Deteksi Covid-19 pada Citra Sinar-X Dada Menggunakan Deep Learning yang Efisien

Yudistira, Novanto; Widodo, Agus; Rahayudi, Bayu

doi:10.25126/jtiik.2020763651

Cited by 12 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The number of pixels in each sub-image is distributed at each gray level. The average number of pixels in each degree of gray is formulated in Equation (1).…”

Section: Data Pre-processingmentioning

confidence: 99%

“…The world is currently experiencing one of the biggest health disasters in human history, we called Corona Virus. Coronavirus Disease 2019 (Covid- 19) was first discovered in Hubei Province, China through reports of the type of Pneumonia whose cause is not yet known [1]. Based on data from the World Health Organization (WHO) on March 11, 2021, confirmed cases of Covid-19 reached 117,799,584 cases and 2,615,018 deaths spread across 223 countries.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pneumonia identification based on lung texture analysis using modified k-nearest neighbour

Saputra

Taufik

Hidayat

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Covid-19 is a virus that was first discovered in China, which has the impact of mild and severe respiratory infections such as pneumonia. Pneumonia is inflammation and consolidation of lung tissue due to infectious agents. Generally pneumonia has a high mortality rate, as do Covid-19 patients. For now, it is very difficult to distinguish between Pneumonia and Covid-19, due to the high similarity of X-Ray image results. The high similarity has an impact on the difficulty of difference between Pneumonia and Covid-19 patients. This research aims to be able to different Pneumonia and Covid-19 patients based on texture analysis of the Gray Level Co-Occurrence Matrix using Modified k-Nearest Neighbour as a classifier. The calculations used in the Gray Level Co-Occurrence Matrix method are Contrast, Correlation, Energy, and Homogeneity which will be input for the Modified k-Nearest Neighbour classifier. The results showed that the highest accuracy is when the value of K = 3 using Manhattan Distance and 80%:20% data percentage, which is 87.5%. For the values of K = 7 and K = 9 there is no change in accuracy, so it can be concluded that the value of K that affects accuracy only occurs at the values of K = 3 and K = 5. Then, the higher the K value, the lower the resulting accuracy.

show abstract

“…The number of pixels in each sub-image is distributed at each gray level. The average number of pixels in each degree of gray is formulated in Equation (1).…”

Section: Data Pre-processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pneumonia identification based on lung texture analysis using modified k-nearest neighbour

Saputra

Taufik

Hidayat

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Metode transfer learning merupakan metode dalam deep neural net yang menggunakan bobot dan fitur yang sudah dilatih menggunakan dataset yang besar, sehingga kaya akan fitur dan dapat mempercepat waktu komputasi. Kelebihan metode CNN dapat digunakan untuk mempelajari secara mandiri fitur-fitur pada citra yang sangat kompleks dan tidak memerlukan ekstraksi fitur apapun melainkan citra mentah (Yudistira, Widodo, & Rahayudi, 2020;Rohim, Sari, & Tibyani, 2019). Selain itu, dalam penelitian ini untuk mekanisme pengujian akan menggunakan mekanisme fine tuning dan freeze layer untuk meningkatkan ragam kualitas model yang dihasilkan dengan melihat nilai akurasi model menggunakan semua layer ekstraksi fitur (fine tuning) dan selanjutnya secara incremental melakukan freeze layer terhadap layer ekstraksi fitur.…”

Section: Pendahuluanunclassified

Klasifikasi citra makanan/non makanan menggunakan metode Transfer Learning dengan model Residual Network

Thiodorus

Prasetia

Ardhani

et al. 2021

teknol. j. ilm. sist. inf.

Self Cite

View full text Add to dashboard Cite

People's activities that often upload photos of food before eating are common in popular social media, such as Facebook, Instagram, Twitter, and Pinterest. The food image data circulating on social media can be used for business purposes, such as analyzing customer behavior patterns. However, not all of the uploaded images are food images, so that before the analysis is carried out, it is necessary to do a classification task between food images and non-food images. Therefore, the researcher proposes automatic food image classification using transfer learning method using the Residual Network model version of 18 (ResNet-18). Residual Network model is used because it has a residual connection mechanism to solve the vanishing gradient problem. In addition, transfer learning was chosen because this method leverages the features and weights that have been generated in the previous training process on large and more general data (Imagenet) and thus reduce computation time and increase accuracy. The test was carried out by comparing the capabilities of the ResNet18 model with AlexNet. In addition, the fine tuning and freeze layer methods used to improve the quality of the model were also carried out in this study. In the experiment, the data set was divided into 3,000 images for training data and 1,000 images for test data, while the evaluation used was correctness accuracy. The results obtained in the ResNet18 model, namely the fine tuning training method, produced an accuracy value of 0.981 while the freeze layer resulted in the best accuracy value of 0.988. The AlexNet model that uses the fine tuning training method produces an accuracy value of 0.970 while the freeze layer produces the best accuracy value of 0.978. It can be concluded that the mechanism with the best accuracy is found in the RestNet18 architecture using the freeze layer 1-3 with an accuracy of 0.988.

show abstract

“…Throughout the years, the trend for image recognition has been going deeper on the layer used in training [16], which means it requires more computing resources, hence causing inefficient research in ANN study with limited resources. Another research conducted by [17] shows that the more layers in an ANN, will affect the training time. This will adversely affect the efficiency of computational time, especially for large data sets processing.…”

Section: Introductionmentioning

confidence: 99%

Mask Usage Recognition using Vision Transformer with Transfer Learning and Data Augmentation

Jahja¹,

Yudistira²,

Sutrisno³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The COVID-19 pandemic has disrupted various levels of society. The use of masks is essential in preventing the spread of COVID-19 by identifying an image of a person using a mask. Although only 23.1% of people use masks correctly, Artificial Neural Networks (ANN) can help classify the use of good masks to help slow the spread of the Covid-19 virus. However, it requires a large dataset to train an ANN that can classify the use of masks correctly. MaskedFace-Net is a suitable dataset consisting of 137016 digital images with 4 class labels, namely Mask, Mask Chin, Mask Mouth Chin, and Mask Nose Mouth. Mask classification training utilizes Vision Transformers (ViT) architecture with transfer learning method using pre-trained weights on ImageNet-21k, with random augmentation. In addition, the hyper-parameters of training of 20 epochs, an Stochastic Gradient Descent (SGD) optimizer with a learning rate of 0.03, a batch size of 64, a Gaussian Cumulative Distribution (GeLU) activation function, and a Cross-Entropy loss function are used to be applied on the training of three architectures of ViT, namely Base-16, Large-16, and Huge-14. Furthermore, comparisons of with and without augmentation and transfer learning are conducted. This study found that the best classification is transfer learning and augmentation using ViT Huge-14. Using this method on MaskedFace-Net dataset, the research reaches an accuracy of 0.9601 on training data, 0.9412 on validation data, and 0.9534 on test data. This research shows that training the ViT model with data augmentation and transfer learning improves classification of the mask usage, even better than convolutional-based Residual Network (ResNet).

show abstract

Deteksi Covid-19 pada Citra Sinar-X Dada Menggunakan Deep Learning yang Efisien

Cited by 12 publications

References 5 publications

Pneumonia identification based on lung texture analysis using modified k-nearest neighbour

Pneumonia identification based on lung texture analysis using modified k-nearest neighbour

Klasifikasi citra makanan/non makanan menggunakan metode Transfer Learning dengan model Residual Network

Mask Usage Recognition using Vision Transformer with Transfer Learning and Data Augmentation

Contact Info

Product

Resources

About