Article Per Year (5 Year)
p-Index From 2021 - 2026
1.503
P-Index
This Author published in this journals
All Journal IKRA-ITH Informatika : Jurnal Komputer dan Informatika Jurnal Pengabdian Teknologi, Ekonomi dan Humaniora Jurnal Sains & Teknologi Fakultas Teknik Universitas Darma Persada Journal Technology Information and Data Analytic
Herianto
Universitas Darma Persada
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mechanical Engineering Social Sciences Other

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : journal technology information and data analytic

 1 
Chatbot Berbasis Retrieval Augmented Generation (RAG) untuk Peningkatan Layanan Informasi Sekolah Shafa Elysia; Herianto
Journal TIFDA (Technology Information and Data Analytic) Vol 1 No 2 (2024)
Publisher : Prodi Teknologi Informasi Universitas Darma Persada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70491/tifda.v1i2.52

Abstract

Penelitian ini bertujuan untuk merancang dan mengembangkan sistem chatbot berbasis model Transformers dengan metode Retrieval Augmented Generation (RAG) untuk layanan informasi di SMP Santo Leo III. Chatbot ini dirancang untuk meningkatkan aksesibilitas dan efisiensi penyampaian informasi, meliputi peraturan sekolah, kegiatan ekstrakurikuler, kalender akademik, dan informasi relevan lainnya. Model yang digunakan adalah LLaMA-3-8B-Instruct, Mistral-7B-Instruct-v0.3, dan Zephyr-7B-β. Pengujian terhadap dataset yang berisi 30 pertanyaan terkait informasi sekolah menunjukkan bahwa model LLaMA-3-8B-Instruct dan Mistral-7B-Instruct-v0.3 mencapai akurasi 100%, sementara Zephyr-7B-β mencapai akurasi 70%. Integrasi model berbasis Transformers dengan metode RAG terbukti efektif dalam menghasilkan jawaban yang relevan terhadap konteks percakapan, meningkatkan kualitas respons chatbot. Hasil penelitian ini menunjukkan potensi besar teknologi Transformers dan RAG dalam menciptakan interaksi mesin yang lebih intuitif dan responsif. Solusi ini dirancang dengan fleksibilitas tinggi, memungkinkan penerapannya di sekolah lain dengan penyesuaian minimal terhadap dataset lokal, sehingga menjadi solusi skalabel untuk meningkatkan layanan informasi di sektor pendidikan. Teknologi ini juga mengatasi keterbatasan pada sistem chatbot berbasis menu, aturan, dan machine learning konvensional. Dengan demikian, penelitian ini memberikan kontribusi signifikan dalam pengembangan sistem chatbot untuk meningkatkan efisiensi penyampaian informasi di lingkungan pendidikan.
Behavioral Biometric-Driven Educational Data Mining: CNN-Based Prediction of Students’ On-Time Graduation from Handwritten Signatures Herianto; Khoirul Mustaan; Yahya; Nur Syamsiyah
Journal TIFDA (Technology Information and Data Analytic) Vol 2 No 2 (2025)
Publisher : Prodi Teknologi Informasi Universitas Darma Persada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70491/tifda.v2i2.112

Abstract

Timely graduation is a fundamental metric in higher-education accreditation and a key indicator of institutional efficiency. Conventional prediction models largely rely on longitudinal academic records, which are lagging indicators and often fail to detect risks during the early stages of study. This research proposes a paradigm shift by leveraging behavioral biometrics—specifically, the analysis of handwritten signatures using Deep Learning—to predict students’ graduation timelines and academic motivation profiles. Using a dataset from the Undergraduate Information Technology Program at Universitas Darma Persada, the study adopts the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework. A Convolutional Neural Network (CNN) model based on the ResNet-50 architecture was developed, employing transfer learning to extract complex graphological features from signature images. Through rigorous data augmentation and statistical normalization, the model addresses the limitations of a small dataset. Empirical evaluation reports a graduation-prediction accuracy of 65% (Recall: 65%, F1-Score: 64%) and an academic-personality prediction accuracy of 70% (Precision: 74%, F1-Score: 69%). Although its absolute performance remains below transcript-based models, the findings validate the potential of signatures as early leading biometric indicators capable of capturing latent discipline and intrinsic motivation. This approach offers a non-invasive decision-support tool for academic advisors within intelligent education ecosystems.
Co-Authors Adam Arif B Afri Yudha Aji Pamungkas Aji Setiawan akmal aditya Atik Kurnianto Bagus Tri Mahardika Brigitta Chesya Pricilla Eva Novianti Khoirul Mustaan Mira Febriana Sesunan Muhammad Ridwan Nila Cahyaningrum Nur Hasanah Nur Syamsiyah Nur Syamsiyah Riski Irawan Shafa Elysia Suzuki Syofian Timor Setiyaningsih Yahya Yahya Yahya