A Mask Detection Algorithm Based on Improved Yolov5s

Aiming at the severe form of new coronavirus epidemic prevention and control, a target detection algorithm is proposed to detect whether masks are worn in public places. The Ghostnet and SElayer modules with fewer design parameters replace the BottleneckCSP part in the original Yolov5s network, which reduces the computational complexity of the model and improves the detection accuracy. The bounding box regression loss function DIOU is optimized, the DGIOU loss function is used for bounding box regression, and the center coordinate distance between the two bounding boxes is considered to achieve a better convergence effect. In the feature pyramid, the depthwise separable convolution DW is used to replace the ordinary convolution, which further reduces the amount of parameters and reduces the loss of feature information caused by multiple convolutions. The experimental results show that compared with the yolov5s algorithm, the proposed method improves the mAP by 4.6% and the detection rate by 10.7 frame/s in the mask wearing detection. Compared with other mainstream algorithms, the improved yolov5s algorithm has better generalization ability and practicability. © 2022 ACM.

A Multimodal Framework for the Identification of Vaccine Critical Memes on Twitter

Memes can be a useful way to spread information because they are funny, easy to share, and can spread quickly and reach further than other forms. With increased interest in COVID-19 vaccines, vaccination-related memes have grown in number and reach. Memes analysis can be difficult because they use sarcasm and often require contextual understanding. Previous research has shown promising results but could be improved by capturing global and local representations within memes to model contextual information. Further, the limited public availability of annotated vaccine critical memes datasets limit our ability to design computational methods to help design targeted interventions and boost vaccine uptake. To address these gaps, we present VaxMeme, which consists of 10,244 manually labelled memes. With VaxMeme, we propose a new multimodal framework designed to improve the memes' representation by learning the global and local representations of memes. The improved memes' representations are then fed to an attentive representation learning module to capture contextual information for classification using an optimised loss function. Experimental results show that our framework outperformed state-of-the-art methods with an F1-Score of 84.2%. We further analyse the transferability and generalisability of our framework and show that understanding both modalities is important to identify vaccine critical memes on Twitter. Finally, we discuss how understanding memes can be useful in designing shareable vaccination promotion, myth debunking memes and monitoring their uptake on social media platforms. © 2023 ACM.

Convolutional neural networks for imbalanced chest X-ray images classification

The COVID-19 epidemic has spread throughout the world and poses a serious threat to human health. Any technical device that provides the accurate and rapid automated diagnosis of COVID-19 can be extremely beneficial to healthcare providers. A new workflow for performing automated diagnosis is proposed in this paper. The proposed methods are built on a well-designed framework, two kinds of CNN architectures including a custom CNN and a pre-trained CNN are utilized to verify the effectiveness of the focal loss function. According to the experimental findings, both CNNs that were enhanced with the focal loss function converged faster and achieved higher accuracy on the test set, outperformed the models that utilized cross-entropy loss that does not consider the class-imbalanced issue in the multi-class image classification with imbalanced Chest X-ray(CXR) image datasets. In addition, image enhancement techniques turned out to be very helpful for enhancing the CXR image signatures to achieve better performance in our work. © 2023 SPIE.

A comparative study for COVID-19 cases forecasting with loss function as AIC and MSE in RNN family and ARIMA

Forecasting COVID-19 incidents is a trending research study in today's world. Since Machine learning models have been occupied in forecasting recently, this study focus on comparing statical and machine learning models such as ARIMA, RNN, LSTM, Seq2Seq, and Stacked LSTM. The performances were evaluated using two loss functions, namely, AIC and RMSE. The results showed that RNN performs with the lowest RMSE with-49.5% compared with the ARIMA. Seq2Seq scored the highest correlation of determination (R2) with 0.92. © 2022 IEEE.

Custom Weighted Balanced Loss function for Covid 19 Detection from an Imbalanced CXR Dataset

In this paper, we have proposed a novel framework, that is ResNet-18 model along with Custom Weighted Balanced loss function, in order to automatically detect Covid-19 disease from a highly imbalanced Chest X-Ray (CXR) dataset. Covid 19 disease has become a global pandemic, for last two years. Early automatic detection of Covid-19, from CXR images has been the key to survive from this pandemic. In the recent advent, researchers have already proposed several Deep Learning (DL) models, which can detect Covid-19 disease (with higher accuracy) from CXR images. However, Covid-19 detection by DL models are fraught with the problem of class imbalance, since most of the available CXR datasets are found highly imbalanced. In this paper, we have worked in a new direction, that is, alleviating the class imbalance problem from CXR dataset by using novel loss function. First, we choose a challengeable CXR dataset in which there are four classes, they are Covid, Normal, Lung Opacity (LO) and Viral Pneumonia (VP). Later we have identified that real problem of this dataset is not only the class imbalance, but also, huge intra-class variance is observed in Covid class. Therefore, we have come up with a new idea, that is, modifying the bias weights in a Weighted Categorical Cross Entropy (WCCE), based on reducing both of the factors, i.e., class imbalance and intra-class variance from the dataset. For the experimentation, we have chosen a ResNet-18 model which is trained from scratch for a large Chexpert CXR dataset and thereafter it is pre-trained on the Covid CXR dataset. Experimental results suggest that ResNet-18 model along with proposed Custom Weighted Balanced loss function, have improved 2-4% accuracy, precision, recall, F1 score and AUC for four class CXR dataset. Furthermore, we have tested the same framework for three class Covid CXR dataset, after excluding LO class. We have achieved 96% accuracy, 97% precision, 96% recall, 97% F1 score and 97% AUC for three class classification task. This is significant (3-4%) improvement than the performance of ResNet-18 model with CCE. © 2022 IEEE.

Hate Speech Detection in Thai Social Media with Ordinal-Imbalanced Text Classification

Cyberbullying has become a serious problem in Thai social media. For example, some Thai people posted hate speeches on Myanmar workers in Thailand during the COVID-19 pandemic, which might elevate hate crime. It is imperative and urgent to detect cyberbullying on Thai social media. The task is a text classification problem. Moreover, hate speeches contain the order of severity levels, but many pieces of work did not consider this point in the model. Therefore, we developed a Thai hate-speech classification method with various loss functions to detect such hate speeches accurately. We evaluated them on a corpus of ordinal-imbalanced Thai text. The evaluated outcomes indicated that the best-in terms of $F$1 -score-model was the model with a loss function of a hybrid between an Ordinal regression loss function and Pearson correlation coefficients (common in similarity function). It yielded an average F1-score of 78.38 %-0.88 % significantly higher than the score achieved by a conventional loss function-and an average mean squared error of 0.2478-5.49 % relative improvement. Thus, the proposed hybrid loss function improved the efficiency of the model. © 2022 IEEE.

Masked Deep Face Recognition using ArcFace and Ensemble Learning

With advancements in technology, human biometrics, especially face recognition, has witnessed a tremendous increase in usage, prominently in the field of security. Face recognition proves to be a convenient, coherent, and efficient way to identify a person uniquely. Face recognition systems are trained generally on human faces sans masks. With the ubiquitous use of face masks due to the ongoing COVID-19 pandemic, face recognition becomes a daunting challenge. In this paper, the deep learning architectures, namely MobileNetV2, DenseNet201, ResNet50V2, and VGG16 with the ArcFace loss function, were trained on the newly created dataset called "MaFaR", which consists of a mixture of masked and unmasked images of 75 distinct individuals, and ensemble learning techniques have been used to improve the performance, achieving an accuracy 93.65%. © 2021 IEEE.

Boosting Iris Recognition by Margin-Based Loss Functions

In recent years, the topic of contactless biometric identification has gained considerable traction due to the COVID-19 pandemic. One of the most well-known identification technologies is iris recognition. Determining the classification threshold for large datasets of iris images remains challenging. To solve this issue, it is essential to extract more discriminatory features from iris images. Choosing the appropriate loss function to enhance discrimination power is one of the most significant factors in deep learning networks. This paper proposes a novel iris identification framework that integrates the light-weight MobileNet architecture with customized ArcFace and Triplet loss functions. By combining two loss functions, it is possible to improve the compactness within a class and the discrepancies between classes. To reduce the amount of preprocessing, the normalization step is omitted and segmented iris images are used directly. In contrast to the original SoftMax loss, the EER for the combined loss from ArcFace and Triplet is decreased from 1.11% to 0.45%, and the TPR is increased from 99.77% to 100%. In CASIA-Iris-Thousand, EER decreased from 4.8% to 1.87%, while TPR improved from 97.42% to 99.66%. Experiments have demonstrated that the proposed approach with customized loss using ArcFace and Triplet can significantly improve state-of-the-art and achieve outstanding results.

Masked Face Recognition from Synthesis to Reality

As we have been seriously hit by the COVID-19 pandemic, wearing a facial mask is a crucial action that we can take for our protection. This paper reports a comprehensive study on the recognition of masked faces. By using facial landmarks, we synthesize the facial mask for each face in several benchmark databases with different challenging factors. The IJB-B and IJB-C databases are selected for evaluating the performance against the variation across pose, illumination and expression (PIE). The FG-Net database is selected for evaluating the performance across age. The SCface is chosen for evaluating the performance on low-resolution images. The MS-1MV2 is exploited as the base training set. We use the ResNet-100 as the feature embedding network connected to state-of-the-art loss functions designed for tackling face recognition. The loss functions considered include the Center Loss, the Marginal Loss, the Angular Softmax Loss, the Large Margin Cosine Loss and the Additive Angular Margin Loss. Both verification and identification are conducted in our evaluation. The performances for recognizing faces with and without the synthetic masks are all evaluated for a complete comparison. The network with the best loss function for recognizing synthetic masked faces is then assessed on a real masked face database, the cleaned RMFRD (c-RMFRD) dataset. Compared with a human user test on the c-RMFRD, the network trained on the synthetic masked faces outperforms human vision for a large gap. Our contributions are fourfold. The first is a comprehensive study for tackling masked face recognition by using state-of-the-art loss functions against various compounding factors. For comparison purpose, the second is another comprehensive study on the recognition of faces without masks by using the same loss functions against the same challenging factors. The third is the verification of the network trained on synthetic masked faces for tackling the real masked face recognition with performance better than human inspectors. The fourth is the highlight on the challenges of masked face recognition and the directions for future research. Our code, trained models and dataset are available via the project GitHub site. Author

Face Recognition Method of Mask Occlusion

Under the influence of the COVID-19, people can effectively prevent New Coronavirus infection by wearing masks in public places. However, the mask obscuration causes some face recognition systems to fail to recognize properly. Therefore, in this paper, we propose Multi-Residual Attention Network(MRANet) based on deep convolutional neural network for recognizing faces obscured by masks and improve a loss function. In our model, an attention mechanism and multiple residual layers skip connections are introduced, which allow the model to focus more on the unobscured facial information and contribute to increase the efficiency of information flow and gradient flow between each network layers. A dynamic addictive angular margin loss function, a more reasonable decision boundary function, is also proposed to improve the model’s discriminative power and convergence speed. Our algorithm can effectively identify and verify not only normal unobstructed faces, but also faces obscured by masks. We achieved a accuracy rate of 96.7% on the widely used Labeled Faces in the Wild dataset (LFW), a accuracy rate of 84.837% on the Real-world Masked Face Recognition Dataset (RMFRD), and the false accepted rate in the simulated face recognition system is as low as 0.944%. © 2021 IEEE.

A Lightweight Face Verification Based on Adaptive Cascade Network and Triplet Loss Function

In the past few years, with the continuous breakthrough of technology in various fields, artificial intelligence has been considered as a revolutionary technology. One of the most important and useful applications of artificial intelligence is face detection. The outbreak of COVID-19 has promoted the development of the noncontact identity authentication system. Face detection is also one of the key techniques in this kind of authentication system. However, the current real-time face detection is computationally expensive which hinders the application of face recognition. To address this issue, we propose a face verification framework based on adaptive cascade network and triplet loss. The framework is simple in network architecture and has light-weighted parameters. The training network is made of three stages with an adaptive cascade network and utilizes a novel image pyramid based on scales with different sizes. We train the face verification model and complete the verification within 0.15 second for processing one image which shows the computation efficiency of our proposed framework. In addition, the experimental results also show the competitive accuracy of our proposed framework which is around 98.6%. Using dynamic semihard triplet strategy for training, our network achieves a classification accuracy of 99.2% on the dataset of Labeled Faces in the Wild. © 2022 Jianhong Lin et al.

CovSeg-Unet: End-to-End Method-based Computer-Aided Decision Support System in Lung COVID-19 Detection on CT Images

COVID-19 epidemic continues to threaten public health with the appearance of new, more severe mutations, and given the delay in the vaccination process, the situation becomes more complex. Thus, the implementation of rapid solutions for the early detection of this virus is an immediate priority. To this end, we provide a deep learning method called CovSeg-Unet to diagnose COVID-19 from chest CT images. The CovSeg-Unet method consists in the first time of preprocessing the CT images to eliminate the noise and make all images in the same standard. Then, CovSeg-Unet uses an end-to-end architecture to form the network. Since CT images are not balanced, we propose a loss function to balance the pixel distribution of infected/uninfected regions. CovSeg-Unet achieved high performances in localizing COVID-19 lung infections compared to others methods. We performed qualitative and quantitative assessments on two public datasets (Dataset-1 and Dataset-2) annotated by expert radiologists. The experimental results prove that our method is a real solution that can better help in the COVID-19 diagnosis process © 2022,International Journal of Advanced Computer Science and Applications.All Rights Reserved

A new lifetime family of distributions: Theoretical developments and analysis of COVID 19 data.

In parametric statistical modeling and inference, it is critical to develop generalizations of existing statistical distributions to make them more flexible in modeling real data sets. Thus , this paper contributes to the subject by investigating a new flexible and versatile generalized family of distributions defined from the alliance of the families known as beta-G and Topp-Leone generated (TL-G), inspiring the name of BTL-G family. The characteristics of this new family are studied through analytical, graphical and numerical approaches. Statistical features of the family such as expansion of density function (pdf), cumulative function (cdf), moments (MOs), incomplete moments (IMOs), mean deviation (MDE), and entropy (ENT) are calculated. The model parameters' maximum likelihood estimates (MaxLEs) and Bayesian estimates (BEs) are provided. Symmetric and Asymmetric Bayesian Loss function have been discussed. A complete simulation study is proposed to illustrate their numerical efficiency. The considered model is also applied to analyze two different kinds of genuine COVID 19 data sets. We show that it outperforms other well-known models defined with the same baseline distribution, proving its high level of adaptability in the context of data analysis.