A Dynamic-Static Dual Input Deep Neural Network Algorithm for Diagnosing COVID-19 by Cough

The COVID-19 (corona virus disease 2019) has caused serious impacts worldwide. Many scholars have done a lot of research on the prevention and control of the epidemic. The diagnosis of COVID-19 by cough is non-contact, low-cost, and easy-access, however, such research is still relatively scarce in China. Mel frequency cepstral coefficients (MFCC) feature can only represent the static sound feature, while the first-order differential MFCC feature can also reflect the dynamic feature of sound. In order to better prevent and treat COVID-19, the paper proposes a dynamic-static dual input deep neural network algorithm for diagnosing COVID-19 by cough. Based on Coswara dataset, cough audio is clipped, MFCC and first-order differential MFCC features are extracted, and a dynamic and static feature dual-input neural network model is trained. The model adopts a statistic pooling layer so that different length of MFCC features can be input. The experiment results show the proposed algorithm can significantly improve the recognition accuracy, recall rate, specificity, and F1-score compared with the existing models. © 2023 Chinese Institute of Electronics. All rights reserved.

A Comprehensive Review of Sound-Based Modalities for Automatic COVID-19 Detection using Deep Learning-Based Techniques

The World Health Organization has labeled the novel coronavirus illness (COVID-19) a pandemic since March 2020. It's a new viral infection with a respiratory tropism that could lead to atypical pneumonia. Thus, according to experts, early detection of the positive cases with people infected by the COVID-19 virus is highly needed. In this manner, patients will be segregated from other individuals, and the infection will not spread. As a result, developing early detection and diagnosis procedures to enable a speedy treatment process and stop the transmission of the virus has become a focus of research. Alternative early-screening approaches have become necessary due to the time-consuming nature of the current testing methodology such as Reverse transcription polymerase chain reaction (RT-PCR) test. The methods for detecting COVID-19 using deep learning (DL) algorithms using sound modality, which have become an active research area in recent years, have been thoroughly reviewed in this work. Although the majority of the newly proposed methods are based on medical images (i.e. X-ray and CT scans), we show in this comprehensive survey that the sound modality can be a good alternative to these methods, providing faster and easiest way to create a database with a high performance. We also present the most popular sound databases proposed for COVID-19 detection. © 2022 IEEE.

Embedded system vehicle based on multi-sensor fusion

As intelligent driving vehicles came out of concept into people’s life, the combination of safe driving and artificial intelligence becomes the new direction of future transportation development. Autonomous driving technology is developing based on control algorithms and model recognitions. In this paper, a cloud-based interconnected multi-sensor fusion autonomous vehicle system is proposed that uses deep learning (YOLOv4) and improved ORB algorithms to identify pedestrians, vehicles, and various traffic signs. A cloud-based interactive system is built to enable vehicle owners to master the situation of their vehicles at any time. In order to meet multiple application of automatic driving vehicles, the environment perception technology of multi-sensor fusion processing has broadened the uses of automatic driving vehicles by being equipped with automatic speech recognition (ASR), vehicle following mode and road patrol mode. These functions enable automatic driving to be used in applications such as agricultural irrigation, road firefighting and contactless delivery under new coronavirus outbreaks. Finally, using the embedded system equipment, an intelligent car was built for experimental verification, and the overall recognition accuracy of the system was over 96%. Author

Improved method for COVID-19 Classification of Complex-Architecture CNN from Chest CT volumes using Orthogonal Ensemble Networks

This paper introduces the improved method for the COVID-19 classification based on computed tomography (CT) volumes using a combination of a complex-architecture convolutional neural network (CNN) and orthogonal ensemble networks (OEN). The novel coronavirus disease reported in 2019 (COVID-19) is still spreading worldwide. Early and accurate diagnosis of COVID-19 is required in such a situation, and the CT scan is an essential examination. Various computer-aided diagnosis (CAD) methods have been developed to assist and accelerate doctors' diagnoses. Although one of the effective methods is ensemble learning, existing methods combine some major models which do not specialize in COVID-19. In this study, we attempted to improve the performance of a CNN for the COVID-19 classification based on chest CT volumes. The CNN model specializes in feature extraction from anisotropic chest CT volumes. We adopt the OEN, an ensemble learning method considering inter-model diversity, to boost its feature extraction ability. For the experiment, We used chest CT volumes of 1283 cases acquired in multiple medical institutions in Japan. The classification result on 257 test cases indicated that the combination could improve the classification performance. © 2023 SPIE.

Study of Clinical Profile and Outcome among COVID-19 Patients during Hospitalization in a Tertiary Care Hospital in Central India

Background: The COVID-19 outbreak in 2019 has presented in the form of pneumonia of unknown etiology in Wuhan. The complete clinical profile including the prevalence of different clinical symptoms of COVID-19 infection among Indian patients who develop a severe disease is largely unknown. This study is aimed to provide a detailed clinical characterization of the cohort of patients who visited our institute with signs and symptoms of COVID-19. Material(s) and Method(s): This was for inpatient hospital (inpatient) based prospective cohort study involving 520 COVID-19 patients admitted to the hospital. The adverse outcome included death and mechanical ventilation. Result(s): Total 520 participants enrolled in the study, (6.9%) participants died, (8.3%) participants required ICU and (5.5%) participants required mechanical ventilation. only signs and symptoms suggestive of severe respiratory system involvement or widespread infection were associated with adverse outcomes, T presence of dyspnoea, cyanosis and hypoxia. The most common chronic disease among patients with adverse outcomes were diabetes, hypertension and pre-existing respiratory disease, personal habit both smoking, and alcoholism was also associated with adverse clinical outcome. Conclusion(s): The adverse clinical outcome among COVID-19 patients is determined by several factors including advanced age, multi-morbidities, and the presence of severe respiratory symptoms.Copyright © 2023, Dr Yashwant Research Labs Pvt Ltd. All rights reserved.

COVID-19 Detection by Using Handcrafted Features Extracted From Chest CT-Scan Images

Coronavirus illness, which was initially diagnosed in 2019 but has propagated rapidly across the globe, has led to increased fatalities. According to professional physicians who examined chest CT scans, COVID-19 behaves differently than various viral cases of pneumonia. Even though the illness only recently emerged, a number of research investigations have been performed wherein the progression of the disease impacts mostly on the lungs are identified using thoracic CT scans. In this work, automated identification of COVID-19 is used by using machine learning classifier trained on more than 1000+ lung CT Scan images. As a result, immediate diagnosis of COVID-19, which is very much necessary in the opinion of healthcare specialists, is feasible. To improve detection accuracy, the feature extraction method are applied on regions of interests. Feature extraction approaches, including Discrete Wavelet Transform (DWT), Grey Level Cooccurrence Matrix (GLCM), Grey Level Run Length Matrix (GLRLM), and Grey-Level Size Zone Matrix (GLSZM) algorithms are used. Then the classification by using Support Vector Machines (SVM) is used. The classification accuracy is assessed by using precision, specificity, accuracy, sensitivity and F-score measures. Among all feature extraction methods, the GLCM approach has given the optimum classification accuracy of 95.6%. . © 2023 IEEE.

HarDNet and Dual-Code Attention Mechanism based model for medical images segmentation

During the formation of medical images, they are easily disturbed by factors such as acquisition devices and tissue backgrounds, causing problems such as blurred image backgrounds and difficulty in differentiation. In this paper, we combine the HarDNet module and the multi-coding attention mechanism module to optimize the two stages of encoding and decoding to improve the model segmentation performance. In the encoding stage, the HarDNet module extracts medical image feature information to improve the segmentation network operation speed. In the decoding stage, the multi-coding attention module is used to extract both the position feature information and channel feature information of the image to improve the model segmentation effect. Finally, to improve the segmentation accuracy of small targets, the use of Cross Entropy and Dice combination function is proposed as the loss function of this algorithm. The algorithm has experimented on three different types of medical datasets, Kvasir-SEG, ISIC2018, and COVID-19CT. The values of JS were 0.7189, 0.7702, 0.9895, ACC were 0.8964, 0.9491, 0.9965, SENS were 0.7634, 0.8204, 0.9976, PRE were 0.9214, 0.9504, 0.9931. The experimental results showed that the model proposed in this paper achieved excellent segmentation results in all the above evaluation indexes, which can effectively assist doctors to diagnose related diseases quickly and improve the speed of diagnosis and patients’quality of life. Author

Using the SIR Model to Analyze the Epidemiological Situation in Kazakhstan and Neighboring Countries

In this paper, we study the epidemic situation in Kazakhstan and neighboring countries, taking into account territorial features in emergency situations. As you know, the excessive concentration of the population in large cities and the transition to a world without borders created ideal conditions for a global pandemic. The article also provides the results of a detailed analysis of the solution approaches to modeling the development of epidemics by types of models (basic SIR model, modified SEIR models) and the practical application of the SIR model using an example (Kazakhstan, Russia, Kyrgyzstan, Uzbekistan and other neighboring countries). The obtained processing results are based on statistical data from open sources on the development of the COVID-19 epidemic. The result obtained is a general solution of the SIR-model of the spread of the epidemic according to the fourth-order Runge-Kutta method. The parameters β, γ, which are indicators of infection, recovery, respectively, were calculated using data at the initial phase of the Covid 2019 epidemic. An analysis of anti-epidemic measures in neighboring countries is given. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

A Hybrid Deep Fused Learning Approach to Segregate Infectious Diseases

Humankind is facing another deadliest pandemic of all times in history, caused by COVID-19. Apart from this challenging pandemic, World Health Organization (WHO) considers tuberculosis (TB) as a preeminent infectious disease due to its high infection rate. Generally, both TB and COVID-19 severely affect the lungs, thus hardening the job of medical practitioners who can often misidentify these diseases in the current situation. Therefore, the time of need calls for an immediate and meticulous automatic diagnostic tool that can accurately discriminate both diseases. As one of the preliminary smart health systems that examine three clinical states (COVID-19, TB, and normal cases), this study proposes an amalgam of image filtering, data-augmentation technique, transfer learning-based approach, and advanced deep-learning classifiers to effectively segregate these diseases. It first employed a generative adversarial network (GAN) and Crimmins speckle removal filter on X-ray images to overcome the issue of limited data and noise. Each pre-processed image is then converted into red, green, and blue (RGB) and Commission Internationale de l'Elcairage (CIE) color spaces from which deep fused features are formed by extracting relevant features using DenseNet121 and ResNet50. Each feature extractor extracts 1000 most useful features which are then fused and finally fed to two variants of recurrent neural network (RNN) classifiers for precise discrimination of three-clinical states. Comparative analysis showed that the proposed Bi-directional long-short-term-memory (Bi-LSTM) model dominated the long-short-term-memory (LSTM) network by attaining an overall accuracy of 98.22% for the three-class classification task, whereas LSTM hardly achieved 94.22% accuracy on the test dataset.

Analyzing COVID-Related Social Discourse on Twitter using Emotion, Sentiment, Political Bias, Stance, Veracity and Conspiracy Theories

Online misinformation has become a major concern in recent years, and it has been further emphasized during the COVID-19 pandemic. Social media platforms, such as Twitter, can be serious vectors of misinformation online. In order to better understand the spread of these fake-news, lies, deceptions, and rumours, we analyze the correlations between the following textual features in tweets: emotion, sentiment, political bias, stance, veracity and conspiracy theories. We train several transformer-based classifiers from multiple datasets to detect these textual features and identify potential correlations using conditional distributions of the labels. Our results show that the online discourse regarding some topics, such as COVID-19 regulations or conspiracy theories, is highly controversial and reflects the actual U.S. political landscape. © 2023 ACM.

Tulsi Leaf Disease Detection using CNN

Since the start of the covid 19 pandemic, a wide range of medications have been produced and are currently being utilized to treat the disease. Tulsi, in addition to all of the chemical-based medications, is an herbal therapy that is particularly effective in the treatment of this ailment. Tulsi has been used to heal ailments and infections for millennia, particularly in India. Because we use tulsi for medicinal purposes, it's vital to monitor its health in order to reap the full benefits of its herbal properties. Plant diseases harm the health and growth of the plant. Disease detection in plants is crucial so that it can be treated before it spreads throughout the plant. To detect illnesses in tulsi leaves, we propose employing a model based on convolution neural networks. Image processing and CNN are widely employed. The prepared model extracts the image's key features and categorizes it into different disorders. The model has a 75 percent accuracy rate. © 2022 IEEE.

An Investigation of Deep-Learned Features for Classifying Radiographic Images of COVID-19

In this proposal, a study based on deep-learned features via transfer learning was developed to obtain a set of features and techniques for pattern recognition in the context of COVID-19 images. The proposal was based on the ResNet-50, DenseNet-201 and EfficientNet-b0 deep-learning models. In this work, the chosen layer for analysis was the avg pool layer from each model, with 2048 features from the ResNet-50, 1920 features from the DenseNet0201 and 1280 obtained features from the EfficientNet-b0. The most relevant descriptors were defined for the classification process, applying the ReliefF algorithm and two classification strategies: individually applied classifiers and employed an ensemble of classifiers using the score-level fusion approach. Thus, the two best combinations were identified, both using the DenseNet-201 model with the same subset of features. The first combination was defined via the SMO classifier (accuracy of 98.38%) and the second via the ensemble strategy (accuracy of 97.89%). The feature subset was composed of only 210 descriptors, representing only 10% of the original set. The strategies and information presented here are relevant contributions for the specialists interested in the study and development of computer-aided diagnosis in COVID-19 images. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

FaST-Net: Face Style Self-Transfer Network for Masked Face Inpainting

During the COVID-19 coronavirus epidemic, people usually wear masks to prevent the spread of the virus, which has become a major obstacle when we use face-based computer vision techniques such as face recognition and face detection. So masked face inpainting technique is desired. Actually, the distribution of face features is strongly correlated with each other, but existing inpainting methods typically ignore the relationship between face feature distributions. To address this issue, in this paper, we first show that the face image inpainting task can be seen as a distribution alignment between face features in damaged and valid regions, and style transfer is a distribution alignment process. Based on this theory, we propose a novel face inpainting model considering the probability distribution between face features, namely Face Style Self-Transfer Network (FaST-Net). Through the proposed style self-transfer mechanism, FaST-Net can align the style distribution of features in the inpainting region with the style distribution of features in the valid region of a face. Ablation studies have validated the effectiveness of FaST-Net, and experimental results on two popular human face datasets (CelebA and VGGFace) exhibit its superior performance compared with existing state-of-the-art methods. © 2023 SPIE.

An approach for Face Detection and Face Recognition using OpenCV and Face Recognition Libraries in Python

With the extraordinary growth in images and video data sets, there is a mind-boggling want for programmed understanding and evaluation of data with the assistance of smart frameworks, since physically it is a long way off. Individuals, unlike robots, have a limited capacity to distinguish unexpected expressions. As a result, the programmed face proximity frame- work is important in face identification, appearance recognition, head-present evaluation, human-PC cooperation, and other applications. Software that uses facial recognition for face detection and identification is regarded as biometric. This study converts the mathematical aspects of a person's face into a face print, which is then stored in a database to verify an individual's identification. A deep learning system compares a digital image or an image taken quickly to a previously stored image(which is saved in the database). The face has a significant function in interpersonal communication for identifying oneself. Face recognition technology determines the size and placement of a human face in a digital picture. Facial recognition software has a wide range of uses in the consumer market and in the security and surveillance sectors. The COVID pandemic has brought facial recognition into greater focus lately than ever before. Face detection and recognition play a vital part in security systems that people need to interact with without making physical contact. The pattern of online exam proctoring is employing face detection and recognition. Facial recognition is used in the airline sector to enable rapid, accurate identification and verification at every stage of the passenger trip. In this research, we focused on image quality because it is the major drawback in existing algorithms and used OPEN CV, Face Recognition, and designed algorithms using libraries in python. This study discusses a method for facial recognition along with its implementation and applications. © 2023 IEEE.

A Hybrid Model of Deep Learning Features and Clinical Features for Severe Cases Predication of COVID-19

COVID-19 has spread around the world since 2019. Approximately 6.5% of COVID-19 a risk of developing severe disease with high mortality rate. To reduce the mortality rate and provide appropriate treatment, this research established an integrated models with to predict the clinical outcome of COVID-19 patients with clinical, deep learning and radiomics features. To obtain the optimal feature combination for prediction, 9 clinical features combination was selected from all available clinical factors after using LASSO, 18 deep learning features from U-Net architecture, and 9 radiomics features from segmentation result. A total of 213 COVID-19 patients and 335 non-COVID-19 patients from 5 hospitals were enrolled and used as training and test sample in this research. The proposed model obtained an accuracy, precision, recall, specificity, F1-score and ROC curve of 0.971, 0.943, 0.937, 0.974, 0.941 and 0.979, respectively, which exceeds the related work using only clinical, deep learning or radiomics factors. © 2023 SPIE.

PQSCT: Pseudo-Siamese BERT for Concept Tagging With Both Questions and Solutions

The global outbreak of the new coronavirus epidemic has promoted the development of intelligent education and the utilization of online learning systems. In order to provide students with intelligent services such as cognitive diagnosis and personalized exercises recommendation, a fundamental task is the concept tagging for exercises, which extracts knowledge index structures and knowledge representations for exercises. Unfortunately, to the best of our knowledge, existing tagging approaches based on exercise content either ignore multiple components of exercises, or ignore that exercises may contain multiple concepts. To this end, in this paper, we present a study of concept tagging. First, we propose an improved pre-trained BERT for concept tagging with both questions and solutions (QSCT). Specifically, we design a question-solution prediction task and apply the BERT encoder to combine questions and solutions, ultimately obtaining the final exercise representation through feature augmentation. Then, to further explore the relationship between questions and solutions, we extend the QSCT to a pseudo-siamese BERT for concept tagging with both questions and solutions (PQSCT). We optimize the feature fusion strategy, which integrates five different vector features from local and global into the final exercise representation. Finally, we conduct extensive experiments on real-world datasets, which clearly demonstrate the effectiveness of our proposed models for concept tagging. IEEE

Less About Privacy: Revisiting a Survey about the German COVID-19 Contact Tracing App

The release of COVID-19 contact tracing apps was accompanied by a heated public debate with much focus on privacy concerns, e.g., possible government surveillance. Many papers studied people's intended behavior to research potential features and uptake of the apps. Studies in Germany conducted before the app's release, such as that by Häring et al., showed that privacy was an important factor in the intention to install the app. We conducted a follow-up study two months post-release to investigate the intention-behavior-gap, see how attitudes changed after the release, and capture reported behavior. Analyzing a quota sample (n=837) for Germany, we found that fewer participants mentioned privacy concerns post-release, whereas utility now plays a greater role. We provide further evidence that the results of intention-based studies should be handled with care when used for prediction purposes. © 2023 ACM.

Radiological Features on HRCT Associated with Poor Outcomes among COVID-19 Patients

Background: Ever since the beginning of the COVID-19 pandemic, physicians started investigating the clinical features and lab markers that can assist in predicting the outcome among hospitalized COVID-19 patients. Aim(s): This study aimed to investigate the association between initial chest CT scan findings and adverse outcomes of COVID-19. Material(s) and Method(s): This was a single centre;hospital (inpatient) based prospective cohort study involving 497 COVID-19 patients admitted to the hospital. The adverse outcome included death and mechanical ventilation. We collected data about 14 identifiable parameters available for the HRCT scan. Result(s): Among 14 studied parameters, only 8 features differed significantly among the patients who had favourable and unfavourable outcomes. These features included number of lobes of lungs involved (3 versus 5, p = 0.008), CT Severity score (16 versus 20, p = 0.004), air bronchogram (p=0.003), crazy paving (p=0.029), consolidation (p=0.021), and pleural effusion (p=0.026). We observed that high CT scores coupled with the diffuse distribution of lung lesions were responsible for poor prognosis in most patients. Conclusion(s): Several features of HRCT when combined can accurately predict adverse outcomes among participants and help in triaging the patient for admission in ICU.Copyright © 2023, Dr Yashwant Research Labs Pvt Ltd. All rights reserved.

CCTwins: A Weakly-Supervised Transformer-based Crowd Counting Method with Adaptive Scene Consistency Attention

Recently, crowd counting has attracted significant attention, particularly in the context of the COVID-19 pandemic, due to its ability to automatically provide accurate crowd numbers in images. To address the challenges of location-level labeling, several transformer-based crowd counting methods have been proposed with only count-level supervision. However, these methods directly use the transformer as an encoder without considering the uneven crowd distribution. To address this issue, we propose CCTwins, a novel transformer-based crowd counting method with only count-level supervision. Specifically, we introduce an adaptive scene consistency attention mechanism to enhance the transformer-based model Twins-SVT-L for feature extraction in crowded scenes. Additionally, we design a multi-level weakly-supervised loss function that generates estimated crowd numbers in a coarse-to-fine manner, making it more appropriate for weakly-supervised settings. Moreover, intermediate features supervised by count-level labels are utilized to fuse multi-scale features. Experimental results on four public datasets demonstrate that our proposed method outperforms the state-of-the-art weakly-supervised methods, achieving up to a 16.6% improvement in MAE and up to a 13.8% improvement in RMSE across all evaluation settings. Moreover, the proposed CCTwins obtains competitive counting performance, even when compared to the state-of-the-art fully-supervised methods. IEEE

Explainable AI for COVID-19 prognosis from early Chest X-ray and clinical data in the context of the COVID-CXR international hackathon

Although many AI-based scientific works regarding chest X-ray (CXR) interpretation focused on COVID-19 diagnosis, fewer papers focused on other relevant tasks, like severity estimation, deterioration, and prognosis. The same holds for explainable decisions to estimate COVID-19 prognosis as well. The international hackathon launched during Dubai Expo 2020, aimed at designing machine learning solutions to help physicians formulate COVID-19 patients' prognosis, was the occasion to develop a machine learning model capable of predicting such prognoses and justifying them through interpretable explanations. The large hackathon dataset comprised subjects characterized by their CXR and numerous clinical features collected during triage. To calculate the prognostic value, our model considered both patients' CXRs and clinical features. After automatic pre-processing to improve their quality, CXRs were processed by a Deep Learning model to estimate the lung compromise degree, which has been considered as an additional clinical feature. Original clinical parameters suffered from missing values that were adequately handled. We trained and evaluated multiple models to find the best one and fine-tune it before the inference process. Finally, we produced novel explanations, both visual and numerical, to justify the model predictions. Ultimately, our model processes a CXR and several clinical data to estimate a patient's prognosis related to the COVID-19 disease. It proved to be accurate and was ranked second in the final rankings with 75%, 73.9%, and 74.4% in sensitivity, specificity, and balanced accuracy, respectively. In terms of model explainability, it was ranked first since it was agreed to be the most interpretable by health professionals. © 2023 SPIE.