Garuda - Garba Rujukan Digital

Studi Deskriptif Mengenai Kepatuhan Mahasiswa Universitas Negeri Padang yang Berdomisili di Kota Padang terhadap Protokol Kesehatan di Situasi Pandemi COVID-19 Fadhilah, Husni; Dirga Dwatra, Free
Jurnal Pendidikan Tambusai Vol. 5 No. 2 (2021): 2021
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Di situasi pandemi seperti saat ini, setiap individu dituntut untuk mematuhi protokol kesehatan guna melindungi diri dari infeksi COVID-19. Setiap individu memiliki kecenderungan untuk mengikuti maupun tidak mengikuti protokol kesehatan. Penelitian ini bertujuan untuk menggambarkan kepatuhan mengikuti protokol kesehatan mahasiswa Universitas Negeri Padang yang berdomisili di kota Padang di situasi pandemi COVID-19. Studi dilakukan dalam bentuk penelitian deskriptif dengan pendekatan kualitatif. Instrumen yang digunakan dalam penelitian yaitu kuisioner terbuka serta teknik analisis data menggunakan koding. Populasi pada penelitian ini yaitu mahasiswa Universitas Negeri Padang yang berdomisili di Kota Padang. Sampel penelitian yang diambil adalah mahasiswa semester 7 sebanyak 85 partisipan dengan menggunakan teknik sampling acak. Hasil pada penelitian ini menemukan bahwa mayoritas mahasiswa semester 7 UNP yang berdomisili di kota Padang mematuhi protokol kesehatan. Namun, masih terdapat mahasiswa yang tidak mematuhi protokol kesehatan yang disebabkan oleh adanya kepercayaan pada teori konspirasi dan kurangnya pengetahuan mengenai COVID-19.

Studi Deskriptif Mengenai Kepatuhan Mahasiswa Universitas Negeri Padang yang Berdomisili di Kota Padang terhadap Protokol Kesehatan di Situasi Pandemi COVID-19 Fadhilah, Husni; Dirga Dwatra, Free
Jurnal Pendidikan Tambusai Vol. 5 No. 2 (2021): 2021
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jptam.v5i2.1371

Di situasi pandemi seperti saat ini, setiap individu dituntut untuk mematuhi protokol kesehatan guna melindungi diri dari infeksi COVID-19. Setiap individu memiliki kecenderungan untuk mengikuti maupun tidak mengikuti protokol kesehatan. Penelitian ini bertujuan untuk menggambarkan kepatuhan mengikuti protokol kesehatan mahasiswa Universitas Negeri Padang yang berdomisili di kota Padang di situasi pandemi COVID-19. Studi dilakukan dalam bentuk penelitian deskriptif dengan pendekatan kualitatif. Instrumen yang digunakan dalam penelitian yaitu kuisioner terbuka serta teknik analisis data menggunakan koding. Populasi pada penelitian ini yaitu mahasiswa Universitas Negeri Padang yang berdomisili di Kota Padang. Sampel penelitian yang diambil adalah mahasiswa semester 7 sebanyak 85 partisipan dengan menggunakan teknik sampling acak. Hasil pada penelitian ini menemukan bahwa mayoritas mahasiswa semester 7 UNP yang berdomisili di kota Padang mematuhi protokol kesehatan. Namun, masih terdapat mahasiswa yang tidak mematuhi protokol kesehatan yang disebabkan oleh adanya kepercayaan pada teori konspirasi dan kurangnya pengetahuan mengenai COVID-19.

Tree-based Ensemble Machine Learning for Phishing Website Detection Fadhilah, Husni; Maulana, Diky Restu; Utari, Rahayu
Komputika : Jurnal Sistem Komputer Vol. 13 No. 2 (2024): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v13i2.12495

Phishing remains a prevalent and perilous cyber threat in the digital age, exploiting human vulnerabilities to deceive individuals into disclosing sensitive information. This paper presents a method to achieve high accuracy in phishing website detection using Tree-based Ensemble Machine Learning techniques. Through rigorous experimentation and evaluation, we identified RandomForest and ExtraTrees as the top-performing models, achieving accuracy, precision, recall, and F1 scores all exceeding 98%. Additionally, our study highlights the significance of feature selection techniques in enhancing model performance, with thresholding methods proving effective in retaining relevant features for classification. By addressing imbalanced datasets and optimizing hyperparameters, our models demonstrate robust detection capabilities against phishing attacks. These findings contribute to the advancement of cybersecurity measures and underscore the potential of ensemble machine learning in combatting online threats, ultimately enhancing internet user security.

Analisis Fraud Hexagon dalam Kasus Korupsi di PT Pertamina Patra Niaga Fitriani, Qonita; Sugiarti, Erika; Fadhilah, Husni; Munyani Putri, Fiqi; Novaria Misidawati, Dwi
Ekonosfera: Jurnal Ekonomi, Akuntansi, Manajemen, Bisnis dan Teknik Global Vol. 1 No. 2 (2025): April
Publisher : Yayasan Cendekia Gagayunan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63142/ekonosfera.v1i2.176

This research is motivated by the rampant corruption cases in the State-Owned Enterprises (BUMN) environment, especially at PT Pertamina Patra Niaga. The main objective of this research is to identify and analyze the factors that cause corruption using the Fraud Hexagon analysis framework. The research method used is a descriptive qualitative approach, with data collection techniques through literature studies from various scientific literature, journals, mass media coverage, and relevant official documents. The results showed that corrupt practices at PT Pertamina Patra Niaga were influenced by six main elements in the Fraud Hexagon model, namely pressure, opportunity, rationalization, capability, arrogance, and collusion. Pressure comes from the lifestyle and job demands of the perpetrator; opportunities arise due to a weak supervisory system and imperfections in the procurement process; rationalization occurs through moral justification for acts of corruption. The capability of perpetrators who occupy strategic positions allows collusion with internal and external parties, which is exacerbated by arrogance. These six elements are interrelated and form a systemic pattern that supports corruption. This research confirms the importance of strengthening the internal control system, instilling an integrity-based organizational culture, and implementing a transparent and reliable reporting system to prevent corrupt practices within SOEs.

Lightweight Brain Tumor Classification with Histogram Oriented Gradients (HOG) Features and Class-Weighted Support Vector Machine (SVM) Warsito, Budi; Fadhilah, Husni; Kartikasari, Puspita; Hakim, Arief Rachman
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1018

Early detection of brain tumors via MRI is crucial for improving patient outcomes. This study investigates a lightweight machine learning approach for multiclass brain tumor classification (glioma, meningioma, pituitary tumor, or no tumor) using Histogram of Oriented Gradients (HOG) for feature extraction and a Support Vector Machine (SVM) classifier. This study utilizes the public Brain Tumor Classification MRI Kaggle dataset, consisting of 2870 training and 394 testing MRI images across four classes. After converting the MRIs to grayscale and resizing them to 16×16 pixels, this study extracts HOG features and applies Principal Component Analysis (PCA) to retain 98% of the variance. An SVM is then trained with a GridSearchCV-optimized kernel and hyperparameters, and a custom class-weighted variant is compared. The best model, a polynomial-kernel SVM with custom class weights, achieved 91.8% test accuracy (95% CI (confidence interval): 90.9-92.7) with an F1-score of 0.919 ± 0.01, outperforming the best unweighted SVM (accuracy 86.0% ± 0.02, F1≈0.847). These results demonstrate that HOG+SVM, with proper weighting for class imbalance, can effectively classify brain tumors on small datasets at low computational cost. The novelty of this work lies in demonstrating that an optimized, class-weighted SVM leveraging compact HOG-PCA features can deliver over 91.8% accuracy with strong generalization on small-scale MRI data, providing a viable and interpretable alternative to complex Convolutional Neural Network (CNN) models. Future work can explore CNN and hybrid feature fusion to improve accuracy and generalization further.

Enhanced Robustness in Image Classification through DistortionMix: A Hybrid Distortion-Based Augmentation Technique Fadhilah, Husni; Warsito, Budi; Faridah, Hasna
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 1 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i1.1558

Deep neural networks perform well on clean image classification tasks but often fail under common corruptions and distribution shifts. This paper introduces DistortionMix, a lightweight hybrid distortion-based augmentation technique designed to improve model robustness. It randomly applies contrast variation, Gaussian noise, or impulse noise to training images, enhancing data diversity and encouraging resilient feature learning. We evaluate DistortionMix on CIFAR-10 (clean) and CIFAR-10-C (corrupted), which includes 19 corruption types at five severity levels. A variety of architectures e.g ResNet, DenseNet, EfficientNet, MobileNet, VGG, AlexNet, GoogleNet, and ViT are fine-tuned with and without DistortionMix. Experimental results show that DistortionMix improves corrupted accuracy by up to 13.8%, while maintaining or slightly improving clean accuracy. Among all models, ViT-Base (timm) achieves the highest robustness, reaching 89.4% on severe corruptions and 97.43% on clean data. These findings highlight DistortionMix as a simple yet effective strategy for enhancing out-of-distribution generalization. Future work includes extending distortion types, developing adaptive augmentation policies, and evaluating performance on real-world corrupted datasets. Source code: github.com/HusniFadhilah/DistortionMix.

Transformer-Based Encoder-Decoder Model for Medical Image Captioning with Concept Embedding Fadhilah, Husni; Utama, Nugraha Priya
Jurnal Masyarakat Informatika Vol 17, No 1 (2026): May 2026 (Ongoing)
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.17.1.75082

This research presents a Transformer-based encoder-decoder model for medical image captioning that incorporates semantic medical knowledge through Concept Unique Identifiers (CUIs) from the Unified Medical Language System (UMLS). The proposed architecture employs a Swin Transformer as the visual encoder and GPT-2 as the language decoder, with CUI integration applied during both caption preprocessing and decoding. Experiments were conducted on the ROCOv2 dataset under two scenarios: baseline (raw captions) and enhanced (CUI-enriched captions). Quantitative evaluation using BLEU, ROUGE, CIDEr, and BERT-based metrics demonstrates that the CUI-integrated model outperforms several baselines, including CNN-LSTM, ViT-BioMedLM, and DeepSeek-VL, achieving a BLEU-1 score of 0.371, ROUGE-L of 0.305, CIDEr of 0.275, and PubMedBERTScore-F1 of 0.893. These results represent a 20.1% improvement in BLEU-1 and a 39.9% increase in ROUGE-L compared to the best-performing model before caption preprocessing (ViT-GPT2 with BLEU-1 = 0.309, ROUGE-L = 0.218). Qualitative assessment by expert radiologists further confirms enhanced diagnostic accuracy, descriptive completeness, and clinical relevance. This study introduces a novel integration of medical semantic knowledge into captioning models, offering a scalable solution for clinical decision support in resource-limited settings such as Indonesia.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search