Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
2 results
Search Results
Item Trustworthiness of COVID-19 News and Guidelines(Springer, 2023) Singh, S.; Nagar, L.; Lal, A.; Chandavarkar, B.R.COVID-19 pandemic is a serious health concern issue over the past couple of years. It spreads mostly due to bio-contacts, which leads people to follow social distancing and stay away from social gatherings. It leads the people to bound themselves to stay with their family members at their home only, being at home, staying idle, or following work from home schedule by working online through the Internet over the electronic gadgets such as mobiles, laptops, desktops, etc. It leads the people to attach to online activities more for spending their time at their home, which enormously increases people interest in social media platforms such as Twitter, Facebook, etc. As it was a major pandemic period, it created panic and a fearful situation in society. It makes the people believe any news and guidelines spreading through social media platforms irrespective of checking their trustworthiness and truthiness of it. This pandemic period created a seriously bad impact on society’s emotional, physical, and mental health that is a great loss to a country even all over the world. Under this, many unwanted messages are spreading for one’s interest or a group to polarize their interest. In a panic situation, it is highly required of a solution that prevents the spread of these negative vibes to maintain the overall health of society. This chapter tries to implement an optimal solution using various kinds of layers and different optimization functions. It particularly gives better performance in the case of sequential data using machine learning (ML) and deep learning (DL) frameworks trained with the dataset for identifying the fake news and guidelines spread over on COVID-19. To train the model, a dataset was taken from the Twitter Application Programming Interface (API). Finally, the truthiness detection technique with social interaction is completed using Twitter dataset. The efficacy of the suggested method is demonstrated by the obtained results on a Twitter dataset. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Transfer Learning-Hierarchical Segmentation on COVID CT Scans(Springer, 2024) Singh, S.; Pais, A.R.; Crasta, L.J.COVID-19—A pandemic declared by WHO in 2019 has spread worldwide, leading to many infections and deaths. The disease is fatal, and the patient develops symptoms within 14 days of the window. Diagnosis based on CT scans involves rapid and accurate detection of symptoms, and much work has already been done on segmenting infections in CT scans. However, the existing work on infection segmentation must be more efficient to segment the infection area. Therefore, this work proposes an automatic Deep Learning based model using Transfer Learning and Hierarchical techniques to segment COVID-19 infections. The proposed architecture, Transfer Learning with Hierarchical Segmentation Network (TLH-Net), comprises two encoder–decoder architectures connected in series. The encoder–decoder architecture is similar to the U-Net except for the modified 2D convolutional block, attention block and spectral pooling. In TLH-Net, the first part segments the lung contour from the CT scan slices, and the second part generates the infection mask from the lung contour maps. The model trains with the loss function TV_bin, penalizing False-Negative and False-Positive predictions. The model achieves a Dice Coefficient of 98.87% for Lung Segmentation and 86% for Infection Segmentation. The model was also tested with the unseen dataset and has achieved a 56% Dice value. © The Author(s), under exclusive licence to The Japanese Society for Artificial Intelligence and Springer Nature Japan KK, part of Springer Nature 2024.