Estimating monthly surface ozone using multi-source satellite products in China based on Deep Forest model

Surface ozone (O3), a well-recognized air pollutant, exists in the atmosphere, which has a detrimental effect on public health and the ecological environment. It is reported that surface O3 has seen a significant increase in many cities from 2019 to 2021 (COVID-19 pandemic). In this study, we applied an innovative machine learning model (Deep Forest) coupled with satellites, the Troposphere Monitoring Instrument (TROPOMI) and the Ozone Monitoring Instrument (OMI), and meteorological datasets to estimate monthly surface O3 of 1 km spatial resolution across China during this pandemic period. Our model achieved an overall R2 of 0.974, 0.963, and root mean square error (RMSE) of 6.016 μg/m3, 7.214 μg/m3 on TROPOMI-based datasets and OMI-based datasets, respectively. Also, we found the higher ozone concentration regions were in Eastern China. Simultaneously, the surface O3 concentration was high in summer(average = 110.57 ± 15.01 μg/m3). And the ozone concentration in summer 2020 (average = 107.78 ± 13.90 μg/m3) declined unprecedently than in summer 2019 (average = 110.54 ± 16.58 μg/m3). Our results indicated that TROPOMI data could provide robust data support for surface ozone concentration estimation. Furthermore, this study could enhance our comprehension of the formation mechanisms of surface O3 in China and assist air environment management decision-making.

Early diagnosis of COVID-19 patients using deep learning-based deep forest model

Coronavirus disease-19 (COVID-19) has rapidly spread all over the world. It is found that the low sensitivity of reverse transcription-polymerase chain reaction (RT-PCR) examinations during the early stage of COVID-19 disease. Thus, efficient models are desirable for early-stage testing of COVID-19 infected patients. Chest X-ray (CXR) images of COVID-19 infected patients have shown some bilateral changes. In this paper, deep transfer learning and a deep forest-based model are proposed to diagnose COVID-19 infection from CXR images. Initially, features of X-ray images are extracted using the well-known deep transfer learning model (i.e., ResNet101), which does not require tuning many parameters compared to the deep convolutional neural network (CNN). After that, the deep forest model is utilised to predict COVID-19 infected patients. The deep forest is based upon ensemble learning and requires a small number of hyper-parameters. Additionally, the proposed model is trained on a multi-class dataset that contains four different classes as COVID-19 (+), pneumonia, tuberculosis, and healthy patients. The comparisons are drawn among the proposed deep transfer learning and deep forest-based models, the competitive models. The obtained results show that the proposed model effectively diagnoses COVID-19 infection with an accuracy of 99.4%.

COVID-19 Mortality Prediction using Machine Learning: A Deep Forest Approach

COVID-19 is an extremely deadly disease which has wreaked havoc worldwide. Initially, the first case was reported in the wet markets of Wuhan, China in the early 2020's. Though the mortality rate is low compared to other dangerous diseases, a lot of people have already succumbed to this virus. Vaccines have been successfully rolled out and it seems effective in preventing the severe symptoms of the coronavirus. However, a section of people (the elderly and people with existing comorbidities) still continue to die. It is extremely important to predict the patient vulnerability using machine learning since appropriate medicines and treatments can be given in time and precious lives can be saved. In this research, the deep forest classifier is utilized to predict the COVID-19 casualty status. This classifier requires extremely low hyperparameter tuning and can easily compete with the deep learning classifiers. This algorithm performed better than the traditional machine learning classifiers with an accuracy of 92%. The positive results obtained signifies the potential use of deep forest to prevent unwanted COVID-19 deaths by effectively deploying them in various medical facilities. Further, it can reduce the extreme burden already existing on healthcare systems caused by the novel coronavirus. © 2022 IEEE.

A Systematic Literature Review in Diagnosis and Severity Estimation of COVID-19 Disease using Machine Learning

In identification of severe acute respiratory syndrome corona virus 2(SARS-CoV-2), the novel corona virus responsible for COVID-19, professionals related to medical domain have been entered to implement various novel technical solutions and patient diagnosis techniques. The COVID-19 pandemic has accelerated enforcement of machine learning (ML) technology, and various other such organizational groups have been eager to embrace and adjust these ML techniques to the outbreak concerns. We have carried out a tremendous analysis based on the literature available till now. The complete assessment carried related to the use of machine learning models to fight against COVID-19, emphasis on various aspects like disease effects, it's diagnosis, percentage of severity estimation, drug and treatment analysis, effective feature selection, and also post-Covid context related. A systematic search of online research repositories which are Google Scholar, Web of Science and PubMed was undertaken in corresponding to the "Preferred Reporting items for Meta-Analysis and Systematic Reviews" criteria to find all related published papers during 2020 and 2022 years. The search process was created by integrating COVID-19-typical terms with the word "machine learning.". Copyright © 2022, Anka Publishers. All rights reserved.