{"id":{"repo_id":"nps","oai_identifier":"oai:calhoun.nps.edu:10945/74164"},"canonical_url":"https://search.dev.ndltd.org/etd/nps/oai:calhoun.nps.edu:10945/74164","repository":{"repo_id":"nps","name":"Naval Postgraduate School","base_url":"https://calhoun.nps.edu/server/oai/request"},"display":{"title":"ANALYZING AND PREDICTING ARMY COMBAT FITNESS TEST PERFORMANCE: A STATISTICAL AND MACHINE LEARNING APPROACH","abstract":"The United States Army emphasizes physical fitness as critical to operational readiness and transitioned from the Army Physical Fitness Test (APFT) to the Army Combat Fitness Test to reflect modern combat demands better and minimize injuries. This thesis applies machine learning techniques—including Logistic Regression (LR), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Random Forests (RF), and Artificial Neural Networks (ANN)—to predict ACFT outcomes using raw ACFT scores alongside demographic and body composition data. The analysis evaluates two feature subsets. One subset combines detailed ACFT event scores and body composition data, while the other relies solely on demographic and anthropometric data. We found that artificial neural networks achieve the highest predictive accuracy, underscoring their effectiveness in capturing complex, nonlinear relationships. ACFT event scores significantly improve prediction accuracy by approximately ten percentage points over demographic factors alone. Key predictors include 2-mile run time for ACFT-specific data and body mass index (BMI) among demographic and anthropometric variables. These insights can guide future Army fitness assessments by prioritizing critical predictors, optimizing testing procedures, and improving resource allocation.","abstract_html":"The United States Army emphasizes physical fitness as critical to operational readiness and transitioned from the Army Physical Fitness Test (APFT) to the Army Combat Fitness Test to reflect modern combat demands better and minimize injuries. This thesis applies machine learning techniques—including Logistic Regression (LR), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Random Forests (RF), and Artificial Neural Networks (ANN)—to predict ACFT outcomes using raw ACFT scores alongside demographic and body composition data. The analysis evaluates two feature subsets. One subset combines detailed ACFT event scores and body composition data, while the other relies solely on demographic and anthropometric data. We found that artificial neural networks achieve the highest predictive accuracy, underscoring their effectiveness in capturing complex, nonlinear relationships. ACFT event scores significantly improve prediction accuracy by approximately ten percentage points over demographic factors alone. Key predictors include 2-mile run time for ACFT-specific data and body mass index (BMI) among demographic and anthropometric variables. These insights can guide future Army fitness assessments by prioritizing critical predictors, optimizing testing procedures, and improving resource allocation.","abstract_has_math":false,"creators":["Ozga, George A."],"institution":"Monterey, CA; Naval Postgraduate School","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Applied Mathematics (MA)","school":null,"contributors":[],"advisors":["Zhou, Hong"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-06","date_published":"2025-06","updated_at":"2026-07-27T20:24:57Z","subjects":[],"languages":[],"rights":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10945/74164","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Zhou, Hong"]},{"key":"dc:contributor.department","label":"Department","values":["Applied Mathematics (MA)"]},{"key":"dc:creator","label":"Author","values":["Ozga, George A."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-08T15:51:48Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-08T15:51:48Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-06"]},{"key":"dc:publisher","label":"Institution","values":["Monterey, CA; Naval Postgraduate School"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10945/74164"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The United States Army emphasizes physical fitness as critical to operational readiness and transitioned from the Army Physical Fitness Test (APFT) to the Army Combat Fitness Test to reflect modern combat demands better and minimize injuries. This thesis applies machine learning techniques—including Logistic Regression (LR), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Random Forests (RF), and Artificial Neural Networks (ANN)—to predict ACFT outcomes using raw ACFT scores alongside demographic and body composition data. The analysis evaluates two feature subsets. One subset combines detailed ACFT event scores and body composition data, while the other relies solely on demographic and anthropometric data. We found that artificial neural networks achieve the highest predictive accuracy, underscoring their effectiveness in capturing complex, nonlinear relationships. ACFT event scores significantly improve prediction accuracy by approximately ten percentage points over demographic factors alone. Key predictors include 2-mile run time for ACFT-specific data and body mass index (BMI) among demographic and anthropometric variables. These insights can guide future Army fitness assessments by prioritizing critical predictors, optimizing testing procedures, and improving resource allocation."]},{"key":"dc:title","label":"Title","values":["ANALYZING AND PREDICTING ARMY COMBAT FITNESS TEST PERFORMANCE: A STATISTICAL AND MACHINE LEARNING APPROACH"]}]}],"canonical_facts":{"dc:contributor.advisor":["Zhou, Hong"],"dc:contributor.department":["Applied Mathematics (MA)"],"dc:creator":["Ozga, George A."],"dc:date.accessioned":["2025-09-08T15:51:48Z"],"dc:date.available":["2025-09-08T15:51:48Z"],"dc:date.issued":["2025-06"],"dc:description.abstract":["The United States Army emphasizes physical fitness as critical to operational readiness and transitioned from the Army Physical Fitness Test (APFT) to the Army Combat Fitness Test to reflect modern combat demands better and minimize injuries. This thesis applies machine learning techniques—including Logistic Regression (LR), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Random Forests (RF), and Artificial Neural Networks (ANN)—to predict ACFT outcomes using raw ACFT scores alongside demographic and body composition data. The analysis evaluates two feature subsets. One subset combines detailed ACFT event scores and body composition data, while the other relies solely on demographic and anthropometric data. We found that artificial neural networks achieve the highest predictive accuracy, underscoring their effectiveness in capturing complex, nonlinear relationships. ACFT event scores significantly improve prediction accuracy by approximately ten percentage points over demographic factors alone. Key predictors include 2-mile run time for ACFT-specific data and body mass index (BMI) among demographic and anthropometric variables. These insights can guide future Army fitness assessments by prioritizing critical predictors, optimizing testing procedures, and improving resource allocation."],"dc:identifier.uri":["https://hdl.handle.net/10945/74164"],"dc:publisher":["Monterey, CA; Naval Postgraduate School"],"dc:rights":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."],"dc:title":["ANALYZING AND PREDICTING ARMY COMBAT FITNESS TEST PERFORMANCE: A STATISTICAL AND MACHINE LEARNING APPROACH"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:24:57Z"}