Article Per Year (5 Year)
p-Index From 2020 - 2025
2.307
P-Index
This Author published in this journals
All Journal Jurnal Simetris Jurnal Ilmiah KOMPUTASI Sinkron : Jurnal dan Penelitian Teknik Informatika Sebatik Astonjadro Simtek : Jurnal Sistem Informasi dan Teknik Komputer JUKI : Jurnal Komputer dan Informatika International Journal Of Science, Technology & Management (IJSTM) Jurnal Locus Penelitian dan Pengabdian Eduvest - Journal of Universal Studies Kohesi: Jurnal Sains dan Teknologi SmartComp
Akbar, Habibullah
Unknown Affiliation
Aerospace Engineering Agriculture, Biological Sciences & Forestry Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Mathematics Mechanical Engineering Neuroscience Social Sciences Transportation Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Fraud Detection in Credit Card Transactions Using HDBSCAN, UMAP and SMOTE Methods Setiawan, Rudy; Tjahjono, Budi; Firmansyah, Gerry; Akbar, Habibullah
International Journal of Science, Technology & Management Vol. 4 No. 5 (2023): September 2023
Publisher : Publisher Cv. Inara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46729/ijstm.v4i5.929

Abstract

Credit card abuse and fraud in credit card transactions pose a serious threat to financial companies and consumers. To overcome this problem, accurate and effective fraud detection is essential. In this study, we propose an approach that combines HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise), UMAP (Uniform Manifold Approximation and Projection), and SMOTE (Synthetic Minority Over-sampling Technique) methods to detect fraud in credit card transactions. The HDBSCAN method is used to group transactions based on their spatial density, allowing identification of suspicious groups of transactions. UMAP is used to reduce the dimension of transaction data, thus enabling better visualization and more efficient data analysis. In addition, we use SMOTE to overcome class imbalances, namely differences in the number of fraudulent and non-fraudulent transactions. In our experiments, we used. In this experiment, we used a dataset of credit card transactions that included both fraudulent and non-fraudulent transactions. The experimental results show that the proposed approach is able to detect fraud with high accuracy. The HDBSCAN method is able to effectively identify suspicious groups of transactions, while UMAP helps in better understanding and visualization of data. The use of SMOTE has successfully overcome class imbalances, resulting in more balanced fraud detection results between fraud and non-fraud. The results of this study show that the combination of HDBSCAN, UMAP, and SMOTE methods is effective in detecting fraud in credit card transactions. This approach can help financial companies identify suspicious transactions with high accuracy, reduce fraud losses, and improve the security of credit card transactions.
Implementation of the Multimedia Development Life Cycle (MDLC) in Solar System Application Design Aryani, Diah; Noviandi, Noviandi; Siti Fatonah, Nenden; Akbar, Habibullah
International Journal of Science, Technology & Management Vol. 5 No. 4 (2024): July 2024
Publisher : Publisher Cv. Inara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46729/ijstm.v5i4.1123

Abstract

Augmented Reality (AR) technology has had an impact on changes in the world of education, especially improving the quality of education which has positively influenced the learning and teaching process, with the use of tools in education it has proven effective in improving the learning and teaching environment in the classroom and even changing the way we view education. This research aims to design a solar system application as an alternative AR-based learning media by integrating 3D models, animation and video to improve the learning experience of students, especially students of SDN Larangan 5 Tangerang. This is based on the lack of student learning experience, especially regarding the solar system material which is still lacking and not yet varied because so far SDN Larangan 5 has not used technology, especially AR technology in the learning process and still uses book texts and videos. This research used the Multimedia Development Life Cycle (MDLC) method and usability testing was carried out using the System Usability Scale (SUS) method with a total of 33 respondents with a test result of 78 which indicates the level of user satisfaction with the solar system application that has been tested on the respondents.
Optimization of Delay Using Killer Whale Algorithm (KWA) on NB-IoT Hadi, Muhammad Abdullah; Widodo, Agung Mulyo; Firmansyah, Gerry; Akbar, Habibullah
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 4 (2023): Article Research Volume 7 Issue 4, October 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.12933

Abstract

Abstract: NB-IoT is designed to connect IoT devices with low-power, wide-area coverage and efficient costs. Ensuring optimal data transmission delay is a challenge in NB-IoT implementation. Inadequate coverage can hinder IoT adoption. Optimization balances energy saving and delay trade-off. The Killer Whale Algorithm (KWA) optimizes delay by adjusting repetition variables. KWA addresses dimensions, variable limits. Applying KWA in NB-IoT optimizes transmission, enhancing QoS. Optimizing delay involves reducing latency in uplink data transmission using repetition variables. This study applies KWA to optimize NB-IoT delay. Analysis in Table 4 shows non-linear repetition-distance correlation. Interestingly, delay outcomes exhibit a contrasting relationship. Still, delay remains advantageous, remaining under 1 second even at 10 km, specifically 9.2674 ms (0.0092674 seconds). This thesis aims to optimize delay in NB-IoT network transmission using the Killer Whale Algorithm (KWA), crucial for modern communication networks and IoT applications. Leveraging KWA, the research identifies solutions to reduce transmission delay, enhancing efficiency and meeting IoT communication demands for speed and timeliness
EVALUASI KINERJA TATA KELOLA TEKNOLOGI INFORMASI TERHADAP TOOLS INTERNAL FRAMEWORK COBIT 2019 Akbar, Habibullah; Saputra, Rahdian
Sebatik Vol. 27 No. 2 (2023): Desember 2023
Publisher : STMIK Widya Cipta Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46984/sebatik.v27i2.2336

Abstract

Di era ini, teknologi informasi dan layanan transportasi terintegrasi untuk meningkatkan produktivitas dan menunjang kebutuhan masyarakat didasari dengan tujuan yang jelas pada perencanaan tata kelola teknologi informasi. Salah satu BUMN yang diberikan kebijakan oleh pemerintah untuk mengelola teknologi informasi adalah PT Telkom Akses. PT Telkom Akses telah menerapkan tata kelola teknologi informasi berdasarkan ISO 270001, ISO 20000-1, dan COBIT dengan membentuk prosedur tata kelola teknologi informasi di Unit Information System serta peraturan, kebijakan, implementasi, monitoring, dan audit teknologi informasi. Agar tujuan yang telah ditetapkan dapat tercapai dan berlaku sesuai rencana, maka perlu dilakukan kegiatan evaluasi terhadap operasional tata kelola teknologi informasi tersebut. Framework COBIT 2019 adalah jenis framework yang sifatnya lebih fleksibel dan bisa dimodifikasi untuk tujuan ataupun konteks tertentu. Berdasarkan pada uraian diatas, maka penelitian ini ditujukan untuk mengetahui hasil evaluasi capability level pada proses teknologi informasi saat ini (as-is) dan yang diharapkan (to-be), serta merangkai usulan yang bisa dijabarkan dari hasil evaluasi. Penelitian ini dilakukan dengan metode pengumpulan data yang berupa observasi, wawancara dan kuesioner serta pengolahan data dengan COBIT 2019. Hasil yang ditemukan dari penelitian ini yaitu PT Telkom Akses memiliki capability level senilai level 3. Kesimpulan yang bisa diambil yaitu domain objektif DSS memiliki kriteria yang sesuai dengan pembahasan pada nilai capability level dan maturity level-nya. Tiap domain proses memberikan resultan tingkat kesenjangan sesuai dengan domain objektif pilihan dari desain faktor.
PENGEMBANGAN APLIKASI MENTALFIRST BERBASIS ANDROID SEBAGAI MEDIA DETEKSI AWAL PTSD DAN MEDIA INFORMASI SEPUTAR PTSD Chiuman, Felix; Akbar, Habibullah
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 14, No 1 (2023): JURNAL SIMETRIS VOLUME 14 NO 1 TAHUN 2023
Publisher : Fakultas Teknik Universitas Muria Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24176/simet.v14i1.9491

Abstract

Trauma merupakan tekanan emosional dan psikologis yang pada umumnya karena kejadian yang tidak menyenangkan atau pengalaman yang berkaitan dengan kekerasan. Secara umum, ada banyak faktor yang bisa menyebabkan seseorang mengalami trauma, termasuk peristiwa menyedihkan, mengguncang jiwa, hingga mengancam nyawa. Ini karena kejadian traumatis dapat menyebabkan gangguan streess pasca trauma (PTSD). Untuk mengatasi kesulitan ini, peneliti melakukan pengembangan sebuah aplikasi berbasis Android yang berfungsi sebagai media deteksi awal PTSD dan juga sebagai media informasi yang berkaitan dengan penanganan PTSD. Aplikasi ini dikembangkan menggunakan metode Test Driven Development dan menggunakan Kotlin dan XML sebagai bahasa pemograman dan layouting aplikasi serta, menggunakan Firebase sebagai back end nya. Test Driven Development sendiri merupakan pengembangan perangkat lunak yang menekankan testing sebelum coding  yang dimana menggunakan pendekatan Agile dan Extreme Programming.Dengan pengujian Black Box Testing aplikasi dapat berjalan dengan baik dan aplikasi ini memiliki nilai SUS (System Usability Scale) rata-rata sebesar 89.75. Aplikasi telah dipublikasi ke dalam Play Store dengan status pengujian terbuka. Dengan demikian, aplikasi “MentalFirst” ini diharapkan dapat membantu masyarakat dapat melakukan deteksi awal dan mendapatkan informasi yang berkaitan dengan PTSD.
Pengembangan Aplikasi Mobile Klasifikasi Penyakit Kulit Berbasis EfficientNet-B0, Arsitektur MVVM dan CI/CD Pipeline Astamar Putra, Ichlasul Fikri; Akbar, Habibullah
Jurnal Ilmiah Komputasi Vol. 23 No. 4 (2024): Jurnal Ilmiah Komputasi : Vol. 23 No 4, Desember 2024
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32409/jikstik.23.4.3676

Abstract

Penyakit kulit sering dianggap sebagai hal yang normal, tetapi dalam beberapa kasus, penyakit kulit dapat berbahaya dan mematikan dan seringkali dianggap abaikan oleh masyarakat luas. Disisi lain, saat ini teknologi berperan penting dalam kehidupan manusia sehari – hari sehingga aplikasi pada smartphone menjadi kebutuhan harian. Penelitian ini akan menjelasakan mengenai pengembangan aplikasi kesehatan kulit yang mengintegrasikan model machine learning dalam penggunaan aplikasi mobile berbasis Android menggunakan metode pengembangan Extreme Programming yang mengedepankan fleksibilitas dan responsif tergantung kebutuhan pengguna juga menekankan komunikasi yang erat antara tim pengembang. Selain itu penelitian ini juga berfokus dalam penerapan pada arsitektur aplikasi yang di rekomendasi oleh Android yaitu menggunakan Model-View-ViewModel (MVVM) dengan tingkat pengujian Black-Box Testing yang memuaskan dan nilai System Usability Scale 92 menandakan aplikasi yang dibuat harapannya dapat diterima dan membantu masyarakat sebagai penanganan tahap awal atau para profesional kesehatan, termasuk dermatologis dalam memberikan perawatan yang lebih baik dan lebih tepat bagi pasien yang mengalami masalah kulit.
Game Edukasi Berbasis Augmented Reality (AR) Menggunakan Metode Marker-Based Tracking dalam Perancangan Aplikasi Tata Surya Aryani, Diah; Noviandi, Noviandi; Fatonah, Nenden Siti; Akbar, Habibullah
JUKI : Jurnal Komputer dan Informatika Vol. 6 No. 2 (2024): JUKI : Jurnal Komputer dan Informatika, Edisi Nopember 2024
Publisher : Yayasan Kita Menulis

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

Abstract

Augmented Reality (AR) technology has had a positive impact on education, particularly in improving the quality of learning and creating an interactive learning environment. This research aims to design a solar system application based on AR as an alternative learning media that integrates 3D models, animations, and videos to enhance the learning experience of students, especially at SDN Larangan 5 Tangerang. The background of this research is the lack of variety in teaching the solar system material at the school, which still relies on textbooks and videos without utilizing AR technology. The method used in this study is Marker-Based Tracking, which involves the use of specific markers to detect objects and display information as well as 3D models of the planets in the Solar System on the device screen. By using this method, the application provides a more interactive and immersive learning experience. For usability testing, the System Usability Scale (SUS) method was used, involving 33 respondents, including teachers, students, and parents. The test results yielded a score of 78, indicating a high level of user satisfaction with the application. This study is expected to be a first step in the application of AR technology to support learning innovation, particularly in enhancing students' understanding of the solar system concept
IMPLEMENTASI DEEP LEARNING TERHADAP PRESENSI MAHASISWA MENGGUNAKAN METODE MTCNN DAN FACENET : (STUDI KASUS: KAMPUS ESA UNGGUL BEKASI) Latumapayahu, Febrian Firmansyah; Herwanto, Agus; Akbar, Habibullah; Prabowo, Ary
Kohesi: Jurnal Sains dan Teknologi Vol. 7 No. 3 (2025): Kohesi: Jurnal Sains dan Teknologi
Publisher : CV SWA Anugerah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.3785/kohesi.v7i3.11681

Abstract

The development of digital technology has opened opportunities for educational institutions to improve the efficiency and accuracy of administrative systems, including student attendance recording. The current attendance system, which relies on RFID cards, often encounters issues such as damaged, lost, or unreadable cards, leading to long queues and the need for manual administration. This study aims to address these problems by developing an automatic attendance system based on facial recognition using deep learning technology. The proposed system integrates the Multi-task Cascaded Convolutional Neural Networks (MTCNN) algorithm for face detection and FaceNet for face recognition. Data collection is conducted by acquiring student facial images as the dataset for model training. The data is processed through normalization, face detection, and feature extraction using FaceNet embeddings. The system is integrated with a MySQL database to record student attendance in real time. Testing results show that the system performs well in detecting and recognizing student faces with satisfactory accuracy levels, despite variations in lighting conditions. By reducing dependency on physical cards, this system can streamline the attendance process and provide ease of use for users. This study demonstrates that the application of deep learning technology has the potential to improve the efficiency of attendance management in higher education institutions.
Implementation of YOLOv5 Algorithm for Exam Cheating Movement detection Suardana, Made Aka; Akbar, Habibullah; Saputra, Martin; Widodo, Agung Mulyo; Tjahjono, Budi
Eduvest - Journal of Universal Studies Vol. 5 No. 6 (2025): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i6.51480

Abstract

The decline in academic integrity due to cheating during exams has become increasingly relevant, particularly following the shift to online learning systems. The absence of direct supervision in online exams creates opportunities for cheating practices that evade detection by the naked eye. This study addresses this challenge by developing an object detection model for cheating behavior using a deep learning approach based on the YOLOv5 algorithm. The dataset comprised 60 ten-second videos, extracted into 1,200 images representing four suspicious head movement patterns. Each image was manually annotated before training five YOLOv5 variants. Models were evaluated using object detection metrics (precision, recall, and mAP at IoU thresholds 0.5–0.95) and analyzed via confusion matrices. Results indicate that the YOLOv5x variant achieved peak performance, with mAP@0.5:0.95 of 83.06% and perfect classification accuracy across all classes. This demonstrates that an object detection–based approach provides a reliable preliminary solution for monitoring cheating during online exams.
Analysis of Drowsiness Detection based on Images Using Convolutional Neural Network Nasihin, Anwar; Akbar, Habibullah; Firmansyah, Gerry; Tjahjono, Budi
ASTONJADRO Vol. 13 No. 2 (2024): ASTONJADRO
Publisher : Universitas Ibn Khaldun Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32832/astonjadro.v13i2.14888

Abstract

Drowsiness detection is crucial in maintaining the safety and alertness of individuals, especially in high-risk situations such as driving or operating heavy machinery. This research aims to develop a drowsiness detection system based on facial images using Convolutional Neural Network (CNN) with a focus on the AlexNet method and its comparison with ResNet. In this study, facial image data was collected from various conditions of drowsiness and normal conditions. Image preprocessing was performed to standardize the size and ensure consistent image quality. AlexNet and ResNet were implemented and trained using the image dataset to identify distinctive patterns that differentiate drowsy faces from faces in a normal state. The results of the experiments showed that the use of AlexNet and ResNet methods effectively detects drowsiness in facial images with high accuracy. However, there are performance differences between the two methods. ResNet demonstrated superior performance in certain conditions, while AlexNet showed advantages in other cases. This research contributes to the development of facial image-based drowsiness detection technology applicable in various fields, including smart vehicles and security systems. The comparison results between AlexNet and ResNet also provide valuable insights for selecting the most suitable CNN method for drowsiness detection applications based on facial images.
Co-Authors Adi Widiantono Andini, Ketrin Vani Astamar Putra, Ichlasul Fikri BUDI TJAHJONO Chiuman, Felix Diah Aryani, Diah Fatonah, Nenden Siti Firmansyah, Gerry Hadi, Muhammad Abdullah Haryoto, Iin Sahuri Herwanto, Agus Latumapayahu, Febrian Firmansyah Martin Saputra, Martin Nasihin, Anwar Noviandi Noviandi, Noviandi Nugroho, Irfan Hari Prabowo, Ary Pramesty, Feranti Destina Reyhan, Athallah Rudy Setiawan Saputra, Rahdian Siti Fatonah, Nenden Suardana, Made Aka Sutanto, Imam Widodo, Agung Mulyo