Claim Missing Document
Check
Articles

Found 33 Documents
Search

Detection of Diabetic Retinopathy Using Hybrid InceptionResNetV2-KELM Method Musfiroh, Musfiroh; Novitasari, Dian C Rini; Hakim, Lutfi; Damayanti, Adelia; Haq, Dina Zatusiva; Aisah, Siti Nur
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11967

Abstract

Diabetic Retinopathy (DR) is a complication of Diabetes Mellitus (DM), both type 1 and type 2 DM. Based on its severity, DR is divided into mild DR, moderate DR, severe DR, and proliferative DR stages. Manual detection is difficult because there is a fairly small difference between normal and DR. The Computer-Aided Diagnosis (CAD) system is a solution for detecting the severity of DR quickly and accurately so that DR sufferers do not get worse, which can cause blindness. This study uses fundus images from the Mesindor dataset consisting of four classes, namely normal, mild DR, moderate DR, and severe DR, with the InceptionResNetV2-KELM hybrid method. InceptionResNetV2 is used as a feature extraction and Kernel Extreme Learning Machine (KELM) as its classification. Several types of kernels are applied as model trials. The results show the highest sensitivity lies in the polynomial kernel experiment with a sensitivity value of 99.88%, an accuracy of 99.88%, and a specificity of 99.96%. The method used is able to detect very well and is quite time-effective compared to conventional CNN.
Penguatan Layanan Informasi dan Laporan Masyarakat di Desa Kalirejo melalui Implementasi Chatbot WhatsApp Terintegrasi Sistem Dashboard Hakim, Lutfi; Kristanto, Sepyan Purnama; Wibowo, Galih Hendra
Archive: Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 2 (2026): Juni 2026
Publisher : Asosiasi Pengelola Publikasi Ilmiah Perguruan Tinggi PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55506/arch.v5i2.272

Abstract

Latar Belakang: Desa Kalirejo menghadapi permasalahan dalam pelayanan publik, khususnya terkait dengan sistem informasi dan laporan keluhan masyarakat yang masih bersifat konvensional, sehingga menyebabkan layanan informasi belum bisa optimal sampai ke masyarakat dan data laporan tidak terintegrasi dan sulit dimonitor. Tujuan: Tujuan dari program ini adalah melakukan penguatan layanan informasi dan laporan masyarakat melalui implementasi sistem perpesanan WhatsApp berbasis Chatbot yang terintegrasi dengan sistem Dashboard berbasis web. Metode: Pendekatan Participatory Action Research digunakan pada program ini yang menempatkan mitra sebagai subjek aktif dalam setiap tahap kegiatan yang meliputi 5 tahapan kegiatan mulai dari tahapan identifikasi dan pemetaan masalah sampai dengan evaluasi dan monitoring. Hasil: SI KARJO dapat diimplementasikan dengan baik dan mitra mampu mengoperasikannya secara mandiri melalui pendampingan berkelanjutan. Kesimpulan: Program ini mendapatkan apresiasi positif dengan skor survey kepuasan mitra sebesar 95,82%.
An Integrated K-Means++–Davies–Bouldin Index Approach for Educational Resource-Based District Clustering: A Case Study of Districts in Surabaya Subaekti, Hendrik; Hakim, Lutfi; Khaulasari, Hani; Yuliati, Dian
Jambura Journal of Mathematics Vol 8, No 1: February 2026
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjom.v8i1.35412

Abstract

Equitable distribution of educational resources is an important prerequisite to ensure that all communities benefit from human resource development. Access to education through the availability of schools and teachers at every level, plays a role in reducing the gap between regions. This study aims to group educational resources at the elementary and junior high school levels in 31 sub-districts of Surabaya City and evaluate the quality of grouping using the Davies–Bouldin Index (DBI). The analysis was carried out using secondary data from the Surabaya City Education Office which included the number of schools, teachers, and students based on education level in each sub-district. The clustering method used is K-Means++, which improves the centroid initialization process to produce more stable clustering. The results of the analysis identified three clusters, namely Development Education Areas (17 sub-districts), Elementary Focused Areas with Limited Junior High Schools (7 sub-districts), and Priority Education Areas (7 sub-districts: Rungkut, Sukolilo, Wonokromo, Sukomanunggal, Genteng, Kenjeran, and Krembangan). The quality of the grouping was validated with a DBI value of 0.752, which indicates a good cluster separation These findings can directly inform the Surabaya City Government in formulating targeted policies for educational equity, especially in teacher placement, student quota adjustment, and infrastructure development.