Article Per Year (5 Year)
p-Index From 2019 - 2024
1.621
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) ComEngApp : Computer Engineering and Applications Journal Perfecting a Video Game with Game Metrics Indonesian Journal of Electrical Engineering and Computer Science Sriwijaya Journal of Informatics and Applications
Darmawahyuni, Annisa
Universitas Sriwijaya
Computer Science & IT Engineering

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
Deep ensemble learning for skin lesions classification with convolutional neural network Renny Amalia Pratiwi; Siti Nurmaini; Dian Palupi Rini; Muhammad Naufal Rachmatullah; Annisa Darmawahyuni
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 10, No 3: September 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v10.i3.pp563-570

Abstract

One type of skin cancer that is considered a malignant tumor is melanoma. Such a dangerous disease can cause a lot of death in the world. The early detection of skin lesions becomes an important task in the diagnosis of skin cancer. Recently, a machine learning paradigm emerged known as deep learning (DL) utilized for skin lesions classification. However, in some previous studies by using seven class images diagnostic of skin lesions classification based on a single DL approach with CNNs architecture does not produce a satisfying performance. The DL approach allows the development of a medical image analysis system for improving performance, such as the deep convolutional neural networks (DCNNs) method. In this study, we propose an ensemble learning approach that combines three DCNNs architectures such as Inception V3, Inception ResNet V2 and DenseNet 201 for improving the performance in terms of accuracy, sensitivity, specificity, precision, and F1-score. Seven classes of dermoscopy image categories of skin lesions are utilized with 10015 dermoscopy images from well-known the HAM10000 dataset. The proposed model produces good classification performance with 97.23% accuracy, 90.12% sensitivity, 97.73% specificity, 82.01% precision, and 85.01% F1-Score. This method gives promising results in classifying skin lesions for cancer diagnosis.
Segmentation atrioventricular septal defect by using convolutional neural networks based on U-NET architecture Ade Iriani Sapitri; Siti Nurmaini; Sukemi Sukemi; M. Naufal Rachmatullah; Annisa Darmawahyuni
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 10, No 3: September 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v10.i3.pp553-562

Abstract

Congenital heart disease often occurs, especially in infants and fetuses. Fetal image is one of the issues that can be related to the segmentation process. The fetal heart is an important indicator in the process of structural segmentation and functional assessment of congenital heart disease. This study is very challenging due to the fetal heart has a relatively unclear structural anatomical appearance, especially in the artifacts in ultrasound images. There are several types of congenital heart disease that often occurs namely in septal defects it consists of the atrial septal defect, ventricular septal defect, and atrioventricular septal defect. The process of identifying the standard of the heart, especially the fetus, can be identified with a 2D ultrasound video in the initial steps to diagnose congenital heart disease. The process of diagnosis of fetal heart standards can be seen from a variety of spaces, i.e., 4 chamber views. In this study, the standard semantic segmentation process of the fetal heart is abnormal and normal in terms of the perspective of 4 chamber views. The validation evaluation results obtained in this study amounted to 99.79% pixel accuracy, mean iou 96.10%, mean accuracy 97.82%, precision 96.41% recall 95.72% and F1 score 96.02%.
Unidirectional-bidirectional recurrent networks for cardiac disorders classification Annisa Darmawahyuni; Siti Nurmaini; Muhammad Naufal Rachmatullah; Firdaus Firdaus; Bambang Tutuko
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 19, No 3: June 2021
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v19i3.18876

Abstract

The deep learning approach of supervised recurrent network classifiers model, i.e., recurrent neural networks (RNNs), long short-term memory (LSTM), and gated recurrent units (GRUs) are used in this study. The unidirectional and bidirectional for each cardiac disorder (CDs) class is also compared. Comparing both phases is needed to figure out the optimum phase and the best model performance for ECG using the Physionet dataset to classify five classes of CDs with 15 leads ECG signals. The result shows that the bidirectional RNNs method produces better results than the unidirectional method. In contrast to RNNs, the unidirectional LSTM and GRU outperformed the bidirectional phase. The best recurrent network classifier performance is unidirectional GRU with average accuracy, sensitivity, specificity, precision, and F1-score of 98.50%, 95.54%, 98.42%, 89.93% 92.31%, respectively. Overall, deep learning is a promising improved method for ECG classification.
Neural network technique with deep structure for improving author homonym and synonym classification in digital libraries Firdaus Firdaus; Siti Nurmaini; Varindo Ockta Keneddi Putra; Annisa Darmawahyuni; Reza Firsandaya Malik; Muhammad Naufal Rachmatullah; Andre Herviant Juliano; Tio Artha Nugraha
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 19, No 4: August 2021
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v19i4.18878

Abstract

Author name disambiguation (AND), also recognized as name-identification, has long been seen as a challenging issue in bibliographic data. In other words, the same author may appear under separate names, synonyms, or distinct authors may have similar to those referred to as homonyms. Some previous research has proposed AND problem. To the best of our knowledge, no study discussed specifically synonym and homonym, whereas such cases are the core in AND topic. This paper presents the classification of non-homonym-synonym, homonym-synonym, synonym, and homonym cases by using the DBLP computer science bibliography dataset. Based on the DBLP raw data, the classification process is proposed by using deep neural networks (DNNs). In the classification process, the DBLP raw data divided into five features, including name, author, title, venue, and year. Twelve scenarios are designed with a different structure to validate and select the best model of DNNs. Furthermore, this paper is also compared DNNs with other classifiers, such as support vector machine (SVM) and decision tree. The results show DNNs outperform SVM and decision tree methods in all performance metrics. The DNNs performances with three hidden layers as the best model, achieve accuracy, sensitivity, specificity, precision, and F1-score are 98.85%, 95.95%, 99.26%, 94.80%, and 95.36%, respectively. In the future, DNNs are more performing with the automated feature representation in AND processing.
Author identification in bibliographic data using deep neural networks Firdaus Firdaus; Siti Nurmaini; Reza Firsandaya Malik; Annisa Darmawahyuni; Muhammad Naufal Rachmatullah; Andre Herviant Juliano; Tio Artha Nugraha; Varindo Ockta Keneddi Putra
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 19, No 3: June 2021
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v19i3.18877

Abstract

Author name disambiguation (AND) is a challenging task for scholars who mine bibliographic information for scientific knowledge. A constructive approach for resolving name ambiguity is to use computer algorithms to identify author names. Some algorithm-based disambiguation methods have been developed by computer and data scientists. Among them, supervised machine learning has been stated to produce decent to very accurate disambiguation results. This paper presents a combination of principal component analysis (PCA) as a feature reduction and deep neural networks (DNNs), as a supervised algorithm for classifying AND problems. The raw data is grouped into four classes, i.e., synonyms, homonyms, homonyms-synonyms, and non-homonyms-synonyms classification. We have taken into account several hyperparameters tuning, such as learning rate, batch size, number of the neuron and hidden units, and analyzed their impact on the accuracy of results. To the best of our knowledge, there are no previous studies with such a scheme. The proposed DNNs are validated with other ML techniques such as Naïve Bayes, random forest (RF), and support vector machine (SVM) to produce a good classifier. By exploring the result in all data, our proposed DNNs classifier has an outperformed other ML technique, with accuracy, precision, recall, and F1-score, which is 99.98%, 97.98%, 97.86%, and 99.99%, respectively. In the future, this approach can be easily extended to any dataset and any bibliographic records provider.
Coronary Heart Disease Interpretation Based on Deep Neural Network Annisa Darmawahyuni; Siti Nurmaini; Firdaus Firdaus
Computer Engineering and Applications Journal Vol 8 No 1 (2019)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (484.945 KB) | DOI: 10.18495/comengapp.v8i1.288

Abstract

Coronary heart disease (CHD) population increases every year with a significant number of deaths. Moreover, the mortality from coronary heart disease gets the highest prevalence in Indonesia at 1.5 percent. The misdiagnosis of coronary heart disease is a crucial fundamental that is the major factor that caused death. To prevent misdiagnosis of CHD, an intelligent system has been designed. This paper proposed a simulation which can be used to diagnose the coronary heart disease in better performance than the traditional diagnostic methods. Some researches have developed a system using conventional neural network or other machine learning algorithm, but the results are not a good performance. Based on a conventional neural network, deeper neural network (DNN) is proposed to our model in this work. As known as, the neural network is a supervised learning algorithm that good in the classification task. In DNN model, the implementation of binary classification was implemented to diagnose CHD present (representative “1”) or CHD absent (representative “0”). To help performance analysis using the UCI machine learning repository heart disease dataset, ROC Curve and its confusion matrix were implemented in this work. The overall predictive accuracy, sensitivity, and specificity acquired was 96%, 99%, 92%, respectively.
Delineation of electrocardiogram morphologies by using discrete wavelet transforms Annisa Darmawahyuni; Siti Nurmaini; Hanif Habibie Supriansyah; Muhammad Irham Rizki Fauzi; Muhammad Naufal Rachmatullah; Firdaus Firdaus; Bambang Tutuko
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 1: April 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v22.i1.pp159-167

Abstract

The accuracy of electrocardiogram (ECG) delineation can affect the precise diagnose for cardiac disorders interpretation. Some nonideal ECG presentation can make a false decision in precision medicine. Besides, the physiological variation of heart rate and different characteristics of the different ECG waves in terms of shape, frequency, amplitude, and duration is also affected. This paper proposes a discrete wavelet transform (DWT), non-stationary signal analysis for noise removal, and onset-offset of PQRST feature extraction. A well-known database from Physionet: QT database (QTDB) is used to validate the DWT function for detecting the onset and offset of P-wave, QRS-complex, and T-wave localization. From the results, P-peak detection gets the highest result that achieves 2.19 and 13.62 milliseconds of mean error and standard deviation, respectively. In contrast, Toff has obtained the highest error value due to differences in the T-wave morphology. It can be affected by inverted or biphasic T-waves and others.
Text Generation using Long Short Term Memory to Generate a LinkedIn Post Muhammad Rizqi Assabil; Novi Yusliani; Annisa Darmawahyuni
Sriwijaya Journal of Informatics and Applications Vol 4, No 2 (2023)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v4i2.64

Abstract

LinkedIn is one of the most popular sites out there to advertise oneself to potential employer. This study aims to create a good enough text generation model that it can generate a text as if it were made by someone who posts on LinkedIn. This study will use a Neural Network layer called Long Short Term Memory (LSTM) as the main algorithm and the train data consists of actual posts made by users in LinkedIn. LSTM is an algorithm that is created to reduce vanishing and exploding gradient problem in Neural Network. From the result, final accuracy and loss varies. Increasing learning rate from its default value of 0.001, to 0.01, or even 0.1 creates worse model. Meanwhile, increasing dimensions of LSTM will sometimes increases training time or decreases it while not really increasing model performance. In the end, models chosen at the end are models with around 97% of accuracy. From this study, it can be concluded that it is possible to use LSTM to create a text generation model. However, the result might not be too satisfying. For future work, it is advised to instead use a newer model, such as the Transformer model.
Co-Authors Ade Iriani Sapitri Andre Herviant Juliano Bambang Tutuko Dian Palupi Rini Firdaus Firdaus Hanif Habibie Supriansyah M. Naufal Rachmatullah Muhammad Irham Rizki Fauzi Muhammad Naufal Rachmatullah Muhammad Rizqi Assabil Novi Yusliani Renny Amalia Pratiwi Reza Firsandaya Malik Siti Nurmaini Sukemi Sukemi Tio Artha Nugraha Varindo Ockta Keneddi Putra