Article Per Year (5 Year)
p-Index From 2020 - 2025
3.935
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) International Journal of Advances in Applied Sciences ComEngApp : Computer Engineering and Applications Journal Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) JSI: Jurnal Sistem Informasi (E-Journal) Scientific Journal of Informatics IJoICT (International Journal on Information and Communication Technology) Sistemasi: Jurnal Sistem Informasi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JOURNAL OF APPLIED INFORMATICS AND COMPUTING JOISIE (Journal Of Information Systems And Informatics Engineering) INFOMATEK: Jurnal Informatika, Manajemen dan Teknologi Jurnal Teknologi Dan Sistem Informasi Bisnis Jurnal Sistem Komputer dan Informatika (JSON) Sriwijaya Journal of Informatics and Applications Jurnal Generic REKA ELKOMIKA: Jurnal Pengabdian kepada Masyarakat Sriwijaya Accounting Community Services
Winda Kurnia Sari
Universitas Sriwijaya
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Other

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
A deep learning-based myocardial infarction classification based on single-lead electrocardiogram signal Darmawahyuni, Annisa; Sari, Winda Kurnia; Afifah, Nurul; Tutuko, Bambang; Nurmaini, Siti; Marcelino, Jordan; Isdwanta, Rendy; Khairunnisa, Cholidah Zuhroh
International Journal of Advances in Applied Sciences Vol 14, No 2: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijaas.v14.i2.pp352-360

Abstract

Acute myocardial infarction (AMI) carries a significant risk, emphasizing the critical need for precise diagnosis and prompt treatment of the responsible lesion. Consequently, we devised a neural network algorithm in this investigation to identify myocardial infarction (MI) from electrocardiograms (ECGs) autonomously. An ECG is a standard diagnostic tool for identifying acute MI due to its affordability, safety, and rapid reporting. Manual analysis of ECG results by cardiologists is both time-consuming and prone to errors. This paper proposes a deep learning algorithm that can capture and automatically classify multiple features of an ECG signal. We propose a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) for automatically diagnosing MI. To generate the hybrid CNN-LSTM model, we proposed 39 models with hyperparameter tuning. As a result, the best model is model 35, with 86.86% accuracy, 75.28% sensitivity and specificity, and 83.56% precision. The algorithm based on a hybrid CNN-LSTM demonstrates notable efficacy in autonomously diagnosing AMI and determining the location of MI from ECGs.
Fake News Detection Using Optimized Convolutional Neural Network and Bidirectional Long Short-Term Memory Sari, Winda Kurnia; Azhar, Iman Saladin B.; Yamani, Zaqqi; Florensia, Yesinta
Computer Engineering and Applications Journal (ComEngApp) Vol. 13 No. 3 (2024)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The spread of fake news in the digital age threatens the integrity of online information, influences public opinion, and creates confusion. This study developed and tested a fake news detection model using an enhanced CNN-BiLSTM architecture with GloVe word embedding techniques. The WELFake dataset comprising 72,000 samples was used, with training and testing data ratios of 90:10, 80:20, and 70:30. Preprocessing involved GloVe 100-dimensional word embedding, tokenization, and stopword removal. The CNN-BiLSTM model was optimized with hyperparameter tuning, achieving an accuracy of 96%. A larger training data ratio demonstrated better performance. Results indicate the effectiveness of this model in distinguishing fake news from real news. This study shows that the CNN-BiLSTM architecture with GloVe embedding can achieve high accuracy in fake news detection, with recommendations for further research to explore preprocessing techniques and alternative model architectures for further improvement.
Sentiment-Based Knowledge Discovery pada Aplikasi iPusnas Menggunakan Metode Machine Learning dan Deep Learning Ayuningtiyas, Pratiwi; Tania, Ken Ditha; Sari, Winda Kurnia
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10258

Abstract

iPusnas is a digital library application developed by the National Library of the Republic of Indonesia since 2016, with over 1.5 million users. Despite its potential to improve literacy, the application has only received a rating of 2.0. This study conducted sentiment analysis on 7.596 reviews obatained through web scraping using the Google Play Scraper Library. The data then underwent preprocessing steps including case folding, data cleaning, tokenization, stopword removal, and stemming. Reviews were automatically labeled based on the rating score, where scores of 1-3 were categorized as negative, with 5.174 entries, and scores 4-5 as positive, with 2.422 entries. The dataset was split in an 80:20 ratio, with 80% for training, and 20% for testing. The machine learning models tested were SVM, Random Forest, CNN, LSTM, and RNN. The evaluation metrics included accuracy, precision, recall, F1-score, and confusion matrix. CNN and LSTM achieved the highest accuracy (82%), Random Forest and CNN achieved the highest precision (81%), RNN the highest recall (79%) and LSTM the highest F1-score (79%). McNemar test showed a significant difference between Random Forest and CNN, Random Forest and LSTM, and between RNN and LSTM, while CNN and LSTM, as well as CNN and RNN, showed no significant difference.
User Review Automation: Detecting Actionable Complaints on Gojek in the Play Store using the LSTM Method Ramadhani, Indira Nailah; Sari, Winda Kurnia; Tania, Ken Ditha
Sistemasi: Jurnal Sistem Informasi Vol 14, No 6 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i6.5708

Abstract

This study aims to develop an automatic complaint detector for Gojek app reviews using Long Short Term Memory (LSTM). The dataset consists of 225,002 user reviews on the Google Play Store. The purpose of this study itself is to facilitate the service team in understanding the shortcomings of the application complained by users. Automatic complaint detection will facilitate the service team to take action to resolve the problems experienced by users. Therefore, the review data provided by users is properly processed using LSTM to create an effective and efficient detection system. Processing is carried out using three different data sharing ratios, namely 90:10, 80:20, and 70:30 to ensure that the system is stable and effective. The accuracy results of the three data sharing ratios reached above 90%, thus proving that the system is able to detect complaints well. A pre-built dashboard is used to visualize the results of the system built using LSTM to facilitate monitoring the classification results. This system is expected to facilitate companies in detecting all user complaints and finding solutions to improve services to provide comfort for users.
Klasifikasi Sinyal EEG Untuk Mengenali Jenis Emosi Menggunakan Recurrent Neural Network Utari, Aspirani; Rini, Dian Palupi; Sari, Winda Kurnia; Saputra, Tommy
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7162

Abstract

This research focuses on in-depth exploration and analysis of the application of two types of Recurrent Neural Network (RNN), namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The two models are drilled with the same parameters, consist of three layer, use the relu activation function, and apply 1 dropout level. In order to compare the performance of the two, experiments were carried out using five groups of datasets for training and performance evaluation purposes. The evaluation includes metrics such as accuracy, recall, F1-score, and area under the curve (AUC). The dataset used is Eeg Emotion which contains 2458 unique variables. In terms of performance, LSTM succeeded in outperforming GRU in the task of classifying emotional data based on EEG signals. On the other hand, GRU shows advantages in accelerating the training process compared to LSTM. Although the accuracy of both methods is almost similar in all data divisions, in the evaluation of the ROC curve, the LSTM model demonstrates superiority with a more optimal curve compared to GRU.
Klasifikasi Sinyal EEG Untuk Mengenali Jenis Emosi Menggunakan Deep Learning Rosemari, Pita; Rini, Dian Palupi; Sari, Winda Kurnia
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7172

Abstract

This research focuses on in-depth exploration and analysis of the application of three types of deep learning, namely Convolutional Neural Networks (CNN), Bidirectional LSTM (BI-LSTM) and Deep Neural Network (DNN). The three models are trained with the same parameters, consisting of three layers, using the Relu activation function, and applying 1 dropout level. In order to compare the performance of the three, experiments were carried out using three dataset groups for training and evaluation of performance. The evaluation includes metrics such as accuracy, recall, F1-Score, and areas under the curve (AUC). The dataset used is EEG Emotion which consists of 2458 unique variables. In terms of performance, BI-LSTM succeeded in outperformed the performance of CNN and DNN in the task of classification of emotional data based on EEG signals. On the other hand, CNN and DNN show excess in the acceleration of the training process compared to BI-LSTM. Although the accuracy of the two methods is almost similar in all data distribution, but in the evaluation of the ROC curve, the BI-LSTM model demonstrates superior with a more optimal curve than CNN and DNN.
Sentiment Analysis on Google Play Store Reviews to Measure User Perception of the Gojek Application Using CNN Anissa, Cahya Rahmi; Tania, Ken Ditha; Sari, Winda Kurnia
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11084

Abstract

This study was conducted to analyze sentiment towards user reviews from the Google Play Store regarding the Gojek application. The analysis aims to measure user perceptions using a Convolutional Neural Network (CNN). This study aims to understand user views on the Gojek application. By understanding user perceptions, the information obtained can be utilized by the company's service team to improve the quality of the application for users. User perceptions are grouped into three labels: positive, neutral, and negative. To produce an effective model, this study uses three data sharing ratios simultaneously with the same parameters: 90:10, 80:20, and 70:30. Due to the large amount of data, random sampling is needed to balance the data and thus increase accuracy in the data processing process. Model evaluation was carried out using a confusion matrix, precision, recall, and F1-Score. The results obtained with the highest accuracy of 84.29%. This study successfully demonstrates that CNN is able to process user review data well.
Co-Authors Aditya Putra Perdana Prasetyo Ahmad Rifai Anissa, Cahya Rahmi Aspirani Utari Aulia, Cantika Ayuningtiyas, Pratiwi B Azhar, Iman Saladin Bambang Tutuko Darmawahyuni, Annisa Deris Stiawan Dian Palupi Rini Dian Palupi Rini Dian Palupi Rini Dian Palupi Rini Dinna Yunika Hardiyanti Ery Erman Firmansyah, M. Daffa Florensia, Yesinta Gumay, Naretha Kawadha Gumay, Naretha Kawadha Pasemah Hardini Novianti Iman Saladin B. Azhar Isdwanta, Rendy Jambak, Muhammad Ihsan Jordan Marcelino Kemahyanto Exaudi Ken Dhita Tania Ken Ditha Tania Khairunnisa, Cholidah Zuhroh Lakeisyah, Eka Therina Marcelino, Jordan Marshella, Siti Hariza Mas Ud, Khalid Al Maulana, Rahmat Mira Afrina Muhammad Afif Muhammad Hidayat Nadrota Acta, Muhammad Fakhri Novi Yusliani Pacu Putra Pangestu, Ridho Putri, Aulia Najibah Putri, Naila Raihana Rachmamtullah, Muhammad Naufal Rahman, M. Fadhil Ramadhani, Indira Nailah Rendy Isdwanta Reza Firsandaya Malik Reza Firsandaya Malik Risyahputri, Aliyananda Robani, M Tsabita Rosemari, Pita Sahira, Mutia Salsabila, Adella Salsabila, Shofi Saputra, Marco Saputra, Tommy Sari, Tri Kurnia Siti Nurmaini Utari, Aspirani Yamani, Zaqqi