Research and Application of 5G Edge AI in Medical Industry

With the development of 5G and AI technology, the infectious virus detection framework system based on the combination of 5G MEC and medical sensors can effectively assist in the intelligent detection and control of influenza viruses such as COVID-19. Employing the edge computing and 5G+MEC model, the virus AI model is trained for the collected influenza virus data. Then the virus AI model can be used to evaluate the virus patients on the local edge computing service platform. Therefore, this paper introduces an algorithm and resource allocation, which uses 5G functions (especially, low latency, high bandwidth, wide connectivity, and other functions) to achieve local chest X-ray or CT scan images to detect COVID-19. Meanwhile, this paper also compares the computational efficiency of different algorithms in the 5G edge AI-based infectious virus detection framework, in this way to select the best algorithm and resource allocation. © 2022 IEEE.

Foreign Bodies Detector Based on DETR for High-Resolution X-Ray Images of Textiles

Foreign bodies (FBs) detection for X-ray images of textiles is a novel and challenging task. To solve the problem of poor performance of anchor-based detectors for FBs detection, we propose a feature-enhanced object detection framework with transformer (FE-DETR). Based on the split-attention of residual split-attention network (ResNeSt), we add convolutional block attention module (CBAM) between residual blocks and replace the $3\times $ 3 convolutional layer of the last residual block with deformable convolution network (DCN) to adapt FBs with different scales. Then, we propose a multiscale feature encoding (MSFE) module to solve the feature dispersion caused by deep convolution. Meanwhile, the transformer module is selected as the prediction head of the detector. During training, several heuristic strategies are used to further optimize the performance of FE-DETR. In addition, we construct a benchmark dataset for the textile FBs detection task. With end-to-end training, FE-DETR achieves higher performance than the baseline and mainstream state-of-the-art methods, with mean average precision (mAP) = 0.74, average precision (AP) = 0.992, average recall (AR) = 0.971, and $F1$ -score = 0.987. This article has been applied to the production line of medical protective clothing during the Corona Virus Disease 2019 (COVID-19) period and has yielded impressive results in actual production. © 1963-2012 IEEE.

A Data Mining Approach to Finding Face Mask from Bangladeshi News Channel

Face Mask Detection is currently a hot topic that has piqued the interest of researchers all over the world. Today, the entire world is dealing with the COVID-19 pandemic. To control the spread of the Coronavirus the most important task people need to do is use a mask. There is still a lot of research and study being done on COVID-19. Several studies have also shown that wearing a face mask significantly reduces the problem of viral transmission. In addition, a person wearing a face mask perceives a sense of protection. When we are at home, we take care of everything, but when we are in public places such as offices, malls, and colleges, it becomes more difficult to keep people safe. Machine Learning and Data Mining are a collection of technologies that provide effective solutions to complex problems in a variety of fields. We attempted to develop a face mask recognition system using machine learning in order to prevent the spread of the Coronavirus. This is a good system for detecting a face mask in news channel images and videos. It can recognize both Mask and No Mask faces. With the advancement of this system, it will be possible to detect whether or not a person is wearing a face mask. If the person is not wearing a face mask, it will display a message such as "No Mask,"otherwise it will display "Mask Detected." © 2022 IEEE.

COVID-19 Infection Forecasting using LSTM-based Model

COVID-19 has now become one of the most severe and acute diseases worldwide. Novel Coronavirus transmission is characterized by its high speed and large social population base, making novel Coronavirus detection very difficult. Therefore, automatic detection systems should be implemented as an option for rapid diagnosis. Automated disease detection frameworks help physicians diagnose diseases with accurate, consistent, and rapid results, and reduce ethics. In this paper, we propose a deep learning method based on long-term Memory (LSTM) for automatic diagnosis of COVID-19 in combination with the existing prediction model SEIR. © 2022 SPIE.

A Correct Face Mask Usage Detection Framework by AIoT

The COVID-19 pandemic, which affected over 400 million people worldwide and caused nearly 6 million deaths, has become a nightmare. Along with vaccination, self-testing, and physical distancing, wearing a well-fitted mask can help protect people by reducing the chance of spreading the virus. Unfortunately, researchers indicate that most people do not wear masks correctly, with their nose, mouth, or chin uncovered. This issue makes masks a useless tool against the virus. Recent studies have attempted to use deep learning technology to recognize wrong mask usage behavior. However, current solutions either tackle the mask/non-mask classification problem or require heavy computational resources that are infeasible for a computational-limited system. We focus on constructing a deep learning model that achieves high-performance results with low processing time to fill the gap in recent research. As a result, we propose a framework to identify mask behaviors in real-time benchmarked on a low-cost, credit-card-sized embedded system, Raspberry Pi 4. By leveraging transfer learning, with only 4–6 h of the training session on approximately 5,000 images, we achieve a model with accuracy ranging from 98 to 99% accuracy with the minimum of 0.1 s needed to process an image frame. Our proposed framework enables organizations and schools to implement cost-effective correct face mask usage detection on constrained devices. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Internal Virus Detection Framework Based on IoT Semantic Interoperability

Since the outbreak of the COVID-19 pandemic, indoor air quality has become increasingly important. The interdisciplinary grouping of academic majors focused on the pursuit of solutions that identify or prevent the airborne transmission and inhalation, initially of Coronavirus and secondarily of viruses such as influenza. Throughout the research work, we aim to contribute by elaborating the teaching-learning technique to select and identify the optimal attributes of viruses' variants of the indoor atmosphere. The novelty is based on the objective to enable real-time identification of the density of the airborne molecules to prevent virus propagation. Several sensors and systems came into the spotlight by conducting a systematic literature review that, in conjunction with our innovative idea, could construct a revolutionary new solution that could eliminate the risk of exposure to viable viruses. The proposed teaching-learning based attribute selection optimisation is among the most popular bio-inspired meta-heuristic methods. Therefore, evolutionary logic and provocative performance can be widely utilised to solve the aforementioned humanitarian problem. The proposed frame constitutes three pivotal steps: the new update mechanism, the novel method of selecting the principal teacher in the teacher's phase, and the support vector machine method to compute the fitness function of optimisation. © 2022 IEEE.

AI Driven Cough Voice-Based COVID Detection Framework Using Spectrographic Imaging: An Improved Technology

This paper develops an improved (more effective) and safer technology for detecting COVID-19 and thus contributes to the literature and the control of COVID-19. Coronavirus is a new infection that causes the coronavirus ailment called COVID-19. This disease was first found in bat at Wuhan, China, in December 2019. Starting from that time, it has spread rapidly throughout the globe. One of the main identifications of COVID-19 is that it can be handily distinguished by fever. Since this flare-up has begun, 'temperature screening utilizing infrared thermometers and RT-PCR has been utilized in advanced and developed countries to check the warmth of the body to identify the infected person. This is not a very effective way of detection, as it demands huge manpower and infrastructure to go and check one-by-one. Moreover, the close contact between the infected and the person checking can lead to the spread of coronavirus at a faster pace. This paper proposes a framework that can detect the coronavirus instantly and non-invasively from a human cough voice. The proposed framework is much safer as compared to conventional technologies used, as it reduces human interactions to a greater extent. It uses spectrographic images of the voice for COVID detection. This framework has been deployed in a web application to use them from any part of the world without exposing themselves to other infected people. This method encourages non-invasive mechanisms that will prevent from hurting sensitive areas, unlike conventional procedures. © 2022 IEEE.

Accurate Real-Time Face Mask Detection Framework Using YOLOv5

After the COVID-19 pandemic, wearing a mask has become a must because it decreases the probability of infection by 68%. That is why a fast and accurate automatic mask detection is crucial to public institutions. In this paper, we present an accurate framework for real-time mask detection using YOLOv5 object detection algorithm. Our framework consists of four stages: image preprocessing by normalization and adding noise, adding negative samples and data augmentation then the detection core based on a modified version of YOLOv5. The proposed framework achieves 95.9% precision and 84.8% mean average precision using the Face Mask Detection dataset with a 10 milliseconds inference time. © 2022 IEEE.

D-FEND: A Diffusion-Based Fake News Detection Framework for News Articles Related to COVID-19

The social confusion caused by the recent pandemic of COVID-19 has been further facilitated by fake news diffused via social media on the Internet. For this reason, many studies have been proposed to detect fake news as early as possible. The content-based detection methods consider the difference between the contents of true and fake news articles. However, they suffer from the two serious limitations: (1) the publisher can manipulate the content of a news article easily, and (2) the content depends upon the language, with which the article is written. To overcome these limitations, the diffusion-based fake news detection methods have been proposed. The diffusion-based methods consider the difference among the diffusion patterns of true and fake news articles on social media. Despite its success, however, the lack of the diffusion information regarding to the COVID-19 related fake news prevents from studying the diffusion-based fake news detection methods. Therefore, for overcoming the limitation, we propose a diffusion-based fake news detection framework (D-FEND), which consists of four components: (C1) diffusion data collection, (C2) analysis of the data and feature extraction, (C3) model training, and (C4) inference. Our work contributes to the effort to mitigate the risk of infodemics during a pandemic by (1) building a new diffusion dataset, named CoAID+, (2) identifying and addressing the class imbalance problem of CoAID+, and (3) demonstrating that D-FEND successfully detects fake news articles with 88.89% model accuracy on average. © 2022 ACM.

COVID-Themed Android Malware Analysis and Detection Framework Based on Permissions

In the context of the COVID-19 pandemic the malicious actors actively creating COVID-themed android malicious apps and without much attention user may often grant all the required permissions to install those fake apps. The Android permissions are crucial sources of vulnerability. This vulnerability often leads to major privacy threats. In this work COVID-themed android malwares were collected and analyzed to develop a detection framework based on the static feature permission and machine learning techniques. The proposed system analyses 100 COVID-themed fake applications which released in 2020. The sensitive permissions are selected using Recursive Feature Elimination (RFE) technique. The study shows better accuracy of 0.830 and 0.812 with Decision tree classifier and Random forest classifier respectively. © 2022 IEEE.

A Deep Learning Based Covid-19 Detection Framework

The CORONA Virus Disease (COVID-19) is a respiratory disease caused by Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2). Although the RT-PCR is the standard testing method, the use of X-rays can be a beneficial alternative COVID-19 testing method, as they can be used to identify abnormalities in the lungs which are suggestive of COVID-19 and can be used to monitor the disease progression.The goal of this paper is to design and implement a GAN enhanced deep learning based COVID-19 detection framework for automatic Covid-19 detection by classifying Chest Radiographs into three classes (Covid-19, pneumonia and Normal). To achieve this, the application of Generative Adversarial Networks and classical data augmentation techniques to a modified VGG-19 convolutional neural network to produce a framework that provides accurate and precise detection of COVID-19 through chest X-rays is proposed. The proposed framework achieved a 91.3% accuracy, 91.3% precision, 90.4% F1 score and 91% recall. © 2021 IEEE.

An Adaptive Data Processing Framework for Cost-Effective COVID-19 and Pneumonia Detection

Medical imaging modalities have been showing great potentials for faster and efficient disease transmission control and containment. In the paper, we propose a cost-effective COVID-19 and pneumonia detection framework using CT scans acquired from several hospitals. To this end, we incorporate a novel data processing framework that utilizes 3D and 2D CT scans to diversify the trainable inputs in a resource-limited setting. Moreover, we empirically demonstrate the significance of several data processing schemes for our COVID-19 and pneumonia detection network. Experiment results show that our proposed pneumonia detection network is comparable to other pneumonia detection tasks integrated with imaging modalities, with 93% mean AUC and 85.22% mean accuracy scores on generalized datasets. Additionally, our proposed data processing framework can be easily adapted to other applications of CT modality, especially for cost-effective and resource-limited scenarios, such as breast cancer detection, pulmonary nodules diagnosis, etc. © 2021 IEEE

A Scalable and Domain Adaptive Respiratory Symptoms Detection Framework using Earables

The COVID-19 pandemic has brought a devastating impact on human health across the globe, and people are still observing face-masking as a preventive measure to contain the spread of COVID-19. Coughing is one of the major transmission mediums of COVID-19, and early cough detection could play a significant r ole i n p reventing t he s pread o f t his life-threatening virus. Many approaches have been proposed for developing systems to detect coughing and other respiratory symptoms in literature, but earable devices are not well-studied and investigated for respiratory symptom detection. In this work, we posited an acoustic research prototype (earable device) - eSense that has acoustic and IMU sensors embedded into user-convenient earbuds to address the following issues: (i) feasibility of the earables in detecting respiratory symptoms, and (ii) scalability of trained machine learning models in the presence of unseen data samples. We performed experimentation with both shallow and deep learning models on the eSense collected data samples. We observed that the deep learning model outperforms the shallow learning models achieving 97% accuracy. Furthermore, we investigated the scalability of the deep learning model on unseen datasets and noticed that the performance of the deep learning model deteriorates when trained on a particular dataset and tested on an unseen dataset. To mitigate such challenges, we postulated an adversarial domain adaptation technique that helps improve the performance of our respiratory symptoms detection framework by a substantial margin. © 2021 IEEE.

COVID-19 Fake News Detection via Graph Neural Networks in Social Media

Recently it is convenient for people to seek out and consume news from social media, but misinformation including fake news and low-quality information also spreads which may have extremely negative impacts on individuals and society especially in the pandemics e.g., Covid-19. Previous fake news detectors view articles or tweets as i.i. d data and ignore the relation between them. In this paper we propose a novel fake news detection framework by exploring the similarity relation between tweets and mapping this problem into a semi-supervised classification task on a graph. We evaluate our proposed framework on a real-world social media dataset and the experimental results demonstrate the effectiveness of our proposed method comparing to different baselines. © 2021 IEEE.

Reinforcement learning based diagnosis and prediction for COVID-19 from CT images

As we all know, COVID-19 is causing more and more human infections and deaths. In order to quickly and efficiently detect COVID-19, this paper has firstly proposed a detection framework based on reinforcement learning for COVID-19 diagnosis. We use the accuracy of the validation set as the reward value, and obtain the initial model for the next epoch by searching the model corresponding to the maximum reward value in each epoch. We also have proposed a prediction framework that integrates multiple detection frameworks using parameter sharing to predict the progression of patients' disease. We experimented with our own dataset screened by professional physicians and obtained more excellent results. In external validation, we still achieved a high accuracy rate without additional training. Finally, the experimental results show that our classification accuracy can reach 96.81%, and the precision, sensitivity, specificity, and AUC (Area Under Curve) are 95.47%, 98.64%, 95.91%, and 0.9698, respectively. The accuracy of external verification can reach 93.04% and 90.85%. The accuracy of our prediction framework is 91.04%. A large number of experiments have proved that our proposed method is effective and robust for COVID-19 detection and prediction. © SPIE 2021.

A Novel Detection Framework About Conditions of Wearing Face Mask for Helping Control the Spread of COVID-19.

Properly wearing a face mask has become an effective way to limit the COVID-19 transmission. In this work, we target at detecting the fine-grained wearing state of face mask: face without mask, face with wrong mask, face with correct mask. This task has two main challenging points: 1) absence of practical datasets, and 2) small intra-class distance and large inter-class distance. For the first challenging point, we introduce a new practical dataset covering various conditions, which contains 8635 faces with different wearing status. For the second challenging point, we propose a novel detection framework about conditions of wearing face mask, named Context-Attention R-CNN, which enlarge the intra-class distance and shorten inter-class distance by extracting distinguishing features. Specifically, we first extract the multiple context feature for region proposals, and use attention module to weight these context feature from channel and spatial levels. And then, we decoupling the classification and localization branches to extract more appropriate feature for these two tasks respectively. Experiments show that the Context-Attention R-CNN achieves 84.1% mAP on our proposed dataset, outperforming Faster R-CNN by 6.8 points. Moreover, Context-Attention R-CNN still exceed some state-of-the-art single-stage detectors.