Claim Missing Document
Check
Articles

Found 4 Documents
Search

Development of a Village Citizen Reporting Website for Smart Village Village Public Services Monika Dian Pertiwi, Kharisma; Muhajir, Daud; Ananda, Dahliar; Santik, Tita Arum Shela; Pratama, Moch. Andi Divangga; Adityo, Kahil Akbar Bayu; Jungjungan, Fadhlan Syahran
Abdi Masyarakat Vol 6, No 2 (2024): Abdi Masyarakat
Publisher : Lembaga Penelitian dan Pendidikan (LPP) Mandala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58258/abdi.v6i2.7491

Abstract

The development of technology that has been supported by the government makes it easier for citizens to get information, and can influence society to get information and participate in public policy. The development of technology carried out by the government starts from public services on digital platforms, such as websites or village applications. Smart Village initiated by Telkom University Surabaya innovates by providing a website to help citizens with easy complaints to providing a space for community aspirations that can be accessed anywhere and anytime by the people of Panjunan Village. The Public Complaints Website has 31 features for citizens, officers and admins, these features have been tested functionally, and have been tested on several users, in the test no functional errors were found in the sense that the system is ready to use.
A Deep Learning Model Comparation for Diabetic Retinopathy Image Classification Mustaqim, Tanzilal; Safitri, Pima Hani; Muhajir, Daud
Scientific Journal of Informatics Vol. 12 No. 1: February 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i1.20939

Abstract

Purpose: This study compares the performance of various deep learning models for diabetic retinopathy (DR) classification, emphasizing the impact of different optimization functions. Early detection of DR is vital for preventing blindness, and the research investigates how optimization functions influence the classification accuracy and efficiency of several convolutional neural networks (CNNs). This study fills a gap in the existing literature by examining how optimization functions affect model performance in conjunction with architectural considerations. Methods: This paper uses the APTOS 2019 dataset, which comprises 3,663 retinal fundus images classified into five classes of diabetic retinopathy severity. Four CNN-based models, including CNN, ResNet50, DenseNet121, and EfficientNet B0, were trained using five optimization techniques: Adam, SGD, RMSProp, AdamW, and NAdam. The performance of the experimental scenarios was evaluated through accuracy, precision, recall, F1-score, training duration, and model size. Result: EfficientNet B0 demonstrated superior computational efficiency with a minimal model size of 16.16 MB. Subsequently, DenseNet121 with the SGD optimizer achieved the highest test accuracy of 96.86%. The experimental results indicate that the optimizer significantly influences model performance. AdamW and NAdam yield superior outcomes for deeper architectures such as ResNet50 and DenseNet121. Novelty: This paper offers an analytical examination of deep learning models and optimization techniques for DR classification, helping to clarify the trade-offs between computational efficiency and classification performance. The findings contribute to the development of more accurate and efficient DR detection systems, which could be utilized in real-world, resource-limited settings.
Rancang Bangun Prototipe Sistem Deteksi Dini Retinopathic Diabetic Berbasis Website Muhajir, Daud; Mustaqim, Tanzilal; Safitri, Pima Hani; Oktavia, Vessa Rizky
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2255

Abstract

Diabetic Retinopathic (DR) is one of the retinal disorders caused by high blood sugar levels. There are fewer ophthalmologists available, and treating DR patients manually is a time-consuming process. Therefore, there is a need for an automatic DR early detection method using Deep Learning. The purpose of this research is to build a web-based DR early detection prototype with retinal image classification using the DenseNet121 Deep Learning model and the Stochastic Gradient Descent (SGD) optimizer to improve the accessibility and efficiency of screening. The software development method used in this research is waterfall which consists of analysis phase, design phase, implementation phase, and testing phase. To ensure the prototype runs as planned, black-box testing is carried out on each of its features to ensure system functionality in accordance with predetermined specifications. This research produces a RD early detection prototype that has been tested with all 16 test cases and has a suitable status. Future research can be carried out further system development by involving real users such as ophthalmologists and can be applied in hospitals.
PELATIHAN DAN IMPLEMENTASI APLIKASI ’KONSELINK’ UNTUK TRANSFORMASI DIGITAL LAYANAN BIMBINGAN KONSELING Hidayati, Sri; Rosidah, Nur Azizah; Muhajir, Daud; Kusumawati, Aris; Prisyanti, Affifiana; Abdillah, Rosyid; Alhari, Muhammad Ilham; Hendradi, Fransisca Aurelia Maranatha; Satriawan, Muhammad Paksi; Ramadhan, Muhammad Ayondi; Septiano, Dino Rossi Eka
JMM (Jurnal Masyarakat Mandiri) Vol 9, No 4 (2025): Agustus
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v9i4.32709

Abstract

Abstrak: Layanan bimbingan konseling (BK) di jenjang sekolah menengah masih banyak yang dilakukan secara manual menggunakan buku pengembangan diri, yang menyebabkan kendala dalam pencatatan, analisis data, dan pemberian intervensi. Tujuan kegiatan pengabdian ini adalah mentransformasi layanan BK konvensional menjadi sistem digital melalui pengembangan dan pelatihan penggunaan aplikasi web “Konselink”. Metode yang digunakan mencakup observasi kebutuhan, pengembangan sistem, pelatihan luring, serta evaluasi. Mitra kegiatan ini adalah guru BK dan siswa di SMAN 1 Kamal. Pelatihan dilakukan di Lab TIK sekolah dan dievaluasi menggunakan kuesioner serta observasi langsung, dengan peserta pelatihan sebanyak 22 guru BK dan perwakilan siswa. Hasil kegiatan menunjukkan peningkatan keterampilan digital guru, serta skor kepuasan peserta rata-rata 4,9 dari 5. Aplikasi Konselink dinilai efektif dalam meningkatkan efisiensi pencatatan, mempermudah analisis perkembangan siswa, dan mendorong keterlibatan siswa dalam layanan konseling yang lebih fleksibel dan adaptif.Abstract: Guidance and counseling (GC) services at the secondary school level are still largely carried out manually using student development logbooks, which leads to challenges in record-keeping, data analysis, and timely intervention. The aim of this community engagement initiative was to transform conventional GC services into a digital system through the development and training in the use of a web-based application called “Konselink.” The methods employed included needs assessment, system development, offline training, and evaluation. The participants in this program consisted of guidance counselors and students. The training was conducted in the school's ICT laboratory and evaluated through questionnaires and direct observation, involving 22 participants comprising GC teachers and student representatives. The results showed an improvement in the digital skills of the teachers, with an average participant satisfaction score of 9.4 out of 10. The Konselink application was found to be effective in improving the efficiency of documentation, facilitating student development analysis, and encouraging more flexible and adaptive student engagement in counseling services.