better performance in accuracy, precision, and sensitivity. The models used were logistic regression (LR), random forest (RF), K-nearest neighbors (KNN), decision tree (DT), and gradient boosting (GB), aimed at hepatitis C prediction. The training of the models was carried out using a dataset composed of 615 records, which incorporate 14 attributes. The structure of the article is divided into six sections, including introduction, review of related articles, methodology, results, discussion, and conclusions. The performance of the models was evaluated through metrics such as accuracy, sensitivity, F1 count, and, mainly, precision. The results obtained place the DT model as the most efficient predictor, reaching a precision, accuracy, sensitivity, and F1-score of 95%
Secure lightweight CAN protocol handling for electric vehicles
Get PDFThe integrity of controller area network (CAN) protocols in electric vehicles (EVs) is of paramount importance, due to their susceptibility to cyber intrusions and unauthorized access. Traditional encryption-based security solutions, such as advanced encryption standard (AES) and anomaly detection methods, often introduce high computational overhead and latency, making them unsuitable for real-time EV communication. This study proposes a secure lightweight CAN protocol (SLCP), implemented using ARDUINO Uno and MCP2515, which enhances message integrity, authentication, and fault recovery without compromising system efficiency. Experimental testing demonstrated that the proposed SLCP reduces message authentication latency by 25% and improves message integrity by 40% compared to conventional encryption techniques. Additionally, packet resynchronization time was reduced by 30%, ensuring minimal disruptions in case of message loss. These findings establish SLCP as a viable, real-time alternative for low-power EV communication networks. The study contributes to advancing lightweight security frameworks for EV networks, paving the way for scalable, real-time cybersecurity solutions in modern electric transportation
Empirical analysis of Bitcoin investment strategy: a comparison of machine learning and deep learning approach
Get PDFA digital currency known as a cryptocurrency uses blockchain technology to record transactions electronically, guaranteeing security and transparency. Cryptocurrencies, in contrast to conventional hard currency, are virtual or soft currencies; that do not exist in the actual world like coins or banknotes. Since all transactions occur digitally, cryptocurrencies are decentralized and frequently stand-alone from conventional financial institutions. Peer-to-peer transfers, increased anonymity, and often quicker transaction processing without middlemen are made possible by this. In this study, two machine learning models; autoregressive integrated moving average (ARIMA), extreme gradient boosting (XGBoost), and two deep learning models; long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM) were compared. By employing past Bitcoin data from 2012 to 2020, we evaluated the models' mean absolute error (MAE) and root mean squared error (RMSE). Compared to other models, the Bi-LSTM model yields minimal RMSE scores of 67.18 and MAE scores of 24.73. This aids in capturing all temporal correlations, which are important for forecasting the price of Bitcoin
Pairing mobile users using K-means algorithm on PD-NOMA-based mmWaves communications system
Get PDFIn this research, we study the effectiveness of the K-means machine learning (ML) clustering approach for pairing mobile users on a power domain nonorthogonal multiple access (PD-NOMA) single input single output (SISO) downlink-based millimeter-wave (mmWave) communication system. The basic concept is to pair the mobile users by using a data set that contains essential information about the mobile users in the micro cell base station (BS) (e.g., the SNR, the distance between the mobile users and the BS, the channel gain, and the data rate of each mobile user). The study conducted in this paper demonstrates that the proposed K-means clustering-based scheme achieves a balance between computational complexity and performance metrics. It outperforms single carrier NOMA (SC-NOMA), the conventional NOMA pairing scheme, and time division multiple access (TDMA), offering an effective trade-off between system efficiency and implementation feasibility
Temperature-dependent based optimal reactive power dispatch by chaotic equilibrium optimization algorithm
Get PDFThe optimal reactive power dispatch (ORPD) problem is considered as an important aspect in power system operation of the reactive power, which is vital to maintain network voltage within desirable limit for system reliability. In conventional ORPD problem, the resistance of components in power systems is considered to be independent to their temperature variations. Actually, there is a correlation between the branch resistance and temperature, thus the temperature should be taken into account when performing power flow analysis to improve the accuracy in the calculation of the power flow and power loss on branches. This paper proposes a new chaotic equilibrium optimization (CEO) method to solve the temperature-dependent based optimal reactive power dispatch (TDORPD) problem in power systems by optimizing the reactive power loss and voltage deviation. The proposed CEO algorithm is implemented for the conventional ORPD and TDORPD problems on the benchmark IEEE 30 bus testing network. Moreover, the effects of temperature variations on the considered TDORPD problem are also considered. The obtained results have demonstrated a better performance of the proposed CEO algorithm compared to the original EO and other methods in the literature review for the problem in terms of the solution quality, which confirms its efficacy to effectively resolve the ORPD and TDORPD problem