Article Per Year (5 Year)
p-Index From 2020 - 2025
7.605
P-Index
This Author published in this journals
All Journal Dinamik Sinkron : Jurnal dan Penelitian Teknik Informatika Jusikom: Jurnal Sistem Informasi Ilmu Komputer Jurnal Teknologi Dan Sistem Informasi Bisnis Jurnal Tekinkom (Teknik Informasi dan Komputer) INFOKUM Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Jurnal Media Informatika TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Jurnal Ilmiah Multidisiplin Indonesia INOVTEK Polbeng - Seri Informatika
Indra, Evta
Universitas Prima Indonesia
Agriculture, Biological Sciences & Forestry Computer Science & IT Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Physics

Published : 49 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 49 Documents
Search

 1   2   3   4   5 
EXPLORATORY DATA ANALYSIS OF CLINICAL HEART FAILURE USING A SUPPORT VECTOR MACHINE Sinaga, Putri tua; Purba, Salda Sari; Wiranto, David; Maharja, Okta Jaya; Indra, Evta
Jurnal Sistem Informasi dan Ilmu Komputer Vol. 7 No. 1 (2023): JUSIKOM: JURNAL SISTEM INFROMASI ILMU KOMPUTER
Publisher : Fakultas Teknologi dan Ilmu Komputer Universitas Prima Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34012/jurnalsisteminformasidanilmukomputer.v7i1.4100

Abstract

This study aims to explore the clinical data of patients diagnosed with heart failure using the Support Vector Machine (SVM) algorithm as a classification method. Clinical data from verified patients has been collected and analyzed to identify patterns, associations, and risk factors contributing to heart failure risk. The exploratory data analysis results reveal essential clinical data characteristics and provide initial insight into patient profiles and clinical variables that can influence heart failure risk. The SVM model was built to predict the risk of heart failure based on clinical data. This model is evaluated using classification metrics such as F1-Score and accuracy. Evaluation results show good performance with an F1-Score reaching 0.83, which indicates a reasonable degree of accuracy and balance in predicting the risk of heart failure. The conclusion of this study shows the potential of the classification model as a tool in managing heart failure patients. This model can help medical personnel identify high-risk patients and provide appropriate treatment to prevent disease progression and improve prognosis. However, these results need further verification with more in-depth analysis and validation using broader data. This model can help medical personnel identify high-risk patients and provide appropriate treatment to prevent disease progression and improve prognosis. However, these results need further verification with more in-depth analysis and validation using broader data. This model can help medical personnel identify high-risk patients and provide appropriate treatment to prevent disease progression and improve prognosis. However, these results need further verification with more in-depth analysis and validation using broader data.   Keywords: Exploratory Data Analysis, Heart Failure, Classification, Python, Support Vector Machine
Tinjauan Sistematis: Teknik eye tracking untuk penyakit Skizofrenia Saragih, Septua Fujima; Ginting, Ricci Kincahar Bastoto Kevin; Simajuntak, Yusuf Natanael; Nasution, Adli Abdillah; Indra, Evta
Jurnal Media Informatika Vol. 5 No. 3 (2024): Jurnal Media Informatika Edisi Mei - Agustus
Publisher : Jurnal Media Informatika

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

Abstract

Eye tracking technology has emerged as an innovative tool for understanding and diagnosing schizophrenia, demonstrating significant potential in revealing different eye movement patterns between patients and healthy individuals. Literature studies indicate that irregular eye fixations and inconsistent saccades in schizophrenia patients may indicate disruptions in visual information processing and attention allocation. Eye tracking metrics, such as gaze duration and fixation stability, provide crucial insights into cognitive functions and emotional states in patients. Integration of eye tracking technology with machine learning techniques, including eXtreme Gradient Boosting (XGB) and Support Vector Machines (SVM), has achieved diagnostic accuracy up to 94%, highlighting its potential to enhance diagnostic precision. Despite these promising advances, challenges such as symptom variability among individuals, patient comfort, and the need for standard protocols remain. The development of non-intrusive eye tracking systems and applications in virtual reality (VR) shows potential for innovative therapies. Further research is needed to address these challenges and ensure effective and consistent implementation of this technology in clinical practice.
Perbandingan Metode Support Vector Machine (SVM) Dan Naive Bayes Pada Analisis Sentimen Ulasan Aplikasi OVO Lowell, Alvis; Lowell, Audric; Candra, Kevin; Indra, Evta
Jurnal Media Informatika Vol. 6 No. 2 (2025): Jurnal Media Informatika
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v6i2.5134

Abstract

In the rapidly evolving digital era, sentiment analysis has become crucial for understanding diverse user opinions. However, there is a gap in comparative studies on the effectiveness of machine learning methods for sentiment analysis of e-wallet applications in Indonesia. This research aims to compare the performance of Support Vector Machine (SVM) and Naive Bayes methods in sentiment analysis of user reviews for the OVO application, sourced from the Google Play Store. A total of 3,000 reviews were collected and processed through text preprocessing stages, including data cleaning, case folding, stopword removal, tokenizing, and stemming. Sentiment labeling was performed automatically using the VADER method, resulting in three categories: positive, neutral, and negative. The data was then transformed into numerical format using TF-IDF before being applied to the SVM and Naive Bayes models. Model performance was evaluated using a confusion matrix with metrics such as accuracy, precision, recall, and F1-score. The results showed that the SVM method delivered better outcomes with an accuracy of 89%, precision of 89%, recall of 89%, and F1-score of 88%, compared to the Naïve Bayes method, which achieved an accuracy of 86%, precision of 88%, recall of 86%, and F1-score of 87%. These findings can serve as a reference in selecting machine learning methods for sentiment analysis of e-wallet applications and assist OVO in improving service quality based on user feedback.
Android Application Prototype for Detecting Mould on Bread using Machine Learning Siregar, Frissy; Barus, Daniel Haganta; Piay, Clara Stephanie Bernadeth; Indra, Evta
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): Juli
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/bptwhn82

Abstract

Mould contamination in bread poses a serious health risk if not detected early, especially in the food industry, which still relies heavily on manual visual inspection. This study aims to develop a prototype Android application capable of automatically detecting mould on bread using a machine learning approach based on the MobileNetV2 architecture. The classification model was trained on a dataset of 666 bread images, consisting of 533 training and 133 validation samples. Training was carried out over 37 epochs using data augmentation techniques and a learning rate of 0.0001. The results demonstrated consistent accuracy improvements and loss reductions without signs of overfitting. The model achieved 94% testing accuracy, with a precision, recall, and F1-score of 0.94 for both "Mouldy" and "Non-Mouldy" classes. The confusion matrix showed 125 correct predictions out of 133 test images. This research addresses the gap in lightweight and practical solutions for mobile-based mould detection. Unlike previous studies that used heavier models such as VGG16 or ResNet, this study shows that MobileNetV2 can achieve high performance with lower computational demands, making it suitable for real-world Android applications. The trained model was integrated into a simple Android interface, allowing users to upload images and instantly receive classification results. For future improvement, this prototype can be enhanced by incorporating object detection or image segmentation techniques such as YOLOv5 or U-Net to enable not only classification but also the localisation of mould areas in real-time.
Integration of YOLOv8 and FastAPI for Early Detection of Nail Diseases Pakpahan, Ferdinand Linggo; Sembiring, Joni Satrio; Abellista, Tivanez Ballerina; Indra, Evta
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 2 (2025): Research Articles April 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i2.14796

Abstract

Nails are important indicators of various health conditions, including fungal infections (onychomycosis), autoimmune disorders (psoriasis), and subungual melanoma (black line). However, early detection of these diseases remains limited due to low accessibility and public awareness. This study aims to develop an end-to-end, web-based early detection system for nail diseases by integrating the YOLOv8 object detection algorithm with the FastAPI framework. A total of 600 annotated nail images obtained from Kaggle were categorized into four classes: healthy nail, psoriasis, black line, and onychomycosis. The model was trained using PyTorch on Google Colab with GPU acceleration and evaluated using precision, recall, and mean Average Precision (mAP@0.5). The model achieved a precision of 93%, recall of 88%, and mAP@0.5 of 89%. Manual testing on 100 images via the deployed web application showed an overall accuracy of 97%. Class-wise accuracy reached 100% for healthy nail and psoriasis, 92% for black line, and 96% for onychomycosis. These results demonstrate that the system performs reliably across various conditions. The main contribution of this study is the implementation of a real-time, web-integrated nail disease detection system that is accessible to both medical professionals and the general public. Future research may focus on expanding the dataset, optimizing model robustness under varied lighting and background conditions, and conducting clinical validation.
Fine-Tuning the Gemini 1.5 Flash Large Language Model for User Perception Classification in BSI Mobile Application Reviews Fidelis, Rio; Vicraj, Vicraj; Bangun, Dea Monica; Mayanti, Nur; Indra, Evta
Jurnal Ilmiah Multidisiplin Indonesia (JIM-ID) Vol. 4 No. 05 (2025): Multidisiplin Indonesia (JIM-ID), Mey 2025
Publisher : Sean Institute

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

Abstract

he growing volume of user reviews on digital platforms such as the Google Play Store presents a major challenge in automatically understanding user perceptions, especially due to the unstructured, varied, and highly subjective nature of the text data. Manual analysis at this scale is inefficient and prone to bias. To address this issue, this study applies fine-tuning on the Large Language Model (LLM) Gemini 1.5 Flash to automatically classify user perceptions of the BSI Mobile application. Perceptions are categorized into three classes: Very Poor, Fair, and Excellent. A total of 120,000 reviews were collected via web scraping and processed through cleaning, normalization, automatic labeling using the IndoBERT model, and conversion into JSONL format for fine-tuning on the Google Cloud Vertex AI platform. Evaluation results show an accuracy of 63.41% for perception classification and 67.31% for sentiment classification, with F1-scores of 28.82% and 28.75%, respectively. The model demonstrated better accuracy in identifying positive perceptions, while neutral or ambiguous reviews remained a challenge. Consistency analysis between predicted perceptions and user ratings showed a match rate of 83.81%. This study demonstrates that the fine-tuned Gemini 1.5 Flash is an effective solution for text-based perception classification and holds strong potential for broader application in user opinion analytics systems.
Analisis dan Prediksi Tingkat Kemiskinan di Sumatera Utara menggunakan Model LSTM berbasis Google Earth Engine Hutabarat, Lerry Yos Santa Angelina; Juliandra, Vella; Pratama, Febryan; Indra, Evta
Dinamik Vol 30 No 2 (2025)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v30i2.10243

Abstract

This study analyzes the prediction of poverty levels in North Sumatra Province by applying the Long Short-Term Memory (LSTM) method based on time series integrated with Google Earth Engine (GEE). Historical poverty data of districts/cities were obtained from the Central Statistics Agency (BPS) and processed using Python in Google Colab for LSTM model training. The prediction results are visualized spatially in the form of thematic maps through GEE to identify areas with high poverty rates. The evaluation model was carried out by calculating MAE, RMSE, MAPE, and prediction accuracy, with most areas having an accuracy above 80%. These findings indicate that this approach is effective in mapping poverty trends and supporting data-driven policies. This predictive model can be the basis for more targeted social interventions and strategies for developing inclusive and sustainable regional development.
MRI Image Classification Analysis of Brain Cancer Using ResNet18 and VGG16 Deep Learning Architectures Sembiring, Yudha Brema Agriva; Indra, Evta
INFOKUM Vol. 13 No. 05 (2025): Infokum
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v13i05.2955

Abstract

Deep learning approaches, particularly Convolutional Neural Networks (CNNs), have proven effective in medical image processing. Two prominent CNN architectures are VGG16 and ResNet18. Previous research has shown that ResNet50 and VGG16 have been used in brain tumor classification with varying accuracy. This study aims to systematically compare the performance of ResNet18 and VGG16 in brain cancer MRI image classification, considering accuracy, computational efficiency, and model generalization capabilities. The results show that the ResNet18 model with pretrained weights achieved the highest accuracy of 97.43%, excelling in detecting all categories of brain tumors with minimal error. In contrast, the VGG16 model trained from scratch performed the lowest with an accuracy of only 63.09%, having significant difficulty distinguishing between classes.
ANALISIS SENTIMEN ULASAN PRODUK MENGGUNAKAN LARGE LANGUAGE MODELS: STUDI KASUS PADA SHOPEE Keliat, Ribka Amelia Yunita; Indra, Evta; Laia, Yonata
Jurnal Sistem Informasi dan Ilmu Komputer Vol. 8 No. 2 (2025): JUSIKOM: JURNAL SISTEM INFROMASI ILMU KOMPUTER
Publisher : Fakultas Teknologi dan Ilmu Komputer Universitas Prima Indonesia

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

Abstract

Perkembangan pesat e-commerce telah meningkatkan jumlah ulasan produk yang tersedia di platform seperti Shopee. Ulasan ini dapat menjadi sumber informasi berharga bagi penjual dalam memahami persepsi konsumen dan meningkatkan strategi pemasaran. Namun, besarnya volume dan kompleksitas bahasa dalam ulasan membuat analisis manual menjadi tidak efisien. Penelitian ini bertujuan untuk menganalisis sentimen ulasan produk di Shopee menggunakan Large Language Models (LLMs), khususnya model Gemini 1.5-Pro yang telah di-fine-tune agar lebih sesuai dengan bahasa pengguna Shopee. Metode yang digunakan mencakup pengumpulan data melalui web scraping, preprocessing data, fine-tuning model, serta evaluasi performa model berdasarkan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model yang dikembangkan mampu mengklasifikasikan sentimen ulasan ke dalam kategori positif, negatif, dan netral dengan akurasi berkisar antara 66,67% hingga 85,71%.
Co-Authors ., Calvin Abellista, Tivanez Ballerina Ahmad Rifai Akbari, Deni Adha Alfi, Ahmad Haikal Alifah, Lutfi Aulia Alvarez, Stevin Amalia Amalia Aminatunnisa, Siti Amir Saleh ANITA . Bangun, Dea Monica Bangun, Frans Aditya Banjarnahor, Jepri Barus, Daniel Haganta Brutu, Lolo Frans M. Butarbutar, Serly Yunarti Buulolo, Deniarwinus Candra, Kevin daniel christian Delima Sitanggang, Delima Dina Pratiwi, Dina Dwi Rizky, Atikah Edison, Rizki Edmi Fahmi, Mohammad Irfan Fando, Al Farrona, Rio Fidelis, Rio Giawa, Well Friend Ginting, Nessa Sanjaya Ginting, Ricci Kincahar Bastoto Kevin Gulo, Agustinus Gultom, Yeni Gurusinga, Alta Harahap, Charles Bronson Hutabarat, Fenna Kemala Hutabarat, Lerry Yos Santa Angelina Hutasoit, Leo Nardo Hutauruk, Jesika Avonia Juanta, Palma Juliandra, Vella Karim, Anggie Monica Keliat, Ribka Amelia Yunita Kumar, Sharen Loi, Mentari Hati Lowell, Alvis Lowell, Audric Lumbanraja, Lamtiur Rondang Wulan Maharja, Okta Jaya Manullang, Murni Esterlita Mariyanti, Eka Marpaung, Aldo Andy Yoseph Tama Matondang, Enjelika Mawaddah Harahap, Mawaddah MAYANTI, NUR Meizar, Abdul Muhammad Farhan Muhammad Yasir Muhardi Saputra Napitupuluh, Christian Deniro Nasution, Adli Abdillah Nasution, Syafrani Putri NK Nababan, Marlince Okta Jaya Harmaja Oloan Sihombing, Oloan Pakpahan, Ferdinand Linggo Panjaitan, Ezra Christina Septiana panjaitan, haris samuel pranada Piay, Clara Stephanie Bernadeth Pratama, Febryan Purba, Salda Sari Rahil, Rafif Rahmad, Julfikar Reinaldo, Erick Rifaldo, Rifaldo Ruben Ruben, Ruben Saragih, Septua Fujima Sembiring, Diarnia Mega Selfia Sembiring, Joni Satrio Sembiring, Yudha Brema Agriva Sianturi, Santo Sanro Siburian, Astri Dahlia Silaban, Herlan Simajuntak, Yusuf Natanael Simamora, Wanda Pratama Putra Simangunsong, Sarah Simanjuntak, Mega Herlin Simarmarta, Brando Benedictus Simbolon, Ongki Sopie Sinaga, Putri tua Sinurat, Stiven Hamonangan Siregar, Frissy Siregar, Reinhrad Shodani Siringo Ringo, Jaka Tomi Ronaldo Sitanggang, Audina L Sitompul, Chris Samuel Sitompul, Daniel Ryan Hamonangan Sitorus, Sarah Tri Yosepha Situkkir, Miando Mangara Situmorang, Andreas Solly Aryza Suhamdani, Dadan Suwanto, Jacky Suyanto, Jao Han Tampubolon, Irfan Saputra Tarigan, Nina Veronika Tarigan, Sri Wahyuni VERONICA VERONICA Vicraj, Vicraj Wijaya, Malvin Luckianto Wiranto, David Wiratama, Westlie Wirhan Fahrozi, Wirhan Yonata Laia Ziegel, Dennis Jusuf