Feature importance analysis.

Feature importance analysis.

<p>Feature importance analysis using SHAP for three models: (a, d) logistic regression, (b, e) random forest, and (c, f) deep neural network.</p>

Saved in:

Bibliographic Details
Main Author:	Wei Yin (64393) (author)
Other Authors:	Sanad H. Ragab (22615302) (author), Michael G. Tyshenko (11719009) (author), Teresa Feria Arroyo (22615305) (author), Tamer Oraby (3073227) (author)
Published:	2025
Subjects:	Ecology Sociology Virology Astronomical and Space Sciences not elsewhere classified Biological Sciences not elsewhere classified west nile virus random forest classifier potential geographic distribution perform various tasks great prediction tools div >< p several machine learning comparing machine learning called reinforcement learning dqn ), reinforce deep neural networks culex pipiens </ common house mosquito reinforcement learning performance predicting species distribution pipiens </ deep learning wnv ), rl ), deep q training agents subtropical regions study objective results revealed primary vector predictive modeling logistic regression limited resources including q classification problems changing environments borne pathogen another set annual precipitation affects humans
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	<p>Feature importance analysis using SHAP for three models: (a, d) logistic regression, (b, e) random forest, and (c, f) deep neural network.</p>

Cannot write session to /tmp/vufind_sessions/sess_ad94as37b80p0o0prp45rctkmr