Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI)
Mega Sari Pasaribu
Institut Teknologi Del
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Image preprocessing and hyperparameter optimization on pretrained model MobileNetV2 in white blood cell image classification Parmonangan R. Togatorop; Yohanssen Pratama; Astri Monica Sianturi; Mega Sari Pasaribu; Pebri Sangmajadi Sinaga
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 12, No 3: September 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v12.i3.pp1210-1223

Abstract

White blood cells play a role in maintaining the immune system which consists of several types such as neutrophils, lymphocytes, monocytes, eosinophils and basophils. MobileNetV2 is one of the pretrained convolutional neural network (CNN) models that provides excellent advantages and performance in classifying images. In this research was conducted to find out how to apply optimization hyperparameters and the impact of image processing on white blood cell image classification using MobileNetV2, so that it is expected to find a combination of preprocessing and combination of hyperparameter values that can produce the highest accuracy value. To maximize the classification process, before classifying the image, several stages of image preprocessing are carried out, namely cropping, grayscale, resizing and augmentation. Hyperparameter tuning was carried out for an experiment to improve model performance. The three main parameters used in hyperparameter tuning are learning rate, batch size, and number of epochs. Performance optimization model performance will be measured using accuracy, sensitivity, specificity and using a confusion matrix. Based on the experimental results in this study, it shows that the best learning rate value is 0.00001, the best batch size value is 32, and the best epoch value is 250.
Co-Authors Astri Monica Sianturi Parmonangan R. Togatorop Pebri Sangmajadi Sinaga Yohanssen Pratama