A Novel-based Swin Transfer Based Diagnosis of COVID-19 Patients

The numbers of cases and deaths due to the COVID-19 virus have increased daily all around the world. Chest X-ray is considered very useful and less time-consuming for monitoring COVID disease. No doubt, X-ray is considered as a quick screening method, but due to variations in features of images which are of X-rays category with Corona confirmed cases, the domain expert is needed. To address this issue, we proposed to utilize deep learning approaches. In this study, the dataset of COVID-19, lung opacity, viral pneumonia, and lastly healthy patients' images of category X-rays are utilized to evaluate the performance of the Swin transformer for predicting the COVID-19 patients efficiently. The performance of the Swin transformer is compared with the other seven deep learning models, including ResNet50, DenseNet121, InceptionV3, Efficient-NetB2, VGG19, ViT, CaIT, Swim transformer provides 98% recall and 96% accuracy on corona affected images of the X-ray category. The proposed approach is also compared with state-of-the-art techniques for COVID-19 diagnosis, and proposed technique is found better in terms of accuracy. Our system could support clin-icians in screening patients for COVID-19, thus facilitating instantaneous treatment for better effects on the health of COVID-19 patients. Also, this paper can contri-bute to saving humanity from the adverse effects of trials that the Corona virus might bring by performing an accurate diagnosis over Corona-affected patients. © 2023, Tech Science Press. All rights reserved.

A Novel-based Swin Transfer Based Diagnosis of COVID-19 Patients

The numbers of cases and deaths due to the COVID-19 virus have increased daily all around the world. Chest X-ray is considered very useful and less time-consuming for monitoring COVID disease. No doubt, X-ray is considered as a quick screening method, but due to variations in features of images which are of X-rays category with Corona confirmed cases, the domain expert is needed. To address this issue, we proposed to utilize deep learning approaches. In this study, the dataset of COVID-19, lung opacity, viral pneumonia, and lastly healthy patients' images of category X-rays are utilized to evaluate the performance of the Swin transformer for predicting the COVID-19 patients efficiently. The performance of the Swin transformer is compared with the other seven deep learning models, including ResNet50, DenseNet121, InceptionV3, EfficientNetB2, VGG19, ViT, CaIT, Swim transformer provides 98% recall and 96% accuracy on corona affected images of the X-ray category. The proposed approach is also compared with state-of-the-art techniques for COVID-19 diagnosis, and proposed technique is found better in terms of accuracy. Our system could support clinicians in screening patients for COVID-19, thus facilitating instantaneous treatment for better effects on the health of COVID-19 patients. Also, this paper can contribute to saving humanity from the adverse effects of trials that the Corona virus might bring by performing an accurate diagnosis over Corona-affected patients.

Depression Detection in Tweets from Urban Cities of Malaysia using Deep Learning

This document was inspired by how the usage of social media platforms in Malaysia such as Twitter have drastically increased ever since the recent Covid-19 pandemic. While practicing social distancing and other pandemic regulations was for the betterment and prevention of physical health, mental health of most was affected negatively. People generally revolve around with having interactions with other humans and once the physical form of it was cut, people tend to turn to social media. A twitter sentiment analysis approach was used to find the casual link between social media and mental health. This project aims to utilise the broaden scope of social media-based mental health measures since research proves the evidence of a link between depression and specific linguistic features as well. Therefore, the research entails on how the problem statement of this project on developing an algorithm that can predict text- based depression symptoms using deep learning and Natural Language Processing (NLP) can be achieved. The objective of the project is to identify depressive tweets using NLP and Deep Learning in the urban cities of Malaysia within the beginning of the Covid-19 period to enable individuals, their caregivers, parents, and even medical professionals to identify the linguistic clues that point towards to signs of mental health deterioration. Additionally, this paper also researches to make the proposed system to identify words that represent depression and categorize them accordingly as well as improve the accuracy of the system in identifying tweets that display the depression related words based on its specific location. This objective will be achieved following the methodology using the Deep Learning approach and Natural Language Processing technique. A recurrent neural network approach was implemented in this project known as the Long-Term Short Memory, which is a form of advanced RNN, that allows information to be preserved. Conducting an analysis on the linguistic indicators from tweets allows for a low-profile assessment that can supplement traditional services which then consequently would allow for a much earlier detection of depressive symptoms. Since this research entails on finding the link between tweets and machine learning's ability to detect depressive symptoms, the success this project brings forth a meaningful help towards those who are mentally affected but are unable to seek help or are unsure on diagnosing themselves as this project helps alert the government and psychologist on the need for it. The project thus far has an accuracy rate of 94%, along with, precision rate of 0.94, recall of 0.96 and an F1 score of 0.95. © 2021 IEEE.