Article Per Year (5 Year)
p-Index From 2021 - 2026
1.873
P-Index
This Author published in this journals
All Journal VOX EDUKASI: Jurnal Ilmiah Ilmu Pendidikan JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Jurnal Teknologi Dan Sistem Informasi Bisnis Jurnal Abdi Insani JTIULM (Jurnal Teknologi Informasi Universitas Lambung Mangkurat) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Computer Science and Information Technology (CoSciTech) Jurnal Abdimas Bina Bangsa Kohesi: Jurnal Sains dan Teknologi Jurnal Informatika Polinema (JIP)
Octariadi, Barry Ceasar
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
PERBANDINGAN FUNGSI OPTIMIZER PADA IDENTIFIKASI DIABETES MENGGUNAKAN METODE FEED FORWARD Setyawan, Rizki Fajar; Abdullah, Asrul; Octariadi, Barry Ceasar
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 11, No 1 (2026)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v11i1.7757

Abstract

Identifikasi dini diabetes merupakan kebutuhan mendesak untuk mencegah komplikasi serius dan mengurangi beban kesehatan global. Penelitian ini bertujuan untuk membandingkan kinerja fungsi optimizer pada model Feed Forward Neural Network (FFNN) dalam mengklasifi-kasikan data diabetes. Optimizer yang diuji meliputi RMSprop, Adam, Adagrad, dan Stochastic Gradient Descent (SGD). Dataset diabetes dari platform Kaggle, yang terdiri dari 768 sampel dengan 9 fitur, dibagi men-jadi data latih dan uji dengan rasio 80:20. Evaluasi model dilakukan menggunakan metrik Accuracy, Precision, Recall, dan F1-Score ber-dasarkan Confusion Matrix. Hasil penelitian menunjukkan bahwa RMSprop memberikan performa terbaik dengan akurasi sebesar 0,759740, Precision 0,660377, Recall 0,648148, dan F1-Score 0,654206, diikuti oleh Adam dengan akurasi 0,746753. RMSprop menunjukkan generalisasi yang lebih baik pada data uji berkat mekanisme pembaruan bobot adaptifnya. Penelitian ini merekomendasikan RMSprop sebagai optimizer optimal untuk model FFNN dalam identifikasi diabetes, memberikan kontribusi bagi pengembangan alat diagnosis yang lebih akurat dan efisien.
Classification Of Anxiety Levels Based On General Anxiety Disorder Data Using The XGBoost Method Rahman, Rovi Royyan; Octariadi, Barry Ceasar; Sucipto
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 11 No. 1 (2026)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v11i1.495

Abstract

Anxiety is a common psychological disorder experienced by individuals and has the potential to reduce quality of life if not treated properly. This study aims to classify anxiety levels into four categories, namely normal, mild, moderate, and severe, using the Extreme Gradient Boosting (XGBoost) algorithm. The data used came from the Kaggle platform, consisting of 671 entries with 11 anxiety symptom features and one target label. The research process involved data exploration (EDA), handling missing values, data balancing using the Synthetic Minority Oversampling Technique (SMOTE), and feature selection based on multivariate correlation. Two models were built with training and test split ratios of 70:30 and 80:20. The evaluation results showed that the XGBoost model achieved good classification performance, with accuracy, precision, recall, and F1-score reaching 93% after optimization. The best model was then implemented as a Streamlit web application to facilitate interactive prediction of anxiety levels. This research is expected to be a tool for initial screening of anxiety disorders and a reference in the development of machine learning-based classification systems in the field of mental health.
Co-Authors Alinafiah, Andika Muhammad Asrul Abdullah azwar, agim aljanata Cahyo, Rahandya Chatarina Umbul Wahyuni Febrilian, Uray Menur Wahyu Pangestika, Menur Wahyu Muhammad Agus Muljanto Putri, Alya Amanda Rachmat Wahid Saleh Insani Rahman, Rovi Royyan Ramadhianto, Muhammad Dwi Repan Sabima, Muhamad Angga Rizki Saputra, Deny Saputra Setyawan, Rizki Fajar Siregar, Alda Cendekia Sucipto Sucipto Sucipto Syarifah Putri Agustini Alkadri Yanti, Dewi