Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 196
Filter
Add filters

Document Type
Year range
1.
Proceedings of SPIE - The International Society for Optical Engineering ; 12626, 2023.
Article in English | Scopus | ID: covidwho-20245242

ABSTRACT

In 2020, the global spread of Coronavirus Disease 2019 exposed entire world to a severe health crisis. This has limited fast and accurate screening of suspected cases due to equipment shortages and and harsh testing environments. The current diagnosis of suspected cases has benefited greatly from the use of radiographic brain imaging, also including X-ray and scintigraphy, as a crucial addition to screening tests for new coronary pneumonia disease. However, it is impractical to gather enormous volumes of data quickly, which makes it difficult for depth models to be trained. To solve these problems, we obtained a new dataset by data augmentation Mixup method for the used chest CT slices. It uses lung infection segmentation (Inf-Net [1]) in a deep network and adds a learning framework with semi-supervised to form a Mixup-Inf-Net semi-supervised learning framework model to identify COVID-19 infection area from chest CT slices. The system depends primarily on unlabeled data and merely a minimal amount of annotated data is required;therefore, the unlabeled data generated by Mixup provides good assistance. Our framework can be used to improve improve learning and performance. The SemiSeg dataset and the actual 3D CT images that we produced are used in a variety of tests, and the analysis shows that Mixup-Inf-Net semi-supervised outperforms most SOTA segmentation models learning framework model in this study, which also enhances segmentation performance. © 2023 SPIE.

2.
Soft comput ; : 1-15, 2023 Jun 03.
Article in English | MEDLINE | ID: covidwho-20238125

ABSTRACT

COVID-19 has created many complications in today's world. It has negatively impacted the lives of many people and emphasized the need for a better health system everywhere. COVID-19 is a life-threatening disease, and a high proportion of people have lost their lives due to this pandemic. This situation enables us to dig deeper into mortality records and find meaningful patterns to save many lives in future. Based on the article from the New Indian Express (published on January 19, 2021), a whopping 82% of people who died of COVID-19 in Tamil Nadu had comorbidities, while 63 percent of people who died of the disease were above the age of 60, as per data from the Health Department. The data, part of a presentation shown to Union Health Minister Harsh Vardhan, show that of the 12,200 deaths till January 7, as many as 10,118 patients had comorbidities, and 7613 were aged above 60. A total of 3924 people (32%) were aged between 41 and 60. Compared to the 1st wave of COVID-19, the 2nd wave had a high mortality rate. Therefore, it is important to find meaningful insights from the mortality records of COVID-19 patients to know the most vulnerable population and to decide on comprehensive treatment strategies.

3.
IEEE Transactions on Radiation and Plasma Medical Sciences ; : 1-1, 2023.
Article in English | Scopus | ID: covidwho-20244069

ABSTRACT

Automatic lung infection segmentation in computed tomography (CT) scans can offer great assistance in radiological diagnosis by improving accuracy and reducing time required for diagnosis. The biggest challenges for deep learning (DL) models in segmenting infection region are the high variances in infection characteristics, fuzzy boundaries between infected and normal tissues, and the troubles in getting large number of annotated data for training. To resolve such issues, we propose a Modified U-Net (Mod-UNet) model with minor architectural changes and significant modifications in the training process of vanilla 2D UNet. As part of these modifications, we updated the loss function, optimization function, and regularization methods, added a learning rate scheduler and applied advanced data augmentation techniques. Segmentation results on two Covid-19 Lung CT segmentation datasets show that the performance of Mod-UNet is considerably better than the baseline U-Net. Furthermore, to mitigate the issue of lack of annotated data, the Mod-UNet is used in a semi-supervised framework (Semi-Mod-UNet) which works on a random sampling approach to progressively enlarge the training dataset from a large pool of unannotated CT slices. Exhaustive experiments on the two Covid-19 CT segmentation datasets and on a real lung CT volume show that the Mod-UNet and Semi-Mod-UNet significantly outperform other state-of-theart approaches in automated lung infection segmentation. IEEE

4.
International Journal of Distributed Systems and Technologies ; 14(1), 2023.
Article in English | Scopus | ID: covidwho-20243534

ABSTRACT

Ubiquitous environments are not fixed in time. Entities are constantly evolving;they are dynamic. Ubiquitous applications therefore have a strong need to adapt during their execution and react to the context changes, and developing ubiquitous applications is still complex. The use of the separation of needs and model-driven engineering present the promising solutions adopted in this approach to resolve this complexity. The authors thought that the best way to improve efficiency was to make these models intelligent. That's why they decided to propose an architecture combining machine learning with the domain of modeling. In this article, a novel tool is proposed for the design of ubiquitous applications, associated with a graphical modeling editor with a drag-drop palette, which will allow to instantiate in a graphical way in order to obtain platform independent model, which will be transformed into platform specific model using Acceleo language. The validity of the proposed framework has been demonstrated via a case study of COVID-19. © 2023 IGI Global. All rights reserved.

5.
IEEE Transactions on Consumer Electronics ; : 1-1, 2023.
Article in English | Scopus | ID: covidwho-20234982

ABSTRACT

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

6.
Bioengineering (Basel) ; 10(5)2023 May 05.
Article in English | MEDLINE | ID: covidwho-20230846

ABSTRACT

A machine learning method for classifying lung ultrasound is proposed here to provide a point of care tool for supporting a safe, fast, and accurate diagnosis that can also be useful during a pandemic such as SARS-CoV-2. Given the advantages (e.g., safety, speed, portability, cost-effectiveness) provided by the ultrasound technology over other examinations (e.g., X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest public lung ultrasound dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art models by at least 5%. The complexity is restrained by adopting specific design choices: ensembling with an adaptive combination layer, ensembling performed on the deep features, and minimal ensemble using two weak models only. In this way, the number of parameters has the same order of magnitude of a single EfficientNet-b0 and the computational cost (FLOPs) is reduced at least by 20%, doubled by parallelization. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where an inaccurate weak model focuses its attention versus an accurate one.

7.
Mater Today Proc ; 2021 Apr 15.
Article in English | MEDLINE | ID: covidwho-2323338

ABSTRACT

The Covid-19 Corona Virus, also known as SARS-CoV-2, has wreaked havoc around the world, and the condition is only getting worse.It is a pandemic disease spreading from person-to-person every day. Therefore, it is important to keep track the number of patients being affected. The current system gives the computerized data in a collective way which is very difficult to analyze and predict the growth of disease in a particular area and in the world. Machine learning algorithms can be used to successfully map the disease and its progression to solve this problem. Machine Learning, a branch of computer science, is critical in correctly distinguishing patients with the condition by analyzing their chest X-ray photographs. Supervised Machine learning models with associated algorithms (like LR, SVR and Time series algorithms) to analyze data for regression and classification helps in training the model to predict the number of total number of global confirmed cases who will be prone to the disease in the upcoming days. In this proposed work, the overall dataset of the world is being collected, preprocessed and the number of confirmed cases up to a particular date are extracted which is given as the training set to the model. The model is being trained by supervised machine learning algorithms to predict the growth of cases in the upcoming days. The experimental setup with the above mentioned algorithms shows that Time series Holt's model outperforms Linear Regression and Support Vector Regression algorithms.

8.
Communication Methods and Measures ; 17(2):150-184, 2023.
Article in English | ProQuest Central | ID: covidwho-2326884

ABSTRACT

Supervised machine learning (SML) provides us with tools to efficiently scrutinize large corpora of communication texts. Yet, setting up such a tool involves plenty of decisions starting with the data needed for training, the selection of an algorithm, and the details of model training. We aim at establishing a firm link between communication research tasks and the corresponding state-of-the-art in natural language processing research by systematically comparing the performance of different automatic text analysis approaches. We do this for a challenging task – stance detection of opinions on policy measures to tackle the COVID-19 pandemic in Germany voiced on Twitter. Our results add evidence that pre-trained language models such as BERT outperform feature-based and other neural network approaches. Yet, the gains one can achieve differ greatly depending on the specific merits of pre-training (i.e., use of different language models). Adding to the robustness of our conclusions, we run a generalizability check with a different use case in terms of language and topic. Additionally, we illustrate how the amount and quality of training data affect model performance pointing to potential compensation effects. Based on our results, we derive important practical recommendations for setting up such SML tools to study communication texts.

9.
2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023 ; : 380-383, 2023.
Article in English | Scopus | ID: covidwho-2319810

ABSTRACT

The Covid-19 virus is still marching all over the world. Many people are getting infected and a few are fatal to death. This research paper expressed that supervised learning has revealed supreme results than unsupervised learning in machine learning. Within supervised learning, random forest regression outplays all other algorithms like logistic regression (LR), support vector machine (SVM), decision tree (DT), etc. Now monkeypox is escalating in other countries at present. This virus is allied to human orthopox viruses. It can expand from one to one through contact person having rash or body fluids etc. The symptoms of monkeypox are much similar to covid19 virus-like fever, cold, fatigue, and body pains. Herewith we concluded that random forest regression shows possible foremost (97.15%) accuracy. © 2023 IEEE.

10.
International Journal of Information Engineering and Electronic Business ; 13(4):28, 2022.
Article in English | ProQuest Central | ID: covidwho-2319633

ABSTRACT

After release of Web 2.0 in 2004 user spawned contents on the internet eminently in abundant review sites, online forums, online blogs, and many other sites. Entire user generated contents are considerable bunches of unorganized text written in different languages that encompass user emotions about one or more entities. Mainly predictive analysis exerts the existing data to forecast future outcomes. Currently, a massive amount of researches are being engrossed in the area of opinion mining, also called sentiment analysis, opinion extraction, review analysis, subjective analysis, emotion analysis, and mood extraction. It can be an utmost choice whilst perceiving the meaning and patterns in prevailing data. Most of the time, there are various algorithms available to work with polling. There are contradictory opinions among researchers regarding the effectiveness of algorithms. We have compared different opinion mining algorithms and presented the findings in this paper.

11.
Applied Sciences ; 13(9):5322, 2023.
Article in English | ProQuest Central | ID: covidwho-2315707

ABSTRACT

Depression is a common illness worldwide with doubtless severe implications. Due to the absence of early identification and treatment for depression, millions of individuals worldwide suffer from mental illnesses. It might be difficult to identify those who are experiencing mental health illnesses and to provide them with the early help that they need. Additionally, depression may be associated with thoughts of suicide. Currently, there are no clinically specific diagnostic biomarkers that can identify the severity and type of depression. In this research paper, the novel particle swarm-cuckoo search (PS-CS) optimization algorithm is proposed instead of the traditional backpropagation algorithm for training deep neural networks. The backpropagation algorithm is widely used for supervised learning in deep neural networks, but it has limitations in terms of convergence speed and the possibility of getting trapped in local optima. These problems were addressed by using a deep neural network architecture for depression detection tasks along with the PS-CS optimization technique. The PS-CS algorithm combines the strengths of both particle swarm optimization and cuckoo search algorithms, which allows for a more efficient and effective optimization of the network parameters. We also evaluated how well the suggested methods performed against the most widely used classification models, including (K-nearest neighbor) KNN, (support vector regression) SVR, and decision trees, as well as the most widely used deep learning models, including residual neural network (ResNet), visual geometry group (VGG), and simple neural network (LeNet). The findings show that the suggested method, PS-CS, in conjunction with the CNN model, outperformed all other models, achieving the maximum accuracy of 99.5%. Other models, such as the KNN, decision trees, and logistic regression, achieved lower accuracies ranging from 69% to 97%.

12.
2022 International Interdisciplinary Conference on Mathematics, Engineering and Science, MESIICON 2022 ; 2022.
Article in English | Scopus | ID: covidwho-2315142

ABSTRACT

The deadfall widespread of coronavirus (SARS-Co V-2) disease has trembled every part of the earth and has significant disruption to health support systems in different countries. In spite of such existing difficulties and disagreements for testing the coronavirus disease, an advanced and low-cost technique is required to classify the disease. For the sense of reason, supervised machine learning (ML) along with image processing has turned out as a strong technique to detect coronavirus from human chest X-rays. In this work, the different methodologies to identify coronavirus (SARS-CoV-2) are discussed. It is essential to expand a fully automatic detection system to restrict the carrying of the virus load through contact. Various deep learning structures are present to detect the SARS-CoV-2 virus such as ResNet50, Inception-ResNet-v2, AlexNet, Vgg19, etc. A dataset of 10,040 samples has been used in which the count of SARS-CoV-2, pneumonia and normal images are 2143, 3674, and 4223 respectively. The model designed by fusion of neural network and HOG transform had an accuracy of 98.81% and a sensitivity of 98.65%. © 2022 IEEE.

13.
Evol Syst (Berl) ; 14(3): 519-532, 2023.
Article in English | MEDLINE | ID: covidwho-2316744

ABSTRACT

Accurate segmentation of infected regions in lung computed tomography (CT) images is essential to improve the timeliness and effectiveness of treatment for coronavirus disease 2019 (COVID-19). However, the main difficulties in developing of lung lesion segmentation in COVID-19 are still the fuzzy boundary of the lung-infected region, the low contrast between the infected region and the normal trend region, and the difficulty in obtaining labeled data. To this end, we propose a novel dual-task consistent network framework that uses multiple inputs to continuously learn and extract lung infection region features, which is used to generate reliable label images (pseudo-labels) and expand the dataset. Specifically, we periodically feed multiple sets of raw and data-enhanced images into two trunk branches of the network; the characteristics of the lung infection region are extracted by a lightweight double convolution (LDC) module and fusiform equilibrium fusion pyramid (FEFP) convolution in the backbone. According to the learned features, the infected regions are segmented, and pseudo-labels are made based on the semi-supervised learning strategy, which effectively alleviates the semi-supervised problem of unlabeled data. Our proposed semi-supervised dual-task balanced fusion network (DBF-Net) creates pseudo-labels on the COVID-SemiSeg dataset and the COVID-19 CT segmentation dataset. Furthermore, we perform lung infection segmentation on the DBF-Net model, with a segmentation sensitivity of 70.6% and specificity of 92.8%. The results of the investigation indicate that the proposed network greatly enhances the segmentation ability of COVID-19 infection.

14.
International Journal of Image, Graphics and Signal Processing ; 13(5):1, 2022.
Article in English | ProQuest Central | ID: covidwho-2305937

ABSTRACT

The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification task of medical CT scans, but medical image datasets often require professional image annotation, and many research datasets are not publicly available. To solve this problem, this paper is inspired by the self-supervised learning algorithm MAE and uses the MAE model pre-trained on ImageNet to perform transfer learning on CT Scans dataset. This method improves the generalization performance of the model and avoids the risk of overfitting on small datasets. Through extensive experiments on the COVID-CT dataset and the SARS-CoV-2 dataset, we compare the SSL-based method in this paper with other state-of-the-art supervised learning-based pretraining methods. Experimental results show that our method improves the generalization performance of the model more effectively and avoids the risk of overfitting on small datasets. The model achieved almost the same accuracy as supervised learning on both test datasets. Finally, ablation experiments aim to fully demonstrate the effectiveness of our method and how it works.

15.
Expert Systems with Applications ; 225, 2023.
Article in English | Scopus | ID: covidwho-2305858

ABSTRACT

Recently the large-scale influence of Covid-19 promoted the fast development of intelligent tutoring systems (ITS). As a major task of ITS, Knowledge Tracing (KT) aims to capture a student's dynamic knowledge state based on his historical response sequences and provide personalized learning assistance to him. However, most existing KT methods have encountered the data sparsity problem. In real scenarios, an online tutoring system usually has an extensive collection of questions while each student can only interact with a limited number of questions. As a result, the records of some questions could be extremely sparse, which degrades the performance of traditional KT models. To resolve this issue, we propose a Dual-channel Heterogeneous Graph Network (DHGN) to learn informative representations of questions from students' records by capturing both the high-order heterogeneous and local relations. As the supervised learning manner applied in previous methods is incapable of exploiting unobserved relations between questions, we innovatively integrate a self-supervised framework into the KT task and employ contrastive learning via the two channels of DHGN, supplementing as an auxiliary task to improve the KT performance. Moreover, we adopt the attention mechanism, which has achieved impressive performance in natural language processing tasks, to effectively capture students' knowledge state. But the standard attention network is inapplicable to the KT task because the current knowledge state of a student usually shows strong dependency on his recently interactive questions, unlike the situation of language processing tasks, which focus more on the long-term dependency. To avoid the inefficiency of standard attention networks in the KT task, we further devise a novel Hybrid Attentive Network (HAN), which produces both the global attention and the hierarchical local attention to model the long-term and short-term intents, respectively. Then, by the gating network, a student's long-term and short-term intents are combined for efficient prediction. We conduct extensive experiments on several real-world datasets. Experimental results demonstrate that our proposed methods achieve significant performance improvement compared to existing state-of-the-art baselines, which validates the effectiveness of the proposed dual-channel heterogeneous graph framework and hybrid attentive network. © 2023 Elsevier Ltd

16.
Informatica ; 47(1):73-80, 2023.
Article in English | ProQuest Central | ID: covidwho-2304984

ABSTRACT

In addition to infecting millions of people and causing hundreds of thousands of deaths, COVID-19 has also caused psychological and economic devastation. Studies on the vaccine, which is considered to be the only way to eliminate this pandemic, have been rapidly completed and more than 10 vaccines have begun to be applied worldwide by 2021. One of the biggest obstacles to the fight against COVID-19 is the hesitation against the vaccine. The fear factor, fed by incomplete and false information spreading rapidly through social media applications such as Twitter, is thought to be the main reason for this hesitation. In this study, the general sentiment against the COVID-19 vaccine is analyzed. For this, in the first week of January 2021, more than 8000 tweets are extracted with R statistical software and Twitter API, and appropriate sentiment analysis methods are applied. On the other hand, accuracy values are obtained by applying Logistic Regression and Naive Bayes methods, which are effective and widely used supervised machine learning methods, for sentiment classification. Although the results indicate that there is a positive attitude about the vaccine, it is remarkable that the rate of negative sentiments is relatively high (30%). Trust is the dominant sentiment on the positive side, while fear is the dominant sentiment on the negative side. According to the results of the classification methods, accuracy values are close to 90%.

17.
Artificial Intelligence in Medical Sciences and Psychology: With Application of Machine Language, Computer Vision, and NLP Techniques ; : 1-173, 2022.
Article in English | Scopus | ID: covidwho-2300992

ABSTRACT

Get started with artificial intelligence for medical sciences and psychology. This book will help healthcare professionals and technologists solve problems using machine learning methods, computer vision, and natural language processing (NLP) techniques. The book covers ways to use neural networks to classify patients with diseases. You will know how to apply computer vision techniques and convolutional neural networks (CNNs) to segment diseases such as cancer (e.g., skin, breast, and brain cancer) and pneumonia. The hidden Markov decision making process is presented to help you identify hidden states of time-dependent data. In addition, it shows how NLP techniques are used in medical records classification. This book is suitable for experienced practitioners in varying medical specialties (neurology, virology, radiology, oncology, and more) who want to learn Python programming to help them work efficiently. It is also intended for data scientists, machine learning engineers, medical students, and researchers. What You Will Learn • Apply artificial neural networks when modelling medical data • Know the standard method for Markov decision making and medical data simulation • Understand survival analysis methods for investigating data from a clinical trial • Understand medical record categorization • Measure personality differences using psychological models • Who This Book Is For Machine learning engineers and software engineers working on healthcare-related projects involving AI, including healthcare professionals interested in knowing how AI can improve their work setting. © 2022 by Tshepo Chris Nokeri.

18.
Revue d'Intelligence Artificielle ; 36(3):467-473, 2022.
Article in French | ProQuest Central | ID: covidwho-2299401

ABSTRACT

Misinformation and misleading actions have appeared as soon as COVID-19 vaccinations campaigns were launched, no matter what the country's alphabetization level or growing index is. In such a situation, supervised machine learning techniques for classification appears as a suitable solution to model the value & veracity of data, especially in the Arabic language as a language used by millions of people around the world. To achieve this task, we had to collect data manually from SM platforms such as Facebook, Twitter and Arabic news websites. This paper aims to classify Arabic language news into fake news and real news, by creating a Machine Learning (ML) model that will detect Arabic fake news (DAFN) about COVID-19 vaccination. To achieve our goal, we will use Natural Language Processing (NLP) techniques, which is especially challenging since NLP libraries support for Arabic is not common. We will use NLTK package of python to preprocess the data, and then we will use a ML model for the classification.

19.
8th IEEE International Conference on Computer and Communications, ICCC 2022 ; : 2334-2338, 2022.
Article in English | Scopus | ID: covidwho-2298980

ABSTRACT

Coronavirus Disease 2019(COVID-19) has shocked the world with its rapid spread and enormous threat to life and has continued up to the present. In this paper, a computer-aided system is proposed to detect infections and predict the disease progression of COVID-19. A high-quality CT scan database labeled with time-stamps and clinicopathologic variables is constructed to provide data support. To our knowledge, it is the only database with time relevance in the community. An object detection model is then trained to annotate infected regions. Using those regions, we detect the infections using a model with semi-supervised-based ensemble learning and predict the disease progression depending on reinforcement learning. We achieve an mAP of 0.92 for object detection. The accuracy for detecting infections is 98.46%, with a sensitivity of 97.68%, a specificity of 99.24%, and an AUC of 0.987. Significantly, the accuracy of predicting disease progression is 90.32% according to the timeline. It is a state-of-the-art result and can be used for clinical usage. © 2022 IEEE.

20.
Traitement du Signal ; 39(3):893-898, 2022.
Article in English | ProQuest Central | ID: covidwho-2298522

ABSTRACT

Many education facilities have recently switched to online learning due to the COVID-19 pandemic. The nature of online learning makes it easier for dishonest behaviors, such as cheating or lying during lessons. We propose a new artificial intelligence - powered solution to help educators solve this rising problem for a fairer learning environment. We created a visual representation contrastive learning method with the MobileNetV2 network as the backbone to improve predictability from an unlabeled dataset which can be deployed on low power consumption devices. The experiment shows an accuracy of up to 59%, better than several previous research, proving the usability of this approach.

SELECTION OF CITATIONS
SEARCH DETAIL