Claim Missing Document
Check
Articles

Found 39 Documents
Search

IMPLEMENTASI LENET-5 DAN MOBILENET-V2 UNTUK KLASIFIKASI KEMATANGAN BUAH CABAI BERBASIS COMPUTER VISION Hadi, Risman; Dwiyansaputra, Ramaditia; Irfan, Pahrul
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 1 (2025): JATI Vol. 9 No. 1
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i1.12725

Abstract

Tingginya konsumsi cabai rawit menjadikannya komoditas dengan permintaan yang selalu tinggi, sehingga memiliki nilai ekonomi yang signifikan bagi para petani . Terlebih lagi, makanan khas Pulau Lombok seperti pelecing kangkung, ayam taliwang, dan bebalung sangat ditentukan cita rasanya oleh cabai sebagai salah satu bahan utama untuk bumbu. Permintaan cabai yang cenderung tinggi sepanjang tahun tanpa mengenal musim menciptakan tantangan dalam pengelolaan kualitas cabai di pasaran. Identifikasi kualitas buah cabai yang masih dilakukan secara visual oleh petani sering kali menghasilkan kesalahan dalam proses sortir yang dapat merugikan konsumen. Oleh karena itu, diperlukan penerapan teknologi computer vision untuk mengatasi masalah ini. Penelitian ini mengimplementasikan arsitektur CNN yaitu Lenet-5 dan MobileNet-V2. Lenet-5 memiliki kelebihan dalam kesederhanaan struktur dan kebutuhan komputasi yang rendah, sehingga cocok digunakan pada perangkat dengan sumber daya terbatas. MobileNet-V2 memiliki unggul dalam efisiensi parameter dan kinerja yang optimal untuk perangkat mobile atau aplikasi real-time. Hasil penelitian menunjukkan bahwa model arsitektur Lenet-5 menunjukkan performa lebih baik dengan accuracy 99%, precission 1.00, recall 1.00 dan F-1 Score 1.00, sedangkan model arsitektur MobileNet-V2 memiliki accuracy 100%, precission 1.00, recall 1.00 dan F-1 Score 0,95. Hal tersebut menunjukkan potensi computer vision berbasis CNN untuk meningkatkan akurasi dan efisiensi dalam klasifikasi tingkat kematangan buah cabai.
Frontend Implementation of UI/UX Design of Sumbawa District Agricultural Service Website using React JS Framework: IMPLEMENTASI FRONTEND DARI DESIGN UI/UX WEBSITE DINAS PERTANIAN KABUPATEN SUMBAWA MENGGUNAKAN FRAMEWORK REACT JS Muayyadin, Muhammad; Irfan, Pahrul; Rassy, Regania Pasca
Jurnal Begawe Teknologi Informasi (JBegaTI) Vol. 6 No. 1 (2025): JBegaTI
Publisher : Program Studi Teknik Informatika, Fakultas Teknik Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jbegati.v6i1.1326

Abstract

Dinas Komunikasi dan Informatika (Kominfo) Kabupaten Sumbawa bekerja sama dengan Dinas Pertanian Kabupaten Sumbawa dalam mengembangkan sistem informasi berbasis digital, yaitu Sistem Informasi Pertanian Sumbawa (SiTAWA), untuk meningkatkan efisiensi layanan publik di sektor pertanian. Implementasi frontend dari sistem ini memainkan peran penting dalam memastikan pengalaman pengguna yang optimal dalam mengakses layanan pengaduan masyarakat, pengumpulan data pertanian, dan penyusunan laporan bulanan. Penelitian ini berfokus pada pengembangan dan implementasi frontend dari desain UI/UX SiTAWA menggunakan framework React JS. React JS dipilih karena keunggulannya dalam membangun antarmuka yang responsif, modular, dan mudah dikelola. Melalui pendekatan desain UI/UX yang baik, diharapkan sistem ini dapat meningkatkan aksesibilitas, efisiensi, serta transparansi layanan pertanian bagi masyarakat dan pemerintah daerah. Hasil penelitian menunjukkan bahwa implementasi frontend berbasis React JS mampu meningkatkan efisiensi dalam proses pelaporan dan pengaduan digital. Selain itu, penerapan prinsip UI/UX yang tepat berkontribusi terhadap peningkatan pengalaman pengguna, baik dari sisi petani, masyarakat, maupun pihak dinas terkait. Dengan demikian, SiTAWA dapat menjadi langkah awal dalam mendukung transformasi digital sektor pertanian di Kabupaten Sumbawa.
Optimization of data integration using schema matching of linguistic-based and constraint-based in the university database Rifqi Hammad; Azriel Christian Nurcahyo; Ahmad Zuli Amrullah; Pahrul Irfan; Kurniadin Abd. Latif
Matrix : Jurnal Manajemen Teknologi dan Informatika Vol. 11 No. 3 (2021): Matrix: Jurnal Manajemen Teknologi dan Informatika
Publisher : Unit Publikasi Ilmiah, P3M, Politeknik Negeri Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31940/matrix.v11i3.119-129

Abstract

University requires the integration of data from one system with other systems as needed. This is because there are still many processes to input the same data but with different information systems. The application of data integration generally has several obstacles, one of which is due to the diversity of databases used by each information system. Schema matching is one method that can be used to overcome data integration problems caused by database diversity. The schema matching method used in this research is linguistic and constraint. The results of the matching scheme are used as material for optimizing data integration at the database level. The optimization process shows a change in the number of tables and attributes in the database that is a decrease in the number of tables by 13 tables and 492 attributes. The changes were caused by some tables and attributes were omitted and normalized. This research shows that after optimization, data integration becomes better because the data was connected and used by other systems has increased by 46.67% from the previous amount. This causes the same data entry on different systems can be reduced and also data inconsistencies caused by duplication of data on different systems can be minimized.
Application of the Blowfish Algorithm in securing patient data in the database Irfan, Pahrul; Hammad, Rifqi; Anas, Andi Sofyan; Fatimatuzzahra; Samudra, Nanang
Matrix : Jurnal Manajemen Teknologi dan Informatika Vol. 12 No. 2 (2022): Matrix: Jurnal Manajemen Teknologi dan Informatika
Publisher : Unit Publikasi Ilmiah, P3M, Politeknik Negeri Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31940/matrix.v12i2.102-108

Abstract

Patient data is one of the datasets managed by the hospital. Patient data in the form of examination results and other data is important data that is private and confidential. Therefore, patient data needs to be secured so that there is no misuse of data by parties who are not responsible for things that can harm the data owner. One of the several methods that can be used to secure data is cryptography. Cryptography itself has several algorithms, one of which is blowfish. This study applies the blowfish algorithm to secure patient data in the database to reduce the possibility of data misuse by irresponsible parties. This study succeeded in implementing the blowfish algorithm for securing patient data. The data stored in the database is the result of encryption using the blowfish algorithm, the results of which are difficult to understand because there is a combination of symbols and text. The application of the algorithm affects the data storage time in the database, which originally took 0.12 seconds to save data and now takes 0.28 seconds to store data.
Geolocation data incorporation in Mapbox for comprehensive mapping of tourism areas on Lombok Island Hammad, Rifqi; Irfan, Pahrul; Panca Mukti, M Thoric
Matrix : Jurnal Manajemen Teknologi dan Informatika Vol. 14 No. 1 (2024): Matrix: Jurnal Manajemen Teknologi dan Informatika
Publisher : Unit Publikasi Ilmiah, P3M, Politeknik Negeri Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31940/matrix.v14i1.33-42

Abstract

Lombok Island is one of the islands that has many tourist areas. With so many tourist areas spread to various regions on the island of Lombok, an accurate and comprehensive tourist area mapping system is needed. The problem faced is that the existing mapping is still constrained regarding accuracy and data persistence. The solution offered in this research is the incorporation of geolocation data on the Mapbox platform to improve the accuracy and detail of data in mapping tourism areas on the island of Lombok. In this research, there are several stages carried out starting from data collection to testing. This research results in a tourist area mapping information system that applies geolocation data incorporation on Mapbox. The test results show an increase in accuracy of 8% from the previous mapping and a usability test score of 81 which means that the system developed is acceptable or feasible by users.
Development of an Integrated Lecturer Workload Monitoring Information System Using the Prototype Model: PENGEMBANGAN SISTEM INFORMASI PEMANTAUAN BEBAN KERJA DOSEN TERINTEGRASI BERBASIS PROTOTIPE Irfan, Pahrul; Wijaya, I Gede Pasek Suta; Akhyar, Halil; Zubaidi, Ariyan; Zafrullah, Ahmad
Jurnal Begawe Teknologi Informasi (JBegaTI) Vol. 6 No. 2 (2025): JBegaTI
Publisher : Program Studi Teknik Informatika, Fakultas Teknik Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jbegati.v6i2.1463

Abstract

Pemantauan beban penugasan dosen di Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram masih dilakukan secara manual dan terpisah. Kondisi ini menyulitkan proses pemantauan serta berpotensi menimbulkan ketidakseimbangan distribusi tugas akademik maupun non-akademik. Untuk mengatasi permasalahan tersebut, dilaksanakan kegiatan pengabdian berupa pengembangan sistem informasi terintegrasi menggunakan metode prototipe, yang meliputi tahapan analisis kebutuhan, perancangan, pengembangan, pengujian, dan implementasi awal. Hasil pengujian menunjukkan sistem berfungsi sesuai spesifikasi berdasarkan Blackbox Testing, sedangkan uji System Usability Scale (SUS) terhadap delapan responden memperoleh skor rata-rata 84,06 yang termasuk kategori Excellent. Temuan ini membuktikan bahwa sistem mudah digunakan, diterima pengguna, dan mendukung efektivitas pemantauan beban kerja dosen. Dengan adanya sistem ini, Program Studi dapat memantau distribusi tugas secara lebih menyeluruh, adil, dan efisien. Selain itu, sistem berpotensi dikembangkan lebih lanjut agar dapat diterapkan tidak hanya di Program Studi Teknik Informatika, tetapi juga pada program studi lain dalam rangka meningkatkan kualitas manajemen beban kerja dosen di lingkungan perguruan tinggi.
Data Augmentation-Driven Predictive Performance Refinement in Multi-Model Convolutional Neural Network for Cocoa Ripeness Prediction Apriani, Apriani; Switrayana, I Nyoman; Hammad, Rifqi; Irfan, Pahrul; Pratama, Gede Yogi
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5298

Abstract

Timely and accurate prediction of cocoa fruit ripeness is critical for optimizing harvest schedules, improving yield quality, and supporting post-harvest processing. Conventional visual inspection methods are prone to subjectivity and inconsistencies, especially when distinguishing among multiple ripeness levels based on fruit age. This study proposes a deep learning approach that leverages multi-model convolutional neural network transfer learning combined with image data augmentation to classify cocoa fruit into four maturity stages derived from fruit age. An augmented dataset of cocoa fruit images was used to fine-tune five well-established pre-trained models: MobileNetV2, Xception, ResNet50, DenseNet121, and DenseNet169. Data augmentation techniques were employed to increase variability and improve model generalization. Model evaluation was conducted using a standard 80:20 training-to-testing split to ensure sufficient data for learning while preserving a representative test set across all ripeness classes. The results demonstrate that DenseNet169 consistently outperformed other models, achieving the highest average accuracy of 85,05%, followed by DenseNet121 84,06%. Across all models, the use of data augmentation led to notable performance gains, highlighting its importance in enhancing predictive capability and reducing overfitting. The proposed framework shows promising potential for automating ripeness classification in agricultural contexts, offering a robust, scalable, and accurate solution for intelligent cocoa harvest management. This work contributes to the growing application of deep learning in precision agriculture, particularly in addressing fine-grained classification problems using limited but enriched visual data.
Selection of Outstanding Students Using AHP and Profile Matching Nasri, Muhammad Haris; Hammad, Rifqi; Irfan, Pahrul
Paradigma - Jurnal Komputer dan Informatika Vol. 26 No. 1 (2024): March 2024 Period
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/p.v26i1.3189

Abstract

The determination of outstanding students is the giving of awards to those who excel in academic and non-academic fields, aimed at motivating increased achievement. However, this process is often hampered by various criteria that must be considered, such as English language skills, work results, awards, and so on. The solution offered to overcome this problem is the development of a decision support system for selecting outstanding students using the AHP and Profile Matching methods. So, the aim of this research is to develop a decision support system for selecting outstanding students using a combination of the AHP and Profile matching methods, where later the system developed can assist decision makers in determining outstanding students. The results obtained from this research are a decision support system that uses 8 criteria and 26 alternative sample data which shows that "Mahasiswa F" is an outstanding student with a score of 4.09. The results of manual calculations with the system show similarities, which shows that the system developed is in accordance with expectations.
SISTEM INFORMASI AKADEMIK DI RUMAH TAHFIZH AN-NAWAWI KAPEK GUNUNGSARI LOMBOK BARAT: Academic Information System at Rumah Tahfizh An-Nawawi Kapek Gunungsari West Lombok Ekaputra, Galang Prasetya; Dwiyansaputra, Ramaditia; Dani, Muhammad; Irfan, Pahrul; Rassy, Regania Pasca
Jurnal Begawe Teknologi Informasi (JBegaTI) Vol. 5 No. 2 (2024): JBegaTI
Publisher : Program Studi Teknik Informatika, Fakultas Teknik Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jbegati.v5i2.1209

Abstract

Rumah Tahfizh Qur’an adalah lembaga pusat kegiatan pembelajaran dan penghafalan Al-Qur’an, serta penerapan dan pembudayaan nilai-nilai Qur’ani dalam kehidupan sehari-hari, yang berbasis pada tempat tinggal, lingkungan, dan komunitas. Rumah Tahfizh An-Nawawi adalah salah satu lembaga keagamaan yang telah berkembang seiring waktu dan diikuti oleh peningkatan jumlah santri. Karena itu, diperlukan inovasi untuk memanfaatkan era digital saat ini agar lebih mudah mengatur sistem akademiknya. Tujuan dari pengabdian kepada masyarakat ini adalah untuk merancang dan membangun sistem informasi akademik Rumah Tahfizh An-Nawawi menggunakan framework laravel. Sistem ini dibangun dengan menggunakan metode pengembangan waterfall dan black box testing sebagai pengujiannya. Berdasarkan hasil pengujian menggunakan metode black box testing terhadap fungsionalitas sistem yang dibuat, dapat disimpulkan bahwa sistem yang telah dibangun dapat berjalan dengan baik.