Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JOISIE (Journal Of Information Systems And Informatics Engineering) Jurnal Minfo Polgan (JMP)
Fergie Joanda Kaunang
Universitas Bunda Mulia
Computer Science & IT Library & Information Science Mathematics Social Sciences

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

Found 2 Documents
Search

 1 
KLASIFIKASI ENGINE FAILURE BERDASARKAN BUNYI MOBIL MENGGUNAKAN MFCC DAN STFT DENGAN MACHINE LEARNING ; Bhustomy Hakim; Fergie Joanda Kaunang; Angelina Pramana Thenata; Ranny Ranny
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 9 No. 1 (2025)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v9i1.4936

Abstract

Deteksi kerusakan mobil sangat penting untuk meningkatkan keselamatan berkendara dan mengurangi biaya perbaikan. Salah satu metode yang umum digunakan oleh mekanik adalah mendiagnosis kerusakan melalui suara yang dihasilkan oleh komponen kendaraan. Namun, proses ini masih bergantung pada keahlian manual dan dapat menyebabkan kesalahan atau keterlambatan diagnosa. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan model klasifikasi kerusakan mobil berbasis suara menggunakan teknik data science, terutama machine learning. Data suara dikumpulkan dari berbagai sumber dari kerjasama bengkel-bengkel di Indonesia berupa file suara mesin dengan format wav dengan label berbeda, kemudian diolah menggunakan metode Mel Frequency Cepstral Coefficients (MFCC) dan Short-Time Fourier Transformation (STFT) untuk mengekstrak fitur penting dari sinyal suara. Selanjutnya, dengan algoritma Multilayer Perceptron diimplementasikan untuk membangun model prediksi kerusakan. Penelitian ini mengevaluasi model berdasarkan nilai akurasi dari confusion matrix untuk menemukan model terbaik dalam mendeteksi jenis kerusakan berdasarkan suara. Model dengan MFCC sebagai metode ekstraksi fitur terbukti menghasilkan akurasi tertinggi sebesar 83,35% ketimbang STFT yang hanya memiliki akurasi sebesar 78,82% dengan konfigurasi fungsi aktivasi ReLU dan layer dengan 512 neuron.
Indonesian Hate Speech Detection Across Diverse Domains Using Parameter-Efficient Fine-Tuning with IndoBERT and LoRA Fergie Joanda Kaunang; Bhustomy Hakim; Angelina Pramana Thenata
Jurnal Minfo Polgan Vol. 15 No. 2 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i2.16581

Abstract

The rapid proliferation of digital connectivity in Indonesia has catalyzed an unprecedented surge in harmful online content, necessitating robust automated systems for hate speech detection that can generalize across diverse digital platforms. Traditional models often struggle with domain shift and the linguistic complexities of Indonesian social media discourse, including informal slang and code-mixing. This research proposes a multi-domain detection framework leveraging the IndoBERT-base-p1 architecture integrated with Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning (PEFT) strategy. The study utilizes a multi-source corpus from Instagram, Twitter, and news portals, employing back-translation to augment scarce Instagram data and stratified downsampling to ensure domain equilibrium. By training only 1–2% of the total 110 million parameters, specifically targeting the query and value attention modules, the model achieves significant computational savings with a training loss of 0.345. Experimental results demonstrate high robustness, with the framework attaining F1-scores of 0.83 for both Instagram and Twitter, and 0.81 for news portals, while maintaining accuracies between 0.81 and 0.85. Qualitative validation through word cloud analysis further confirms the model's ability to distinguish between aggressive sociopolitical triggers and neutral functional discourse. This study contributes a scalable and resource-efficient solution for real-time content moderation, proving effective across both formal journalistic Indonesian and informal digital dialects. The findings indicate that IndoBERT+LoRA provides a promising and resource-efficient approach for multi-domain Indonesian hate and abusive speech classification, while stricter leave-one-domain-out evaluation remains an important direction for future work.
Co-Authors Bhustomy Hakim Ranny Ranny Thenata, Angelina P.