Computer Engineering and Applications Journal (ComEngApp, Universitas Sriwijaya)
Not a member yet
102 research outputs found
Sort by
An Improved Myocardial Infarction Detection using Convolutional Neural Network and Graph Neural Network Algorithm
No full textMyocardial infarction (MI) is a crucial health problem and its mortality rate is higher than that of cancer. It is the damage and death of heart muscle from the sudden blockage of a coronary artery by a blood clot. Although lots of researches have been carried out with impressive performance record for detection of MI, however, existing approaches for MI detection can be improved upon for better performance. A vital piece of medical technology that aids in the diagnosis of a number of heart-related disorders in patients is an electrocardiogram (ECG). To find significant episodes in long-term ECG data, an automated diagnostic method is needed. Cardiologists face a very difficult problem when trying to quickly examine long-term ECG records. To pinpoint critical occurrences, a computer-based diagnosing tool is necessary. In this study we employ Convolutional Neural Network (CNN) algorithm with Graph Neural Network (GNN) to select best features and make appropriate classifications. The result of the study gave f1 score of 99.58%, precision of 99.5% and an accuracy of 99.72%. Our proposed model have shown a significant improvement in the detection of MI, this will aid in effectively addressing the challenge of performance drawback in this domain of research
The Eye and Nose Identification Chip Controller-Based on Robot Vision Using Weightless Neural Network Method
No full textIncreasingly advanced image analysis in computer vision, allowing computers to interpret, identify, and analyze pictures with accuracy comparable to humans. The availability of data sources in decimal, hexadecimal, or binary forms enables researchers to take the initiative in applying their study findings. Decimal formats are typically used on traditional computers like desktops and minicomputers, whereas hexadecimal and binary formats were utilized on single-chip controllers. Weightless Neural Network is a method that can be implemented in a single chip controller. The aim of this research is to develop a facial recognition system, for eye and mouth identification, that works in a single chip controller or also called a microcontroller. The suggested method is a Weightless Neural Network with Immediate Scan approach for processing and identifying eye and nose patterns. The data will be handled in many memory locations that are specifically designed to handle massive volumes of data. The data is made up of primary face data sheets and face input data. The data sets utilized are (x,y) pixels, and frame sizes range from 90x90 pixels to 110x110 pixels. Each face shot will be processed by selecting the region of the eyes and nose and saving it as an image file. The eye and nose will identify the face frame. Next, the photos will be converted to binary format. A magazine matrix will be used to transmit binary data from a minicomputer to a microcontroller via serial connection. Based on a known pattern, the resultant similarity accuracy is 83,08% for the eye and 84,09% for the sternum. In contrast, the similarity percentage for an eye ranges from 70% to 85% for an undefined pattern
MRI-Based Brain Tumor Instance Segmentation Using Mask R-CNN
No full textBrain tumor segmentation is a crucial step in medical image analysis for the accurate diagnosis and treatment of patients. Traditional methods for tumor segmentation often require extensive manual effort and are prone to variability. In this study, we propose an automated approach for brain tumor segmentation using Mask R-CNN, a state-of-the-art deep learning model for instance segmentation. Our method leverages MRI images to identify and delineate brain tumors with high precision. We trained the Mask R-CNN model on a dataset of annotated MRI images and evaluated its performance using the mean Average Precision (mAP) metric. The results demonstrate that our model achieves a high mAP of 90.3%, indicating its effectiveness in accurately segmenting brain tumors. This automated approach not only reduces the manual effort required for tumor segmentation but also provides consistent and reliable results, potentially improving clinical outcomes
A Hybrid of Fuzzy C-Means For The Segmentation In CT Scan and X-Ray Images For Screening The COVID-19 Patients
No full textIn this paper, using CT scan and X-ray images, we present a hybrid approach, based on combining fuzzy C-means with k-means clustering, to evaluate and determine pneumonia infection caused by the coronavirus disease (COVID-19). To achieve this objective, we introduce a hybrid method that combines fuzzy C-means clustering with K-means clustering. This hybrid approach is designed to effectively segment object boundaries within medical images, enabling the precise identification of pneumoniarelated features. In addition to our hybrid method, we compare its performance with two other segmentation approaches: the Expectation Maximization (EM) algorithm and 2D Entropy segmentation. Which, the method we propose uses a comparison between the performances of the based on a database of medical imaging test. Experimental results showed that the proposed approach outperforms, it was found that the hybrid fuzzy C-means algorithm segmentation images methods give better performance in terms of accuracy, precision, and F-measure, which is effective in boundaries segmentation. Comparative results of the accuracy and image quality index demonstrate the robustness of AI. It also helps to improve work efficiency with accurate analysis of COVID-19 infection on CT scan and X-rays. In addition, the approach helps radiologists make clinical decisions for diagnosis, follow-up, and prognosis
Image Classification of Traditional Indonesian Cakes Using Convolutional Neural Network (CNN)
No full textIndonesia is one of the countries famous for its traditional culinary. Traditional cakes in Indonesia are traditional snacks typical of the archipelago\u27s culture which have a variety of textures, shapes, colors that vary and some are similar so that there are still many people who do not know the name of the cake from the many types of traditional Indonesian cakes. The problem can be solved by creating a traditional cake image recognition system that can be programmed and trained to classify various types of traditional Indonesian cakes. The Convolutional Neural Network method with the AlexNet architecture model is used in this research to predict various kinds of traditional Indonesian cakes. The dataset used in this research is 1846 datasets with 8 classes of cake images. This study trained the AlexNet model with several optimizers, namely, Adam optimizer, SGD, and RMSprop. The best parameters from the model testing results are at batchsize 16, epoch 50, learning rate 0.01 for SGD optimizer and learning rate 0.001 for Adam and RMSprop optimizers. Each optimizer tested produces different accuracy, precision, recall, and f1_score values. The highest test results that have been carried out on the image dataset of typical Indonesian traditional cakes are obtained by the Adam optimizer with an accuracy value of 79%
Augmented Reality in STEM Using Personalized Learning to Promote Students’ Understanding
No full textThe current curriculum highlights the premise of self-directed learning performed by students. Additionally, technological uses in educational settings prove to be a challenging task in a sense of implementing them in learning media and materials used in the classroom. This study aims at investigating the utilization of augmented reality (AR) in STEM (Science, Mathematics, Engineering, and Technology) using personalized learning. This study employed pre-experimental research design, specifically adopting One-Group Pretest-Posttest Design. The findings highlight that students’ pretest scores on average reached 51,6 and significantly improved to 82,67 in their posttest, whereas students’ gain score reached 0,64 which is considered as moderate. Their perspectives towards the use of augmented reality with personalized learning were significantly positive with the percentage of 82,1%. It is evident that the use of augmented reality with personalized learning is a viable option when it comes to affecting the learning outcomes
Optimization of Distributed RSA Encryption and Decription Processing Using Process Scheduling Method In Single Board Computer Cluster Architecture (SBC)
No full textData security is still a major issue regarding the need for data confidentiality. The encryption process using the RSA algorithm is still the most popular method used in securing data because the complexity of the mathematical equations used in this algorithm makes it difficult to hack. However, the complexity of the RSA algorithm is still a major problem that hinders its application in a more complex application. Optimization is needed in the processing of this RSA algorithm, one of which is by running it on a distributed system. In this paper, we propose an approach with a FIFO process scheduling algorithm that runs on a single board computer cluster. The test results show that the allocation of resources in a system that uses a FIFO process scheduling algorithm is more efficient and shows a decrease in the overall processing time of RSA encryption
Application of Machine Learning in Clustering Maize Producing Regions in Indonesia
No full textMaize is considered an important commodity with promising market prospects. Given the importance of maize, there is a need to increase maize production to meet people\u27s needs and maintain price stability. This study aims to group maize production in Indonesia by region, with the hope of finding areas that have the potential to become maize production centers to reduce dependence on imports. The data used in this research was obtained from the Central Statistics Agency, covering information from 34 provinces during the 2017-2021 period. This analysis uses the K-Means method with the Python programming language. The number of groups is determined using the Elbow Method. The results of this research show that there are three categories of maize production regions: regions with low maize production (below average), regions with medium maize production, and regions with high maize production. A total of 25 provinces are in the low production category, eight provinces are in the medium category, and only East Java is in the high production category. 
Imbalanced Data NearMiss for Comparison of SVM and Naive Bayes Algorithms
No full textThe study aims to improve the diagnosis, management, and prevention of HIV/AIDS by using classification algorithms. The dataset used consists of 707,379 records and 89 columns. Data preprocessing includes removing irrelevant attributes, handling inconsistencies, and balancing the data using the NearMiss method, resulting in a balanced proportion of reactive and non-reactive HIV cases. Once the data is balanced, it is split into several ratios: 60:40, 70:30, 80:20, and 90:10. The classification models used in this study are Naive Bayes and SVM. The models are evaluated using the metrics Accuracy, Precision, Recall, and F1-Score. The results show that the SVM model achieves the highest accuracy of 82.6% with a 90:10 data split at a 6-fold value, and 82.2% with a 60:40 data split at a 5-fold value. On the other hand, Naive Bayes achieves the highest accuracy of 61.1% with a 60:40 data split
The Combination of Black Hat Transform and U-Net in Image Enhancement and Blood Vessel Segmentation in Retinal Images
No full textDiabetic Retinopathy (DR) is a disorder of the eye caused by damage to blood vessels in the retina. Damage to the retinal blood vessels can be analyzed by segmenting the blood vessels on the image. This study proposes a combination of image enhancement and blood vessel segmentation in retinal images. Retinal image enhancement is carried out using the black hat transform method to obtain a detailed view of blood vessels in retinal images. Segmentation of blood vessels in retinal images is carried out using the U-Net architecture. The results of image enhancement are measured using MSE and PSNR. This study has an MSE value below 0.05 and a PSNR above 90dB. The MSE and PSNR values obtained show that the black hat transform method is very good at image enhancement. Segmentation has an accuracy value above 0.95 and a sensitivity value above 0.85. In addition, the specificity value and f1-score are above 0.8. This shows that the proposed stages of image enhancement and blood vessel segmentation are able to accurately recognize blood vessel features in retinal images