Detecting Pneumonia for COVID 19 Patients using Multi-Image Fusion for CT Images

Early in 2020, the global spread of Coronavirus Disease 2019 (COVID-19) triggered an existential health crisis. Automated lung infection diagnosis using Computed Tomography (CT) images has the potential to significantly improve the current healthcare approach to combat COVID-19. But segmenting infected regions from CT slices is difficult due to the wide variety in infection traits and the weak contrast between infected and healthy tissues. Additionally, gathering a lot of data quickly is impractical, which hinders the training of a deep model. This study proposes COVID-SegNet, a convolutional-based deep learning technique for automatically segmenting COVID-19 infection areas and the whole lungs from chest CT images. The suggested deep CNN includes a feature variation (FV) block that adaptively modifies the global properties of the features for segmenting COVID-19 infection. This can improve its capacity to express features in various situations efficiently and adaptively. To deal with the complex shape variations of COVID-19 infection zones, additionally recommend the use of PASPP, a progressive atrous spatial pyramid pooling. After a simple convolution module, PASPP generates the final features using multistage parallel fusion branches. In order to cover a variety of receptive fields, PASPP uses atrous filters with an acceptable dilation rate in each atrous convolutional layer. For the segmentation of COVID-19 and the lungs, the dice similarity coefficients are 0.987 as well as 0.726, respectively. Experiments carried out on data gathered in the scan centre demonstrate that effectively produce good performance. © 2022 IEEE.

Assessing the impacts of COVID-19 on carbon emissions from the road transport sector in China

The outbreak and spread of the COVID-19 pandemic has altered transport patterns in China, leading to significant changes in energy consumption and carbon dioxide (CO2) emissions. This study assessed the spatiotemporal characteristics of transport-related CO2 emissions at the provincial level in China during the COVID-19 pandemic. Provincial-level time-series emissions were estimated based on monthly transport demand data, including both passenger and freight transport demand in China’s 31 provinces, as well as mode share, technology mix, energy intensity, and emission factor data obtained from an energy system model. Spatial autocorrelation and hot spot analyses of CO2 emissions were then conducted to detect the regional disparities and spatial clusters of the impacts of the COVID-19 pandemic on CO2 emissions. By assessing how transport emissions responded to the outbreak of the COVID-19 pandemic, a series of policy implications were devised that could provide a future decarbonization pathway.

Reimagining “Space”: An Approach to Increase Participants’ Social Aspects During Online Conferencing

Online conferencing has become a new normal after the COVID-19 pandemic. However, existing systems like ZOOM fall short of facilitating informal social aspects like chats, talks, discussions, dialogues, gatherings, secrets, or even gossip or quarrel, which often occur spontaneously during physical meetings. In this study, we design and prototype a novel system considering key spatial features that influence social interactions offline. The proposed system consists of three typical meeting modes: square mode for free social, room mode for split group discussion, stage mode for speech and presentation. Through Wizard-of-Oz testing with 10 participants, we summarize the design features that contribute to the richness of ambiance, the flexibility of distance, the serendipity of interaction of online conferences, and the effect of these aspects on social interaction. Together with the limitations and suggestions for future work, we hope this paper can inspire the design of spatial interaction on screen, with the aim to improve informal social aspects of online conferencing. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Learning Discriminant Spatial Features with Deep Graph-based Convolutions for Occluded Face Detection

The use of face masks has become a widespread non-pharmaceutical practice to mitigate the transmission of COVID-19. However, achieving accurate facial detection while people wear masks or similar face occlusions is a major challenge. This paper introduces a model to detect occluded or masked faces based on fused convolutional graphs. This model includes a deep neural architecture with two spatial-based graphs that rely on a set of key facial features. First, a distance graph is used to identify geographical similarity between the facial nodes that represent certain key face parts. Second, a correlation graph is formulated to compute the correlations between every two nodes that represent two different augmented facial modalities. Transfer learning is then performed using a pretrained deep architecture as a baseline to map the semantic information into multiple feature filters. Then, discriminant graph convolutions are constructed based on the fusion of distance and correlation graphs. This model evaluates two tasks of facial detection, which are the binary detection of masked or unmasked faces, and multi-category detection of masked, unmasked, or occluded face with no mask. The experimental results on two benchmarking real-world datasets show that the proposed deep learning model is highly effective with an accuracy of 98% achieved in binary detection. Even with high variance in image occlusions, our proposed model has great promise in detecting and distinguishing between types of facial occlusion with an accuracy of 86% reported in multi-category detection. Author

DeepAttentiveNet: An automated deep based method for COVID-19 diagnosis based on chest x-rays

The recent outbreak of coronavirus has impacted the whole world. The infectious respiratory disease has killed millions of people all over the world. The process of detecting the disease through RT-PCR and other tests is very time-consuming, and testing kits are not widely available. Chest x-rays and chest CT scans are also very effective techniques for diagnosing respiratory diseases. This paper proposes a DeepAttentiveNet, a deep-based architecture that applies the pre-trained CNN-based architecture DenseNet to extract the spatial features from the images. This is followed by the attention mechanism, which focuses on the information-rich region on the images, thus enhancing the overall classification process. The performance of our model is analyzed on the COVID 19 Radiography dataset, which contains 21,000 x-ray images corresponding to different respiratory infections like COVID 19, lung opacity, and viral pneumonia. Hence our model can categorize the x-rays with a 97.1% F1 score and 97.5% accuracy. We have also compared our architecture with other popular CNN-based models and baseline methods to demonstrate the superior performance of the model. © 2022 IEEE.