Development of technology predicting based on EEMD-GRU: An empirical study of aircraft assembly technology

Expert Systems with Applications, Год журнала: 2024, Номер 246, С. 123208 - 123208

Опубликована: Янв. 10, 2024

Язык: Английский

---

A Self-Activated CNN Approach for Multi-Class Chest-Related COVID-19 Detection

Applied Sciences, Год журнала: 2021, Номер 11(19), С. 9023 - 9023

Опубликована: Сен. 28, 2021

Chest diseases can be dangerous and deadly. They include many chest infections such as pneumonia, asthma, edema, and, lately, COVID-19. COVID-19 has similar symptoms compared to breathing hardness burden. However, it is a challenging task differentiate from other diseases. Several related studies proposed computer-aided detection system for the single-class detection, which may misleading due of This paper proposes framework 15 types diseases, including disease, via X-ray modality. Two-way classification performed in Framework. First, deep learning-based convolutional neural network (CNN) architecture with soft-max classifier proposed. Second, transfer learning applied using fully-connected layer CNN that extracted features. The features are fed classical Machine Learning (ML) methods. improves accuracy increases predictability rates experimental results show framework, when state-of-the-art models diagnosing more robust, promising.

Язык: Английский

---

Machine Learning Approaches for Tackling Novel Coronavirus (COVID-19) Pandemic

SN Computer Science, Год журнала: 2021, Номер 2(5)

Опубликована: Июль 19, 2021

Novel coronavirus (COVID-19) has become a global problem in recent times due to the rapid spread of this disease. Almost all countries world have been affected by pandemic that made major consequence on medical system and healthcare facilities. The is going through critical time because COVID-19 pandemic. Modern technologies such as deep learning, machine data science are contributing fight COVID-19. paper aims highlight role learning approaches situation. We searched for latest literature regarding from various sources like IEEE Xplore, PubMed, Google Scholar, Research Gate, Scopus. Then, we analyzed described them throughout study. In study, noticed four different applications methods combat These trying contribute aspects helping physicians make confident decisions, policymakers take fruitful identifying potentially infected people. challenges existing systems with possible future trends outlined paper. researchers coming using techniques face serving great deal. recommend can be useful tool proper analyzing, screening, tracking, forecasting, predicting characteristics

Язык: Английский

---

COVID-19 Pandemic Forecasting Using CNN-LSTM: A Hybrid Approach

Journal of Control Science and Engineering, Год журнала: 2021, Номер 2021, С. 1 - 23

Опубликована: Июль 30, 2021

COVID-19 has sparked a worldwide pandemic, with the number of infected cases and deaths rising on regular basis. Along recent advances in soft computing technology, researchers are now actively developing enhancing different mathematical machine-learning algorithms to forecast future trend this pandemic. Thus, if we can accurately globally, spread pandemic be controlled. In study, hybrid CNN-LSTM model was developed time-series dataset confirmed COVID-19. The proposed evaluated compared 17 baseline models test data. primary finding research is that outperformed them all, lowest average MAPE, RMSE, RRMSE values both Conclusively, our experimental results show that, while standalone CNN LSTM provide acceptable efficient forecasting performance for time series, combining encoder-decoder structure provides significant boost performance. Furthermore, demonstrated suggested produced satisfactory predicting even small amount

Язык: Английский

---

Intelligent system for COVID-19 prognosis: a state-of-the-art survey

Applied Intelligence, Год журнала: 2021, Номер 51(5), С. 2908 - 2938

Опубликована: Янв. 6, 2021

This 21st century is notable for experiencing so many disturbances at economic, social, cultural, and political levels in the entire world. The outbreak of novel corona virus 2019 (COVID-19) has been treated as a Public Health crisis global Concern by World Organization (WHO). Various models COVID-19 are being utilized researchers throughout world to get well-versed decisions impose significant control measures. Amid standard methods worldwide epidemic prediction, easy statistical, well epidemiological have got more consideration authorities. One main difficulty controlling spreading inadequacy lack medical tests detecting identifying solution. To solve this problem, few statistical-based advances enhanced turn into partial resolution up-to some level. deal with challenges field, broad range intelligent based methods, frameworks, equipment recommended Machine Learning (ML) Deep Learning. As ML DL ability predicting patterns complex large datasets, they recognized suitable procedure producing effective solutions diagnosis COVID-19. In paper, perspective research conducted applicability systems such ML, others solving related issues. intention behind study (i) understand importance approaches pandemic, (ii) discussing efficiency impact these prognosis COVID-19, (iii) growth development type advanced prognosis,(iv) analyzing data types nature along processing COVID-19,(v) focus on future inspire innovating enhancing their knowledge other impacted sectors due

Язык: Английский

---

COVID-19 prevalence forecasting using Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN): Case of Turkey

Journal of Infection and Public Health, Год журнала: 2021, Номер 14(7), С. 811 - 816

Опубликована: Май 5, 2021

A local outbreak of unknown pneumonia was detected in Wuhan (Hubei, China) December 2019. It is determined to be caused by a severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) and called COVID-19 scientists. The has since spread all over the world with total 120,815,512 cases 2,673,308 deaths as 16 March 2021. health systems collapsed many countries due pandemic were negatively affected social life. In such situations, it very important predict load that will occur system country. this study, prevalence Turkey inspected. infected cases, number deaths, recovered are predicted Autoregressive Integrated Moving Average (ARIMA) Artificial Neural Networks (ANN) Turkey. techniques compared terms correlation coefficient mean square error (MSE). results showed used successful estimation

Язык: Английский

---

Application of Artificial Intelligence-Based Regression Methods in the Problem of COVID-19 Spread Prediction: A Systematic Review

International Journal of Environmental Research and Public Health, Год журнала: 2021, Номер 18(8), С. 4287 - 4287

Опубликована: Апрель 18, 2021

COVID-19 is one of the greatest challenges humanity has faced recently, forcing a change in daily lives billions people worldwide. Therefore, many efforts have been made by researchers across globe attempt determining models spread. The objectives this review are to analyze some open-access datasets mostly used research field regression modeling as well present current literature based on Artificial Intelligence (AI) methods for tasks, like disease Moreover, we discuss applicability Machine Learning (ML) and Evolutionary Computing (EC) that focused regressing epidemiology curves COVID-19, provide an overview usefulness existing specific areas. An electronic search various databases was conducted develop comprehensive latest AI-based approaches spread COVID-19. Finally, conclusion drawn from observation reviewed papers algorithms clear application epidemiological may be crucial tool combat against coming pandemics.

Язык: Английский

---

A new hybrid ensemble machine-learning model for severity risk assessment and post-COVID prediction system

Mathematical Biosciences & Engineering, Год журнала: 2022, Номер 19(6), С. 6102 - 6123

Опубликована: Янв. 1, 2022

<abstract> <p>Starting from December 2019, the COVID-19 pandemic has globally strained medical resources and caused significant mortality. It is commonly recognized that severity of SARS-CoV-2 disease depends on both comorbidity state patient's immune system, which reflected in several biomarkers. The development early diagnosis prediction methods can reduce burden health care system increase effectiveness treatment rehabilitation patients with severe cases. This study aims to develop validate an ensemble machine-learning model based clinical immunological features for risk assessment post-COVID duration patients. dataset consisting 35 122 instances was collected Lviv regional center. contains age, gender, weight, height, BMI, CAT, 6-minute walking test, pulse, external respiration function, oxygen saturation, 15 markers used predict relationship between biomarkers using machine learning approach. predictions are assessed through area under receiver-operating curve, classification accuracy, precision, recall, F1 score performance metrics. A new hybrid feature selection a proposed as automatic cut-off rank identifier. three-layer high accuracy stacking intelligent analysis short datasets presented. Together weak predictors, associative rules allowed improving quality. allows random forest aggregator repressors' results generalization. (AUC 0.978; CA 0.920; 0.921; precision 0.924; recall 0.920) higher than five models, viz. tree algorithm forward pruning; Naïve Bayes classifier; support vector RBF kernel; logistic regression, calibrated learner sigmoid function decision threshold optimization. Aging-related biomarkers, CD3+, CD4+, CD8+, CD22+ were examined duration. best reached case linear kernel (MAPE = 0.0787) classifier (RMSE 1.822). predicted cytokines physiological point out changes studied associated be monitor forecast duration.</p> </abstract>

Язык: Английский

---

Benchmarking Framework for COVID-19 Classification Machine Learning Method Based on Fuzzy Decision by Opinion Score Method

Iraqi Journal of Science, Год журнала: 2023, Номер unknown, С. 922 - 943

Опубликована: Фев. 28, 2023

Coronavirus disease (COVID-19), which is caused by SARS-CoV-2, has been announced as a global pandemic the World Health Organization (WHO), results in collapsing of healthcare systems several countries around globe. Machine learning (ML) methods are one most utilized approaches artificial intelligence (AI) to classify COVID-19 images. However, there many machine-learning used COVID-19. The question is: machine method best over multi-criteria evaluation? Therefore, this research presents benchmarking methods, recognized decision-making (MCDM) problem. In recent century, trend developing different MCDM raised based on perspectives; however, latest one, namely, fuzzy decision opinion score that was produced 2020, efficiently able solve some existing issues other could not manage solve. because multiple criteria problem and have conflict methodology divided into two main stages. first stage related identifying matrix eight ML chest X-ray (CXR) images extracted new so assess methods. second FDOSM problems. follows: (1) individual three makers nearly identical; among all neural networks (NN) achieved results. (2) group comparable, network (3) final rank more logical closest decision-makers' opinion. (4) Significant differences groups' scores shown our validation results, indicate authenticity Finally, benefits, especially for hospitals medical clinics, with view speeding up diagnosis patients suffering from using method.

Язык: Английский

---

A Review of the Potential of Artificial Intelligence Approaches to Forecasting COVID-19 Spreading

AI, Год журнала: 2022, Номер 3(2), С. 493 - 511

Опубликована: Май 19, 2022

The spread of SARS-CoV-2 can be considered one the most complicated patterns with a large number uncertainties and nonlinearities. Therefore, analysis prediction distribution this virus are challenging problems, affecting planning managing its impacts. Although different vaccines drugs have been proved, produced, distributed after another, several new fast-spreading variants detected. This is why numerous techniques based on artificial intelligence (AI) recently designed or redeveloped to forecast these more effectively. focus such methods deep learning (DL) machine (ML), they nonlinear trends in epidemiological issues appropriately. short review aims summarize evaluate trustworthiness performance some important AI-empowered approaches used for COVID-19. Sixty-five preprints, peer-reviewed papers, conference proceedings, book chapters published 2020 were reviewed. Our criteria include exclude references reported documents. results revealed that although under discussion suitable potential predict COVID-19, there still weaknesses drawbacks fall domain future research scientific endeavors.

Язык: Английский

---