Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Journal Of Chemical Process Engineering
Ramadhani, Tarisa
Unknown Affiliation
Aerospace Engineering Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Energy Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Innovation of Traditional Salt Pond by Enhancing Evaporation Rate using Coconut Coir Waste Yani, Setyawati; Yani, Syamsuddin; Artiningsih, Andi; Adawiah, Rifani Rabiatul; Ramadhani, Tarisa
Journal of Chemical Process Engineering Vol. 9 No. 2 (2024): Journal of Chemical Process Engineering
Publisher : Fakultas Teknologi Industri - Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/jcpe.v9i2.967

Abstract

National salt production capacity is dominated by smallholder salt production through the crystallization process in traditional salt ponds. One of the salt producing areas in South Sulawesi Province is located in Jeneponto Regency. Salt farmers in Jeneponto Regency produce salt through traditional salt ponds. Jeneponto Regency is also one of the main coconut producing areas. Coconut coir from the people's plantation industry is currently only used as fuel in small and medium home industries or is simply thrown away as waste. Coconut coir has the ability to absorb water. The aim of this research is to innovate the use of coconut coir waste to increase the surface area for water evaporation in traditional laboratory-scale salt ponds. This research was also carried out by conducting analysis on traditional ponds to study the factors that influence the salting process. Next, the salting process was carried out on a laboratory scale by making a replica of the traditional pond salting process which was equipped with the addition of coconut coir to increase the evaporation surface area. The results of the research show that the salting process in traditional salt ponds is greatly influenced by the season. The sun plays a very important role in the evaporation process in traditional salt ponds until salt crystals form in the ponds. Laboratory scale salt pond equipment shows that the use of coconut coir plays a very important role in speeding up the evaporation process and has the potential to increase salt production in traditional salt ponds.
Penerapan Metode Retrieval-Augmented Generation (RAG) Pada Chatbot E-Commerce Berbasis Gemini Ai Ramadhani, Tarisa; Nada, Noora Qotrun; S, Nugroho Dwi
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 8, No 2 (2025): Juli
Publisher : Akademi Ilmu Komputer Ternate

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v8i2.384

Abstract

Abstrack: Perkembangan e-commerce yang pesat telah meningkatkan harapan untuk sistem layanan pelanggan yang cerdas dan sadar konteks. Chatbot berbasis aturan tradisional terbukti tidak memadai dalam memenuhi permintaan yang semakin meningkat untuk respons yang akurat, cepat, dan relevan secara kontekstual. Penelitian ini mengusulkan pengembangan sistem chatbot berbasis Gemini AI yang terintegrasi dengan pendekatan Retrieval-Augmented Generation (RAG). Sistem ini mengambil dokumen-dokumen relevan dari basis data internal (katalog produk, kebijakan, riwayat pelanggan) dan menggunakan model LLaMA sebagai generator untuk menghasilkan jawaban yang faktual dan sejalan secara semantis. Dataset yang digunakan mencakup 214 pasangan percakapan yang telah dibersihkan yang bersumber dari Kaggle, diproses menggunakan Sentence-BERT untuk embedding kalimat. Sistem chatbot dievaluasi melalui metrik pengambilan dan generatif. Hasil menunjukkan kinerja tinggi dengan Mean Reciprocal Rank (MRR) sebesar 0,83, Exact Match (EM) sebesar 100%, F1 Score sebesar 82,05%, dan Similarity Semantis sebesar 97,45%, Tingkat kesetiaan 91,67% dan relevansi jawaban 94,21%. Temuan ini menunjukkan bahwa integrasi Gemini AI dengan RAG dapat secara signifikan meningkatkan akurasi, fakta, dan relevansi konteks dari respons chatbot di domain dinamis yang didorong oleh data seperti e-commerce.Kata kunci: chatbot, e-commerce, Gemini AI, Retrieval-Augmented Generation, kesamaan semanticAbstract: The rapid growth of e-commerce has raised expectations for intelligent and context-aware customer service systems. Traditional rule-based chatbots have proven inadequate in meeting the growing demand for accurate, fast, and contextually relevant responses. This research proposes the development of a Gemini AI-based chatbot system integrated with a Retrieval-Augmented Generation (RAG) approach. The system retrieves relevant documents from internal databases (product catalogues, policies, customer histories) and uses the LLaMA model as a generator to produce factual and semantically aligned answers. The dataset used includes 214 cleaned conversation pairs sourced from Kaggle, processed using Sentence-BERT for sentence embedding. The chatbot system is evaluated through retrieval and generative metrics. The results show high performance with a Mean Reciprocal Rank (MRR) of 0.83, an Exact Match (EM) of 100%, an F1 Score of 82.05%, a Semantic Similarity of 97.45%, a Fidelity Rate of 91.67%, and an answer relevance of 94.21%. These findings indicate that the integration of Gemini AI with RAG can significantly improve the accuracy, factuality, and contextual relevance of chatbot responses in dynamic, data-driven domains such as e-commerce.Keywords: chatbots, e-commerce, Gemini AI, Retrieval-Augmented Generation, semantic similarity.
Co-Authors Adawiah, Rifani Rabiatul Andi Artiningsih Noora Qotrun Nada, Noora Qotrun S, Nugroho Dwi Yani, Setyawati Yani, Syamsuddin