Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) JURNAL ILMIAH INFOKOM
Susiana Khosasih
Universitas Potensi Utama
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
A Analisis Perbandingan CNN, SVM, dan Hybrid CNN-SVM untuk Deteksi Anomali Trafik Jaringan Susiana Khosasih; Romi Antoni; Ricky Irnanda; Iswanto; Rahmat Humala Putra Hasibuan
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.748

Abstract

The rapid growth of information technology has significantly increased the volume and complexity of network traffic, leading to cyber security threats that are increasingly dynamic and difficult to detect using traditional security systems. The limitations of signature-based detection systems in identifying new attacks, including zero-day attacks, necessitate the adoption of more adaptive anomaly detection approaches through the utilization of machine learning and deep learning within Network Intrusion Detection Systems (NIDS). This study aims to analyze and compare the performance of Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and a hybrid CNN–SVM model in detecting network traffic anomalies. This research employs a quantitative approach using an experimental method to evaluate the performance of the three models based on the CIC-IDS2017 dataset. The experimental process includes data preprocessing, model development, and performance evaluation using accuracy, precision, recall, F1-score, and confusion matrix metrics. The results indicate that the CNN and SVM baseline models achieve high accuracy levels of 98.85% and 98.66%, respectively, but still exhibit limitations in detecting minority attack classes. The hybrid CNN–SVM model achieves the best performance with an accuracy of 99.41% and a more balanced macro-average recall, indicating improved generalization across classes. The integration of CNN as a feature extractor and SVM as a classifier is proven to be effective in leveraging the complexity of network traffic features while enhancing classification stability. Therefore, the hybrid CNN–SVM approach can be recommended as a more effective and reliable network traffic anomaly detection method compared to single-model approaches in supporting modern network security systems.
Klasifikasi Penyakit Daun Tomat Menggunakan Pengolahan Citra Dan Algoritma Machine Learning Romi Antoni; Susiana Khosasih; Ricky Irnanda; Iswanto; Farhan Sardy Abdillah; Yiska Dayanti Zagoto; Rika Rosnelly
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.778

Abstract

Klasifikasi penyakit daun tomat merupakan langkah penting untuk meningkatkan produktivitas pertanian dan meminimalkan kerugian akibat patogen. Penelitian ini bertujuan membandingkan dan mengevaluasi performa algoritma Naive Bayes dan Support Vector Machine (SVM) dalam klasifikasi penyakit daun tomat berbasis pengolahan citra digital. Pipeline penelitian mencakup segmentasi citra berbasis HSV, ekstraksi fitur warna, bentuk, dan tekstur menggunakan metode Gray Level Co-occurrence Matrix (GLCM) dan Local Binary Pattern (LBP), serta proses klasifikasi. Sistem diimplementasikan dalam bentuk Graphical User Interface (GUI) berbasis MATLAB untuk memudahkan manajemen data latih, pelatihan model, klasifikasi, dan evaluasi performa. Hasil pengujian menunjukkan bahwa SVM mencapai akurasi 92,36%, lebih tinggi dibandingkan Naive Bayes sebesar 79,41%. Kontribusi penelitian ini meliputi analisis komparatif Naive Bayes dan SVM dalam klasifikasi penyakit daun tomat, integrasi fitur warna, bentuk, dan tekstur dalam satu pipeline, dan pengembangan GUI interaktif untuk klasifikasi. Penelitian ini diharapkan dapat mendukung pertanian presisi melalui deteksi penyakit daun tomat yang lebih cepat, akurat, dan efisien.
PREDIKSI JUMLAH WISATAWAN MANCANEGARA KE INDONESIA MENGGUNAKAN ALGORITMA LINEAR REGRESSION DAN RANDOM FOREST REGRESSION Adil Setiawan; Susiana Khosasih; Marulak Lasron Siahaan; Khoiri Sutan Hasibuan; Bualazatulo Laia; Satriyo Wibowo
INFOKOM (Informatika & Komputer) Vol 13 No 1 (2025): JURNAL INFOKOM JUNI 2025
Publisher : POLITEKNIK PIKSI GANESHA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56689/infokom.v13i1.2326

Abstract

Tourism is one of Indonesia’s leading sectors, contributing significantly to the national economy. Forecasting the number of international tourist arrivals is a strategic necessity to support policy planning and the sustainable development of the tourism industry. This study aims to compare the performance of two regression algorithms, Linear Regression and Random Forest Regression, in forecasting international tourist arrivals to Indonesia. The dataset covers the period 2020–2025, obtained from the Central Bureau of Statistics (BPS) with variables that underwent preprocessing such as normalization and handling of missing values. The methodology includes an 80:20 train-test split, tabular regression, and parameter tuning for Random Forest Regression to enhance model performance. Linear Regression was selected as a baseline model, while Random Forest Regression was chosen for its capability to model nonlinear patterns. Model evaluation was conducted using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R² Score. The results show that Linear Regression produced an RMSE of 59,967.668, MAE of 14,837.645, and R² Score of 0.007, indicating low accuracy. In contrast, Random Forest Regression achieved substantially better results with an RMSE of 9,696.530, MAE of 1,193.143, and R² Score of 0.974. These findings confirm that Random Forest Regression provides higher accuracy than Linear Regression, particularly in addressing seasonal patterns and uncertainties caused by global factors. In conclusion, Random Forest Regression can be considered a more reliable forecasting method for predicting international tourist arrivals. The forecasting results can serve as a basis for decision-making in destination capacity planning, foreign exchange revenue estimation, and risk mitigation against global disruptions (pandemics, geopolitical issues, crises), thereby supporting adaptive and sustainable strategies for national tourism development.
Co-Authors Andri Armaginda Siregar Bualazatulo Laia Farhan Sardy Abdillah Iswanto Jalaluddin Nasution Khoiri Sutan Hasibuan Marulak Lasron Siahaan Mhd. Agung Irnanda Rahmat Humala Putra Hasibuan Ricky Irnanda Rika Rosnelly Romi Antoni Satriyo Wibowo Setiawan, Adil Wahyu Saptha Negoro Yiska Dayanti Zagoto