Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Jurnal Teknoif Teknik Informatika Institut Teknologi Padang Journal Science Informatica and Robotics
Aji Bayu Permadi
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Mechanical Engineering

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

Found 3 Documents
Search

 1 
IMPLEMENTASI QUESTION ANSWERING SYSTEM TAFSIR AL-AZHAR MENGGUNAKAN LANGCHAIN DAN LARGE LANGUAGE MODEL BERBASIS CHATBOT TELEGRAM Aji Bayu Permadi; Nazruddin Safaat H; Lestari Handayani; Yusra
Jurnal Teknoif Teknik Informatika Institut Teknologi Padang Vol 12 No 1 (2024): TEKNOIF APRIL 2024
Publisher : ITP Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21063/jtif.2024.V12.1.62-69

Abstract

Tafsir is a main gateway for a Muslim to study and understand the content of the verses in the Quran. One example is Tafsir Al-Azhar. Tafsir Al-Azhar is a commentary authored by Professor Dr. Hamka, which demonstrates how Dr. Hamka connects modern Islamic history with Quranic studies. Tafsir Al-Azhar has a large number of pages, requiring extra effort when searching for information within it. This research aims to create a system capable of receiving questions about Tafsir Al-Azhar in natural language and answering them in user-friendly terms. The technology used in this research includes Langchain and Large Language Models, implemented using a Telegram chatbot. Telegram was chosen for its popularity and user-friendly interface. The Question Answering system was tested using User Acceptance Testing (UAT) and the DeepEval framework. The UAT resulted in an accuracy score of 83.71%, while testing using the DeepEval framework yielded a hallucination score of 41%, contextual precision of 90%, contextual recall of 81%, and contextual relevancy of 79%.
IMPLEMENTASI QUESTION ANSWERING SYSTEM TAFSIR AL-AZHAR MENGGUNAKAN LANGCHAIN DAN LARGE LANGUAGE MODEL BERBASIS CHATBOT TELEGRAM Aji Bayu Permadi; Lestari Handayani; Yusra; Nazruddin Safaat H
Jurnal Teknoif Teknik Informatika Institut Teknologi Padang Vol 12 No 1 (2024): TEKNOIF APRIL 2024
Publisher : ITP Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21063/jtif.2024.V12.1.62-69

Abstract

Tafsir is a main gateway for a Muslim to study and understand the content of the verses in the Quran. One example is Tafsir Al-Azhar. Tafsir Al-Azhar is a commentary authored by Professor Dr. Hamka, which demonstrates how Dr. Hamka connects modern Islamic history with Quranic studies. Tafsir Al-Azhar has a large number of pages, requiring extra effort when searching for information within it. This research aims to create a system capable of receiving questions about Tafsir Al-Azhar in natural language and answering them in user-friendly terms. The technology used in this research includes Langchain and Large Language Models, implemented using a Telegram chatbot. Telegram was chosen for its popularity and user-friendly interface. The Question Answering system was tested using User Acceptance Testing (UAT) and the DeepEval framework. The UAT resulted in an accuracy score of 83.71%, while testing using the DeepEval framework yielded a hallucination score of 41%, contextual precision of 90%, contextual recall of 81%, and contextual relevancy of 79%.
ANALISIS EFEKTIVITAS INGEST MODULE DALAM MENDETEKSI DAN MEMULIHKAN BUKTI DIGITAL YANG DISAMARKAN TERENKRIPSI Aji Bayu Permadi; Febrian Rizki Adi Sutiyo; M. Redho Eka Saputra
JOCITIS-Journal Science Infomatica and Robotics Vol. 1 No. 2 (2023): JOCOTIS - Journal Science Informatica and Robotics
Publisher : JOCITIS-Journal Science Infomatica and Robotics

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

Abstract

Perkembangan teknologi yang sangat pesat membawa dampak positif dan negatif. Kemudahan produksi, distribusi, dan pendistribusian data dapat meningkatkan penggunaan data. Kemudahan tersebut dapat menyebabkan kejahatan dunia maya. Oleh karena itu keamanan data digital menjadi hal penting untuk keamanan informasi. Penelitian ini bertujuan untuk menguji efektivitas ingest module untuk mendeteksi dan memulihkan bukti digital yang disamarkan. Hasil penelitian ini menunjukkan bahwa kinerja ingest module sangat luar biasa dengan kecepatan yang optimal. Algoritma deteksi yang digunakan pada modul ini menghasilkan Tingkat akurasi yang tinggi dan respon yang cepat terhadap bukti digitial yang terlindungi (enkripsi).
Co-Authors Febrian Rizki Adi Sutiyo M. Redho Eka Saputra Nazruddin Safaat H Nazruddin Safaat H Yusra