Automatic Detection of Pneumonia using Concatenated Convolutional Neural Network

Abstract

Pneumonia is a life-threatening disease and early detection can save lives, many automated systems have contributed to the detection of this disease and currently deep learning models have become one of the most widely used models for building these systems. In this study, two deep learning models are combined: DenseNet169 and pre-activation ResNet models and used for automatic detection of pneumonia. DenseNet169 model is an extension of the ResNet model, while the second is a modified version the ResNet model, these models achieved good results in the field of medical imaging. Two methods are used to deal with the problem of unbalanced data: class weight, which enables to control the percentage of data to be used from the original data for each class of data, while the other method is resampling, in which modified images are produced with an equal distribution using data augmentation. The performance of the proposed model is evaluated using a balanced dataset consists of 5856 images. Achieved results were promising compared to several previous studies. The model achieved a precision value of 98%, an area under curve (AUC) based on ROC of 97%, and a loss value of 0.23.

Detection of Pneumonia from Chest X-ray Images Utilizing MobileNet Model

“…From Table 9, it can be analyzed that the authors in [22][23][24][25] had worked on the diagnosis of COVID. Whereas the authors in [5,9,[26][27][28][29][30][31][32][33] had worked on the diagnosis of pneumonia. The authors in [22,23,25] achieved higher accuracy than the proposed model, but they worked on the diagnosis of COVID whereas the proposed model is used In this section, the proposed model is compared with the work of other researchers that have worked on pneumonia and COVID diagnoses using different techniques and different datasets.…”

Modulation Signal Recognition Based on Endpoint Detection and Cepstral Parameters

“…Compared to traditional pattern recognition algorithms, Deep Learning Algorithms can automatically extract more effective data features to obtain better classification results. Currently, Networks with structures such as Convolutional Neural Networks [18][19][20][21], Recurrent Neural Networks [22][23], and others have achieved good results in the field of automatic modulation recognition. However, most current Deep Learning architectures primarily use Convolutional Networks, Recurrent Neural Networks, or Attention Mechanisms singularly, resulting in incomplete signal representation, and the models cannot simultaneously handle the recognition of multiple modulation types [24][25][26].…”