Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal Rekayasa Sistem Informasi dan Teknologi Journal of Data Analytics, Information, and Computer Science (JDAICS)
Sam Farisa Chaerul Haviana
Universitas Islam Sultan Agung Semarang
Computer Science & IT Decision Sciences, Operations Research & Management Mathematics Other

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

Found 3 Documents
Search

 1 
SISTEM PENDETEKSI OBJEK ROKOK MENGGUNAKAN ALGORITMA YOU ONLY LOOK ONCE (YOLO) PADA KAWASAN LARANGAN MEROKOK Muhammad Azmi Abdillah Sulaeman; Sam Farisa Chaerul Haviana
Jurnal Rekayasa Sistem Informasi dan Teknologi Vol. 3 No. 3 (2026): Februari
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jrsit.v3i3.2394

Abstract

Merokok di area publik masih menjadi masalah yang sulit dikendalikan, terutama di lingkungan yang telah menerapkan kawasan bebas rokok. Oleh karena itu, dibutuhkan sebuah sistem otomatis yang mampu mendeteksi aktivitas merokok secara real-time. Penelitian ini bertujuan untuk membangun sebuah sistem deteksi rokok berbasis model You Only Look Once version 8 (YOLOv8) yang diintegrasikan dengan aplikasi web menggunakan Streamlit. Dataset yang digunakan diperoleh dari platform Roboflow dan dilatih menggunakan beberapa parameter, termasuk optimizer yang divariasikan untuk mengetahui pengaruhnya terhadap performa model. Model dilatih dengan menggunakan tiga jenis optimizer, yaitu SGD, Adam, dan auto. Hasil evaluasi menunjukkan bahwa auto optimizer, yang secara otomatis memilih algoritma AdamW, memberikan performa terbaik dengan nilai precision sebesar 0.878, recall sebesar 0.795, dan mAP50 sebesar 0.863. Selain itu, sistem diuji menggunakan tiga jenis sumber input, yaitu webcam, IP camera, dan file upload. Hasil pengujian menunjukkan bahwa sistem mampu mendeteksi objek rokok secara akurat dan menampilkannya melalui antarmuka pengguna dengan bounding box dan perhitungan jumlah objek terdeteksi. Dari hasil penelitian ini, dapat disimpulkan bahwa sistem deteksi rokok yang dibangun mampu bekerja secara efektif dalam berbagai kondisi input dan dapat digunakan sebagai alat bantu pengawasan untuk mendeteksi aktivitas merokok secara otomatis di area terlarang.
IMPLEMENTATION OF INDOBERT IN AN EXTRACTIVE QUESTION ANSWERING CHATBOT FOR INFORMATION SERVICES AT LAZIS SULTAN AGUNG Ella Heriyawati; Sam Farisa Chaerul Haviana
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 2 (2026): April
Publisher : Yayasan Nuraini Ibrahim Mandiri

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

Abstract

Advances in AI and Natural Language Processing (NLP) technology have facilitated the use of chatbots as a means of providing automated information in various sectors, including religious and social organizations. LAZIS Sultan Agung still operates its information services manually via WhatsApp and in-person interactions, which limits responsiveness due to time and staff availability. This research aims to create an Extractive Question Answering (EQA)-based information chatbot utilizing the IndoBERT model to automatically assist users in obtaining information about services, programs, zakat, and donations at LAZIS Sultan Agung. The approach used in this research involves TF-IDF for the context retrieval process and IndoBERT for the answer extraction step. The dataset was obtained from official documents and the LAZIS Sultan Agung knowledge base, which contains service information and frequently asked questions. This web-based system uses Flask and MySQL for data storage. The evaluation results show that the system achieved an Exact Match (EM) value of 0.5294, Cosine Similarity of 0.7875, Precision of 0.8059, Recall of 0.8244, and F1-Score of 0.8052. Furthermore, black box testing showed that the chatbot was able to provide appropriate answers to user questions and could reject questions outside the scope of the system. Thus, the developed chatbot can accelerate, automate, and improve the efficiency of the information receiving process of LAZIS Sultan Agung. Keyword : Chatbot, IndoBERT, Extractive Question Answering, TF-IDF, NLP.
CHATBOT AKADEMIK BERBASIS RAG UNTUK INFORMASI AKADEMIK MAHASISWA Ikharista Ayu Nusrotun Afifah; Sam Farisa Chaerul Haviana
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 2 (2026): April
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i2.3636

Abstract

This study aims to develop a Retrieval-Augmented Generation (RAG)-based academic chatbot to provide accurate, relevant, and official document-based academic information for students of the Informatics Engineering Study Program, FTI UNISSULA. The methods used include collecting and pre-processing academic documents, chunking processes, forming vector representations using the Sentence-BERT model, and storing them in the FAISS database to support semantic search. The RAG system integrates document retrieval results with the capabilities of the Large Language Model (LLM) in generating contextual responses. System evaluation was carried out using the ROUGE-1 and BLEU-4 metrics on 50 questions consisting of FAQ and non-FAQ categories. The test results showed that the system was able to respond to all questions given, with high performance in the FAQ category (ROUGE-1 of 0.957 and BLEU-4 of 0.877), and lower performance in the non-FAQ category due to paraphrasing variations in academic documents. These results indicate that the RAG approach is effective in improving the accuracy and relevance of academic chatbot answers, and is able to reduce the risk of misinformation compared to a purely generative approach.
Co-Authors Ella Heriyawati Ikharista Ayu Nusrotun Afifah Muhammad Azmi Abdillah Sulaeman