Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Bima Abdi: Jurnal Pengabdian Masyarakat Jurnal Kecerdasan Buatan dan Teknologi Informasi
San Sudirman
Universitas Teknologi Mataram
Computer Science & IT Education Languange, Linguistic, Communication & Media Other

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

Found 4 Documents
Search

 1 
COLONOSCOPIC POLYP SEGMENTATION USING SEGFORMER-B0 WITH A DICE-BCE HYBRID LOSS Ahmad Yani; San Sudirman; M. Zulpahmi; Emi Suryadi; Bahtiar Imran
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 2 (2026): May 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i2.476

Abstract

Colorectal cancer is one of the leading causes of cancer-related deaths worldwide, with most cases originating from early lesions such as colon polyps. Early detection through colonoscopy is essential to reduce mortality rates; however, accurate polyp identification remains challenging due to variations in shape, size, texture, and illumination conditions. This study aims to implement and evaluate the SegFormer-B0 architecture combined with a Dice-BCE hybrid loss function for polyp segmentation in colonoscopy images. The study utilized the public Kvasir-SEG dataset consisting of 1,000 colonoscopy images with pixel-level annotations. The dataset was divided into 80% training data and 20% validation data. Image preprocessing included resizing to 256×256 pixels and normalization using ImageNet statistics. The model was trained for 25 epochs using the AdamW optimizer with a learning rate of 1×10⁻⁴. Performance evaluation was conducted using Dice Coefficient, Intersection over Union (IoU), Sensitivity, and Specificity metrics. The experimental results demonstrated that the proposed model achieved a Dice Coefficient of 89.92%, Mean IoU of 81.90%, Sensitivity of 89.12%, and Specificity of 98.51%. The training process also showed stable convergence, supported by a training loss of 7.53% and validation loss of 23.30%. The findings indicate that the integration of SegFormer-B0 with the Dice-BCE hybrid loss effectively improves segmentation accuracy and stability while addressing class imbalance issues in colonoscopy images. Therefore, the proposed approach has strong potential to support computer-aided diagnosis systems for colorectal cancer screening.
Peningkatan Keterampilan Peserta Didik Mengkonfigurasi Jaringan LAN melalui Program Uji Kompetensi Keahlian (UKK) di SMK Qamarul Huda Emi Suryadi; Ahmad Yani; San Sudirman; Selamet Riadi
Bima Abdi: Jurnal Pengabdian Masyarakat Vol. 6 No. 2 (2026): Bima Abdi: Jurnal Pengabdian Masyarakat
Publisher : Yayasan Pendidikan Bima Berilmu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53299/ba-jpm.v6i2.4525

Abstract

Uji Kompetensi Keahlian (UKK) memastikan penguasaan keterampilan dan pengetahuan pada bidang jaringan LAN. Selain sebagai syarat kelulusan, proses UKK dapat menilai kesiapan dalam memasuki dunia kerja atau melanjutkan pendidikan lebih tinggi. Kegiatan UKK kelas XII jurusan TKJ berlangsung selama 5 hari yang bertempat di Laboratorium Komputer SMK Qamarul Huda. Evaluasi peserta didik dilakukan melalui uji kompetensi untuk mengukur keterampilan dalam konfigurasi jaringan LAN. Pelaksanaan  UKK melibatkan penguji internal yaitu guru produktif dan asesor eksternal sebagai penguji. Instrumen yang digunakan meliputi lembar tugas UKK, rubrik penilain, lembar observasi, serta perangkat peraktek yang mendukung pelaksanaan UKK. Proses evaluasi kompetensi peserta didik SMK Qamarul Huda memiliki tiga tahapan yaitu tahapan pertama persiapan, mempersiapkan perlengkapan dan bahan yang akan digunakan serta mengundang asesor eksternal dari perguruan tinggi. Tahapan kedua yaitu disini peserta didik akan melakukan praktek dengan mengkonfigurasi jaringan komputer LAN agar dapat terkoneksi antara server dan client. Tahapan terakhir yaitu evaluasi, pada tahapan ini asesor melakukan penilaian dengan melihat hasil kerja peserta didik selama mengikuti proses ujian. Peserta didik yang mengikuti UKK berjumlah 90 orang dari jurusan TKJ SMK Qamarul Huda. Hasil evaluasi konfigurasi jaringan LAN bahwa telah diperoleh sebanyak 98% peserta didik dinyatakan sangat kompeten dan 2% dinyatakan kompeten. Kegiatan ini dapat meningkatkan keterampilan praktek serta kesiapan peserta didik dalam menekuni bidang jaringan komputer. Program UKK ini dapat membantu sekolah memastikan ketercapaian kompetensi lulusan peserta didik dalam meghadapi dunia kerja.
A SECURE DIGITAL TRADING PLATFORM FOR ONLINE GAME ACCOUNTS USING DUAL AUTHENTICATION AND SMART PAYMENT INTEGRATION Lalu Moh. Nurkholis; San Sudirman; Maspaeni; Muhammad Said
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 1 (2026): January 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i1.422

Abstract

The rapid growth of online gaming has increased the economic value of game accounts, leading to the emergence of online game account trading. However, most transactions are still conducted through informal channels, such as social media and online forums, which lack security, transparency, and reliable transaction records. This study aims to design and implement a web-based information system for online game account buying and selling by integrating OTP-based dual authentication and a payment gateway to improve security and transaction efficiency. The system was developed using the Waterfall method, consisting of requirement analysis, system design, implementation, testing, and maintenance stages. UML diagrams and an Entity Relationship Diagram were used to model system functionality and database structure. The system was implemented using PHP and MySQL and supports key features such as user management, game account management, secure login with OTP, transaction processing, payment gateway integration, reviews, and complaints. Black-box testing results indicate that all system functions operate according to the defined requirements. The implementation of OTP-based authentication improves access security by reducing the risk of unauthorized account use, while payment gateway integration ensures accurate and automated payment verification. The system also enhances transaction transparency through digital transaction records and purchase history. The results show that the proposed system provides a secure, efficient, and practical solution for online game account trading in a local business environment, supporting digital transformation and service professionalism for small-scale enterprises.
EFFICIENT HYBRID CNN-VISION TRANSFORMER FOR MEDICAL IMAGE CLASSIFICATION WITH LIMITED ANNOTATIONS San Sudirman; Ahmad Yani; Lalu Darmawan Bakti
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 4 No. 3 (2025): September 2025
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v4i3.453

Abstract

Medical image classification is a critical component of computer-aided diagnosis systems, yet its performance is often hindered by the scarcity of annotated data. This situation is common in the medical domain due to ethical, cost, and labeling constraints. Convolutional Neural Networks (CNNs) are effective at extracting local features but are suboptimal at capturing global context. Conversely, Vision Transformers (ViTs) excel at modeling long-range dependencies but require large amounts of training data. To address these limitations, this study proposes a hybrid CNN–Vision Transformer model that integrates the strengths of both to improve classification performance under limited annotation conditions. The model was tested using the OrganAMNIST dataset, consisting of 53,339 two-dimensional abdominal CT images with 11 organ classes. Experimental results show that the model achieves an accuracy of 92.3%, an F1-score of 91.8%, and an AUC of 99.5%, with only 3.67 million parameters. Compared to ResNet50, this model reduces the number of parameters by 84% and increases inference speed by up to 2.4 times. Additionally, the model demonstrates better training stability compared to baseline models such as ResNet50 and ViT-Small. The results of the study show that the integration of local and global features in a hybrid architecture can simultaneously improve accuracy and efficiency. This approach has the potential to be applied to medical diagnosis systems with limited data and computational resources.
Co-Authors Ahmad Yani Ahmad Yani Imran, Bahtiar Lalu Darmawan Bakti Lalu Moh. Nurkholis M. Zulpahmi Maspaeni Muhammad Said Selamet Riadi Suryadi, Emi