Article Per Year (5 Year)
p-Index From 2020 - 2025
1.975
P-Index
This Author published in this journals
All Journal JOURNAL OF APPLIED INFORMATICS AND COMPUTING ILKOM Jurnal Ilmiah KOMPUTIKA - Jurnal Sistem Komputer JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) JATI (Jurnal Mahasiswa Teknik Informatika) Jurnal Pengabdian kepada Masyarakat Nusantara LOGIC : Jurnal Ilmu Komputer dan Pendidikan
Baita, Anna
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Social Sciences Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Uji Kernel SVM dalam Analisis Sentimen Terhadap Layanan Telkomsel di Media Sosial Twitter Fremmuzar, Pangestu; Baita, Anna
Komputika : Jurnal Sistem Komputer Vol 12 No 2 (2023): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v12i2.9460

Abstract

Telkomsel is an internet service provider in Indonesia which was launched in 1995. As an internet service provider with the most users, Telkomsel has become the center of attention of internet users in Indonesia. This invites user opinions and perspectives on Telkomsel, which is commonly referred to as sentiment. One of the media commonly used to express an opinion and point of view is Twitter. Twitter is a social media platform that is often a place for sharing and spreading the news, and discussing ideas, and opinions of Twitter users. In this study, the algorithm used is the Support Vector Machine. In the Support Vector Machine, there is a kernel trick that will be used to determine kernel performance and analyze sentiment. The sentiments analyzed amounted to 537 tweets collected by scraping. The collected tweets will go through the preprocessing stage, namely cleaning, case folding, tokenizing, normalization, stemming, stopword removal, and detokenizing. A sentiment is classified into 2 labels, namely positive and negative. Based on the test results, the sigmoid kernel has the best performance with an accuracy value of 0.950, a precision of 0.945, a recall of 0.860, an f1-score of 0.896, and sentiment tend toward negative.
MobileNet V2 Implementation in Skin Cancer Detection Pradnya Dhuhita, Windha Mega; Ubaid, Muhammad Yahya; Baita, Anna
ILKOM Jurnal Ilmiah Vol 15, No 3 (2023)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v15i3.1702.498-506

Abstract

Skin cancer is one of the most worrying diseases for humans. In Indonesia alone, skin cancer occupies the third position after cervical cancer and breast cancer. Currently, doctors still use the biopsy method to diagnose skin cancer. It is less effective because this method requires the performance of an experienced doctor, takes a long time, and is a painful process. Because of that, we need a way in which skin cancer can be classified using dermoscopic images to help doctors diagnose skin cancer earlier. Researchers proposed to classify skin cancer into seven classes, namely actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevus, and vascular lesions. The method used in this study is a convolutional neural network (CNN) with the MobileNet V2 architecture. The dataset used is the HAM10000 dataset, with a total of 10015 images. In this study, a comparison was made between data augmentation, learning rate, epochs, and different amounts of data. Based on the test results, the highest accuracy results were obtained, namely 79%. The best model is implemented into a mobile application.
Diagnosa Kerusakan Sepeda Motor 2-Tak Menggunakan Case Based Reasoning Nur Rachman, Ali; Baita, Anna
LOGIC : Jurnal Ilmu Komputer dan Pendidikan Vol. 2 No. 5 (2024): Logic : Jurnal Ilmu Komputer dan Pendidikan
Publisher : Shofanah Media Berkah

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

Abstract

Sepeda motor merupakan salah satu alat transportasi yang banyak digunakan oleh masyarakat Indonesia. Salah satu jenis sepeda motor yang masih banyak digunakan masyarakat yaitu jenis sepeda motor dua tak. Dikarenakan jenis sepeda motor dua tak merupakan produksi lama, kerusakan sepeda motor dua tak merupakan masalah yang sering terjadi dan dialami oleh sebagian pengguna. Hal ini terjadi juga karena kurangnya pengetahuan pengguna dalam permasalahan kerusakan sepeda motor dan cara mengatasinya. Penelitian ini bertujuan untuk menyelesaikan permasalah bagaimana merancang suatu sistem pakar berbasis website yang ramah terhadap pengguna untuk mendeteksi kerusakan pada sebuah sepeda motor jenis dua tak secara cepat dan akurat. Sistem pakar ini dibangun menggunakan metode Case Based Reasoning (CBR). Metode ini akan mengambil keputusan berdasarkan solusi dari kasus-kasus telah ada sebelumnya. Hasil dari penelitian ini berupa sistem pakar yang dapat digunakan untuk mendiagnosa kerusakan sepeda motor 2-tak berdasarkan gejala kerusakan yang dialami dan diinputkan oleh pengguna. System akan memberikan informasi jenis kerusakan sepeda motor dan menampilkan solusi perbaikan kerusakan. Berdasarkan hasil pengujian dengan metode Black Box Testing, keseluruhan fungsionalitas aplikasi telah berfungsi dengan baik. Selain itu sistem pakar ini berhasil  nilai akurasi sebesar 80%.
ANALISIS SENTIMEN KOMENTAR MASYARAKAT TERHADAP RANGKA ESAF HONDA MENGGUNAKAN ALGORITMA NAIVE BAYES DAN SUPER VECTOR MACHINE Andika Joni, Gusti; Cahyono, Nuri; Baita, Anna; Aini, Nur
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 8 No. 5 (2024): JATI Vol. 8 No. 5
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v8i5.11164

Abstract

Honda, sebagai salah satu merek motor terkemuka di Indonesia, memperkenalkan teknologi Enhanced Smart Architecture Frame (eSAF) untuk meningkatkan stabilitas dan kenyamanan pengendalian sepeda motor. Namun, teknologi ini mendapatkan berbagai tanggapan dari masyarakat terkait masalah keropos, karat, dan kerentanannya terhadap patah, yang banyak dibahas di media sosial, terutama Instagram. Penelitian ini bertujuan untuk menganalisis sentimen terhadap kerangka eSAF menggunakan metode Multinomial Naive Bayes (MNB) dan Support Vector Machine (SVM). Data dikumpulkan dari akun Instagram resmi PT. Astra Honda Motor (@welovehonda_id) antara 29 Juli 2023 hingga 11 September 2023, dengan total 4607 komentar, yang setelah pre-processing berkurang menjadi 4435 komentar. Labeling sentimen dilakukan dengan kamus VADER, menghasilkan distribusi sentimen yang seimbang: 50,69% positif dan 49,31% negatif. Evaluasi model menggunakan rasio data 90:10, 80:20, 70:30, 60:40, dan 50:50 menunjukkan bahwa SVM unggul dalam Precision, dengan nilai tertinggi 91% pada rasio 70:30. MNB memiliki Precision tertinggi 87% pada rasio 90:10 dan Accuracy 87% pada rasio yang sama. Secara keseluruhan, SVM menunjukkan kinerja lebih baik dibandingkan MNB, terutama dalam ketepatan prediksi (Precision), sehingga direkomendasikan untuk analisis sentimen di masa depan.
Implementation of the K-Nearest Neighbors (KNN) Regressor Method to Predict Toyota Used Car Prices Ghaisani, Mauhiba Salmaa; Baita, Anna
Journal of Applied Informatics and Computing Vol. 9 No. 1 (2025): February 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i1.8860

Abstract

The development of the automotive industry in Indonesia has experienced significant growth in recent decades, especially in the used car market segment. One of the used car brands that has high demand is Toyota, because it has a reliable reputation and quality. However, there are challenges that are often faced by sellers and buyers of used cars, namely in determining prices correctly and accurately. Incorrect pricing can be detrimental to one party, either the price is too high or too low. Prices that are too high can slow down the turnover of goods in the market. While low prices can cause sellers to experience losses. The purpose of this study is to help find good performance in determining the price of used Toyota cars. This study will use one of the Machine Learning methods, namely K-Nearest Neighbors Regressor. The KNN method is one method that can be used for classification and regression. In addition, this algorithm is a simple algorithm and can provide accurate prediction results based on its proximity to existing data. This study uses selected relevant features, namely model, year, kilometer, tax, mpg, and cc. The results of this study obtained MAE = 3.31686, MSE = 26.43640, RMSE = 5.14163, and R2-Score = 0.99501 using 90:10 data division and k = 1. This proves that KNN Regressor is an effective method in predicting the price of used Toyota cars. Therefore, the K-Nearest Neighbors (KNN) Regressor method is able to provide a fairly accurate price estimate with a minimal error rate.
Optimization of Decision Tree Algorithm for Chronic Kidney Disease Classification Based on Particle Swarm Optimization (PSO) Aulia Fitri, Laili; Baita, Anna
Journal of Applied Informatics and Computing Vol. 9 No. 1 (2025): February 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i1.8940

Abstract

The body's most important vital organ is the kidney. The kidneys are responsible for maintaining acid and alkaline balance, regulating blood pressure, and filtering blood to prevent the accumulation of metabolic waste in the body. However, chronic kidney disease does not always show symptoms and signs but can progress to kidney failure. Algorithm-based predictive methods in data processing show great potential in the health field to predict various diseases, one of which is kidney disease. One of the techniques in data mining is classification. One of the classification algorithms in data mining that is often used to detect diseases is Decision Tree. In this study, it is expected that by combining these two methods, it will make a new contribution to the Decision Tree algorithm that is optimized with Particle Swarm Optimization (PSO) for the selection of relevant features, and improve the weaknesses in the model to improve more accurate predictions. By performing feature selection with the Particle Swarm Optimization (PSO) algorithm, it is shown that the use of Particle Swarm Optimization (PSO) can improve the accuracy and performance of the Decision Tree algorithm in the chronic kidney disease classification process. The accuracy of the Decision Tree algorithm with feature selection using Particle Swarm Optimization (PSO) is higher, reaching 0.967%, compared to the accuracy of Decision Tree without Particle Swarm Optimization (PSO) feature selection which is only 0.95%. This shows that Particle Swarm Optimization (PSO) is effective in selecting relevant features so that it can significantly improve model performance.
Multi-Aspect Sentiment Analysis Pada Review Film Menggunakan Metode Bidirectional Encoder Representations From Transformers (BERT) Karimah, Nur; Baita, Anna
Komputika : Jurnal Sistem Komputer Vol 13 No 1 (2024): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v13i1.11098

Abstract

Penelitian ini dilakukan untuk mengaplikasikan metode Bidirectional Encoder Representation from Transformer (BERT) pada multi-aspect sentiment analysis terhadap ulasan film. Data review diambil dengan menggunakan metode scrapping. Data yang digunakan berjumlah 1899 dengan jumlah data yang memiliki sentimen positif sebanyak 3245, sentimen netral sebanyak 4825, dan sentimen negatif sebanyak 1424. Pendekatan yang diusulkan mencakup aspek-aspek seperti acting, plot, cast, animation, dan music. Aspek yang memiliki sentimen positif terbanyak terdapat pada aspek music dengan total 631 data, sentimen netral berada pada aspek animation dengan total 1146, dan sentimen negatif berada pada aspek plot dengan total 362. Dataset yang digunakan melalui tahap cleaning yang terdiri dari case folding dan penghapusan Tag HTML, tanda baca, angka dan karakter. Penelitian ini menggunakan model BERTBASE-UNCASE dengan empat kali percobaan menggunakan hyperparameters max_epoch 10, batch size 16, dan learning rate 1e-4, 5e-5, 3e-5, dan 2e-5. Hasil penelitian menunjukkan bahwa, dari semua percobaan didapatkan bahwa nilai accuracy terbaik berada pada percobaan ketiga dengan menggunakan learning rate 3e-5 sebesar 82,32%. Sedangkan nilai precision, recall, dan f1-score terbaik terletak pada aspek animation sebesar 86%, 85%, dan 85%.
OPTIMASI NILAI IMPERCEPTIBILITY PADA WATERMARKING CITRA WARNA BERBASIS DCT-DWT Baita, Anna; Firmansyah, Rohmatullah Batik; Anggita, Sharazita Dyah
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 1 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i1.6878

Abstract

Teknik penyisipan watermark telah banyak digunakan untuk melindungi hak cipta, proses authentikasi maupun tamper detection. Terdapat dua jenis watermark berdasarkan tingkat persepsi visualnya, yakni visible watermark dan invisible watermark. Tantangan terbesar dari invisible watermark adalah mempertahankan tingkat imperceptibility namun tetap menjamin keamanan watermark dari berbagai serangan. Tujuan dari penelitian ini adalah untuk menghasilkan skema watermarking citra warna yang memiliki imperceptibility yang tinggi pada basis DCT DWT. Metode DWT dikenal memilki performa yang baik dalam invisible watermark. Untuk itu Chanel blue dipilih sebagai area penyisipan watermark karena mata manusia kurang sensitive terhadap warna ini.  Untuk meningkatkan keamanan, skema yang diusulkan menggunakan transformasi Arnold untuk mengacak watermark. Skema watermark yang diusulkan dapat menghasilkan imperceptibility yang cukup tinggi, yakni dengan nilai PSNR sebesar 43.786 dB. Nilai NC yang dihasilkan dalam skema ini sebesar 0.985 menunjukkan bahwa skema watermark mampu bertahan dari beberapa serangan. Akan tetapi skema ini kurang tahan terhadap serangan salt pepper serta cropping.
Comparison of Support Vector Machine and Decision Tree Algorithm Performance with Undersampling Approach in Predicting Heart Disease Based on Lifestyle Febriyanti, Gusti Ayu Putu; Baita, Anna
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.8941

Abstract

Heart disease is one of the leading causes of death in the world with risk factors such as atherosclerosis, high blood pressure, and smoking. Early diagnosis is essential to reduce mortality and improve patients' quality of life. This study evaluates the performance of two machine learning algorithms, namely Support Vector Machine (SVM) and Decision Tree (DT), in predicting heart disease risk by applying undersampling techniques to handle data imbalance. The K-fold cross-validation method with K=10 and hyperparameter tuning were applied to obtain the optimal performance of both models. The results showed that SVM without undersampling achieved 92% accuracy, while with undersampling the accuracy decreased to 76%. DT without undersampling has 91% accuracy, while with undersampling the accuracy reaches 75%. The undersampling technique successfully improved the balance in recognizing minority classes, although it reduced the overall accuracy. This finding confirms that SVM is more reliable in predicting heart disease in datasets with unbalanced class distribution.
Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk Damayanti, Annisa; Baita, Anna
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.9009

Abstract

Gestational Diabetes Mellitus (GDM) is a condition of glucose intolerance that develops during pregnancy until the birth process, which is characterized by an abnormal increase in blood sugar levels. Accurate early diagnosis is very important to provide information that can accelerate the treatment process and reduce complications in the mother and baby. One of the machine learning methods that can be used to predict GDM is the Support Vector Machine (SVM) algorithm and the Random Forest (RF) algorithm. This study aims to compare, and evaluate GDM disease prediction models using the SVM and RF algorithms by balancing the target data using the Random Undersampling Technique. The approach using the random undersampling technique managed to increase accuracy by 18% from the accuracy before using the random undersampling technique. The SVM model in this study also uses hyperparameter tuning with kernel parameters, C (cost), and gamma, while the RF model uses Scoring Metrix and four other parameters, namely N_estimators, max_depth, min_samples_split, and min_samples_leaf. The best parameter search process is carried out using GridSearchCV on both models. The results of the study showed that the SVM classification model with random undersampling technique and hyperparameter tuning with K-Fold achieved an average accuracy of 100% with precision, recall, f1-score values also reaching 100%, with the Best Parameter Kernel Linear, C value = 0.1 and gamma value = 0.001 reaching the highest accuracy of 1.0, with a ROC-AUC value of 99% indicating very good prediction performance. While the RF model showed an accuracy result of 99%, tuning was also carried out using the appropriate parameters resulting in the same accuracy of 99%, with a ROC-AUC value of 99% as well. From both models, it shows that the SVM and RF algorithms have very good prediction performance in predicting DMG, but the SVM algorithm can predict DMG better than RF because the number of prediction errors is lower. 
Co-Authors Andika Joni, Gusti Anggita, Sharazita Dyah Aulia Fitri, Laili Aviva Pradasyah Damayanti, Annisa Febriyanti, Gusti Ayu Putu Firmansyah, Rohmatullah Batik Fremmuzar, Pangestu Ghaisani, Mauhiba Salmaa Karimah, Nur Nur Aini Nur Rachman, Ali Nuri Cahyono Pradnya Dhuhita, Windha Mega Pramudya Hidayat, Muhammad Rifqi Rohmatun, Lina Ubaid, Muhammad Yahya