Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Artificial intelligence approaches for cardiovascular disease prediction: a systematic review
Get PDFCardiovascular disease (CVD) remains a top global cause of mortality, highlighting the critical need for precise prediction models to improve patient outcomes and optimize healthcare resource allocation. Accurate prediction of CVD is paramount for early diagnosis and reducing mortality rates. Achieving efficient CVD detection and prediction requires a deep understanding of health history and the underlying causes of heart disease. Harnessing the power of data analytics proves advantageous in leveraging vast datasets to make informed predictions, aiding healthcare clinics in disease prognosis. By consistently maintaining comprehensive patient-related data, healthcare providers can anticipate the emergence of potential diseases. Our study conducts a meticulous comparative analysis of CVD prediction methods, focusing on various artificial intelligence (AI) algorithms, particularly classification and predictive algorithms. Scrutinizing approximately sixty papers on cardiovascular disease through the prism of AI techniques, this study carefully assesses the selected literature, uncovering gaps in existing research. The outcomes of this study are expected to empower medical practitioners in proactively predicting potential heart threats and facilitating the implementation of preventive measures
Wind farm integration with the objective of transmission expansion power in South Africa
Get PDFGrowing renewable energy (RE) use mitigates climate change. The integration of large-scale intermittent renewable energy resources (RER) like wind energy into electrical networks has increased during the past decade. However, careful planning is needed to accommodate the long-term energy demand increase. Transmission network expansion planning (TNEP) is the methodical and profitable process of increasing power infrastructure to meet predicted electricity demand while preserving reliability. This article is for those interested in integrating renewable energy sources (RES) into HVTL to increase power availability and decrease losses. The Eros-VuyaniNeptune 400 kV transmission powerline connecting KwaZulu-Natal to the Eastern Cape is used in this study. It was implemented during the transfer of affected residents in the Ingquza Hill Local Municipality, which includes Lusikisiki and Flagstaff villages. This study connects the existing Metro wind farm to the Vuyani substation, which is connected to the Eros substation through a 400 kV transmission line. This research enhanced transmission line power while preserving grid stability with a 27 MW wind farm, and also increased external grid reserve capacity for future usage or unexpected power demand. This paper outlines TNEP’s significant advances using classic (mathematical) and advanced (heuristic and meta-heuristic) optimization approaches
Optimizing supervised learning model for thermal comfort and air quality
Get PDFThermal comfort and indoor air quality are essential factors that directly influence occupants’ health and activity efficiency. Ensuring optimal thermal conditions also supports energy-efficient buildings by preventing energy waste. Machine learning models have been extensively applied to classify thermal comfort and air quality, with supervised learning algorithms such as support vector machine (SVM) and K-nearest neighbor (KNN) showing high accuracy. However, no prior study has compared or combined these two models for simultaneous prediction of thermal comfort and air quality, especially in diverse geographical settings. This study aims to develop and compare SVM and KNN to determine the most accurate model for enhancing thermal comfort and air quality in highland and lowland Islamic boarding schools. Using a quantitative approach, we collected datasets from schools in Wonosobo (highland) and Pontianak (lowland). The results show that KNN outperforms SVM in accuracy, precision, and F1-score. Additionally, a hybrid model integrating both algorithms further improves accuracy, achieving 91%. These findings highlight the effectiveness of machine learning in optimizing environmental conditions in educational settings
Advanced generalized integrator based phase lock loop under complex grid condition: a comparative analysis
Get PDFIntegration of renewable energy systems (RESs) to the grid leads to various power quality issues. A proper control approach for the interfaced inverter is required to mitigate the uncertainties caused in the grid due to the RESs association to maintain the grid stability. The presence of harmonics and DC offset in the input grid voltage of a phase lock loop (PLL) leads to inaccurate phase estimation due to fundamental frequency oscillations. Though many advanced generalized integrator (GI) based PLLs have been developed still there is a need for a robust PLL for synchronization with faster dynamic response, both the harmonics and DC offset rejection ability with precise estimation. This paper proposes some simple yet effective advanced PLLs employing low pass filters (LPFs) in the existing GI based PLLs for faster and accurate phase angle estimation for seamless synchronization under complex grid circumstances. These advanced generalized integrators with LPFs (GI-LPF) based PLLs will provide enhanced and robust synchronization for the grid integrated RESs thereby addressing multiple power quality issues like voltage unbalance, harmonics and DC offsets. The simulation based comparative analysis of the proposed controllers confirm their effective disturbance rejection capability under complex grid conditions by providing advanced and precise response
Ensuring transcript integrity with SHA-3 and digital signature standard: a practical approach
Get PDFAcademic transcripts are essential documents in higher education, reflecting students’ academic performance and capabilities. However, the current management of transcript data at Halu Oleo University (UHO) lacks safeguards against unauthorized alterations, compromising their authenticity. This study proposes a method using the secure hash algorithm 3 (SHA-3) and the digital signature standard (DSS) scheme to ensure the integrity of transcript data. A Python-based web module for managing transcripts and a signing program using SHA-3 and DSS were developed and implemented. This method digitally signs transcript files, ensuring that subsequent changes invalidate the current digital signature. Efficiency tests demonstrated an average signing time of 0.242 seconds, indicating a practical and efficient solution. The study’s findings emphasize how SHA-3 and DSS effectively authenticate academic transcript files, preventing unauthorized modifications and safeguarding the integrity of critical educational records. This method presents a robust and efficient solution for educational institutions to strengthen the security and reliability of their academic record management systems
Fabric materials classification device using YOLOv8 algorithm
Get PDFThe fashion industry in Indonesia significantly contributes to the country’s creative economy. However, public knowledge about various types of fabric materials is still limited, often leading to fraud. This research aims to develop a device that can classify fabric materials based on their structure using computer vision techniques. The device uses a digital microscope endoscope magnifier 1600x USB camera to capture fabric structure images and the YOLOv8 algorithm to classify 17 types of fabric materials from 1,700 raw image data. The research methodology includes collecting fabric image datasets, preprocessing data, and training the YOLOv8 model. The results show that the YOLOv8 model achieves an accuracy of 98%. The classification results are displayed on an LCD connected to NodeMCU ESP8266. System testing shows that the device effectively classifies fabric materials, sends the results to the database via API, and displays the results on the LCD. Overall, this device provides an effective solution for distinguishing types of fabrics and preventing fraud in fabric purchases
Nusantara capital city sentiment analysis using support vector machine and logistic regression
Get PDFThe decision to move position the capital city of Indonesia to East Kalimantan has drawn people’s opinions, both pro and con, among the public, especially ahead of the presidential and vice-presidential elections. Discussions relevant to the relocation and construction of the capital city are increasingly crowded on social media, especially Twitter or X. This research aims to determine public sentiment regarding the development of the national capital to help the government and policymakers improve communication strategies, evaluate existing policies, and make more informed decisions based on public feedback. Public sentiment related to developing the Capital city of the Nusantara, including the presidential palace, toll road, and government offices, is analyzed. Support vector machine (SVM) and logistic regression (LR) algorithms are utilized for the sentiment classification. The results reveal that the SVM performs better in classifying sentiments in X data relevant to developing the Capital city of Nusantara, achieving an average accuracy of 91.97%
Deepfake detection using convolutional neural networks: a deep learning approach for digital security
Get PDFThe development of artificial intelligence technology, especially deep learning, has facilitated the emergence of increasingly sophisticated deepfake technology. Deepfakes utilize generative adversarial networks (GANs) to manipulate images or videos, making it appear as if someone said or did things that never actually happened. As a result, deepfake detection has become a critical challenge, particularly in the context of the spread of false information and digital crime. The purpose of this research is to create a method for detecting deepfakes using a convolutional neural network (CNN) approach, which has been proven effective in visual pattern recognition. Through training with a dataset of original facial images and deepfakes, the CNN model achieved an accuracy of 81.3% in detecting deepfakes. The evaluation results for metrics such as precision, recall, and F1-score indicated good performance overall, although there is still room for improvement. This study is expected to make a significant contribution to enhancing digital security, especially in detecting visual manipulations based on deepfakes
Enhanced deep auto encoder technique for brain tumor classification and detection
Get PDFA brain tumor can develop due to uncontrolled proliferation of aberrant cells in brain tissue. Malignant tumor can influence the nearby brain tissues, potentially resulting in the person's death. Early diagnosis of a brain tumor is crucial for ensuring the survival of patients. This article introduces an improved method using a deep auto encoder for the classification and detection of brain tumor. Magnetic resonance imaging (MRI) images are obtained from the BraTS data sets. The images undergo preprocessing using an adaptive Wiener filter. Image preprocessing is essential for eliminating noise from the input MRI pictures, hence enhancing the accuracy of MRI image classification. The fuzzy C-means technique is used to accomplish image segmentation. The classification model comprises deep auto encoder, convolution neural network (CNN), and K-nearest neighbor techniques. The classification model is developed and evaluated using MRI image slices from the BraTS dataset. Accuracy of deep auto encoder is 98.81%. Accuracy of CNN is 95.50 and accuracy of K-nearest neighbor (KNN) technique is 91.30%
Short-term recall comparison of iconic auditory and visual feedback stimuli in a memory game
Get PDFMultimedia user interfaces incorporate various feedback methods using different modalities. Cognitive processing of audiovisual information requires the ability to recall visual and auditory information, either separately, or in combination. Short-term memory capabilities vary individually and depend on factors such as signal presentation and the number and type of visual and auditory items. In an experiment involving 40 subjects, we aimed to compare short-term auditory and visual capabilities in a serious game application. Subjects played the ‘Pairs’ game at different resolutions, using either visual icons or audio samples, while the total time cost and number of flips were recorded. The results indicate that visual memory is not superior, and female subjects performed better than males at higher levels in the visual task. Additionally, human sound samples, speech and familiar auditory icons were found to be easier to recall than artificial measurement signals