Article Per Year (5 Year)
p-Index From 2021 - 2026
3.747
P-Index
This Author published in this journals
All Journal Teknika TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Jurnal Informatika JUITA : Jurnal Informatika Jurnal Ilmiah KOMPUTASI Jurnal Nasional Komputasi dan Teknologi Informasi IJISCS (International Journal Of Information System and Computer Science) JSR : Jaringan Sistem Informasi Robotik JATI (Jurnal Mahasiswa Teknik Informatika) Jurnal Teknik Informatika (JUTIF) IndraTech TIERS Information Technology Journal SIENNA Jurnal Sistem Cerdas dan Rekayasa ROUTERS: Jurnal Sistem dan Teknologi Informasi Seminar Nasional Teknologi dan Multidisiplin Ilmu INOVTEK Polbeng - Seri Informatika IJISCS (International Journal of Information System and Computer Science) Smatika Jurnal : STIKI Informatika Jurnal
Sriyanto, Sriyanto
Department Of Informatics Engineering, Institute Of Informatics And Business Darmajaya Lampung
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Library & Information Science Neuroscience Social Sciences Transportation Other

Published : 31 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 31 Documents
Search

 1   2   3   4 
NEURAL NETWORK OPTIMIZATION WITH GENETIC ALGORITHM FOR HEART DISEASE PREDICTION M Agus Badruzaman Al Khoir; Sriyanto Sriyanto
IJISCS (International Journal of Information System and Computer Science) Vol 6, No 2 (2022): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v6i2.1235

Abstract

Coronary Heart Disease (CHD) is a contributor to the number 1 cause of death in the world besides cardiovascular disease. The tendency of Indonesian people who do not know and ignore coronary heart disease is a factor that causes Indonesia to be high a contributor to deaths caused by coronary heart disease. This research is expected to produce new predictions of heart disease using genetic optimization of neural networks with better prediction results and can obtain algorithms with new percentage values in predicting coronary heart disease. Genetic optimization of the neural network is used because the algorithm follows the human nervous system which has the characteristics of parallel processing, processing elements in large quantities, and fault tolerance. The results of the research carried out are the accuracy obtained by 82.18% and increased to 83.50% after using genetic algorithm optimization, from these results it can be concluded that the neural network algorithm can be better if it is supported by genetic algorithm optimization
Enhancing Chronic Kidney Disease Classification Using Decision Tree And Bootstrap Aggregating: Uci Dataset Study With Improved Accuracy And Auc-Roc Zuriati, Zuriati; Meilantika, Dian; Arpan, Atika; Permata, Rizka; Sriyanto, Sriyanto; Mas'ud, Mohd. Zaki
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5271

Abstract

Chronic Kidney Disease (CKD) is a progressive medical disorder that requires timely and precise identification to avoid permanent impairment of kidney function. However, Decision Tree models, although widely used in clinical applications due to their transparency, ease of implementation, and ability to handle both categorical and numerical data, are prone to overfitting and instability when applied to small or imbalanced datasets. The purpose of this study is to optimize CKD classification by integrating Bootstrap Aggregating (Bagging) with Decision Tree to enhance accuracy and robustness. The methodology involves testing two model variants a standalone Decision Tree and a Bagging-supported Decision Tree using 10-fold cross-validation and evaluating performance with accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC). Findings reveal that Bagging enhances model accuracy from 0.980 to 0.987, raises precision from 0.976 to 1.000, and improves recall from 0.954 to 0.954, and increases F1-score from 0.965 to 0.976. These results demonstrate that Bagging significantly improves the reliability and generalizability of Decision Tree classifiers, making them more effective for CKD prediction.
Hybrid Machine Learning Approach for Nutrient Deficiency Detection in Lettuce Zuriati, Zuriati; Widyawati, Dewi Kania; Arifin, Oki; Saputra, Kurniawan; Sriyanto, Sriyanto; Ahmad, Asmala
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7143

Abstract

Early detection of nutrient deficiencies in lettuce is essential for precision agriculture. However, this task remains challenging due to limited data availability and class imbalance, which reduce model sensitivity toward minority classes and hinder generalization. This study introduces a hybrid machine learning approach integrating SMOTE, Optuna, and SVM to enhance the accuracy of nutrient deficiency classification using digital leaf image analysis. The dataset, obtained from Kaggle, includes four categories: Nitrogen Deficiency (-N), Phosphorus Deficiency (-P), Potassium Deficiency (-K), and Fully Nutritional (FN). Image features were extracted using MobileNetV2 pretrained on ImageNet and classified with a Support Vector Machine. Three scenarios were tested: (1) SVM before SMOTE, (2) SVM after SMOTE, and (3) Optuna-SVM after SMOTE, evaluated using accuracy, precision, recall, and f1-score. The hybrid model achieved the best performance with accuracy 0.929, precision 0.946, recall 0.835, and f1-score 0.869, outperforming the other scenarios. This hybrid framework effectively addressed class imbalance and improved classification margin stability through adaptive hyperparameter tuning using the Tree Structured Parzen Estimator within Optuna. The novelty of this study lies in combining MobileNetV2 based feature extraction with SMOTE and Optuna-SVM for small agricultural datasets. The proposed approach offers an efficient, accurate, and practical solution for automated nutrient deficiency diagnosis and contributes to the development of AI-driven smart agriculture systems.
Evaluation of CNN Architectures for Kidney Stone Classification in Ultrasound Image Zuriati Zuriati; Sriyanto Sriyanto; Agiska Ria Supriyatna; Nurul Qomariyah; Dian Ayu Afifah; Zarnelly Zarnelly
JUITA: Jurnal Informatika JUITA Vol. 14 Issue 1, March 2026
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v14i1.28352

Abstract

Kidney stone diagnosis requires fast and reliable evaluation, yet ultrasound interpretation still largely depends on clinical expertise. This study evaluates four Convolutional Neural Network (CNN) architectures, VGG16, ResNet50, MobileNetV2, and EfficientNetB0 for classifying kidney ultrasound images into Normal and Stone categories. Using a public dataset of 9,416 images, the models were assessed in terms of predictive performance and computational efficiency. MobileNetV2 achieved perfect classification performance, recording 100% accuracy, precision, recall, and F1-score, while maintaining the smallest parameter size (≈3.6M) and fastest training time (~44 s/epoch). VGG16 and ResNet50 also delivered near perfect accuracy (99.79% and 99.89%) with full recall for Stone cases. In contrast, EfficientNetB0 failed to generalize, yielding only 51.62% accuracy due to severe misclassification of Normal images. These results demonstrate that MobileNetV2 provides the most reliable and efficient solution for ultrasound based kidney stone classification, highlighting its strong potential for practical clinical deployment.
Analisis Pengaruh Feature Decontamination terhadap Kinerja Deteksi Ransomware Menggunakan Random Forest Sriyanto; Zuriati; Zarnelly; Yuri Fitrian
Jurnal Sistem Cerdas dan Rekayasa (JSCR) Vol 8 No 1 (2026): Jurnal Sistem Cerdas dan Rekayasa (JSCR) 2026
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Widya Kartika (LPPM UWIKA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61293/jscr.v8i1.955

Abstract

Studi ini memfokuskan analisis pada dampak dekontaminasi fitur (feature decontamination) terhadap stabilitas model klasifikasi saat mengidentifikasi ransomware menggunakan dataset UNSW-NB15. Isu krusial pada data deteksi intrusi umumnya terletak pada kebocoran data (data leakage) atau kontaminasi fitur, yang berisiko memicu peningkatan performa model secara semu tanpa menggambarkan kapabilitas aslinya di lingkungan nyata. Penelitian ini menggunakan dua skenario eksperimen, yaitu tanpa feature decontamination dan dengan feature decontamination. Tahapan preprocessing meliputi encoding fitur kategorikal, normalisasi menggunakan StandardScaler, serta penyeimbangan data menggunakan SMOTE. Model klasifikasi yang digunakan adalah Random Forest, dipilih karena kemampuannya dalam menangani data tabular. Hasil penelitian menunjukkan bahwa model tanpa feature decontamination menghasilkan performa sempurna dengan nilai akurasi, precision, recall, dan F1 score sebesar 1.000, yang mengindikasikan adanya data leakage. Setelah dilakukan feature decontamination, performa model menjadi lebih realistis dengan akurasi sebesar 0.9028, precision sebesar 0.8820, recall sebesar 0.9506, dan F1-score sebesar 0.9150, serta nilai AUC sebesar 0.9795. Temuan ini menunjukkan bahwa feature decontamination berperan penting dalam meningkatkan validitas evaluasi model dengan menghilangkan bias dari fitur yang terkontaminasi. Dengan demikian, integritas data menjadi faktor kunci dalam pengembangan sistem deteksi ransomware yang andal.
Perbandingan Algoritma Random Forest, Decision Tree, dan K-Nearest Neighbor untuk Penentuan Model Klasifikasi Gaya Belajar VARK Hefri Juanto; M Said Hasibuan; Sriyanto
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.5086

Abstract

The mismatch between teaching methods and individual learning style preferences in e-learning platforms often hinders the effectiveness of information absorption for students. The primary issue lies in the one-size-fits-all learning approach and the inefficiency of identifying learning styles through manual questionnaires, which are subjective and time-consuming. This study aims to evaluate the performance of Random Forest, Decision Tree, and K-Nearest Neighbor (KNN) algorithms in automating VARK (Visual, Auditory, Read/Write, Kinesthetic) learning style classification. The novelty of this research lies in the implementation of the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance in the Read/Write modality, which initially accounted for only 14.2% of the total population. Following the CRISP-DM framework, a balanced dataset of 1,410 records was utilized. Experimental results show that Random Forest and KNN achieved the highest identical accuracy of 97.87%. However, based on stability evaluation through 10-Fold Cross Validation, Random Forest proved to be the most optimal model with the highest Mean CV score of 0.9592, outperforming KNN (0.9503). These findings provide a precise scientific foundation for developing adaptive recommendation systems to deliver personalized and effective instructional materials.
IMPROVING FRAUD DETECTION IN FINANCIAL TRANSACTIONS USING SMOTE AND MACHINE LEARNING TECHNIQUES Zahratul Umamah; Joko Triloka; Sutedi Sutedi; Sriyanto Sriyanto
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 10 No. 3 (2026): JATI Vol. 10 No. 3
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v10i3.18211

Abstract

Perkembangan teknologi informasi mendorong meningkatnya penggunaan sistem transaksi keuangan digital yang memberikan kemudahan dan efisiensi dalam aktivitas ekonomi. Namun, peningkatan tersebut juga diikuti oleh meningkatnya risiko financial fraud yang dapat menimbulkan kerugian finansial serta menurunkan kepercayaan terhadap sistem keuangan digital. Permasalahan utama dalam deteksi fraud adalah ketidakseimbangan distribusi data antara transaksi normal dan transaksi fraud yang menyebabkan model klasifikasi kurang optimal dalam mengenali kelas minoritas. Penelitian ini bertujuan untuk meningkatkan kinerja sistem deteksi financial fraud melalui penerapan teknik penyeimbangan data menggunakan Synthetic Minority Oversampling Technique (SMOTE) yang dikombinasikan dengan algoritma machine learning. Metode penelitian meliputi analisis karakteristik dataset, preprocessing data, penerapan SMOTE, pembangunan model menggunakan Logistic Regression, Support Vector Machine, dan Random Forest, serta evaluasi performa menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa penerapan SMOTE mampu meningkatkan kemampuan model dalam mendeteksi transaksi fraud, dengan algoritma Random Forest memberikan performa terbaik dibandingkan algoritma lainnya
Benchmark and comparison between hyperledger and MySQL Onno W. Purbo; Sriyanto Sriyanto; Suhendro Suhendro; Rz Abd. Aziz; Riko Herwanto
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 2: April 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i2.13743

Abstract

In this paper, we report the benchmarking results of Hyperledger,  a Distributed Ledger, which is the derivation Blockchain Technology.  Method to evaluate Hyperledger in a limited infrastructure is developed. Themeasured infrastructure consists of 8 nodes with a load of up to 20000 transactions/second. Hyperledger consistently runs all evaluation, namely, for 20,000 transactions, the run time 74.30s, latency 73.40ms latency, and 257 tps. The benchmarking of Hyperledger shows better than a database system in a high workload scenario. We found that the maximum size data volume in one transaction on the Hyperledger network is around ten (10) times of MySQL. Also, the time spent on processing a single transaction in the blockchain network is 80-200 times faster than MySQL. This initial analysis can provide an overview for practitioners in making decisions about the adoption of blockchain technology in their IT systems.
Machine learning and deep learning for ransomware detection via feature decontamination Sriyanto Sriyanto; Chairani Fauzi; Mohd Faizal Abdollah; Zuriati Zuriati
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 24, No 3: June 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v24i3.27833

Abstract

The continuous escalation of ransomware attacks poses a severe risk to network infrastructure and data integrity, highlighting the urgent requirement for dependable detection systems. This paper presents a comparative analysis of deep learning (DL) and machine learning (ML) techniques for identifying ransomware traffic using the UNSW-NB15 dataset. A significant obstacle in many intrusion detection investigations is feature contamination, where specific attributes inadvertently leak label data or reflect post-incident statistics, resulting in inflated and overly optimistic performance evaluations. To mitigate this concern, a feature decontamination protocol is implemented to isolate 29 reliable attributes, followed by the application of the synthetic minority over-sampling technique (SMOTE) to address the issue of class imbalance. Empirical results demonstrate that the random forest (RF) model achieves superior performance, reaching an accuracy of 0.9027 and a recall of 0.9507. Among the DL candidates, the multi-layer perceptron (MLP) delivers the most competitive outcomes with an accuracy of 0.8859 and an F1-score of 0.8996. These results suggest that ensemble-based ML frameworks offer more effective and computationally efficient ransomware detection when applied to decontaminated tabular datasets.
Avocado Ripeness Classification Based on Digital Imagery Using an Artificial Neural Network Sriyanto; Febri Pratama; Zuriati
SMATIKA JURNAL : STIKI Informatika Jurnal Vol 16 No 02 (2026): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM Universitas Bhinneka Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v16i02.2390

Abstract

Traditional methods for determining avocado ripeness rely primarily on subjective visual observation, which is highly prone to error. This study aims to develop an automated classification system for avocado ripeness using a sequential Artificial Neural Network (ANN) based on digital image data. The dataset consisted of 1,500 balanced avocado images distributed across three classes: Ripe (500 images), Rotten (500 images), and Unripe (500 images). A total of 1,200 images were used for training and 300 images for validation. Images were preprocessed through resizing to 128 × 128 pixels and pixel intensity normalization. The proposed ANN architecture consisted of a Flatten layer, two hidden Dense layers with ReLU activation, and an output layer with Softmax activation. Experimental results showed that the model achieved an overall accuracy of 89.00%, with macro-average Precision, Recall, and F1-Score values of 0.92, 0.89, and 0.89, respectively. The best classification performance was achieved for the Rotten class, with a Precision of 1.00 and a Recall of 0.96. Classification errors mainly occurred between the Unripe and Ripe classes, where visual similarities during the ripening transition stage led to cross-class predictions. Overall, the proposed ANN model demonstrated reliable performance for avocado ripeness classification using digital image data and showed its potential as a simple image-based decision-support tool for post-harvest quality assessment.
Co-Authors A. Toding Adhi Tristiyanto Agiska Ria Supriyatna Ahmad, Asmala Ahmed Jamal Abdullah Al-Gburi Arifin, Oki Arpan, Atika Asep Eryana Asep Eryana Ayu Brahdika Putri Aziz, RZ. Abdul Chairani Chairani Chairani Chairani Chairani Fauzi Dian Ayu Afifah Febri Pratama Firmansyah Firmansyah Yunialfi Fitria . Hartono Hartono Hefri Juanto Herwanto, Riko Irma Agustina Joko Triloka Juwariyem Juwariyem Khodijah Khodijah Kurniawan Saputra M Agus Badruzaman Al Khoir M Said Hasibuan M. Abu Mas'ud, Mohd. Zaki meilantika, Dian Mohammed Yousif Zeain Mohd Faizal Abdollah Muhamad Fahrurrozi Nursiyanto Nurul Qomariyah Oktaf Rina Onno W. Purbo Onno W. Purbo Pakarti Riswanto Permata, Rizka R. Syahputri Rifki Arif Rifki Suhendro Suhendro Sutedi Sutedi Sutedi Sutedi Widyawati, Dewi Kania Y. Suhendro Yuri Fitrian Z. Zakaria Zahratul Umamah Zarnelly Zarnelly Zarnelly Zuriati Zuriati, Zuriati