<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Artificial intelligence technology is rapidly developing and has been widely used in various industries, for the current social focus on ideology and politics, so this paper uses artificial intelligence technology to study the ideological elements of public mental health courses in colleges and universities. We measure the dataset so that the number of samples is not too large, select the smallest subset of features according to the criteria, make the classifier less complex and improve its ability to generalize the algorithm, remove redundant or irrelevant features, and simplify the dataset to achieve dimensionality reduction. The probability relationship between the attribute set and the class variable is modeled using Bayesian, and the category corresponding to the guess with the highest probability is selected to obtain the classification effect in the supervised learning sample set, and the probabilities are estimated from the training tuples, considering two different attribute types separately. Combined with the logistic regression model to obtain the weights of the independent variables, the output likelihood is calculated according to the selected parameters, the appropriate parameter vector for the model is found, and the parameter that minimizes the cost function is found to complete the mining of the SiM elements. The analysis results show that artificial intelligence technology has better accuracy and prediction in performance, and it is concluded that moral education is the best development and physical education is the relatively worst in the study of Civic and Political Science elements, with a different value of 5.48%, and after deepening teaching will make the elements balanced and students develop better in all aspects.</p>
</abstract>

Artificial intelligence technology is rapidly developing and has been widely used in various industries, for the current social focus on ideology and politics, so this paper uses artificial intelligence technology to study the ideological elements of public mental health courses in colleges and universities. We measure the dataset so that the number of samples is not too large, select the smallest subset of features according to the criteria, make the classifier less complex and improve its ability to generalize the algorithm, remove redundant or irrelevant features, and simplify the dataset to achieve dimensionality reduction. The probability relationship between the attribute set and the class variable is modeled using Bayesian, and the category corresponding to the guess with the highest probability is selected to obtain the classification effect in the supervised learning sample set, and the probabilities are estimated from the training tuples, considering two different attribute types separately. Combined with the logistic regression model to obtain the weights of the independent variables, the output likelihood is calculated according to the selected parameters, the appropriate parameter vector for the model is found, and the parameter that minimizes the cost function is found to complete the mining of the SiM elements. The analysis results show that artificial intelligence technology has better accuracy and prediction in performance, and it is concluded that moral education is the best development and physical education is the relatively worst in the study of Civic and Political Science elements, with a different value of 5.48%, and after deepening teaching will make the elements balanced and students develop better in all aspects.

Artificial intelligence technology-based approach to mining Civic Science elements in public mental health courses in universities

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Artificial intelligence technology is rapidly developing and has been widely used in various industries, for the current social focus on ideology and politics,...

Artificial intelligence technology-based approach to mining Civic Science elements in public mental health courses in universities

Publié en ligne: 18 mai 2023

Pages: -

Reçu: 06 juin 2022

Accepté: 11 nov. 2022

DOI: https://doi.org/10.2478/amns.2023.1.00261

Mots clés
Artificial intelligence technology, Mental health thinking element, Feature selection, Bayesian, Logistic regression model

© 2023 Xi Zhang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Artificial intelligence technology-based approach to mining Civic Science elements in public mental health courses in universities

Publié en ligne: 18 mai 2023

Pages: -

Reçu: 06 juin 2022

Accepté: 11 nov. 2022

DOI: https://doi.org/10.2478/amns.2023.1.00261

Mots clésArtificial intelligence technology, Mental health thinking element, Feature selection, Bayesian, Logistic regression model

© 2023 Xi Zhang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Artificial intelligence technology, Mental health thinking element, Feature selection, Bayesian, Logistic regression model