Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Research trends in spatial modeling of PM2.5 concentration using machine learning: a bibliometric review
Get PDFSpatial modeling is commonly used to map research variables, including particulate matter 2.5 (PM2.5) concentrations, in specific areas. The article that surveys publications on the application of machine learning in spatial modeling of PM2.5 using bibliometric methods has not been identified yet. This paper aims to analyze trends in applying machine learning in the spatial modeling of PM2.5 using bibliometric methods. The review was conducted on publications indexed in the Scopus database over the decade (2014–2023) comprising 335 articles. The analysis included co-authorship and co-occurrence using VOSviewer. From the two stages of analysis, it can be concluded that research on this topic has constantly increased over the past 10 years, with the highest productivity coming from researchers in China. This research topic is multidisciplinary, with most publications appearing in environmental science. The research also shows a very high collaboration rate of 0.98. A deeper examination of the keywords reveals the most commonly used machine learning techniques by researchers. The random forest method is the most frequently found in the analyzed documents, followed by deep learning, long short-term memory (LSTM), extreme gradient boosting (XGBoost), and ensemble model
Deep learning techniques for satellite image classification
Get PDFBecause of its wide range of uses in computer vision applications, including image retrieval, remote sensing, object recognition, scene analysis, and surveillance, image classification has attracted a lot of attention. Assigning appropriate class labels to images according to their contents is the primary objective of image classification. In the domain of remote sensing, image classification and analysis play crucial roles in both military and civil applications. Conventional methods for scene analysis and remote sensing depended on low-level representations of features, such as those of color and texture. However, recent advancements have shifted towards the use of convolutional neural networks (CNNs), which have shown promising results in remote sensing and scene classification tasks. In light of effectiveness of deep learning (DL) models, this research aims to develop four DL models by fine tuning already existing DL models-CNNs, residual neural network (ResNet), visual geometry group (VGG-19), network mobile net V2 based model and classifies satellite images of RSI-CB256 data set in to four classes namely cloudy, desert, green_area and water. For the RSI-CB256 dataset, appropriate network structures are explored in this research to get good performance. The CNN, ResNet and VGG-19 base models achieved an accuracy of 90.48, 92.68 and 91.18 respectively. While the mobile net V2 based model outperformed the other three models with 96.83% accuracy
An intelligent intrusion detection system to prevent URL redirection attack
Get PDFIn today’s digital age, the widespread use of social networking platforms like Facebook, Twitter, and Instagram, alongside messaging services such as Email and WhatsApp, has increased the convenience of communication. However, this accessibility has also provided a fertile ground for cybercriminals and spammers to exploit these platforms through URL redirection attacks, which are often used to steal sensitive user information. Existing solutions, including machine learning (ML), deep learning (DL), and ensemble methods have been employed to combat such threats. Despite their effectiveness, these approaches struggle to detect emerging types of attacks and suffer from limitations when dealing with imbalanced data, leading to reduced detection performance. To address these challenges, this research introduces an improved extreme gradient boosting (IXGB) algorithm that optimizes the weight adjustments in the model, aiming to enhance the detection of malicious URLs. The proposed method focuses on improving classification accuracy, especially for new or unseen types of attacks. Experimental results on a standard dataset demonstrate that IXGB achieves superior accuracy compared to traditional models, making it a promising approach for enhancing cybersecurity on social media and messaging platforms
Novel method for multi-user collaborative spectral decision in decentralized cognitive radio networks
Get PDFCognitive radio networks positively impact the performance of wireless communications and have proven to be an excellent alternative for efficient and effective use of the radio spectrum. However, few proposals collaboratively work on decision-making in decentralized cognitive radio networks. The present work refers to a novel method and device that reduces the rate of channel changes during secondary user communications in decentralized cognitive radio networks through a collaborative spectral decision between several secondary users while allowing multiple secondary users access to the network. This proposal consists of a multi-user unit that regulates the access of multiple secondary users (SUs) to the spectrum, a priority unit that guarantees timely access to the SUs according to their level of importance, and a prediction unit that forecasts the arrival time of the primary user (PU). This multichannel unit regulates the assignment of multiple spectral opportunities to the SU according to the type of application it is using and a unit of deep learning that determines which spectral opportunity(s) are most suitable for each SU and spectral allocation. The results obtained allow us to satisfactorily validate the proposal developed and corroborate the importance of collaborative work in decision-making to select spectral opportunities
Analysis of VFDPC for three-level neutral point clamped AC-DC converters with capacitor balancing solution
Get PDFThis paper presents an analysis of the dynamic performance of a three-level neutral point clamped (NPC) AC-DC converter utilizing the advanced control technique of virtual flux direct power control (VFDPC). VFDPC estimates the three-phase grid voltage and instantaneous active and reactive power components, eliminating the need for an AC input voltage sensor used in conventional direct power control (DPC). This reduction in sensors decreases system complexity and cost while mitigating high-frequency noise and interference. Integrating VFDPC into 3L NPC AC-DC converters significantly enhances overall performance, leading to more efficient and robust power conversion systems. However, a significant challenge in the three-level NPC topology is the voltage imbalance in the neutral point of the DC-link capacitor, which can cause excessive voltage stress on switching devices and degrade system performance. To address this, a novel lookup table has been developed, incorporating strategies to balance the capacitor voltage. The results of this study demonstrate that VFDPC generates nearly sinusoidal line currents with reduced current total harmonic distortion (THD). Additionally, VFDPC ensures unity, lagging, and leading power factor operation, while providing flexibility to adjust the DC-link output voltage and accommodate load variations. These capabilities highlight VFDPC effectiveness in managing power quality and system stability, even under varying load conditions
Integrating ELECTRA and BERT models in transformer-based mental healthcare chatbot
Get PDFOver the last decade, the surge in mental health disorders has necessitated innovative support methods, notably artificial intelligent (AI) chatbots. These chatbots provide prompt, tailored conversations, becoming crucial in mental health support. This article delves into the use of sophisticated models like convolutional neural network (CNN), long-short term memory (LSTM), efficiently learning an encoder that classifies token replacements accurately (ELECTRA), and bidirectional encoder representation of transformers (BERT) in developing effective mental health chatbots. Despite their importance for emotional assistance, these chatbots struggle with precise and relevant responses to complex mental health issues. BERT, while strong in contextual understanding, lacks in response generation. Conversely, ELECTRA shows promise in text creation but is not fully exploited in mental health contexts. The article investigates merging ELECTRA and BERT to improve chatbot efficiency in mental health situations. By leveraging an extensive mental health dialogue dataset, this integration substantially enhanced chatbot precision, surpassing 99% accuracy in mental health responses. This development is a significant stride in advancing AI chatbot interactions and their contribution to mental health support
EMSPLA for accurate feature molecular extraction from protein-ligand interactions
Get PDFProtein-ligand interactions are fundamental in various biological and medical fields, influencing drug discovery and therapeutic development. In recent years, deep learning (DL) has revolutionized the study of these interactions, but significant challenges remain in accurately representing molecular structures for DL models. Traditional featurization techniques often depend on handcrafted features, requiring expert knowledge and potentially missing crucial molecular aspects. This work addresses these challenges by developing and evaluating a novel protein-ligand feature extraction system using an enhanced molecular similarity protein-ligand aligner (EMSPLA). The primary objective is to leverage EMSPLA for similarity matching in protein-ligand interactions, improving predictive model accuracy. The methodology combines convolutional neural networks (CNN) for local feature extraction with an attention module to capture long-distance dependencies, enhancing binding site predictions. Using the PDBbind v.2020 dataset, the EMSPLA model demonstrated superior performance with a root mean square error (RMSE) of 0.67, surpassing current state-of-the-art models. These findings highlight the system’s potential for efficient deployment and scalability, positioning it as a powerful tool in computational biology and drug discovery, ultimately advancing our understanding of protein-ligand interactions
Remove glasses diffusion model an innovative conditioned of eye glasses removal with image diffusion model
Get PDFThe presence of eyeglasses in facial images poses challenges for image processing, particularly in facial recognition. This paper introduces the remove glasses diffusion model (RGDM), a conditioned denoising diffusion probabilistic model (DDPM) designed for precise glasses removal. RGDM employs conditional modeling to focus on the glasses region while seamlessly restoring facial features. An eyes position accuracy mechanism, leveraging facial landmarks, ensures accurate eye restoration post-removal. Comprehensive evaluations on the CelebA dataset demonstrate RGDM’s superior performance, achieving the lowest Fréchet inception distance (FID) of 27.09 and learned perceptual image patch similarity (LPIPS) of 0.299, outperforming state-of-the-art methods such as 3D synthetic, cycleconsistent generative adversarial network (CycleGAN), and eyeglasses removal generative adversarial network (ERGAN). These results highlight the model’s effectiveness in producing natural and high-fidelity facial reconstructions. This work advances glasses removal technology and underscores the significance of conditional models in image processing. The proposed approach has practical implications for facial recognition and image enhancement, paving the way for more accurate and robust real-world applications
Calibration of phased array antenna with the minimum point finding method of the array factor
Get PDFThe problem of phased array antenna calibration with the minimum point finding method of the array factor is investigated. A mathematical model of the minimum point finding method is presented. Then, the proposed method is applied to the phased array antenna and compared with the traditional rotating-element electric-field vectors method. Experimental verification of the mathematical model of the proposed method showed the following: the minimum point finding method determines the phase shift more accurately than the maximum point finding method of the array factor; the proposed method showed a better detection range per phase change corresponding to a 35 dB higher resolution. The error ranges of the minimum and the maximum point finding methods were 50 and 700 , respectively. The peak of the combined beam when using the minimum point finding method is higher than the maximum point finding method which is 3.7 ... 4.1 dB. One can use the research results in large-scale phased array antenna calibration systems during the production phase
Investigating the recall efficiency in abstractive summarization: an experimental based comparative study
Get PDFThis study explores text summarization, a critical component of natural language processing (NLP), specifically targeting scientific documents. Traditional extractive summarization, which relies on the original wording, often results in disjointed sequences of sentences and fails to convey key ideas concisely. To address these issues and ensure comprehensive inclusion of relevant details, our research aims to improve the coherence and completeness of summaries. We employed 25 different large language models (LLMs) to evaluate their performance in generating abstractive summaries of scholarly scientific documents. A recall-oriented evaluation of the generated summaries revealed that LLMs such as 'Claude v2.1,' 'PPLX 70B Online,' and 'Mistral 7B Instruct' demonstrated exceptional performance with ROUGE-1 scores of 0.92, 0.88, and 0.85, respectively, supported by high precision and recall values from bidirectional encoder representations from transformers (BERT) scores (0.902, 0.894, and 0.888). These findings offer valuable insights for NLP researchers, laying the foundation for future advancements in LLMs for summarization. The study highlights potential improvements in text summarization techniques, benefiting various NLP applications