Pneumonia Detection using Depth-Wise Convolutional Neural Network (DW-CNN)

Abstract

Pneumonia is most significant disease in today's world. It resulted around 15 % of the total deaths of children of the same age group. OBJECTIVES: This paper proposes Depth Wise Convolution Neural Network (DW-CNN) using the SWISH Activation and Transfer Learning (VGG16) to reliably diagnose pneumonia. METHODS: The proposed model contains 10 layers of convolutional neural networks. Also, three dense layers with the Swish activation function with a dropout of 0.7 and 0.5 respectively in each layer. The model was trained on 5216 augmented with weighted contrast and brightened radiograph Images and tested on 624 radiogram images using Deep Learning and Transfer Learning (VGG16). RESULT: The model was trained on 5216 augmented radiograph Images and tested on 624 radiogram images using Deep Learning and Transfer Learning (VGG16) and the final results obtained with training accuracy of 98.5%, testing accuracy of 79.8% and validation accuracy of 75%. CONCLUSION: The model can be improved by using different transfer learning models and hyperparameter tuning parameters.

Evaluating Deep Neural Network Architectures with Transfer Learning for Pneumonitis Diagnosis

“…Stephen et al explore the performance of a custom CNN model [ 21 ]. Walia et al developed a depthwise convolutional neural network that outperforms inception and VGG networks on the Kaggle chest X-ray dataset [ 22 ]. CheXNet by Rajpurkar et al achieves remarkable accuracy on the ChestX-ray14 dataset in classifying 14 diseases [ 23 ].…”

Recognizing Pneumonia Infection in Chest X-Ray Using Deep Learning

“…The following is one of the results. The discussion is based on previous research by [15], which also uses deep learning to detect pneumonia. This study uses simple CNN with data augmentation and simple CNN without data augmentation.…”

“…Then, research conducted by [3] used 6 convolution layers with data augmentation. Research by [15] Simple CNN without Data Augmentation 0.72% Simple CNN with Data Augmentation 0.78% Research by [3] CNN with Data Augmentation 77% Proposed research CNN with data augmentation 89.743%…”

“…Information in the image can be processed well by CNN because the system is like image recognition in the human visual cortex [14]. Research conducted by [15] compared six deep-learning models. A simple CNN was used with data augmentation, and a simple CNN without data augmentation was used to detect pneumonia.…”

An Integrated Approach for Monitoring Social Distancing and Face Mask Detection Using Stacked ResNet-50 and YOLOv5

“…A system has been designed that automatically tracks the public places in real-time using Raspberry pi4 which captures the real-time videos of different public places to keep track of whether the people are wearing masks and abiding by the social distancing norms or not [35,36]. An integrated system was proposed where visual descriptors were used to measure the distance between the people and the methodology was able to achieve an accuracy of 93.3% [37].…”