Article Per Year (5 Year)
p-Index From 2020 - 2025
3.48
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 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 : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
Text Classification Using Long Short-Term Memory With GloVe Features Winda Kurnia Sari; Dian Palupi Rini; Reza Firsandaya Malik
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 5, No 2 (2019): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (771.053 KB) | DOI: 10.26555/jiteki.v5i2.15021

Abstract

In the classification of traditional algorithms, problems of high features dimension and data sparseness often occur when classifying text. Classifying text with traditional machine learning algorithms has high efficiency and stability characteristics. However, it has certain limitations with regard to large-scale dataset training. Deep Learning is a proposed method for solving problems in text classification techniques. By tuning the parameters and comparing the eight proposed Long Short-Term Memory (LSTM) models with a large-scale dataset, to show that LSTM with features GloVe can achieve good performance in text classification. The results show that text classification using LSTM with GloVe obtain the highest accuracy is in the sixth model with 95.17, the average precision, recall, and F1-score are 95
Klasifikasi Teks Multilabel pada Artikel Berita Menggunakan Long Short-Term Memory dengan Word2Vec Winda Kurnia Sari; Dian Palupi Rini; Reza Firsandaya Malik; Iman Saladin B. Azhar
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 2 (2020): April 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (639.099 KB) | DOI: 10.29207/resti.v4i2.1655

Abstract

Multilabel text classification is a task of categorizing text into one or more categories. Like other machine learning, multilabel classification performance is limited to the small labeled data and leads to the difficulty of capturing semantic relationships. It requires a multilabel text classification technique that can group four labels from news articles. Deep Learning is a proposed method for solving problems in multilabel text classification techniques. Some of the deep learning methods used for text classification include Convolutional Neural Networks, Autoencoders, Deep Belief Networks, and Recurrent Neural Networks (RNN). RNN is one of the most popular architectures used in natural language processing (NLP) because the recurrent structure is appropriate for processing variable-length text. One of the deep learning methods proposed in this study is RNN with the application of the Long Short-Term Memory (LSTM) architecture. The models are trained based on trial and error experiments using LSTM and 300-dimensional words embedding features with Word2Vec. By tuning the parameters and comparing the eight proposed Long Short-Term Memory (LSTM) models with a large-scale dataset, to show that LSTM with features Word2Vec can achieve good performance in text classification. The results show that text classification using LSTM with Word2Vec obtain the highest accuracy is in the fifth model with 95.38, the average of precision, recall, and F1-score is 95. Also, LSTM with the Word2Vec feature gets graphic results that are close to good-fit on seventh and eighth models.
Multilabel Classification for News Article Using Long Short-Term Memory Winda Kurnia Sari; Dian Palupi Rini; Reza Firsandaya Malik
Sriwijaya Journal of Informatics and Applications Vol 1, No 1 (2020)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

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

Abstract

Multilabel text classification is a task of categorizing text into one or more categories. Like other machine learning, multilabel classification performance is limited when there is small labeled data and leads to the difficulty of capturing semantic relationships. In this case, it requires a multi-label text classification technique that can group four labels from news articles. Deep Learning is a proposed method for solving problems in multi-label text classification techniques. By comparing the seven proposed Long Short-Term Memory (LSTM) models with large-scale datasets by dividing 4 LSTM models with 1 layer, 2 layer and 3-layer LSTM and Bidirectional LSTM to show that LSTM can achieve good performance in multi-label text classification. The results show that the evaluation of the performance of the 2-layer LSTM model in the training process obtained an accuracy of 96 with the highest testing accuracy of all models at 94.3. The performance results for model 3 with 1-layer LSTM obtained the average value of precision, recall, and f1-score equal to the 94 training process accuracy. This states that model 3 with 1-layer LSTM both training and testing process is better.  The comparison among seven proposed LSTM models shows that model 3 with 1 layer LSTM is the best model.
Penerapan Data Mining Dan Tekonologi Machine Learning Pada Klasifikasi Penyakit Jantung Iman Saladin B. Azhar; Winda Kurnia Sari
Jurnal Sistem Informasi Vol 14, No 1 (2022)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (398.495 KB) | DOI: 10.36706/jsi.v14i1.16140

Abstract

Saat ini, dalam dunia kesehatan, data analisis dapat diproses untuk mendeteksi dan mendiagnosa penyakit. Dengan perkembangan teknologi, peranan data mining, dan kebutuhan studi digunakan untuk memecahkan masalah tersebut. Maka dari itu, kami memutuskan untuk mengklasifikasikan penyakit jantung menggunakan 3 teknik machine learning: Logistic Regression, K-Nearest Neighbors, Random Forest, dan Tuned K-Nearest Neighbors dengan bahasa pemrograman python. Dataset yang digunakan dalam penelitian ini mempunyai 13 fitur, 1 variabel label, dan 303 contoh di mana 138 menderita karena penyakit cardiovascular dan 165 sehat. Pengukuran yang digunakan untuk membandingkan kinerja teknik data mining yaitu akurasi, presisi, recall, dan f-measure. Hasilnya menunjukkan bahwa Logistic Regression merupakan teknik dengan kinerja terbaik dan mendapatkan akurasi tertinggi 88,52%.
Penerapan Knowledge Management System (KMS) Berbasis Web Studi Kasus Bagian Teknisi dan Jaringan Fakultas Ilmu Komputer Universitas Sriwijaya Winda Kurnia Sari; Ken Dhita Tania
Jurnal Sistem Informasi Vol 6, No 2 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (363.722 KB) | DOI: 10.36706/jsi.v6i2.1713

Abstract

Abstrak Fakultas Ilmu Komputer Universitas Sriwijaya adalah salah satu perguruan tinggi yang menyadari pentingnya sebuah pendokumentasian dari data dan informasi bagi keberlangsungan kegiatan perguruan tinggi. Saat ini pendokumentasian pengetahuan tentang teknis komputer dan jaringan yang ada di FASILKOM belum terstruktur sehingga berdampak pada kegiatan fakultas yang terasa tidak efektif. Berdasarkan hasil analisa, terdapat banyak knowledge penting dibagian teknisi komputer dan jaringan yang fungsinya untuk menunjang kegiatan perguruan tinggi. Metodologi yang digunakan pada penelitian ini merujuk ke metodologi knowledge management yang dikembangkan oleh Amrit Tiwana. Pada metodologi ini terdapat 4 tahap utama, yaitu: persiapan dan evaluasi infrastruktur, analisis dan desain knowledge management, pengembangan knowledge management dan evaluasi. Knowledge management terasa sangat dibutuhkan pada saat ini untuk memfasilitasi masalah pendokumentasian dan penggunaannya serta meningkatkan kualitas kerja bagi pegawai Fakultas Ilmu Komputer Universitas Sriwijaya.Kata kunci: Knowledge Management System Abstract Faculty of Computer Science Sriwijaya University is one college that is aware of the importance of a documentation of the data and information for the sustainability activities of the college. Currently documenting existing knowledge about computer engineering and network in FASILKOM is unstructured so that the company has not impacted on the activities of the faculty that was not effective. Based on the analysis, there is a lot of important knowledge whose function is to support the college. The methodology used in this study refers to knowledge management methodology developed by Amrit Tiwana. In this methodology, there are 4 main stages, namely: preparation and evaluation of infrastructure, analysis and design of knowledge management, knowledge management development and evaluation. Knowledge management was urgently needed at this time to facilitate the documentation and usage issues and improve the quality of the employee at Faculty of Computer Science Sriwijaya University.Keyword: Knowledge Management System
Perbandingan Kinerja Neural Network dengan Metode Klasifikasi Tradisional dalam Mendiagnosis Penyakit Jantung: Sebuah Studi Komparatif Winda Kurnia Sari; Iman Saladin B Azhar
Jurnal Sistem Informasi Vol 15, No 1 (2023)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/jsi.v15i1.20875

Abstract

Dalam dunia medis, penyakit jantung menjadi salah satu penyebab kematian terbanyak. Oleh karena itu, perlu dikembangkan sistem yang dapat membantu dalam deteksi dan diagnosis penyakit jantung. Dalam penelitian ini, kami menggunakan proses neural network untuk membantu dalam deteksi penyakit jantung dengan menggunakan data training dan testing yang telah dikumpulkan. Data yang digunakan terdiri dari berbagai fitur klinis dan faktor risiko yang dikumpulkan dari pasien yang terkena penyakit jantung. Hasil dari penelitian lain untuk mendiagnosa penyakit jantung dengan metode klasifikasi tradisional menunjukkan akurasi: Logistic Regression 88.52%, K-Nearest Neighbors 78.69%, Random Forest Classifier 86.89%, dan Tuned K-Nearest Neighbors 85.25%. Sedangkan, model neural network yang dikembangkan dapat mengklasifikasikan pasien berdasarkan kondisi jantung mereka dengan akurasi mencapai 91%. Proses pelatihan model melibatkan penggunaan algoritma optimasi RMSprop, dengan cross-validation dan parameter tuning yang dilakukan untuk mencapai hasil terbaik. Model ini mampu memproses input dengan kecepatan tinggi dan menghasilkan hasil klasifikasi yang akurat. Neural network dapat membantu diagnosis awal penyakit jantung bagi tenaga medis. Namun, peningkatan akurasi dan keandalan membutuhkan penelitian lebih lanjut dengan data yang lebih besar dan fitur klinis yang beragam. Dengan optimalisasi model ini, diharapkan penanganan penyakit jantung menjadi lebih efektif dan efisien.
Exploring Long Short-Term Memory and Gated Recurrent Unit Networks for Emotion Classification from Electroencephalography Signals Dian Palupi Rini; Winda Kurnia Sari; Novi Yusliani; Deris Stiawan; Aspirani Utari
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47734

Abstract

This study delves into comparing LSTM and GRU, two recurrent neural network (RNN) models, for classifying emotion data through electroencephalography (EEG) signals. Both models adeptly handle sequential data challenges, showcasing their unique strengths. In EEG emotion dataset experiments, LSTM demonstrated superior performance in emotion classification compared to GRU, despite GRU’s quicker training processes. Evaluation metrics encompassing accuracy, recall, F1-score, and area under the curve (AUC) underscored LSTM’s dominance, which was particularly evident in the ROC curve analysis. This research sheds light on the nuanced capabilities of these RNN models, offering valuable insights into their efficacy in emotion classification tasks based on EEG data. The study explores parameters, such as the number of layers, neurons, and the utilization of dropout, providing a detailed analysis of their impact on emotion recognition accuracy.Purpose: The proposed model in this study is the result of optimizing LSTM and GRU networks through careful parameter tuning to find the best model for classifying EEG emotion data. The experimental results indicate that the LSTM model can achieve an accuracy level of up to 100%.Methods: To improve the accuracy of the LSTM and GRU methods in this research, hyperparameter tuning techniques were applied, such as adding layers, dense layers, flattening layers, selecting the number of neurons, and introducing dropout to mitigate the risk of overfitting. The goal was to find the best model for both methods.Results: The proposed model in this study is capable of classifying EEG emotion data very effectively. The experimental results demonstrate that the LSTM model achieves a maximum accuracy of 100%, while the GRU model achieves a highest accuracy of approximately 98%.Novelty: The novelty of this research lies in the optimization of hyperparameters for both LSTM and GRU methods, leading to the development of novel architectures capable of effectively classifying EEG emotion data.
Optimizing Hyperparameters of CNN and DNN for Emotion Classification Based on EEG Signals Dian Palupi Rini; Winda Kurnia Sari
International Journal on Information and Communication Technology (IJoICT) Vol. 10 No. 1 (2024): Vol. 10 No.1 June 2024
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v10i1.857

Abstract

EEG emotion is a research topic that has gained significant attention in the development of emotion classification systems. This study focuses on optimizing the hyperparameters of CNN (Convolutional Neural Network) and DNN (Deep Neural Network) for classifying EEG emotion signals. The data is divided into three train-test data ratio scenarios: 80:20, 70:30, and 60:40. After modeling and the classification process, hyperparameter tuning was conducted on both models to achieve the best results. Experimental results showed the highest accuracy of 98.36% for CNN, while DNN reached 98.18% in the 80:20 data ratio scenario. Despite the high accuracy, the differences in the loss curves between CNN and DNN reflect the complexity of the performance of both models. The train-test data ratio was also found to significantly impact the performance of both models, with the 80:20 data split yielding the best results, while the 70:30 and 60:40 splits resulted in slightly lower accuracies.
Analisis Bisnis Proses Keberatan Dan Pengurangan PBB di BAPENDA Kota Palembang Pangestu, Ridho; Putra, Pacu; Jambak, Muhammad Ihsan; Hardiyanti, Dinna Yunika; Sari, Winda Kurnia; Gumay, Naretha Kawadha
Jurnal Teknologi Dan Sistem Informasi Bisnis Vol 5 No 4 (2023): Oktober 2023
Publisher : Prodi Sistem Informasi Universitas Dharma Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jteksis.v5i4.1056

Abstract

The Internal Control System (ICC) is a crucial workflow in actions and activities that are continuously carried out by superiors and all employees to ensure the achievement of organizational targets through efficient and effective measures, reliability of financial reports, protection of state assets, and compliance with applicable laws and regulations. In the business process of objection and reduction of PBB at the Regional Revenue Agency (BAPENDA) of Palembang City shows that the previous business process has several existing obstacles, such as from existing staff, process time, and in terms of tasks in the business process. Therefore, it is necessary to analyze the business process of objection and reduction of PBB at the Regional Revenue Agency (BAPENDA) of Palembang City. So that the research aims to analyze the suitability of this procedure with SPIP and other inhibiting factors. The method used in this research is the Business Proceses Improvement (BPI) method, which is a method used to analyze the business process of tax objections and UN reductions, and uses the Bizagi Modeler application as a simulation of business process analysis, and uses Streamlining Tools in making improvements to the old business so that it becomes a more effective and efficient business process. Based on the results obtained, it shows that the original business process takes a long time so that new business process recommendations are made. This is intended to make the time required shorter than the old one.
ECG Signal Denoising Using 1D Convolutional Neural Network Rifai, Ahmad; Rachmamtullah, Muhammad Naufal; Sari, Winda Kurnia
Computer Engineering and Applications Journal Vol 13 No 2 (2024)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v13i2.482

Abstract

Electrocardiogram (ECG) signals are crucial for monitoring cardiac activity and diagnosing various cardiovascular conditions. However, these signals are often contaminated by different types of noise, such as baseline wander, muscle artifacts, and power line interference, which can obscure critical information and hinder accurate diagnosis. This study used a 1-Dimensional Convolutional Neural Network (1D CNN) architecture with seven convolutional layers for denoising ECG signals. The model utilizes a fully convolutional autoencoder approach, comprising an encoder that transforms noisy input signals into compact feature representations and a decoder that reconstructs the cleaned signals. The proposed architecture was tested using the MIT-BIH Noise Stress Test Database, which includes ECG recordings with simulated noise conditions. Performance evaluation metrics such as Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), and Mean Absolute Deviation (MAD) were used to assess the model's effectiveness. Results showed a low MSE of 0.034, a high SNR of 15.8 dB, and a MAD of 0.754, indicating significant noise reduction and high-quality signal reconstruction. These findings demonstrate that the 1D CNN architecture effectively reduces various types of noise in ECG signals, thereby enhancing signal quality and facilitating more accurate analysis and diagnosis. The model's ability to maintain the integrity of crucial ECG features while removing noise suggests its potential utility in clinical applications for improving cardiovascular disease diagnosis
Co-Authors Aditya Putra Perdana Prasetyo Ahmad Rifai 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 Rendy Isdwanta Reza Firsandaya Malik Reza Firsandaya Malik Risyahputri, Aliyananda Robani, M Tsabita Sahira, Mutia Salsabila, Adella Salsabila, Shofi Saputra, Marco Sari, Tri Kurnia Siti Nurmaini Yamani, Zaqqi