Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal MULTINETICS RESOLUSI : REKAYASA TEKNIK INFORMATIKA DAN INFORMASI
Arifa Nofriyaldi Chan
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
Optimasi Model Machine Learning untuk Klasifikasi dan Prediksi Citra Menggunakan Algoritma Convolutional Neural Network Eko Setia Budi; Arifa Nofriyaldi Chan; Prilly Priscillia Alda; Muh. Arif Fauzi Idris
Resolusi : Rekayasa Teknik Informatika dan Informasi Vol. 4 No. 5 (2024): RESOLUSI May 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/resolusi.v4i5.1892

Abstract

Convolutional Neural Networks (CNN) have become the dominant algorithm in image classification and prediction due to their ability to recognize complex visual patterns. However, to achieve optimal performance, CNN models require various optimization techniques. This study aims to explore and implement optimization techniques in training CNN models to enhance the accuracy and generalization capabilities of the model in image classification. The techniques implemented include learning rate scheduling, batch normalization, regularization with dropout and L2, data augmentation, and the use of transfer learning with pre-trained models such as VGG16. Additionally, early stopping methods and advanced optimization algorithms like Adam and RMSprop are applied to improve convergence and prevent overfitting. The results show that the combination of applied optimization techniques significantly improves the performance of CNN models. Analysis of the model training history visualization indicates a reduction in loss and an increase in accuracy, with slight indications of overfitting towards the end of training. These findings emphasize the importance of employing holistic optimization strategies in developing CNN models for image classification and prediction applications. However, in some experiments, the trained models still exhibited prediction errors. This can be attributed to factors such as overfitting or underfitting, data quality and quantity, data diversity, model architecture, and optimization methods. Therefore, further optimization is needed in data preparation, determination of optimization methods, and data cleaning.
Utilisasi Teknik Segmentasi Background dalam Meningkatkan Akurasi Prediksi Citra pada Algoritma Convolutional Neural Network Indah Purnamasari; Arifa Nofriyaldi Chan; Prilly Priscillia Alda; Muhammad Arif Fauzi Idris; Fitri Meliani; Brandon Jevri Wanta
MULTINETICS Vol. 12 No. 1 (2026): MULTINETICS Mei (2026)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v12i1.7404

Abstract

       Convolutional Neural Network (CNN) mampu mengenali pola visual pada berbagai skala dan orientasi, menjadikannya unggul dalam tugas pengenalan gambar seperti klasifikasi objek, deteksi, dan segmentasi citra. Namun, CNN menghadapi tantangan dalam mengelola dataset dengan latar belakang kompleks yang dapat mengganggu ekstraksi fitur utama. Penelitian ini bertujuan untuk meningkatkan akurasi prediksi citra pada model CNN melalui teknik segmentasi latar belakang. Model memiliki performa baik dalam mendeteksi gesture batu dan kertas dengan akurasi tinggi, terutama pada citra yang memiliki latar belakang tersegmentasi dengan baik. Namun, kualitas segmentasi latar belakang citra sangat mempengaruhi keakuratan prediksi. Untuk hasil yang lebih konsisten, diperlukan peningkatan pre-processing, terutama pada teknik segmentasi latar belakang citra. Dataset yang digunakan terdiri dari citra permainan gunting, batu, dan kertas dengan latar belakang warna hijau yang telah dilabeli. Selanjutnya segmentasi citra dilakukan menggunakan deteksi warna HSV untuk latar belakang citra berwarna hijau dan thresholding Otsu untuk menghilangkan elemen latar belakang citra selain warna hijau. Citra hasil segmentasi kemudian diproses melalui augmentasi data, normalisasi batch, dan transfer learning. Model CNN dilatih menggunakan optimizer Adam dan fungsi loss categorical cross-entropy dengan model pralatih VGG16. Evaluasi model dilakukan menggunakan analisis confusion matrix, pengukuran akurasi, serta visualisasi training-validation loss. Hasil uji model menunjukkan akurasi prediksi citra di atas 97%, hal ini menegaskan bahwa penghapusan latar belakang dapat meningkatkan performa CNN.  
Co-Authors Brandon Jevri Wanta Eko Setia Budi Fitri Meliani Indah Purnamasari Muh. Arif Fauzi Idris Muhammad Arif Fauzi Idris Prilly Priscillia Alda Prilly Priscillia Alda