Dataset Information

Analyzing COVID-19 Using Multisource Data: An Integrated Approach of Visualization, Spatial Regression, and Machine Learning.

ABSTRACT: Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2, was first identified in Wuhan, China, in December 2019. As the number of COVID-19 infections and deaths worldwide continues to increase rapidly, the prevention and control of COVID-19 remains urgent. This article aims to analyze COVID-19 from a geographical perspective, and this information can provide useful insights for rapid visualization of spatial-temporal epidemic information and identification of the factors important to the spread of COVID-19. A new type of vitalization method, called the point grid map, is integrated with calendar-based visualization to show the spatial-temporal variations in COVID-19. The combination of mixed geographically weighted regression (mixed GWR) and extreme gradient boosting (XGBoost) is used to identify the potential factors and the corresponding importance. The visualization results clearly reflect the spatial-temporal patterns of COVID-19. The quantified results reveal that the impact of population outflow from Wuhan is the most important factor and indicate statistically significant spatial heterogeneity. Our results provide insights into how multisource big geodata can be employed within the framework of integrating visualization and analytical methods to characterize COVID-19 trends. In addition, this work can help understand the influential factors for controlling and preventing epidemics, which is important for policy design and effective decision-making for controlling COVID-19. The results reveal that one of the most effective ways to control COVID-19 include controlling the source of infection, cutting off the transmission route, and protecting vulnerable groups.

SUBMITTER: Wu C

PROVIDER: S-EPMC8335962 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The ecological effects of accidental or malicious radioactive contamination are insufficiently understood because of the hazards and difficulties associated with conducting studies in radioactively-polluted areas. Data sets from severely contaminated locations can therefore be small. Moreover, many potentially important factors, such as soil concentrations of toxic chemicals, pH, and temperature, can be correlated with radiation levels and with each other. In such situations, commonly-used statistical techniques like generalized linear models (GLMs) may not be able to provide useful information about how radiation and/or these other variables affect the outcome (e.g. abundance of the studied organisms). Ensemble machine learning methods such as random forests offer powerful alternatives. We propose that analysis of small radioecological data sets by GLMs and/or machine learning can be made more informative by using the following techniques: (1) adding synthetic noise variables to provide benchmarks for distinguishing the performances of valuable predictors from irrelevant ones; (2) adding noise directly to the predictors and/or to the outcome to test the robustness of analysis results against random data fluctuations; (3) adding artificial effects to selected predictors to test the sensitivity of the analysis methods in detecting predictor effects; (4) running a selected machine learning method multiple times (with different random-number seeds) to test the robustness of the detected "signal"; (5) using several machine learning methods to test the "signal's" sensitivity to differences in analysis techniques. Here, we applied these approaches to simulated data, and to two published examples of small radioecological data sets: (I) counts of fungal taxa in samples of soil contaminated by the Chernobyl nuclear power plan accident (Ukraine), and (II) bacterial abundance in soil samples under a ruptured nuclear waste storage tank (USA). We show that the proposed techniques were advantageous compared with the methodology used in the original publications where the data sets were presented. Specifically, our approach identified a negative effect of radioactive contamination in data set I, and suggested that in data set II stable chromium could have been a stronger limiting factor for bacterial abundance than the radionuclides 137Cs and 99Tc. This new information, which was extracted from these data sets using the proposed techniques, can potentially enhance the design of radioactive waste bioremediation.

Project description:The COVID-19 pandemic has worsened the psychological and social stress levels of university students due to physical illness, enhanced dependence on mobile devices and internet, a lack of social activities, and home confinement. Therefore, early stress detection is crucial for their successful academic performance and mental well-being. The advent of machine learning (ML)-based prediction models can have a crucial impact in predicting stress at its early stages and taking necessary steps for the well-being of individuals. This study aims to develop a reliable machine learning-based prediction model for perceived stress prediction and validate the model using real-world data collected through an online survey among 444 university students from different ethnicity. The machine learning models were built using supervised machine learning algorithms. Principal Component Analysis (PCA) and the chi-squared test were employed as feature reduction techniques. Moreover, Grid Search Cross-Validation (GSCV) and Genetic Algorithm (GA) were employed for hyperparameter optimization (HPO). According to the findings, around 11.26% of individuals were identified with high levels of social stress. In comparison, approximately 24.10% of people were found to be suffering from extremely high psychological stress, which is quite alarming for students' mental health. Furthermore, the prediction results of the ML models demonstrated the most remarkable accuracy (80.5%), precision (1.000), F1 score (0.890), and recall value (0.826). The Multilayer Perceptron model was shown to have the maximum accuracy when combined with PCA as a feature reduction approach and GSCV for HPO. The convenience sampling technique used in this study only considers self-reported data, which may have biased results and lack generalizability. Future research should consider a large sample of data and focus on tracking long-term impacts with coping strategies and interventions. The results of this study can be used to develop strategies to mitigate adverse effects of the overuse of mobile devices and promote student well-being during pandemics and other stressful situations.

Dataset Information

Analyzing COVID-19 Using Multisource Data: An Integrated Approach of Visualization, Spatial Regression, and Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets