Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Bulletin of Electrical Engineering and Informatics Jurnal Informatika Journal of Data Science and Software Engineering Journal of Computing Theories and Applications
Andi Farmadi
Lambung Mangkurat University
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Implementasi Metode Haralick dengan Random Forest Classifier untuk identifikasi Penyakit Kentang Pada Citra Daun Muhammad Syahriani Noor Basya Basya; Andi Farmadi; Dwi Kartini; Radityo Adi Nugroho; Rudy Herteno
Journal of Data Science and Software Engineering Vol 3 No 03 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

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

Abstract

Potato plants are one of the most widely grown food crops in the highlands of Indonesia. Besides being used as food, potatoes are now known to be used to fight free radicals, control blood sugar, and nourish the digestive system. Therefore, potatoes have good prospects for development. In connection with efforts to develop potatoes in Indonesia, there are obstacles, namely the attack of potato plants by disease. As for the disease in potato plants, one of the characteristics of knowing it is on the leaves. To identify the leaf image, the texture feature is an important feature to recognize the leaf from an image. This is because there are differences in texture between normal and diseased leaves. To perform image processing through texture features, one method that can be used is haralick. In this study, a system was created to identify the types of diseases present in potato leaves using the Haralick method with the Random Forest Classifier. The image used is 300 data consisting of 3 classes, namely Late Blight, Early Blight, and Health. In this study, the testing was carried out by dividing the training and testing data with a percentage of 70:30, 80:20, and 90:10. The highest accuracy value in this study was obtained by using a combination of 80:20 split data, which was 0.88. The 70:30 data split gets an accuracy of 0.85 and the 90:10 data split gets an accuracy of 0.87.
Random Forest Dengan Random Search Terhadap Ketidakseimbangan Kelas Pada Prediksi Gagal Jantung Muhammad Ali Abubakar; Muliadi Muliadi; Andi Farmadi; Rudy Herteno; Rahmat Ramadhani
Jurnal Informatika Vol 10, No 1 (2023): April 2023
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/inf.v10i1.14531

Abstract

Prediksi keberlangsungan hidup pasien gagal jantung telah dilakukan pada penelitian untuk mencari tahu tentang kinerja, akurasi, presisi dan performa dari model prediksi ataupun metode yang digunakan dalam penelitian, dengan menggunakan dataset heart failure clinical records. Namun dataset ini memiliki permasalahan yaitu bersifat tidak seimbang yang dapat menurunkan kinerja model prediksi karena cenderung menghasilkan prediksi kelas mayoritas. Pada penelitian ini menggunakan pendekatan level algoritma untuk mengatasi ketidakseimbangan kelas yaitu teknik bagging dengan metode Random Forest lalu digabungkan dengan metode Hyper-Parameter Tuning agar kinerja yang dihasilkan menjadi lebih baik. Selanjutnya model dilatih dengan dataset dan dibandingkan dengan metode lain, hasilnya menunjukkan bahwa Random Forest dengan Random Search Hyper Parameter-Tuning mencapai nilai AUC sebesar 0,906 dan untuk model Random Forest tanpa Random Search memperoleh nilai AUC sebesar 0,866. Prediction of the survival of heart failure patients has been carried out in research to find out about the performance, accuracy, precision and performance of the prediction model or method used in the study, using the heart failure clinical records dataset. However, this dataset has a problem, namely being unbalanced which can reduce the performance of the prediction model because it tends to produce predictions for the majority class. This study uses an algorithm level approach to overcome class imbalance, namely the bagging technique with the Random Forest method and then combined with the Hyper-Parameter Tuning method so that the resulting performance is better. Then the model was trained with the dataset and compared with other methods, the results showed that the Random Forest with Random Search Hyper Parameter-Tuning achieved an AUC value of 0,906 and for the Random Forest model without Random Search the AUC value of 0,866 was obtained. 
Quantifying the Impact of Text Preprocessing on IndoBERT Fine-Tuning for Indonesian Informal Culinary Sentiment Analysis Rahmat Budianoor; Setyo Wahyu Saputro; Friska Abadi; Radityo Adi Nugroho; Andi Farmadi
Journal of Computing Theories and Applications Vol. 3 No. 4 (2026): JCTA 3(4) 2026
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.15980

Abstract

Indonesian culinary comments on social media platforms such as Instagram are characterized by informal spelling, regional language mixing, slang expressions, and emojis, posing substantial challenges for automated sentiment classification. While IndoBERT has demonstrated strong performance across Indonesian natural language processing tasks, the contribution of individual preprocessing components to fine-tuning performance on informal text remains underexplored, particularly in the culinary domain. This study addresses this gap by conducting a systematic preprocessing ablation study on IndoBERT-Base fine-tuning for Indonesian culinary sentiment classification, accompanied by a comparative evaluation against Naive Bayes with TF-IDF, SVM with TF-IDF, and BiLSTM as representative baselines. A dataset of 3,500 manually labeled Instagram culinary comments across three sentiment classes was used, with a stratified 80/10/10 split. Six preprocessing variants were evaluated under identical experimental conditions to isolate the contribution of each component. The results show that slang normalization is the most impactful single preprocessing step, yielding a macro F1-score gain of +0.0609 over the no-preprocessing baseline, while the full pipeline achieves an accuracy of 0.8800 and a macro F1-score of 0.8465. IndoBERT-Base with the full pipeline outperforms all baselines across all evaluation metrics. Per-class analysis reveals that the negative class achieves the lowest F1-score of 0.7600, with sarcastic expressions and Banjar regional vocabulary identified as primary sources of misclassification. These findings indicate that preprocessing decisions have a measurable and non-uniform effect on IndoBERT fine-tuning performance. In this study, slang normalization provides the most substantial individual contribution in bridging the vocabulary gap between informal user-generated text and the model’s pre-training distribution.
Feature extraction and machine learning methods for biometric recognition based on fusion of ECG and fingerprint Hafiz Ilhami; Dodon Turianto Nugrahadi; Mohammad Reza Faisal; Irwan Budiman; Andi Farmadi; Dwi Kartini; Puput Dani Prasetyo Adi; Jumadi Mabe Parenreng
Bulletin of Electrical Engineering and Informatics Vol 15, No 3: June 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i3.10541

Abstract

This research introduces a multimodal biometric authentication framework by amalgamating electrocardiogram (ECG) and fingerprint modalities through the utilization of diverse feature extraction methodologies and machine learning classifiers. The proposed methodology aspires to augment precision and mitigate spoofing vulnerabilities in contrast to traditional single-modality systems. Among the feature extraction techniques assessed—grayscale, binary, Sobel edge detection, and minutiae—Naïve Bayes (NB) in conjunction with minutiae features exhibited superior performance, attaining an accuracy rate of 96.25%. Supplementary experiments employing random forest (RF) and support vector machine (SVM) also revealed commendable classification efficacy, underscoring the robustness of the fusion methodology. This investigation provides a pragmatic and secure biometric framework by harnessing complementary biometric characteristics to enhance authentication dependability. The proposed system presents promising applications in real-world contexts, particularly concerning mobile security and healthcare access control. Future research endeavors will tackle challenges associated with ECG signal variability, computational efficiency, and extensive deployment.
Co-Authors Dodon Turianto Nugrahadi Dwi Kartini, Dwi Friska Abadi Hafiz Ilhami Irwan Budiman Jumadi Mabe Parenreng Muhammad Ali Abubakar Muhammad Reza Faisal, Muhammad Reza Muhammad Syahriani Noor Basya Basya Muliadi Muliadi Puput Dani Prasetyo Adi Radityo Adi Nugroho Rahmat Budianoor Rahmat Ramadhani Rudy Herteno Rudy Herteno Setyo Wahyu Saputro