Article Per Year (5 Year)
p-Index From 2021 - 2026
3.575
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Jurnal Gamma TELKOMNIKA (Telecommunication Computing Electronics and Control) JUTI: Jurnal Ilmiah Teknologi Informasi CommIT (Communication & Information Technology) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) International Journal of Artificial Intelligence Research IJCIT (Indonesian Journal on Computer and Information Technology) JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Indonesian Journal of Artificial Intelligence and Data Mining Jiko (Jurnal Informatika dan komputer) Technologia: Jurnal Ilmiah Jurnal Abdimas Madani dan Lestari (JAMALI) bit-Tech ILKOMNIKA: Journal of Computer Science and Applied Informatics Automata TIN: TERAPAN INFORMATIKA NUSANTARA JURNAL PENDIDIKAN, SAINS DAN TEKNOLOGI Jurnal Informatika: Jurnal Pengembangan IT
Arrie Kurniawardhani
Universitas Islam Indonesia
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Social Sciences Veterinary Other

Published : 35 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 35 Documents
Search

 1   2   3   4 
Automated Brain Tumor Classification and Segmentation Using Standard U-Net on Balanced Multi-Class MRI Dataset Aljunaid, Wajeehaldeen Ahmed Qasem; Kurniawardhani, Arrie
AUTOMATA Vol. 7 No. 1 (2026)
Publisher : AUTOMATA

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

Abstract

Brain tumor classification and segmentation are essential tasks for medical diagnosis and treatment planning. This study presents a comprehensive approach for simultaneous brain tumor classification and segmentation using a standard U-Net architecture applied to 2D brain MRI scans. The primary contribution of this work is the development of a novel balanced multi-class dataset comprising 6,380 MRI images created by merging and balancing two publicly available datasets, ensuring equal representation across four classes: no tumor, glioma, meningioma, and pituitary tumors (1,595 images per class). Our unified framework performs both pixel-level segmentation and image-level classification in a single forward pass, where classification is derived from segmentation outputs through spatial probability analysis. The standard U-Net model achieved robust performance with test accuracy of 99.62\%, Dice coefficient of 0.8423, and IoU of 0.9913. Image-level classification demonstrated precision and recall values ranging from 0.89 to 0.97 across all tumor classes. The perfectly balanced dataset eliminates class imbalance issues commonly encountered in medical imaging, enabling fair model evaluation and robust performance across all tumor types. This work provides a strong baseline for brain tumor analysis and demonstrates the effectiveness of proper dataset curation combined with classical deep learning architectures for medical image analysis applications.
KLASIFIKASI SERANGAN DISTRIBUTED DENIAL OF SERVICE MENGGUNAKAN ENSEMBLE STACKING Juan Parez Mangku Alamsyah; Fayruz Rahma; Arrie Kurniawardhani
PENDIDIKAN SAINS DAN TEKNOLOGI Vol 12 No 4 (2025)
Publisher : STKIP PGRI Situbondo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47668/edusaintek.v12i4.1930

Abstract

Serangan Distributed Denial of Service (DDoS) merupakan jenis serangan siber yang bertujuan untuk membuat layanan atau sumber daya jaringan tidak dapat diakses oleh pengguna yang sah dengan membanjiri lalu lintas jaringan secara masif. Pola serangan DDoS yang semakin kompleks dan bervariasi menuntut adanya sistem deteksi yang tidak hanya andal, tetapi juga adaptif terhadap berbagai jenis serangan. Sebagian besar penelitian sebelumnya masih terbatas pada klasifikasi biner sehingga kurang efektif dalam menghadapi tantangan klasifikasi serangan yang lebih beragam. Penelitian ini bertujuan untuk mengembangkan model Intrusion Detection System (IDS) berbasis machine learning dengan pendekatan ensemble learning untuk klasifikasi multiclass serangan DDoS. Model ini dibangun menggunakan pendekatan stacking, dengan K-Nearest Neighbors, Decision Tree, Naive Bayes, dan Support Vector Machine sebagai base learners, serta Logistic Regression sebagai meta learner. Dataset CIC-DDoS2019 digunakan sebagai sumber data untuk proses pelatihan dan pengujian model. Hasil evaluasi menunjukkan bahwa model ensemble stacking memberikan kinerja terbaik dengan accuracy sebesar 78,8%, F1-score sebesar 78,4%, dan nilai AUC tertinggi sebesar 0,982. Dengan demikian, pendekatan ensemble learning terbukti mampu meningkatkan kinerja dan keakuratan sistem deteksi serangan DDoS dalam skenario klasifikasi multiclass dibandingkan model individual.
Volcanic Object Identification in Volcano Images Using Deep Learning–Based Instance Segmentation Resa Zulfikar; Arrie Kurniawardhani
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 10 No. 1 (2026): Issues July 2026
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v10i1.16144

Abstract

Indonesia is home to over 120 active volcanoes, many of which pose significant risks to surrounding communities and global atmospheric conditions. The rapid and accurate identification of volcanic objects remains a challenging task for effective volcano monitoring and disaster mitigation. To enable rapid and accurate automatic identification of volcanic objects, this study leverages two Deep Learning models focused on instance segmentation. The two instance segmentation models, You Only Look Once version 7 (YOLOv7) and Mask Region-Based Convolutional Neural Network (Mask R-CNN), were evaluated for their effectiveness in segmenting volcanic objects, namely lava flows, volcanic ash, mountains, and vegetation, from volcanic imagery and videos. A dataset of 140 labeled volcanic images was used for training and validation, while video data were employed to assess model performance under real-time conditions. Both models were trained using transfer learning with pre-trained MS COCO weights and their performance was measured using mean Average Precision (mAP). The results indicate that YOLOv7 achieves higher accuracy (mAP50 = 0.872) along with faster training and inference times, while Mask R-CNN obtains lower accuracy (mAP50 = 0.535) but consistently produces higher confidence scores (>0.90). These findings suggest that YOLOv7 is more suitable for real-time volcano monitoring, while Mask R-CNN is preferable in applications where high detection confidence is prioritized. The results imply that deep learning–based instance segmentation can support automated volcano monitoring systems and enhance disaster mitigation efforts through rapid identification of critical volcanic features.
KOMPARASI ARSITEKTUR YOLOV8, YOLOV10, YOLO11, DAN YOLO26 UNTUK DETEKSI BAKTERI MYCOBACTERIUM TUBERCULOSIS PADA CITRA MIKROSKOPIS Raisha Alma Sahara; Arrie Kurniawardhani; Izzati Muhimmah
Technologia : Jurnal Ilmiah Vol 17 No 3 (2026): Technologia (Juli)
Publisher : Universitas Islam Kalimantan Muhammad Arsyad Al Banjari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/jit.v17i3.23393

Abstract

Tuberkulosis (TBC) masih menjadi ancaman kesehatan global yang serius, khususnya di negara berkembang seperti Indonesia yang menempati peringkat kedua dengan beban TBC tertinggi di dunia. Deteksi dini berbasis citra mikroskopis apusan sputum dengan pewarnaan Ziehl-Neelsen merupakan metode diagnosis yang umum digunakan, namun proses pembacaan slide secara manual memerlukan keahlian tinggi dan rentan terhadap human error. Penelitian ini membandingkan performa delapan varian model dari empat generasi arsitektur You Only Look Once (YOLO), yaitu YOLOv8 (Nano, Small, Medium), YOLOv10 (Medium), YOLO11 (Nano dan Small), dan YOLO26 (Nano dan Small), untuk mendeteksi bakteri Mycobacterium tuberculosis secara otomatis pada citra mikroskopis pewarnaan Ziehl-Neelsen. Dataset yang digunakan terdiri dari 1.265 citra (7.027 anotasi bounding box) yang bersumber dari Kaggle, dibagi dengan rasio 70:20:10 untuk pelatihan, validasi, dan pengujian. Seluruh model dilatih dengan konfigurasi identik menggunakan optimizer SGD dengan learning rate 0,01 selama 100 epoch pada resolusi input 640×640 piksel, dengan pretrained weights dari dataset COCO. Evaluasi dilakukan berdasarkan metrik mAP@50, mAP@50-95, Precision, Recall, F1-Score, inference time, dan ukuran model TFLite sebagai indikator kelayakan edge deployment. Hasil eksperimen menunjukkan bahwa YOLO11n meraih performa terbaik secara keseluruhan dengan mAP@50 sebesar 0,850, F1-Score 0,782, inference time 10,56 ms, serta ukuran TFLite 2,85 MB hanya dengan 2,5 juta parameter, menjadikannya kandidat terkuat untuk implementasi pada perangkat edge computing seperti Raspberry Pi. Sementara itu, YOLO11s menawarkan recall tertinggi sebesar 79,2% yang lebih sesuai untuk skenario skrining awal, dan YOLOv8n menjadi alternatif terbaik ketika kecepatan inferensi menjadi prioritas utama. YOLOv10m ditemukan tidak kompatibel dengan format TFLite akibat inkompatibilitas struktural pada lapisan head-nya. Temuan ini mengkonfirmasi bahwa efisiensi desain arsitektur memiliki peran yang lebih signifikan terhadap performa dibandingkan penambahan kapasitas parameter semata, dan bahwa pemilihan model harus disesuaikan dengan prioritas klinis serta keterbatasan perangkat target.
Augmented Reality in Secondary Science: Implementation, Evaluation, and Cognitive Learning Outcomes Anggito Sulistyo Adi; Arrie Kurniawardhani
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3730

Abstract

Science learning at the secondary school level remains challenging due to the abstract and complex nature of subjects such as physics, chemistry, and biology, which require advanced spatial and conceptual reasoning. Although Augmented Reality (AR) has increasingly been introduced to enhance visualization and interactivity in science classrooms, empirical evidence remains fragmented across implementation types, evaluation designs, and reported learning outcomes. Prior educational technology reviews rarely provide a focused synthesis explaining how specific AR implementation features relate to cognitive learning outcomes in secondary science education, leaving an important gap in understanding the pedagogical conditions under which AR becomes instructionally effective. This study systematically reviews recent empirical research on AR in secondary science education to identify dominant implementation patterns, examine evaluation approaches, and synthesize reported cognitive learning outcomes. A Systematic Literature Review (SLR) was conducted following Kitchenham’s guidelines and the PRISMA 2020 framework. Searches in ScienceDirect and Taylor & Francis Online identified 15 peer-reviewed studies published between 2020 and 2025 that met the inclusion criteria. A structured comparative synthesis categorized AR trigger mechanisms, media formats, and evaluation strategies to identify patterns linking implementation characteristics with learning outcomes. The results show that marker-based AR integrated with interactive three-dimensional models or simulations is the most common approach and is more consistently associated with positive cognitive outcomes. Studies employing structured pre-post or quasi-experimental designs reported clearer evidence of learning gains than those relying primarily on perception-based assessments. Overall, AR effectiveness appears to depend more on instructional design quality and rigorous evaluation methods than on technological novelty alone.
Co-Authors Abidatul Izzah Afdhari, Fahrezi Bintang Agus Eko Minarno Agus Zainal Arifin Ahmad Faris Akbar Alfaz, Revansha Zulfikar Alhanafi, Ahmad Azzam Aljunaid, Wajeehaldeen Ahmed Qasem Andaru, Gabriel Imam Anggito Sulistyo Adi Ayu Septya Maulani Aziz, Achmad Noer Catur Singgih Daniel Swanjaya Dhomas Hatta Fudholi Diana Purwitasari Dimas Setyawan Ramadhansyah Fathurrahman, Ihya Fayruz Rahma Ferdian Nursulistio Fitri Bimantoro Fudholi, Dhomas Hatta Huda, Sheila Nurul Ihya Fathurrahman Fathurrahman Indra Lukmana Indrayanti, Indrayanti Indrayanti, Indrayanti Irving V. Paputungan Isye Arieshanti Izzati Muhimmah Juan Parez Mangku Alamsyah Khoirunnisa Shofwatul Laili Mufti Leriansyah Muhammad Rizqi Az Zayyad Muhimmah, Izzati mukhamad masrur Najmudin, Nabil Nanik Suciati Nur Jati Lantang Marfu'ah Pandu Avilba Rahadian Kurniawan Raisha Alma Sahara Rasyadi, M Javier Resa Zulfikar Rio Galang Jati Respati Salsabila Zahirah Pranida Santoso, Muhammad Lucky Lazuardi Setya Winarno Siti Mutrofin Sri Kusumadewi Yuda Munarko