Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Enhancing IoT security: a hybrid intelligent intrusion detection system integrating machine learning and metaheuristic algorithm
Get PDFThe rapid proliferation of the internet of things (IoT) has introduced significant security and privacy challenges. As IoT devices often have limited computational power and memory, they are highly vulnerable to cyber threats. Traditional intrusion detection systems (IDS) struggle to operate efficiently in these constrained environments, necessitating more adaptive and optimized security solutions. To address these challenges, this study proposes an innovative IDS model, MSAMLP, which combines the moth search algorithm (MSA) with a multilayer perceptron (MLP) classifier. The objective is to enhance the classification accuracy of malicious and benign network traffic while maintaining computational efficiency. The model was evaluated using two widely recognized intrusion detection datasets, benchmarking its performance against existing IDS approaches. Experimental results indicate that MSAMLP outperforms conventional classification models, achieving high accuracy, improved detection rates, and reduced false alarm rates. Its adaptive learning capability ensures better anomaly detection in dynamic IoT environments. In conclusion, the proposed MSAMLP model demonstrates superior performance in securing IoT networks, offering an effective solution to mitigate evolving cyber threats. This research contributes to the advancement of IoT security by introducing a robust and scalable intrusion detection approach
Optimizing carrier transport properties in the intrinsic layer of a-Si single and double junction solar cells through numerical design
Get PDFThis research aims to improve the performance of a-Si: H solar cells, particularly in terms of carrier transport properties, through a numerical design approach utilizing AFORS-HET simulation software. By performing a series of rigorous computer simulations, we explore the potential regulation of the intrinsic layer thickness, carrier mobility, loading factor, and density of states (DoS) distribution in the solar cell's intrinsic layer. Recombination losses are reduced, and light absorption efficiency is significantly increased when the intrinsic layer thickness is adjusted, as shown by simulation findings. Moreover, reduction of transit times and enhancement of the total efficiency of the solar cells depend on increased carrier mobility. Parameters can be adjusted to attain optimal performance under various operating situations by adjusting the DoS and load factors. Furthermore, the simulations provide insightful information about the interactions between the junctions in solar cells with double junctions. Our results of this research provide an important contribution to efforts to develop more efficient and sustainable a-Si: H solar cells and emphasize the importance of numerical design approaches in photovoltaic technology
Internet of things enabled landfill pollution gas monitoring
Get PDFDue to the increasing concern on how to manage wastes and ensure environmental safety across the globe, a new tool that assists in the monitoring of methane, humidity, and temperature in the landfill using internet of things (IoT) has been created. This system uses ESP32 microcontroller and MQ-4 and DHT-22 sensors to measure environmental conditions at three different spots in a landfill. The samples of data are collected at three times a day, that is, in the morning at 7:00 am, at midday at 12:00 pm and in the evening at 5:00 pm and the data is transmitted to an online sheet where the public can access it in real time hence increasing transparency in the management of wastes. The tool shows a very good precision and effectiveness and the parameters are 94. 6% data integrity over three months testing period. The first findings show that the mean methane concentration is the highest at midday, which is related to the temperature and underlines the role of temperature in the methane emission process. The presented IoT based monitoring system also enhances the accuracy and efficiency in the monitoring of landfill gas and at the same time reduces the intervention of human effort and increases the capability to make prompt adjustments to changes in the environment. Used as an instrument for obtaining accurate and easily understandable data, it is hoped that this tool will in some way help to enhance global environmental health and safety standards, and help pave a way for methane storage for renewable energy purposes
Analysis of FinFET based SRAM cells with improved performance parameters
Get PDFTo resist the advanced process variation and enable ultra-low power operation, static random-access memory (SRAM) undergoes an expansion stage. The most common type of memory is SRAM, which occupy more than 60% of the chip area. All memories have occupied more than 80% of the circuit area in that day’s micro devices, and this trend is expected to continue. This paper develops into the deployment of SRAM using FinFET technology for implementation, with a primary objective of mitigating critical memory parameters, including parameters named as power dissipation, data retention and noise voltage. In this article, multiple simulations are carried out among conventional SRAM cells and FinFET based SRAM cells (6T, 7T, and 8T) utilizing the Cadence Virtuoso tool with a 45nm technology node. In modern era, FinFET is gaining increased preference over CMOS for high controllability of short-channel effects and flexible adjustment of threshold voltage (Vth) through the presence of a double gate. The thinner width of FinFET (Wfin) shows less degradation in performance in compared to thicker width of FET. To improve the circuit performance, the key factors like area, power and delay should be reduced. In the proposed SRAM cell using FinFET, power dissipation is lowered by 17% data retention voltage is reduced by 7% and noise voltage abridged up to 35% as compared to conventional SRAM cell
A multi-scale convolutional neural network and discrete wavelet transform based retinal image compression
Get PDFThe different applications of medical images have contributed significantly to the growing amount of image data. As a result, compression techniques become essential to allow real-time transmission and storage within limited network bandwidth and storage space. Deep learning, particularly convolutional neural networks (CNN) have marked rapid advances in many computer vision tasks and have progressively drawn attention for being used in image compression. Therefore, we present a method for compressing retinal images based on deep CNN and discrete wavelet transform (DWT). To further enhance CNN capabilities, multi-scale convolutions are introduced into the network architecture. In this proposed method, multiscale CNNs are used to extract useful features to provide a compact representation at the encoding stage and guarantee a better reconstruction quality of the image at the decoding stage. Based on compression efficiency and reconstructed image quality, a wide range of experiments have been conducted to validate the proposed technique performance compared with popular image compression standards and existing deep learning-based methods. At a compression ratio (CR) of 80, the proposed method achieved an average peak signal-to-noise ratio (PSNR) value of 38.98 dB and 96.8% similarity in terms of multi-scale structural similarity (MS-SSIM), demonstrating its effectiveness
Design and evaluation of performance metrics of a pentaband broadband microstrip patch antenna for mm wave applications
Get PDFThis paper reports design and results of a microstrip patch antenna for broadband application in the millimeter wave communication with multiband features. Electromagnetic solver high-frequency structure simulator (HFSS) is employed to measure the effectiveness of the electromagnetic properties and electrical behaviour of the antenna. The proposed microstrip patch antenna (MPA) can be easily fabricated on a single substrate using standard photolithography process to attach the radiating element and feed lines to the dielectric material. On a 4.93 mm×5.86 mm metallic patch, over FR4 epoxy substrate with dielectric constant 4.4 and loss tangent 0.03, two L-shaped slots are placed along with a few micro slots of varied dimensions, and the antenna is fed with microstrip feedline with resistive load termination of 50 Ω. Pentaband resonant frequencies are realized in the K-band at 13.6 GHz, 23.2 GHz, 29.68 GHz, 32.96 GHz, and 38.56 GHz, with minimum return loss of -23.17 dB, bandwidth 2.32 GHz, omnidirectional radiation pattern, and maximum reported gain of 4.5 dB. The designed antenna achieved good electromagnetic radiation properties and electrical behaviour, and is a good choice for broadcasting over short distances, surveillance and monitoring, wireless sensor backhauls and telecommunication in the K-band networks
Strengthening resilience against cyberattacks in Moroccan Universities through AHP, TOPSIS, and ITIL v4
Get PDFThis study addresses the complex challenges of digital transformation in higher education by enhancing IT governance to combat cyber threats in Moroccan universities. By adopting a hybrid multi-criteria decision-making (MCDM) framework, the research combines the analytic hierarchy process (AHP) and the TOPSIS method to evaluate fourteen IT governance criteria, categorized into structural, procedural, and relational dimensions. Using TOPSIS, the study identifies the most relevant SVC services from the ITIL v4 value chain for each category, with the aim of developing an optimized strategic approach against cyberattacks. The input from ten academic experts was crucial in prioritizing these services. The results show that SVC services A5 and A2 are fundamental for optimizing the resources of structural and procedural mechanisms, while A4 and A2 play a key role in relational mechanisms. This strategic alignment enhances the resilience of Moroccan universities to cyber threats by ensuring a more efficient allocation of security resources and providing a robust defense against potential attacks
Performance analysis of different BERT implementation for event burst detection from social media text
Get PDFThe language models play very important role in natural language processing (NLP) tasks. To understand natural languages, the learning models are required to be trained on large corpus. This requires a lot of time and computing resources. The detection of information like events, and locations from text is an important NLP task. As events detection is to be done in real-time so that immediate actions can be taken, hence we need efficient decision-making models. The pertained models like bi-directional encoders representation from transformers (BERT) gaining popularity to solve NLP problems. As BERT based models are pre-trained on large language corpus it requires very less time to adapt for domain specific NLP task. Different implementations of BERT have been proposed to enhance efficiency and applicability of the base model. The selection of right implementation is essential for overall performance of NLP based system. This work presents the comparative insights of five widely used BERT implementations named as BERT-base, BERT-large, Distill BERT, Robust BERT approach (RoBERTa-base) and RoBERT-large for event detection from the text extracted from social media streams. The results show that Distill-BERT model outperforms on basis of performance metric like precision, recall, and F1-score while the fastest to train also
Enhancing malware detection capabilities using deep learning with advanced hyperparameter tuning
Get PDFAs the threat landscape evolves with sophisticated malware and advanced persistent threats (APTs), the need for effective detection solutions increases. Traditional methods, such as signature-based and heuristic analysis, struggle to keep up with rapidly changing malicious activities. While machine learning offers a promising approach, it often falls short due to the manual extraction and selection of features, leading to time-consuming and error-prone processes. This research introduces a novel malware detection solution leveraging deep learning and focusing on portable executable (PE) file analysis to address these weaknesses. By customizing the hyperparameters of artificial neural networks (ANN), convolutional neural networks (CNN), and recurrent neural networks (RNN), the proposed approach enhances detection capabilities. The primary objective is to overcome the limitations of traditional and machine learning methods by tailoring these deep learning algorithms. The methodology includes a comparative study to demonstrate the advantages of the customized approach over conventional methods. Key findings reveal the proposed solution’s superior performance, accuracy, and adaptability in combating evolving cyber threats. This research contributes to the development of robust and adaptive malware detection solutions
Analysis of LLC resonant converter performance with PIDD2 controller for electric vehicle application
Get PDFThe key uses of the latest developments is electric vehicles (EV’s). As a result, several researchers were drawn to EV’s control to propose appropriate controllers and predicted that control engineers face a challenge when it comes to regulating the LLC resonant converter output voltage. In this regard, the study proposes a PID Type modified controller for regulation of voltage across output in LLC resonant converter. The design and control procedure of this modified proportional integral derivative double derivative (PIDD2) is explained along with EDF modeling in LLC resonant converter. This work proposes to use two controllers to drive the voltage output of a resonant converter LLC to constantly track the desired value. Proportional integral derivative controller (PID) is the first, while the PIDD2 method is the foundation of the second. Every controller has undergone simulation testing and the results are compared based on how the evaluated controllers respond dynamically in accordance with settling time, rising time and overshoot