Article Per Year (5 Year)
p-Index From 2021 - 2026
1.94
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Ilmu Komputer dan Informasi Journal of Information Systems Engineering and Business Intelligence Indonesia Symposium on Computing Indonesian Journal on Computing (Indo-JC) IJoICT (International Journal on Information and Communication Technology) JOIN (Jurnal Online Informatika) International Journal of Artificial Intelligence Research JURNAL MEDIA INFORMATIKA BUDIDARMA Indonesian Journal of Artificial Intelligence and Data Mining Jurnal Teknologi dan Informasi TEKNOLOGIA Building of Informatics, Technology and Science Journal of Data Science and Its Applications Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Teknik Informatika (JUTIF) Charity : Jurnal Pengabdian Masyarakat eProceedings of Engineering Proceeding of Community Service and Engagement
Untari Novia Wisesty
Telkom University
Arts Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mathematics Social Sciences

Published : 41 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 41 Documents
Search

 1   2   3   4   5 
Momentum Backpropagation Optimization for Cancer Detection Based on DNA Microarray Data Wisesty, Untari Novia; Sthevanie, Febryanti; Rismala, Rita
International Journal of Artificial Intelligence Research Vol 4, No 2 (2020): December 2020
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (251.127 KB) | DOI: 10.29099/ijair.v4i2.188

Abstract

Early detection of cancer can increase the success of treatment in patients with cancer. In the latest research, cancer can be detected through DNA Microarrays. Someone who suffers from cancer will experience changes in the value of certain gene expression.  In previous studies, the Genetic Algorithm as a feature selection method and the Momentum Backpropagation algorithm as a classification method provide a fairly high classification performance, but the Momentum Backpropagation algorithm still has a low convergence rate because the learning rate used is still static. The low convergence rate makes the training process need more time to converge. Therefore, in this research an optimization of the Momentum Backpropagation algorithm is done by adding an adaptive learning rate scheme. The proposed scheme is proven to reduce the number of epochs needed in the training process from 390 epochs to 76 epochs compared to the Momentum Backpropagation algorithm. The proposed scheme can gain high accuracy of 90.51% for Colon Tumor data, and 100% for Leukemia, Lung Cancer, and Ovarian Cancer data.
Analysis of Data and Feature Processing on Stroke Prediction using Wide Range Machine Learning Model Wisesty, Untari Novia; Wirayuda, Tjokorda Agung Budi; Sthevanie, Febryanti; Rismala, Rita
JOIN (Jurnal Online Informatika) Vol 9 No 1 (2024)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v9i1.1249

Abstract

Stroke is a disease which cause the death of brain cells, so that the part of the body controlled by the brain loses its function. If not treated immediately, this disease can cause long-term disability, brain damage, and death. In this research, stroke prediction was carried out on the Stroke dataset acquired from the Kaggle dataset using various machine learning models. Then, data sampling techniques are used to handle data imbalance problems in the stroke dataset, which include Random Undersampling, Random Oversampling, and SMOTE techniques. Pearson Correlation and Principal Component Analysis are also used for dimensional reduction and analyzing the important features that are most influential in predicting stroke. Pearson Correlation produces five attributes that have the highest Pearson coefficient, namely age, hypertension, heart disease, blood sugar level, and marital status. Experimental results have demonstrated that the utilization of RUS, ROS, and SMOTE sampling techniques can significantly boost the F1-Score testing by an impressive 43.44%, 34.44%, and 35.55% respectively, as compared to experiments conducted without implementing any data sampling techniques. The highest F1-Score testing was achieved using the Support Vector Machine and Gaussian Naïve Bayes models, namely 0.83.
Gastroesophageal Reflux Disease Early Detection using XGBoost Method Classifier Wisesty , Untari Novia; Delfina, Haura Adzkia; Kurniawan, Isman
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 2 (2025): JUTIF Volume 6, Number 2, April 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.2.4143

Abstract

Gastroesophageal reflux disease (GERD) is a clinical condition that occurs when the gastric content within the stomach rises into the esophagus. If left untreated, GERD can result in complications such as esophageal inflammation, ulcers, and even cancer. In this study, the early detection of GERD is performed using the GERD dataset obtained from the Harvard Dataverse online repository and processed with the XGBoost machine learning model. The SMOTE technique was implemented as a solution to address the data imbalance present in the dataset. In addition, this study applied Principal Component Analysis (PCA) and Pearson Correlation to select the most relevant attributes, with the aim of improving computational efficiency. The results demonstrated that feature selection through Pearson correlation and feature extraction using principal component analysis (PCA) yielded the optimal model performance when utilizing 16 attributes and 16 principal components, respectively. The XGBoost model with PCA achieves a macro average F1-score of 0.9615, while the XGBoost model with Pearson Correlation attains a value of 0.9809. Subsequently, the XGBoost model based on the original dataset yielded a macro F1-score value of 0.9568. The findings of this research indicate that the XGBoost model with the Pearson Correlation-based feature selection method has a better f1-score value than the feature extraction method with PCA or based on the original dataset with a difference in value of 0.0194 and 0.0241 respectively in enhancing the performance of the XGBoost model for early detection of GERD in this study.
Sentiment Analysis on a Large Indonesian Product Review Dataset Romadhony, Ade; Al Faraby, Said; Rismala, Rita; Wisesty, Untari Novia; Arifianto, Anditya
Journal of Information Systems Engineering and Business Intelligence Vol. 10 No. 1 (2024): February
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.10.1.167-178

Abstract

Background: The publicly available large dataset plays an important role in the development of the natural language processing/computational linguistic research field. However, up to now, there are only a few large Indonesian language datasets accessible for research purposes, including sentiment analysis datasets, where sentiment analysis is considered the most popular task. Objective: The objective of this work is to present sentiment analysis on a large Indonesian product review dataset, employing various features and methods. Two tasks have been implemented: classifying reviews into three classes (positive, negative, neutral), and predicting ratings. Methods: Sentiment analysis was conducted on the FDReview dataset, comprising over 700,000 reviews. The analysis treated sentiment as a classification problem, employing the following methods: Multinomial Naí¯ve Bayes (MNB), Support Vector Machine (SVM), LSTM, and BiLSTM. Result: The experimental results indicate that in the comparison of performance using conventional methods, MNB outperformed SVM in rating prediction, whereas SVM exhibited better performance in the review classification task. Additionally, the results demonstrate that the BiLSTM method outperformed all other methods in both tasks. Furthermore, this study includes experiments conducted on balanced and unbalanced small-sized sample datasets. Conclusion: Analysis of the experimental results revealed that the deep learning-based method performed better only in the large dataset setting. Results from the small balanced dataset indicate that conventional machine learning methods exhibit competitive performance compared to deep learning approaches.   Keywords: Indonesian review dataset, Large dataset, Rating prediction, Sentiment analysis
Detecting Type and Index Mutation in Cancer DNA Sequence Based on Needleman–Wunsch Algorithm Wisesty, Untari Novia; Mengko, Tati Rajab; Purwarianti, Ayu; Pancoro, Adi
Jurnal Ilmu Komputer dan Informasi Vol. 17 No. 2 (2024): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v17i2.1273

Abstract

Detecting DNA sequence mutations in cancer patients contributes to early identification and treatment of the disease, which ultimately enhances the effectiveness of treatment. Bioinformatics utilizes sequence alignment as a powerful tool for identifying mutations in DNA sequences. We used the Needleman-Wunsch algorithm to identify mutations in DNA sequence data from cancer patients. The cancer sequence dataset used includes breast, cervix uteri, lung, colon, liver and prostate cancer. Various types of mutations were identified, such as Single Nucleotide Variant (SNV)/substitution, insertion, and deletion, locate by the nucleotide index. The Needleman Wunch algorithm can detect type and index mutation with the average F1-scores 0.9507 for all types of mutations, 0.9919 for SNV, 0.7554 for insertion, and 0.8658 for deletion with a tolerance of 5 bp. The F1-scores obtained are not correlated with gene length. The time required ranges from 1.03 seconds for a 290 base pair gene to 3211.45 seconds for a gene with 16613 base pairs.
PELATIHAN PEMBUATAN PORTOFOLIO ONLINE SEBAGAI MEDIA PROMOSI UNTUK SISWA SMK TELKOM DALAM MEMPERSIAPKAN DIRI MENGHADAPI DUNIA KERJA Febryanti Sthevanie; Untari Novia Wisesty; Tjokorda Agung Budi Wirayuda
The Proceeding of Community Service and Engagement (COSECANT) Seminar Vol. 3 No. 1 (2023): Prosiding COSECANT : Community Service and Engagement Seminar
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/cosecant.v3i1.7104

Abstract

Pada era digital seperti sekarang, teknologi telah menjadi bagian tidak terpisahkan dari kehidupan sehari-hari dan dunia pekerjaan. Banyak perusahaan menggunakan portofolio sebagai salah satu kriteria penilaian dalam proses seleksi dan rekrutmen. Kegiatan pengabdian masyarakat siswa SMK Telkom dilaksanakan dengan menggunakan pendekatan pembelajaran simultan yaitu pemberian materi dan praktek terbimbing untuk membuat portofolio secara online dengan memanfaatkan Google Site. Ketersediaan portofolio secara online akan memudahkan siswa untuk memperbaharui portofolio dan melakukan refleksi pengetahuan seiring dengan tahapan pembelajaran. Dari sisi guru dan perusahaan, tersedianya portofolio online memberikan kemudahan akses untuk mendapatkan gambaran holistik tentang kemampuan, prestasi, dan potensi siswa. Terdapat kurang lebih 256 siswa kelas XI SMK Telkom (10 kelas) yang mengikuti pelatihan dalam dua sesi dan telah selesai membuat portofolio online menggunakan Google Site. Pengujian mengenai dampak dari kegiatan pelatihan dilakukan melalui analisis hasil pre-test dan post-test dengan hasil analisis gabungan dari 10 kelas mengindikasikan terdapat perbedaan signifikan antara pengetahuan siswa sebelum dan setelah diberikan materi serta praktik langsung terkait pembuatan portofolio online menggunakan Google Site. Peningkatan nilai yang signifikan terjadi pada 6 dari 15 soal yang menunjukkan efektivitas materi dan pendampingan yang diberikan pada kegiatan pengabdian masyarakat. Hasil analisis mendukung efikasi pembelajaran dan menunjukkan bahwa meode pengajaran yang diterapkan yaitu pembelajaran simultan dengan pemberian materi disertai praktek langsung memberikan dampak positif terhadap pemahaman siswa.
Classification of Lung Cancer using Vision Transformer on Histopathological Images Raihan Akbar, Muhamad Rafi; Novia Wisesty, Untari
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 3 (2026): Maret 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i3.9399

Abstract

Lung cancer is the leading cause of cancer-related deaths worldwide, with early diagnosis often hindered by morphological variations in histopathological images. The main problem is the difficulty in accurately and rapidly distinguishing cancer types such as adenocarcinoma and squamous cell carcinoma from benign tissue. This research processes histopathological images as input to produce a three-class classification: adenocarcinoma, squamous cell carcinoma, and benign tissue. Early detection of lung cancer can improve survival rates by up to 50%, but manual diagnosis by pathologists depends on subjective experience, causing errors of up to 20% in ambiguous cases. For example, in developing countries like Indonesia, the shortage of pathologists exacerbates treatment delays. This gap demands a reliable automated approach to support more timely clinical decisions. The developed solution involves implementing Vision Transformer (ViT) with two different architectures: ViT-B/16 (base model with 86 million parameters) and ViT-L/16 (large model with 304 million parameters). Histopathological images are processed through normalization and patch embedding of 16×16 pixels, then features are extracted using self-attention mechanism. Models are trained with transfer learning from ImageNet-21k, applying fine- tuning on lung cancer histopathological images dataset. The process includes data splitting into training (70%), validation (15%), and testing (15%), as well as data augmentation to improve robustness. The ViT-B/16 model achieved testing accuracy of 98.40% with F1-score of 0.984, while ViT-L/16 achieved accuracy of 98.18% with F1-score of 0.982. Both models demonstrated perfect capability in detecting benign tissues (precision 1.00). The average AUC-ROC value reached 0.999 for ViT-B/16 and 0.998 for ViT-L/16, indicating very high discriminative power. The main contribution of this research is a comprehensive comparison between two scales of Vision Transformer for automated lung cancer diagnosis, proving that the smaller model (ViT-B/16) can achieve equivalent or better performance with higher computational efficiency.
Klasifikasi Penyakit Kulit Menggunakan Model Deep Learning EfficientNet pada Citra Dermastokopi Muhammad Imam Fernandi; Untari Novia Wisesty
eProceedings of Engineering Vol. 13 No. 1 (2026): Februari 2026
Publisher : eProceedings of Engineering

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

Abstract

Penyakit kulit merupakan salah satu masalahkesehatan yang umum terjadi dan dapat berkembang menjadikondisi serius seperti melanoma, salah satu jenis kanker kulityang berbahaya. Proses diagnosis manual sering kali memakanwaktu, bergantung pada keahlian subjektif, serta berpotensimenghasilkan hasil yang tidak konsisten. Penelitian inibertujuan mengembangkan model klasifikasi penyakit kulitberbasis Convolutional Neural Network (CNN) denganarsitektur EfficientNet pada citra dermatoskopi. Dataset yangdigunakan adalah HAM10000, yang berisi 10.015 citradermatoskopi dari tujuh kategori lesi kulit. Tahapan penelitianmeliputi preprocessing data, augmentasi untukmenyeimbangkan kelas, serta pelatihan model denganpendekatan dua tahap, yaitu feature extraction dan fine-tuning.Tiga varian model diuji, yaitu EfficientNetB0,EfficientNetV2B0, dan EfficientNetV2B3. Hasil pengujianmenunjukkan bahwa EfficientNetV2B3 memberikan performaterbaik dengan akurasi 90,53% dan F1-score 85,56%,mengungguli dua model lainnya. Temuan ini menunjukkanbahwa arsitektur EfficientNetV2B3 memiliki potensi besardalam mendukung sistem diagnosis berbasis citra dermatoskopisecara lebih akurat dan efisien.Kata kunci — CNN, EfficientNet, dermatoskopi,HAM10000, klasifikasi penyakit kulit, akurasi
MNetNCR: MobileNet model for efficient traditional Nusantara script character recognition Untari Novia Wisesty; Aditya Firman Ihsan; Mahmud Dwi Sulistiyo; Donni Richasdy; Prasti Eko Yunanto; Gamma Kosala; Arfive Gandhi; Febryanti Sthevanie
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i2.pp1513-1528

Abstract

Preservation of traditional Nusantara scripts is very important because these traditional scripts are part of the cultural heritage that reflects the identity and history of the nation. This research proposed MobileNet for Nusantara character recognition (MNetNCR) model based on MobileNetV3 architecture to recognize traditional Nusantara scripts with lightweight, efficient architecture, and accurate recognition. The novel and comprehensive datasets for traditional Nusantara scripts have been curated in this research, that will later be stored digitally and can be used in further research. This novel dataset includes handwritten Balinese, Batak, Javanese, Lontara, and Sundanese scripts, each with unique visual characteristics. The proposed MNetNCR model is highly effective in recognizing characters, achieving F1-scores of 0.9934 for Balinese, 0.9450 for Batak, 0.9788 for Javanese, 0.9936 for Lontara, and 0.9961 for Sundanese scripts, according to the experimental results. The MNetNCR model built in this research has been proven to be effective and efficient in recognizing traditional scripts accurately. It also supports the preservation and promotion of the nation's cultural and historical heritage.
Swin Transformer V2 for Invasive Ductal Carcinoma Classification in Histopathological Imaging Puguh Aiman Ariyanto; Untari Novia Wisesty
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 8 No. 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

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

Abstract

Breast cancer is the second leading cause of mortality in women globally, with Invasive Ductal Carcinoma being the most dominant subtype that requires accurate diagnosis to increase patient life expectancy. Conventional diagnosis based on manual histopathological examinations is time-consuming, prone to misinterpretation, and exhibits significant inter-observer variability. This study implemented the Swin Transformer V2 architecture for the automatic classification of Invasive Ductal Carcinoma on 277,524 histopathological images, each measuring 50×50 pixels, which were resized to 256×256 pixels with geometric augmentation. The model was trained using AdamW optimization with a learning rate of 1 × 10⁻⁴, weight decay of 1 × 10⁻⁴, a batch size of 16, and mixed precision (FP16) for five epochs at a 70:20:10 data sharing ratio. The data augmentation includes a 50% probability of a random horizontal flip and a maximum of 10 degrees of random rotation to improve the model's generalization capabilities. Evaluation of 27,754 independent test samples resulted in an accuracy of 92.82%, an accuracy of 88.48%, a recall of 86.05%, an F1-score of 87.25%, and an AUC of 0.91. A hierarchical window attention-shifted mechanism with residual post-normalization has been shown to be effective in extracting local and global features from complex microscopic images. The results show that Swin Transformer V2 has significant potential as a diagnostic aid system to enhance the efficiency and accuracy of early breast cancer detection in clinical pathology practice.
Co-Authors Aaz M Hafidz Azis Ade Romadhony Adi Pancoro Aditya Firman Ihsan Aditya Kusuma Setyanegara Adiwijaya Agung Toto Wibowo Agus Nursikuwagus Al Azhar Al Azhar Al Faraby, Said Ali Zainal Abidin Assajjad Anditya Arifianto Andrian Fakhri Annisa Aditsania Arfive Gandhi Ayu Purwarianti Brama Hendra Mahendra Delfina, Haura Adzkia Devy Yendriani Dieka Nugraha Karyana Dimitri Mahayana Donni Richasdy Echa Pangersa Sugianto Oeoen Eko Darwiyanto Ergandara Purba Setra Ersa Christian Prakoso Fathurrohman Elkusnandi Febryanthi Sthevanie Febryanti Sthevanie Gamma Kosala Hadli Fadli Santoso Henri Tantyoko Hifzi Priabdi Hikmawati, Erna Huda Sepriandi Ibrahim Intan Raharni Wijaya Iqbal Hapid Sukana Putra Isman Kurniawan Jondri Lalu Gias Irham Lidya Ningsih Mahmud Dwi Sulistiyo Mengko, Tati Rajab Muhammad Imam Fernandi Munggana, Wira Prasti Eko Yunanto Puguh Aiman Ariyanto Putri Tsatsabila Ramadhani Raihan Akbar, Muhamad Rafi Renette Ersti Riko Bintang Purnomoputra Rita Rismala Stefanus Christian Adi Pradhana Sugondo Hadiyoso Tiara Laksmi Basuki Tjokorda Agung Budi Wirayuda Wahyu Hauzan Rafi Wisnu Adhi Pradana Yosua Nababan