Ntambara etienne (4 resultados)

Taschenbuch. Condición: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware 92 pp. Englisch.

Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - This book presents a machine learning framework for placing students into suitable technical programs at Rwanda Polytechnic. Using 399 student records and 128 curriculum-aligned features from Rwanda's national examination results, Artificial Neural Network, XGBoost, and Random Forest models were trained and compared across 13 technical programs. The Artificial Neural Network achieved 94% testing accuracy with a minimal generalization gap. SHAP, LIME, permutation importance, and mutual-information analyses were used to explain predictions and identify influential features. The study also examines class imbalance, fairness, confidence-based human-AI decision routing, dimensionality, feature selection, robustness, and ensemble feature importance. Worked recommendation examples demonstrate practical application. A deployment blueprint aligned with available institutional hardware is also proposed. The framework offers researchers, administrators, and policymakers a transparent and practical approach to responsible AI-assisted student admission and placement in technical and vocational education.…

Taschenbuch. Condición: Neu. Artificial Intelligence for Student Admission and Placement in TVET | AI-Driven Field Recommendations for Incoming Students at Rwanda Polytechnic | Ntambara Etienne | Taschenbuch | Englisch | 2026 | GlobeEdit | EAN 9786630253306 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu Print on Demand. …

Taschenbuch. Condición: Neu. This item is printed on demand - Print on Demand Titel. Neuware -This book presents a machine learning framework for placing students into suitable technical programs at Rwanda Polytechnic. Using 399 student records and 128 curriculum-aligned features from Rwanda's national examination results, Artificial Neural Network, XGBoost, and Random Forest models were trained and compared across 13 technical programs. The Artificial Neural Network achieved 94% testing accuracy with a minimal generalization gap. SHAP, LIME, permutation importance, and mutual-information analyses were used to explain predictions and identify influential features. The study also examines class imbalance, fairness, confidence-based human-AI decision routing, dimensionality, feature selection, robustness, and ensemble feature importance. Worked recommendation examples demonstrate practical application. A deployment blueprint aligned with available institutional hardware is also proposed. The framework offers researchers, administrators, and policymakers a transparent and practical approach to responsible AI-assisted student admission and placement in technical and vocational education. 92 pp. Englisch.…