Automatic Leukocytes Classification using Deep Convolutional Neural Network
نویسندگان
چکیده
ABSTRAK Sel darah putih atau leukosit adalah salah satu bagian yang bertanggung jawab untuk sistem kekebalan tubuh. Penghitungan setiap jenis merupakan hal krusial menentukan status kesehatan. dihitung menggunakan hematology analyzer. Namun, perangkat ini hanya tersedia di laboratorium klinik pusat rumah sakit. Saat masih banyak clinician melakukan perhitungan manual dengan memperkirakan jumlah mikroskop. Hal berpotensi menimbulkan kesalahan tinggi. Oleh karena itu, penelitian mengusulkan suatu dapat mengklasifikasikan jenis-jenis leukosit. Metode convolutional neural network (CNN) arsitektur VGG-19 digunakan dalam klasifikasi Beberapa skenario pengujian mengubah parameter epoch dan ukuran batch diterapkan mendapatkan akurasi terbaik. Hasil simulasi model pembelajaran menghasilkan hingga 100% neutrofil, eosinofil, monosit, limfosit. dicapai pengoptimal Adam, Epoch=5 size=60. Kata kunci: leukosit, klasifikasi, CNN, VGG-16 ABSTRACT White blood cells or leukocytes are one of the components responsible for body's immune system. Counting each type leukocyte is a crucial thing to determine health status. Blood were counted using However, this device only available in central clinical laboratories hospitals. Currently, there still many clinicians doing calculations by estimating number microscope. This has potential generate high errors calculations. Therefore, study proposes system that can classify types leukocytes. The method with architecture was employed classification. Several test scenarios changing and size parameters applied obtain best accuracy. results simulation learning used accuracy up classifying neutrophils, eosinophils, monocytes, lymphocytes. result achieved Adam optimizer, epoch=5 Keywords: leukocyte, classification,
منابع مشابه
Relation Classification via Convolutional Deep Neural Network
The state-of-the-art methods used for relation classification are primarily based on statistical machine learning, and their performance strongly depends on the quality of the extracted features. The extracted features are often derived from the output of pre-existing natural language processing (NLP) systems, which leads to the propagation of the errors in the existing tools and hinders the pe...
متن کاملAutomatic Tagging Using Deep Convolutional Neural Networks
We present a content-based automatic music tagging algorithm using fully convolutional neural networks (FCNs). We evaluate different architectures consisting of 2D convolutional layers and subsampling layers only. In the experiments, we measure the AUC-ROC scores of the architectures with different complexities and input types using the MagnaTagATune dataset, where a 4-layer architecture shows ...
متن کاملGas Classification Using Deep Convolutional Neural Networks
In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. ...
متن کاملObject Classification using Deep Convolutional Neural Networks
The objective of this research project is to explore the impact on performance by varying architectures of deep neural networks. Deep neural networks have resurged in interest by researchers when, in 2012, Krizhevsky et al. submitted a deep convolutional neural network to the ILSVRC (ImageNet Large Scale Visual Recognition Challenge) and achieved significantly-higher results than the entire com...
متن کامل3D model classification using convolutional neural network
Our goal is to classify 3D models directly using convolutional neural network. Most of existing approaches rely on a set of human-engineered features. We use 3D convolutional neural network to let the network learn the features over 3D space to minimize classification error. We trained and tested over ShapeNet dataset with data augmentation by applying random transformations. We made various vi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Elkomika
سال: 2023
ISSN: ['2338-8323', '2459-9638']
DOI: https://doi.org/10.26760/elkomika.v11i1.195