Design and Implementation of Intelligent Truck Based on Azure Kinect

In recent years, due to the impact of COVID-19, the market prospect of non-contact handling has improved and the development potential is huge. This paper designs an intelligent truck based on Azure Kinect, which can save manpower and improve efficiency, and greatly reduce the infection risk of medical staff and community workers. The target object is visually recognized by Azure Kinect to obtain the center of mass of the target, and the GPS and Kalman filter are used to achieve accurate positioning. The 4-DOF robot arm is selected to grasp and transport the target object, so as to complete the non-contact handling work. In this paper, different shapes of objects are tested. The experiment shows that the system can accurately complete the positioning function, and the accuracy rate is 95.56%. The target object recognition is combined with the depth information to determine the distance, and the spatial coordinates of the object centroid are obtained in real time. The accuracy rate can reach 94.48%, and the target objects of different shapes can be recognized. When the target object is grasped by the robot arm, it can be grasped accurately according to the depth information, and the grasping rate reaches 92.67%. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Research on Chest X-Ray Image Diagnosis of Covid-19 Based on Improved ResNet

With the outbreak of covid-19 in 2020, timely and effective diagnosis and treatment of each covid-19 patient is particularly important. This paper combines the advantages of deep learning in image recognition, takes RESNET as the basic network framework, and carries out the experiment of improving the residual structure on this basis. It is tested on the open source new coronal chest radiograph data set, and the accuracy rate is 82.3%. Through a series of experiments, the training model has the advantages of good generalization, high accuracy and fast convergence. This paper proves the feasibility of the improved residual neural network in the diagnosis of covid-19. © 2023 SPIE.

Bayesian optimization for artificial neural networks: application to Covid-19 image classification

Training a Convolutional Neural Network (CNN) is a difficult task, especially for deep architectures that estimate a large number of parameters. Advanced optimization algorithms should be used. Indeed, it is one of the most important steps to reduce the error between the ground truth and the model prediction. In this sense, many methods have been proposed to solve the optimization problems. In general, regularization, more specifically, non-smooth regularization, can be used in order to build sparse networks, which make the optimization task difficult. The main aim is to develop a novel optimizer based on Bayesian framework. Promising results are obtained when our optimizer is applied on classification of Covid-19 images. By using the proposed approach, an accuracy rate equal to 94% is obtained surpasses all the competing optimizers that do not exceed an accuracy rate of 86%, and 84% for standard Deep Learning optimizers. © 2022 IEEE.

Facemask detection using Deep Learning

COVID-19 was raised in the year 2020 which became more dangerous to society. According to the medical results, 100 million confirmed cases and 6 million deaths. This virus became an obstacle to gathering people in public places. This virus has spread all over the world. So, the Government has implemented a facemask policy to prevent the hazardous virus. It is a very difficult task to observe manually in crowded places. Most people are not wearing facemasks properly in public a place which causes the increase of the virus. So, the proposed model will detect the face mask whether the people are wearing it or not. By using, the HAAR-CASCADE technique we can able to detect whether the people are wearing the mask or not. By using this algorithm, we can able to prevent affecting of the virus to the person. This algorithm works effectively for detecting facemasks. The system compares faces with masks and faces without the mask. If people are not wearing a mask, the system detects through the camera and alerts by the alarm sound. The experiment results show the proposed technique achieves a 95% accuracy rate. © 2023 IEEE.

Detection of Pneumonia by Binary Image Classification Using Hybrid Neural Networks

Pneumonia is a more contagious virus with worldwide health implications. If positive cases are detected early enough, spread of the pandemic sickness can be slowed. Pneumonia illness estimation is useful for identifying patients who are at risk of developing health problems. So, the conventional method like PCR kits used to detect the covid patients lead to an increase in pneumonia cases as it failed to detect at the earliest. A polymerase chain reaction (PCR) test will be performed right away on the blood or sputum to quickly identify the DNA of the bacteria that cause pneumonia. With the help of CXR images, the pneumonia is diagnosed with a high accuracy rate utilizing the HNN (Hybrid Neural Network) method. Thus, isolating them at the earlier stage and preventing the spread of disease. © 2022 IEEE.

COVID-19 Detection in the Images of Chest CT Scan Using K-NN in Comparison with NB Classifier to Improve the Accuracy

This chapter is about the improvisation in the accuracy in COVID-19 detection using chest CT-scan images through K-Nearest Neighbour (K-NN) compared with Naive-Bayes (NB) classifier. The sample size considered for this detection is 20, for group 1 and 2, where G-power is 0.8. The value of alpha and beta was 0.05 and 0.2 along with a confidence interval at 95%. The K-NN classifier has achieved 95.297% of higher accuracy rate when compared with Naive Bayes classifier 92.087%. The results obtained were considered to be error-free since it was having the significance value of 0.036 (p < 0.05). Therefore, in this work K-Nearest Neighbor has performed significantly better than Naive Bayes algorithm in detection of COVID-19. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Turnstile Access based on Facial Recognition and Vaccine Passport Verification

This paper aims to provide a system ensuring turnstile access based on facial recognition and vaccine passport verification in order to enable touch-free entrance to buildings, universities, offices, etc. The algorithm of the proposed method is comprised of two essential parts: YOLO algorithm for face detection and CNN for face recognition. After successful user authentication, there are two important criteria that should be met for granting access to the person: Person should not be an active COVID-19 patient and Person should have a valid vaccine passport. The proposed method results 95.57% accuracy rate for face detection with YOLO algorithm and 70% for face recognition with CNN. © 2022 IEEE.

Application Foot Kick Classification in Taekwondo with Inertia Sensor and Machine Learning

Taekwondo is a sport that is quite popular in Indonesia. This can be seen from the number of taekwondo competitions held in Indonesia and the many achievements that Indonesia has in the Taekwondo sport. However, the emergence of the Covid-19 pandemic impacted the sport of taekwondo, especially in the implementation of the taekwondo competition. This is because the government limits all crowding activities so that activities are ultimately carried out online. This also applies to taekwondo competitions which are finally held online. Seeing this, a device was made that can classify the types of foot kick movements expected to assist the judges in making judgments when conducting taekwondo competitions. This device can classify foot kick foot and send the classification results using a smartphone so that the results can be seen directly. In this study, we seek for an appropriate feature extraction and machine learning technique to incorporate into the device to build a device that can categorize Taekwondo kicks. It trains several statistical feature extraction and machine learning methods. The best classifier for application is K-Nearest Neighbor for the right foot and Support Vector Machine for the left foot using kurtosis feature extraction. For the right foot, the results of the device testing on subject 1 resulted in an accuracy rate of 88.33%, on subject 2 of 68.33%, and on subject 3 of 73.66%. Meanwhile for the left foot, testing result on subject 1 resulted in an accuracy rate of 81.6%, on subject 2 of 60%, and on subject 3 of 73%. The existence of this device can be an example of implementing the use of human activity recognition in the field of sports. © 2022 IEEE.

Sentiment Analysis of Public on Social Media about Covid-19 origin theory using Machine Learning

Covid-19 has been found in Wuhan, China, for approximately a year and a half ago, and the virus's origin remains a mystery. However, it has been in the news in recent weeks, with reports suggesting that an infectious disease was spilled in a Chinese laboratory, which was previously refuted by a hoax in the area. In this research paper, we have presented a model where there will be a sentimental analysis based on users' comments on social media about the origin of corona virus. Nowadays most people express their feelings and the truth around them and many lies on social media. And we are taking this opportunity to do a sentimental analysis of the true, false, and confusing feelings that people have expressed on social media about the origin of corona virus. We used 20000 data (comments) taken from corona virus-related popular Facebook news posts. In order to achieve the maximum results, we used five distinct machine learning classifiers, and our support vector machine and logistic regression model outscored them all. The support vector model had a testing accuracy rate of 83.73 %, whereas logistic regression had an accuracy rate of 81.39 %. The important thing about our research is that at the end of the whole work, thousands of people's personal feelings, truths, hesitations, and confusion come together to know a strong possibility about the origin of the corona virus. © 2022 IEEE.

An Improved EfficientNet Model and its Applications in Pneumonia Image Classification

Since the outburst of COVID-19, the medical system has been facing great challenges due to the explosive growth in detection and treatment needs within a short period. To improve the working efficiency of doctors, an improved EfficientNet model of Convolutional Neural Network (CNN) was proposed and applied for the diagnosis of pneumonia cases and the classification of relevant images in the present study. First, the acquired images of pneumonia cases were divided to determine the zones with target features, and image size was limited to improve the training speed of the network. Meanwhile, reinforcement learning was performed to the input dataset to further improve the training effect of the model. Second, the preprocessed images were inputted into the improved EfficientNet-B4 model. The depth and width of the model, as well as the resolution of the input images, were determined by optimizing the combination coefficient. On this basis, the model was scaled, and then its ability in extracting the features of deep-layer images was strengthened by introducing the attention mechanism. Third, the learning rate was adjusted by using the Adaptive Momentum (ADAM), and the training efficiency of the model was accelerated. Finally, the test set was inputted into the trained model. Results demonstrate that the improved model could detect 98% of patients with pneumonia and 97% of patients without pneumonia. The accuracy rate, precision rate, and sensitivity of the model were generally improved. Lastly, the training and test results of VGGNet, SqueezeNet-Elus, SqueezeNet-Relu, and the improved EfficientNet-B4 models were compared and evaluated. The improved EfficientNet-B4 model achieved the highest comprehensive accuracy rate, reaching 92.95%. The proposed method provides some references to the application of the CNN model in image classification and recognition. © 2022 School of Science, IHU. All Rights Reserved.

Machine Learning and Deep Transfer Learning approaches were used to create a Face Mask Identification model for COVID-19

COVID-19 pandemic has led to an international health emergency the WHO considers wearing a face mask an appropriate form of public health protection. This work will describe a face mask identification model that incorporates both deep and traditional machine learning techniques. Parts of the suggested model can be divided into two. Using Resnet50, the initial part of the system is set up for feature extraction. The second component classifies face masks using decision trees, support vector machines (SVMs), and the ensemble approach. The research will focus on three face-masked datasets. The Real-World Masked Face Dataset Includes three datasets: real-world masked faces, simulated faces, and wild faces (LFW). 99.64% of RMFD's SVM classifier is accurate throughout testing.. It achieved a 99.49% accuracy rate in SMFD and a 100% accuracy rate in LFW. © 2022 IEEE.

Automatic Detection of Dental Lesions Based on Deep Learning

Objective Since the outbreak of COVID-19, many hospitals have become overloaded with patients seeking examination, resulting in an imbalance between medical staff and patients. These high concentrations of people in hospital settings not only aggravate the risk of cross-infection among patients, but also stall the public medical system. Consequently, mild and chronic conditions cannot be treated effectively, and eventually develop into serious diseases. Therefore, the use of deep learning to accurately and efficiently analyze X-ray images for diagnostic purposes is crucial in alleviating the pressure on medical institutions during epidemics. The method developed in this study accurately detects dental X-ray lesions, thus enabling patients to self-diagnose dental conditions. Methods The method proposed in this study employs the YOLOV5 algorithm to detect lesion areas on digital X-ray images and optimize the network model's parameters. When hospitals and medical professionals collect and label training data, they use image normalization to enhance the images. Consequently, in combination with the network environment, parameters were adjusted into four modules in the YOLOV5 algorithm. In the Input module, Mosaic data enhancement and adaptive anchor box algorithms are used to generate the initial box. The focus component was added to the Backbone module, and a CSP structure was implemented to determine the image features. When the obtained image features are input into the Backbone module, the FPN and PAN structures are used to realize feature fusion. Subsequently, GIOU_Loss function is applied to the Head moudule, and NMS non-maximum suppression is used to generate a regression of results. Results and Discussions The proposed YOLOV5-based neural network yields satisfactory training and testing results. The training algorithm produced a recall rate of 95%, accuracy rate of 95%, and F1 score of 96%. All evaluation criteria are higher than those of the target detection algorithms of SSD and Faster-RCNN (Table 1). The network converges to smoothness after loss is reduced in the training process (Fig. 6), which proves that the network successfully learns the necessary features. Thus, the difference between predicted and real values is very small, which indicates good model performance. The mAP value of network training is 0.985 (Fig. 7), which proves that the network training meets the research requirements. Finally, an observation of the visualized thermodynamic diagram reveals that the network's region of interest matches the target detection region (Fig. 8). Conclusions This study proposes the use of the YOLOV5 algorithm for detecting lesions in dental X-ray images, training and testing on the dataset, modifying the network's nominal batch size, selecting an appropriate optimizer, adjusting the weight parameters, and modifying the learning rate attenuation strategy. The model's training results were compared with those of algorithms used in previous studies. Finally, the effect of feature extraction was analyzed after the thermodynamic diagram was visualized. The experimental results show that the algorithm model detects lesion areas with an accuracy rate of more than 95%, making it an effective autonomous diagnostic tool for patients. © 2022 Science Press. All rights reserved.

New Normal Regulation with Face Recognition Technology Using AttendX for Student Attendance Algorithm

In this new normal era, the community is directed to minimize activities and meet other people or goods. This is aimed at avoiding an increase in the number of the spread of the Covid-19 virus. Following the government directive, a study was conducted to facilitate one of the activities of students and educators, namely online attendance called AttendX. The way this system works is effortless. By just registering, the system can verify faces that have been registered for attendance. This application is designed with modern facial recognition technology that has developed rapidly, with this sophistication can make it easier to detect faces in structured parts such as the forehead, cheekbones, eyes, and even the nose. In compliance with the new normal regulations, the AttendX platform is designed to detect faces if the user is wearing a mask. Because of the convenience of online attendance using faces, this AttendX study resulted in a peak implementation with an accuracy rate of 99%. This shows that AttendX can be used to perform student attendance well. © 2022 IEEE.

COVID-19 Classification from Chest X-rays Based on Attention and Knowledge Distillation

The Coronavirus Disease 2019 (COVID-19) is the pandemic that has had the greatest impact on world economic development in recent years. Early detection is critical to identify patients with COVID-19, chest x-ray is used for early detection is a rapid, extensive and cost-effective method. The existing technology use deep learning methods, and have achieved very good results. However, the training time of deep learning method is long, and the model size makes it difficult to deploy on hardware system. In this work, we have proposed an attention-based ResNet50v2 network, and taken the network as the teacher network to transfer the knowledge to the student network by knowledge distillation. Thus, the student network has higher accuracy and sensitivity to the positive samples of COVID-19 under the condition of low model parameters, high training speed. The experimental results show that our network of teacher and student have achieved 100% accuracy and sensitivity in both COVID-19 and Normal binary classification. In addition, the accuracy rate of teacher network is 98.20%, the sensitivity is 99.58%, the accuracy rate of student network is 97.68%, the sensitivity is 99.17% in the COVID-19, Viral pneumonia and Normal multiple classification, and the parameters of the student network are only 0.269M. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Global Vaccination Progress During COVID-19 Outbreak based on Data mining

In the context of the COVID-19 epidemic, the development and popularization of vaccines have effectively alleviated people's panic. Twitter, as one of the world's largest social platforms, promptly reflects the trend of emotional changes in screen names. Currently, vaccines such as Pfizer, Sputnik, and Moderna have successfully made a large number of people gain high immunity against the COVID-19 virus. However, a few cases of death due to vaccines have caused some people to question and worry about the safety of vaccines. A comprehensive understanding of progress of vaccine popularization is conducive making wiser decisions and calming people's panic. Since the large number of Tweets updated daily on Twitter can represent attitudes of netizens on the progress of vaccination, we used Bert model to predict and classify emotion categories to which different Tweets belong, with an accuracy rate of 80%. It is found that with the promotion of vaccination, fluctuation of netizen sentiment for vaccine progress has gradually decreased. Tweets with neutral sentiment still account for a majority of proportion, and the proportion of tweets with positive sentiment has gradually increased. In addition, we used LSTM model to predict the growth of cases with MSE less than 0.001. The growth of new cases in most countries gradually decreased to less than 10, 000 people per day after June. Therefore, most vaccines have made significant progress in both winning public support and preventing COVID-19 infection. © VDE VERLAG GMBH · Berlin · Offenbach.

Predicting the mental health of rural Bangladeshi children in coronavirus disease 2019

The novel coronavirus disease 2019 (COVID-19) current pandemic is a worldwide health emergency like no other. It is not the only COVID-19 infection in infants, children, and adolescents that is causing concern among their families and professionals;there are also other serious issues that must be carefully detected and addressed. Major things are identified due to COVID-19, some elements are affecting children’s healthcare in direct or indirect ways, affecting them not just from a medical standpoint but also from social, psychological, economic, and educational perspectives. All these factors may have affected children’s mental development, particularly in rural settings. As Bangladesh faces a major challenge such as a lack of public mental health facilities, especially in rural areas. So, we discovered a method to predict the mental development condition of rural children that they are facing at this time of COVID-19 using machine learning technology. This research work can predict whether a rural child is mentally developed or mentally hampered in Bangladesh and this prediction gives nice feedback. © 2022 Institute of Advanced Engineering and Science. All rights reserved.

Covid-19 Disease Detection with Improved Deep Learning Algorithms on X-Ray Data

The COVID-19 pandemic has brought human life to a startling halt around the world from the moment it emerged and took thousands of lives. The health system has come to the point of collapse, many people in the world have died from being infected, and many people who have survived the disease have had permanent lung damage with the spread of COVID-19 in 212 countries and regions. In this study, an answer is sought to diagnose the disease-causing virus through Artificial Intelligence Algorithms. The aim of the study is to accelerate the diagnosis and treatment process of COVID-19 disease. Enhancements were made using Deep Learning methods, including CNN, VGG16, DenseNet121, and ResNet50. For this study, the disease was detected by using X-Ray images of patients with and without COVID-19 disease, and then it was evaluated how to increase the accuracy rate with the limited available data. To increase the accuracy rate, the results of data augmentation on the image data were examined and the time complexity of the algorithms with different layers was evaluated. As a result of the study, it was seen that data augmentation increased the performance rate in all algorithms and the ResNet50 algorithm was more successful than other algorithms. © 2022 IEEE.

The Impact of COVID-19 Pandemic and Consumer Purchase Behaviour on the Automotive Industry

The outbreak of COVID-19 has forced countries to lock borders to prevent the spread of infection. It broadly affects numerous industries and economies globally termed 'Coronanomics.' Subsequently, many corporate performances have suffered during this time, leading to dramatic changes in business activities and consumer behaviour. The pandemic outbreak has disrupted and challenged many industries. Hence, this study explores how the pandemic affected in automotive industry and factors influencing consumers' purchasing intention. Discuss the major aspects that motivate vehicle purchase after the pandemic outbreak and how the pandemic's negative effect partially reduced vehicle purchases' propensity and factors that could potentially affect the new car purchase decision. This project methodology adopted the CRISP-DM framework using power BI for data visualisation and R programming in implementation. This project focused on comparing traditional machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Neural Network (NeuralNet, NNet), and deep learning algorithms: Multilayer Perceptron (MLP) to predict how likely it a customer will purchase a vehicle after the pandemic. Establish the models using a confusion matrix, and evaluate the accuracy rate and low misclassification rate. The most suitable algorithm with a higher accuracy rate and lower error rate will be chosen in the final model comparison and evaluation section. Furthermore, the NeuralNet model, with its accuracy of 99.97%, is the best fit model to predict vehicle purchase intention. © 2022 IEEE.

Covid19 Vaccination and Lifestyle Counsel using Machine Learning algorithms

Machine Learning is a predominant area in Artificial Intelligence. It gets the ability to make predictions by learning the past observed values and information. This learning process is Machine Learning. A large amount of data is accessed and processed to gain more accurate results. Nowadays anyone around the world can use any Machine Learning algorithm to obtain competitive and accurate results. The main objective of this project is to recommend the Life style modification of the people after covid19 and to predict whether the particular person needs for the vaccination intake or not by accessing thousands of patient details. Hence the accuracy rate is very high compared to other predicting processes. These techniques are used to predict the current health conditions of the people. © 2022 IEEE.

A Novel System for Prediction of Facemask and maintaining Social Distance in COVID

SARS stands for Severe Acute Respiratory Syndrome, which is also known as COVID-19. Covid is an uncommonly overwhelming contamination that spreads through breathing dots from corrupted individuals talking, sneezing, or hacking. At whatever point you come into near contact with a polluted person or contact a contaminated surface or thing, the disease can spread rapidly. There's clearly no checking pro open to battle COVID-19, and the foremost sublime strategy for ensuring oneself against an sickness is to remain lost from it. Wearing a facemask that covers the nose and mouth in an open reach and washing hands routinely utilizing something like 70% alcohol based sanitizers are prescribed to diminish viral degradation. Significant Learning advancement has shown its capacity to see and arrange things by analyzing photographs. A collected picture data includes 20,000 photos that were consistently cropped in 224×224 pixels and had a 97 percent accuracy rate during the model's training. Utilizing Python and Open CV utilizing Tensor Stream, the developed system sees individuals wearing or not wearing a facemask and chooses the genuine separate between them. The detected informational stored in cloud. It raises an alert when it recognizes persons who aren't wearing a mask and snaps images of their faces. It is unconcerned with physical distance. This study will aid in preventing the virus from spreading and in preventing people from contracting it. © 2022 IEEE.