Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Manajemen Informatika Jurnal Teknik Informatika dan Teknologi Informasi
Muhammad Ali Zafar Sidiq
Universitas Adhirajasa Reswara Sanjaya
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
PERBANDINGAN KEEFEKTIFAN ALGORITMA BACKTRACKING DAN SOFT COMPUTING DALAM MEMECAHKAN PERMAINAN PAPAN NONOGRAM Muhammad Ali Zafar Sidiq; Aldi Supriyadi; Asti Herliana
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 3 No. 1 (2023): April: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v3i1.2069

Abstract

Solving logic puzzles using specific algorithms presents an intriguing challenge where the efficiency of the approaches is crucial. One such puzzle involves solving nonograms, where the task is to fill in board fields according to the conditions specified for each row and column. The availability of various methods allows for comparing their efficiency and effectiveness. This study aimed to evaluate the effectiveness of two algorithms from different categories. We selected a modified Depth-First Search (DFS) method and a soft computing method based on permutations generation to solve a set of chosen nonograms. The research was conducted using four different board sizes, and the results indicated that the effectiveness of the methods largely depends on the complexity of the nonogram. The algorithm employing permutations consistently produced stable results, while the DFS method did not always guarantee a complete solution.
Klasifikasi Jenis Jerawat Secara Otomatis Dengan Convolutional Neural Network Menggunakan Arsitektur Resnet-50 Muhammad Iqbal Anshori; Muhammad Ali Zafar Sidiq; Rifki Ainul Yaqin; Ignatius Wiseto Prasetyo Agung
Jurnal Manajemen Informatika JAMIKA Vol 15 No 1 (2025): Jurnal Manajemen Informatika (JAMIKA)
Publisher : Program Studi Manajemen Informatika, Fakultas Teknik dan Ilmu Komputer, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/jamika.v15i1.13712

Abstract

Acne is a common skin problem that requires different treatments based on its type, such as blackheads, conglobata, and papulopustular. This research develops an automatic acne type classification system using deep learning-based Residual Network (ResNet-50) architecture. With its 50 layers, ResNet-50 is effective in image classification. The objective of of this research is to classify the type of acne from skin images on the face, so that it can help diagnosis and treatment. face, so that it can help diagnosis and treatment. The method used in this research includes several main stages, namely the collection of the dataset, model training using CNN with ResNet-50 architecture, model testing, and performance evaluation. model, and performance evaluation. The dataset was obtained from Roboflow, consisting of three classes: acne-comedonica, acne-conglobata, and acne-papulopustulosa. The process involves image preprocessing, data augmentation, and model parameter adjustment, including Adam's dropout and optimizer techniques. The model can achieve 98.35% accuracy with loss of 0.0489 and the highest validation accuracy of 92.86% with a validation loss of 0.1976. In addition, confusion matrix analysis shows an accuracy result of 93%, which indicates the performance of the model in distinguishing between acne classes effectively. These results show that the model is effective in classifying the types of acne and can have a significant impact in assisting a more accurate and faster diagnosis. more accurate and quicker diagnosis.
Co-Authors Aldi Supriyadi Asti Herliana, Asti Ignatius Wiseto Prasetyo Agung Muhammad Iqbal Anshori Rifki Ainul Yaqin