Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Deportation of constant amplitude impulsive outlier (CAIO) through novel repetitive new switching-based median filtering approach
Get PDFThis research paper nominates a novel repetitive new switching-based median filtering approach (R-NSBMF) for outlier deportation on computer numerical pictures that are surpassingly subverted by constant amplitude impulsive outlier (CAIO) or Salt & Pepper noise. This approach reestablishes the outlier numerical pictorial feature (which has the minimum amplitude or the maximum amplitude) by the median filter of the finite impulse response (FIR) linear predictor of all the non-outlier numerical pictorial feature in the calculating numerical pictorial division under the repetitive groundwork. The proposed R-NSBMF approach is investigated on numerous computer numerical pictures (Girl, Lena, Pepper and F16) on spacious outlier percentage and the proposed R-NSBMF approach exposes admirable outlier-deportation numerical pictures than the mean filter (mf), standard median filter (SMF), adaptive median filter (AMF), weight median filter (WMF) and original NSBMF and it professes admirable peak signal-to-noise ratio (PSNR) and pictorial quality
Integrating blockchain, internet of things, and cloud for secure healthcare
Get PDFThis research paper shows a decentralized healthcare architecture using the integration of internet of things (IoT), blockchain, and cloud to improve speed up tuple broken security as well as scalability. Real time health information (e.g., pulse rate, sugar level) from patients is captured by IoT devices and preprocessed at the fog computing layer to securely send them to a cloud platform. Immutability and transparency Patient health records recorded by blockchain solutions are highly irreversible due to the underlying technology, while smart contracts take care of data integrity and privacy. The cloud layer delivers storage that scales and works, also including real-time analytics to access patient data from anywhere for healthcare providers while the core helps manage long-term information architecture. It does so by automating healthcare workflows and taking some of the manual interventional processes out such that care delivery becomes even more efficient. Together, these technologies provide a secure, efficient, patient-centered healthcare system whose architecture can easily support future needs in remote patient monitoring and inter-institutional collaboration, responding to emerging demands from modern healthcare systems
Multimodal perception for enhancing human computer interaction through real-world affect recognition
Get PDFHuman-Computer Interaction can benefit from real-world affect recognition in applications like healthcare and assistive robotics. Human express emotions through various modalities, with audio-visual being the most significant. Using a unimodal approach, such as only speech or visual, is challenging in natural, dynamic environments. The proposed methodology integrated a pretrained model with a convolution neural network (CNN) to provide a robust initialization point and address the limited availability of facial expression data. The multimodal framework enhances discriminative power by combining visual scores with speech. This work addresses the challenges at each stage of the real-world affect recognition framework, including data preprocessing, feature extraction, feature fusion, and final classification. A 1D-CNN is employed for training on spectral and prosodic audio features, while deep visual features are processed using a 2D-CNN. The proposed system's performance was evaluated on the extended Cohn-Kanade (CK+), acted-facial-expressions in-the-wild (AFEW), and real-world-affective-face-database (RAF) datasets, which are commonly used in face recognition research. Experimental results indicate that 2% to 5% of visual data from natural settings were undetected, and the inclusion of the audio modality improved performance by providing relevant and supplementary information
Enhancing BEMD decomposition using adaptive support size for CSRBF functions
Get PDFDespite their widespread development, the Fourier transform and wavelet transform are still unsuitable for analyzing non-stationary and non-linear signals. To address this limitation, bidimensional empirical mode decomposition (BEMD) has emerged as a promising technique. BEMD effectively extracts structures at various scales and frequencies but faces significant computational complexity, primarily during the extremum interpolation phase. To mitigate this, different interpolation functions were presented and suggested, with BEMD using compactly supported radial basis functions (BEMD-CSRBF) showing promising results in reducing computational cost while maintaining decomposition quality. However, the choice of support size for CSRBF functions significantly impacts the quality of BEMD. This article presents an enhancement to the BEMD-CSRBF algorithm by adjusting the CSRBF support size based on the extrema distribution of the image. Our method’s results show a significant improvement in the BEMD-CSRBF algorithm’s quality. Furthermore, when compared to the other two approaches to BEMD, it shows higher accuracy in terms of both intrinsic mode function (IMF) quality and computational efficiency
Energy and cost-aware workload scheduler for heterogeneous cloud platform
Get PDFParallel scientific workloads, often represented as directed acyclic graphs (DAGs), consist of interdependent tasks that require significant data exchange and are executed on distributed clusters. The communication overhead between tasks running on different nodes can lead to substantial increases in makespan, energy usage, and monetary costs. Therefore, there is potential to balance communication and computation to reduce these costs. In this paper, we introduce an energy and cost-aware workload scheduler (ECAWS) tailored for executing parallel scientific workloads, generated by the internet of things (IoT), in a heterogeneous cloud environment. The performance of the proposed ECAWS model is evaluated against existing models using the Inspiral scientific workload. Results indicate that ECAWS outperforms other models in reducing makespan, costs, and energy consumption
Study on postal life insurance attributes and its growth prediction using machine learning algorithms
Get PDFThe oldest insurer in the country, since 1884, is Postal Insurance. For today's livelihood, the citizens of India's life-saving coverage and insurance have become necessary. For customers to overcome difficult situations, life insurance is crucial in creating confidence. This is one of the highlights of the Postal organization. Under postal life insurance (PLI), the volume of new policies is enrolled throughout India, and a supervised machine learning (ML) process for finding the business cluster is carried out based on this data, which is discussed. A ML algorithm that predicts the growth for the future, using a suitable algorithm for accessing the features and process to identify the prediction model, has been developed, which is the main goal of this study. Simulation results show that expected is one of the most important variables used to predict and that both random forest (RF) and logistic regression outperformed the other two models. The RF model is the most effective and fastest in predicting the system's future state, and it shows the highest value for the PLI product
Photoplethysmograph-based time-frequency and machine learning applications on biomedical signal analysis for medical diagnosis
Get PDFMachine learning (ML) integration in biomedical signal processing and medical diagnosis has the potential to revolutionize healthcare by improving diagnostic accuracy. This paper focuses on the applications of different ML algorithms for analyzing real-time physiological data collected from Photoplethysmography (PPG) sensors. Heart rate variability (HRV) analysis using electrocardiography (ECG) signals makes the process longer and bulky. Therefore, this paper demonstrates the real-time generation of HRV signals using a simple, low-cost, and non-invasive PPG sensor which is further processed using the Arduino ATMEGA328P microcontroller and then interfaced to a PC for display to investigate the usefulness of HRV feature analysis. HRV features have been computed using time domain analysis (TA), and frequency domain analysis (FA). At last, these TA and FA indices have been given to different ML models that could predict the gender, age group, and physiological conditions of a human being. Prediction of the physiological conditions using TA, FA, and ML models simultaneously makes the proposed approach more novel than the other existing methods. Comparative analysis of different ML approaches using ROC curves and confusion matrices has been shown to find the effectiveness and precision of different proposed models. It shows random forest ML approach has achieved 91% accuracy in identifying the physiological conditions. This simple yet accurate real-time PPG-based time-frequency ML system might be useful in medical assessment with faster response
Prediction of chronic diseases based on ML packages using spark MLlib
Get PDFHeart disease, diabetes, and breast cancer pose significant global health challenges, and effectively addressing these chronic diseases necessitates a coordinated international effort. The integration of machine learning and predictive analytics offers promising solutions for tackling these issues. Our study presents a unified model that utilizes the random forest (RF) algorithm and SparkMLlib to predict these three diseases, testing the model on three distinct datasets and evaluating its performance using scientific metrics, including the receiver operating characteristic (ROC) curve, accuracy, precision, recall, and F1-score. Furthermore, we aim to investigate whether variations in medical data and contextual factors impact the results. The findings indicate that while the model shows strong overall performance, its effectiveness may differ for each disease due to factors such as data characteristics, disease-specific features, model behavior, and various biological and medical considerations; understanding these factors is essential for improving model performance and ensuring its appropriate use in clinical environments
Advanced tourist arrival forecasting: a synergistic approach using LSTM, Hilbert-Huang transform, and random forest
Get PDFAn advanced synergistic approach for forecasting tourist arrivals is presented, integrating long short-term memory (LSTM), Hilbert-Huang transform (HHT), and random forest (RF). LSTM is leveraged for its capability to capture long-term dependencies in sequential data. Additional data from Google Trends (GT) is processed with HHT for feature extraction, followed by feature selection using the RF algorithm. The combined HHT-RF-LSTM model delivers highly accurate forecasts. Evaluation employs regression analysis with metrics such as root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and mean square error (MSE), highlighting the effectiveness of this innovative approach in predicting tourist arrivals. This methodology provides a robust framework for handling limited datasets and improving forecast reliability. By incorporating diverse data sources and advanced preprocessing techniques, the model enhances prediction performance, demonstrating the strong performance of RF in feature selection
Evaluating low-cost internet of things and artificial intelligence in agriculture
Get PDFThis article investigates the transformative impact of low-cost internet of things (IoT) solutions on the agricultural sector, with a particular emphasis on integrating artificial intelligence (AI) and machine learning (ML) technologies. The study aims to illustrate how affordable IoT technologies, when combined with advanced AI and ML capabilities, can serve as a significant asset for small and medium-sized farms. It addresses the economic and technical barriers these farms face in adopting such technologies, including high initial costs and the complexity of implementation. By conducting a comprehensive evaluation of existing IoT hardware and software, the research identifies and highlights innovative, cost-effective solutions that have the potential to drive significant advancements in agricultural practices. The findings underscore how these integrated technologies can enhance operational efficiency, increase productivity, and support sustainable agricultural development. Additionally, the paper explores the potential challenges and limitations of adopting these technologies, offering insights into how they can be mitigated. Overall, the study demonstrates that the convergence of low-cost IoT with AI and ML presents a valuable opportunity for modernizing agriculture and improving farm management