Claim Missing Document
Check
Articles

Found 2 Documents
Search

A Web-Based Forward-Chaining Expert System for Smartphone Selection A Decision Support Tool for Novice Daffa Ihsan Al Hakim; Lucky Edward; Muhammad Fitrizhika; Deosa Putra Caniago
Journal on Informatics Visualization and Social Computing Vol. 2 No. 1 (2026): Journal on Informatics Visualization and Social Computing (JIVSC)
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/jivsc.v2i1.125

Abstract

Background: The ratio of ophthalmologists to the population in Indonesia is extremely low, leading to unequal access to eye care and making it difficult for the public to obtain early information regarding eye symptoms.Aims: This study aims to develop and validate an efficient, domain-specific eye care chatbot using the Llama 3.2 1B Instruct model, focusing on an optimal fine-tuning pipeline for limited hardware constraints.Methods: Utilizing an Experimental Research (Model Development) design, a QLoRA 4-bit quantization technique was applied on a Google Colab T4 GPU (15.64GB VRAM). The training dataset comprised 16,742 samples from Kaggle Eye Care and MedQuad Indonesian Translation, with a subset of 5,000 samples used for experiments.Result: After training for 3 epochs (750 steps), the Training Loss decreased from 1.3394 to 0.7188 (46.3% improvement), while Perplexity reached 2.3620, categorized as excellent. The model maintained stability with a final gap of 0.1407 between training and validation loss.Conclusion: The Meta-Llama 3.2 1B Instruct model, fine-tuned with 4-bit QLoRA, is highly effective for building a domain-specific healthcare chatbot, successfully operating within an 8GB VRAM limit while maintaining high generalization capabilities.
PREDIKSI OPINI AUDIT MENGGUNAKAN FORWARD CHAINING DAN CERTAINTY FACTOR Yogi Ginanjar; Deosa Putra Caniago; Rahmat Ridho Putra; Egies Risalatul Falah
JURNAL AKUNTANSI DAN SISTEM INFORMASI Vol 7 No 3 (2026): Edisi Oktober 2026
Publisher : Program Studi Akuntansi Fakultas Ekonomika dan Bisnis Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/k7av4n73

Abstract

Laporan keuangan merupakan fondasi utama akuntabilitas dan pengambilan keputusan bisnis, namun kompleksitas standar akuntansi, estimasi, dan pertimbangan profesional sering mempersulit penentuan opini audit yang objektif dan konsisten. Penelitian ini bertujuan membangun model prediksi opini audit laporan keuangan menggunakan pendekatan sistem pakar dengan metode Forward Chaining dan Certainty Factor. Forward Chaining digunakan untuk menelusuri inferensi berbasis aturan dari indikator audit, sedangkan Certainty Factor digunakan untuk mengelola ketidakpastian informasi dan tingkat keyakinan terhadap kesimpulan. Penelitian dilakukan melalui studi literatur, akuisisi pengetahuan auditor, pembentukan basis aturan, perancangan sistem, implementasi prototipe berbasis web, serta pengujian dan validasi prediksi. Hasil pengujian terhadap 100 laporan keuangan perusahaan yang telah diaudit menunjukkan tingkat keberhasilan rata-rata sebesar 92% dalam memprediksi opini audit sesuai dengan opini aktual. Temuan ini menunjukkan bahwa model sistem pakar yang dikembangkan mampu memberikan prediksi awal opini audit secara transparan, terstruktur, dan dapat ditelusuri. Model ini berpotensi menjadi alat bantu pengambilan keputusan bagi auditor maupun manajemen dalam mengidentifikasi risiko opini audit secara lebih dini.