Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi CAUCHY: Jurnal Matematika Murni dan Aplikasi Abdimas: Jurnal Pengabdian Masyarakat Universitas Merdeka Malang
Zainal Abidin
Teknik Informatika, Fakultas Sains Dan Teknologi, Universitas Islam Negeri Maulana Malik Ibrahim Malang
Humanities Computer Science & IT Engineering Mathematics

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Identifikasi Pohon Tropis di Daerah Perkotaan Menggunakan Multispectral Drone Imagery Zainal Abidin; Fatchurrohman Fatchurrohman; Okta Qomaruddin Aziz
Techno.Com Vol 21, No 4 (2022): November 2022
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/tc.v21i4.6778

Abstract

Vegetasi di daerah perkotaan tumbuh diantara gedung dan jalan. Bangunan di sekitar pohon berdampak pada identifikasi tanaman menggunakan citra drone. Paper ini menjelaskan tentang perbandingan kemampuan citra drone pada band cahaya tampak, near infrared, dan red-edge untuk identifikasi pohon tropis di daerah perkotaan. Kami menyusun dataset yang berisi paduan pohon saman (Samanea Saman), cemara (Casuarina equisetifolia), dan pohon-lain. Setiap citra melalui tahapan proses filtering, segmentasi, dan classification. Hasil uji coba menunjukkan bahwa band cahaya tampak dapat mengidentifikasi saman, cemara, dan pohon-lain dibandingkan dengan citra pada band near-infrared dan red-edge.
Hybrid project learning and peer teaching as learning strategies for learners with high activity Fakhris Khusnu Reza Mahfud; Zainal Abidin; Usman Nurhasan
Abdimas: Jurnal Pengabdian Masyarakat Universitas Merdeka Malang Vol. 9 No. 2 (2024): May 2024
Publisher : University of Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/abdimas.v9i2.12261

Abstract

The mosque is the Muslim community's place of worship and education. Regular worship occurs according to a timetable. However, educational activities require quite a long time, so the mosque management schedules learning activities periodically. In addition, mosque congregations have a very high diversity and density of activities, especially mosque congregations in urban areas. The management of urban mosques has difficulty organizing learning consistently because the congregation has difficulty meeting at the same time periodically. This paper offers a solution by teaching with a hybrid learning method between project learning and peer teaching. Projects are created based on the needs of the environment and the congregation. The project development team is formed from worshipers who can work on projects. Other congregants receive knowledge through the project development team when the project is in the process of being created and run. This hybrid learning was experimented with by creating an aquaponics project. Aquaponics is operated with solar electricity. The project development team consists of a congregation of children to parents. The project has successfully transferred knowledge to the project development team members. The project operation attracts non-team worshippers to discuss independently with team members. Some non-team members have developed fish farming independently.
A Damped Hessian-Free Newton--Conjugate Gradient Method for Weighted Multiclass Neural Classification Andy Irawan; Zainal Abidin; Mohammad Jamhuri
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 11, No 1 (2026): CAUCHY: JURNAL MATEMATIKA MURNI DAN APLIKASI
Publisher : Mathematics Department, Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/cauchy.v11i1.40243

Abstract

This study presents a deterministic damped Hessian-free Newton--CG method for weighted multiclass neural classification. The method is built from a weighted categorical cross-entropy objective, a damped local quadratic model, and a matrix-free curvature representation through Hessian--vector products. The search direction is computed by an inexact conjugate gradient solve, while Armijo backtracking and adaptive damping are used to improve stability. The method is implemented for the classification of academic predicate categories using preprocessed student data with mixed categorical and numerical features. Its numerical behavior is compared with SGD with momentum, RMSProp, and Adam under the same loss, initialization, and network architecture. The proposed method is computationally feasible, attains the best overall weighted test-set performance among the compared methods, and exhibits a distinct optimization trajectory driven by curvature-informed updates. These results show that a damped Hessian-free formulation provides a mathematically transparent, reproducible, and practically competitive framework for second-order optimization in multiclass neural classification.
Co-Authors Andy Irawan Fakhris Khusnu Reza Mahfud Fatchur Rohman Mohammad Jamhuri Okta Qomaruddin Aziz Usman Nurhasan