Claim Missing Document
Check
Articles

Found 15 Documents
Search

Pengujian Regresi Otomasi pada Aplikasi Mobile Satudikti Menggunakan Katalon Studio Akram, Abdullah; Pratiwi, Nunik
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 6 No. 4 (2023): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

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

Abstract

Satudikti is a one-stop application from the many services available at the Directorate General of Higher Education, to make it easier for users to access various higher education services in one application. Before the application can be widely used, a testing step is indispensable. This is due to potential problems in higher education data that can have a fatal impact, considering that this data is closely related to state information. And if there is an error in the software, the Directorate General of Higher Education must restart the development process that can harm the state. Therefore, the purpose of this study is to test the readiness of the application when it is widely used and reduce the risk of errors to ensure that the application remains of sufficient quality for users, as well as analyze the effectiveness of the application and then whether automated regression testing using Katalon Studio has more value than manual testing. Testing in this study was carried out manually with the black-box testing method and automated testing using Katalon Studio as an automated testing tool. Testing using Katalon Studio found that the functionality, features, and access to the tested pages worked well according to existing requirements. The implementation of automation testing using Katalon Studio has also proven to be more efficient in reducing test time and providing detailed test results to detect errors with easy-to-understand reporting.
ANALISIS KINERJA ALGORITMA MACHINE LEARNING DALAM MENDETEKSI ANOMALI KETINGGIAN AIR LAUT: STUDI PERBANDINGAN ONE-CLASS SVM DAN ISOLATION FOREST Alifandra, Dhafa; Pratiwi, Nunik
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.405

Abstract

This study aims to compare the performance of two machine learning algorithms for anomaly detection One-Class SVM and Isolation Forest in identifying anomalies in sea level data in Indonesia, a region with high tsunami risk. The data were obtained from an official Indonesian government source over a one-year period and underwent preprocessing, including data cleaning and standardization. The models were evaluated using statistical analysis (Mann-Whitney U test), clustering metrics (Davies-Bouldin Index and Silhouette Score), and visual inspection. The results indicate that Isolation Forest outperformed the other algorithm with a Davies-Bouldin Index of 0.8124, while One-Class SVM achieved the highest Silhouette Score at 0.4381, although its Davies-Bouldin Index was higher at 0.9163. This study contributes to the selection of effective algorithms for ocean monitoring systems as part of disaster mitigation strategies in Indonesia.
PREDIKSI HARGA DAN RISIKO SAHAM TELKOM DAN INDOSAT MENGGUNAKAN LSTM DAN VAR DENGAN VISUALISASI Alam, Indera Nurul; Pratiwi, Nunik
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.399

Abstract

Investment in Indonesia shows a growing trend, with Telkom (TLKM) and Indosat (ISAT) being among the mostactively traded stocks with high volatility. This condition raises the need for reliable stock price prediction andinvestment risk analysis. This study aims to develop a daily stock closing price prediction model using the Long Short-Term Memory (LSTM) algorithm with a Bidirectional LSTM architecture and to conduct risk analysis based on Valueat Risk (VaR) through parametric Monte Carlo simulation. Fourteen years of historical stock data were utilized andprocessed through feature engineering techniques (return, moving average, volatility) and 30-day windowing.Baseline models with one to four layers were tested, and the best model was further optimized through hyperparametertuning using the Random Search method. The results indicate that the single-layer Bidirectional LSTM modeldemonstrated the best performance on the testing data. Evaluation shows a significant performance improvement aftertuning, with RMSE decreasing from 69 to 67, MAPE from 1.61% to 1.59%, and R-Square remaining high at 0.97 forTelkom, as well as a reduction in RMSE from 91 to 74, MAPE from 2.81% to 2.27%, and an increase in R-Squarefrom 0.76 to 0.84 for Indosat. The VaR analysis reveals that the predicted daily and 80-day risk values show onlyminor deviations from the actual values, supporting the validity
DETEKSI PORNOGRAFI PADA CITRA KARAKTER ANIMASI DENGAN HSV DAN YCBCR MENGGUNAKAN NAÏVE BAYES Jannah, Azzahratul; Pratiwi, Nunik
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.v10i1.5883

Abstract

Teknologi pembuatan animasi berkembang semakin pesat. Animasi perempuan digunakan dalam berbagai bidang seperti komik atau karakter anime, film, iklan, dan game online. Dengan berkembangnya animasi juga menimbulkan dampak negatif dan positif. Adanya simbol yang mengarah pada pornografi merupakan salah satu dampak negatif yang muncul.. Sebagian besar animasi yang memiliki unsur negatif tersebar luas melalui internet dan dapat mudah dijangkau oleh semua orang, tanpa memandang usia. sehingga dapat menyebabkan kecanduan pornografi dan penyimpangan lainnya. Saat ini kecerdasan buatan yang berkembang pesat juga memungkinkan pendeteksian dini terhadap karakter animasi yang mengandung unsur pornografi. Salah satunya adalah dengan deteksi citra animasi yang dilakukan dengan menggunakan metode deteksi warna kulit yang menggabungkan ruang warna HSV dan YCbCr dan kemudian diklasifikasikan dengan algoritma Naïve Bayes. Berdasarkan pengujian yang dilakukan terhadap 396 citra yang terdiri dari 198 citra kelas porno dan 198 kelas non_porn dengan, diperoleh akurasi sebesar 76,25%. Hasil percobaan menunjukkan bahwa dengan menggabungkan kedua ruang warna tersebut, model dapat bekerja dengan baik dalam mendeteksi ada atau tidaknya unsur pornografi pada citra karakter animasi perempuan.
IDENTIFIKASI PENYAKIT TUMBUHAN TOMAT DAN ANGGUR MENGGUNAKAN CNN DENGAN ARSITEKTUR VGG-16 Rahman, Fadllin Fadlu; Pratiwi, Nunik
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.v10i1.5663

Abstract

Tanaman tomat dan anggur dikenal sebagai tanaman yang populer di Indonesia. Mayoritas penyakit yang menyerang kedua tanaman ini dapat teridentifikasi melalui gejala yang muncul pada daunnya. Penelitian ini mengusulkan identifikasi penyakit tanaman tomat dan tanaman anggur menggunakan algoritma Convolutional Neural Network dengan arsitektur VGG-16 didalamnya dengan tujuan membantu masyarakat yang memiliki kedua tanaman tersebut agar dapat menganalisis penyakit dari tanaman anggur dan tanaman tomat. Hasil akurasi yang berhasil diperoleh dari penelitian ini dengan ujicoba epoch sebanyak 100 menghasilkan akurasi sebesar 92% dari total sampel data sebanyak 10.717 yang Merupakan gabungan dari penyakit tanaman anggur dan tanaman tomat. Penyakit tanaman anggur yang digunakan yaitu black rot, esca, healthy, dan leaf blight. Sedangkan penyakit tanaman tomat yang digunakan yaitu bacteria spot, early blight, healthy, late blight, leaf mold, septoria leaf spot, spider mites, target spot, mosaic virus, dan yellow leaf curl virus.