DEVELOPMENT OF A PREDICTIVE SYSTEM FOR PREDICTING PREGNANCY COMPLICATIONS IN WOMEN USING MACHINE LEARNING ALGORITHMS

By: AYODELE OLUWATOBI OLUWANIFEMIMaterial type: TextTextPublisher: Ibafo Computer Science and Mathematics 2022Edition: Dr. (Mrs.) Chinwe P. IgiriDescription: xi,; 43pSubject(s): Computer ScienceSummary: This study is aimed at the application of predicting pregnancy complication with the use of different machine algorithms. The study achieved this by eliciting knowledge on the variables, collecting relevant data, formulating the classification model, simulating the model. The use of different articles/studies were used as a guiding tools in the means of gathering the necessary data and features needed. The result of the study showed that out 11 variables, 7 variables were associated with the classification of predicting pregnancy complications. The result also identified a number of variables which had missing values from the data collected. The simulation showed that the higher the proportion of dataset used for training then the higher performance of the model on the testing dataset. So using 90% of the dataset for training and 10% for dataset for testing showed the highest performance.
Tags from this library: No tags from this library for this title. Log in to add tags.
    Average rating: 0.0 (0 votes)
Current location Call number Status Date due Barcode Item holds
Main Library
Not for loan 18010301063
Total holds: 0

This study is aimed at the application of predicting pregnancy complication with the use of different machine algorithms. The study achieved this by eliciting knowledge on the variables, collecting relevant data, formulating the classification model, simulating the
model. The use of different articles/studies were used as a guiding tools in the means of gathering the necessary data and features needed. The result of the study showed that out 11 variables, 7 variables were associated with the classification of predicting pregnancy complications. The result also identified a number of variables which had missing values from the data collected. The simulation showed that the higher the proportion of dataset used for training then the higher performance of the model on the testing dataset. So using 90% of the dataset for training and 10% for dataset for testing showed the highest performance.

There are no comments on this title.

to post a comment.

Powered by Koha