Related Experiment Video
Updated: Jul 26, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
An automatic and personalized recommendation modelling in activity eCoaching with deep learning and ontology.
Ayan Chatterjee1,2, Andreas Prinz3, Michael Alexander Riegler4
1Department of Information and Communication Technology, University of Agder, 4879, Grimstad, Norway. ayan.chatterjee@uia.no.
This study introduces a novel deep learning and semantic ontology approach for personalized eCoaching recommendations, specifically for physical activity. The hybrid model achieves high accuracy in forecasting and classification, enhancing user guidance.
Area of Science:
- * Computer Science
- * Artificial Intelligence
- * Health Informatics
Background:
- * Electronic coaching (eCoach) aims to optimize human behavior for goal achievement.
- * Automatic generation of personalized recommendations in eCoaching is a significant challenge.
- * Current methods lack the sophistication for truly individualized guidance.
Purpose of the Study:
- * To develop a novel approach for generating hybrid and personalized recommendations in eCoaching.
- * To utilize deep learning and semantic ontologies for enhanced recommendation systems.
- * To apply and evaluate the approach using physical activity as a case study.
Main Methods:
- * Employed time-series forecasting (CNN1D, LSTM, GRU) and classification (MLP, Rocket).
- * Integrated processed data into activity datasets using the OntoeCoach semantic ontology.
- * Utilized SPARQL for semantic representation, reasoning, and understandable recommendation generation.
Main Results:
- * The CNN1D model achieved 97% prediction accuracy; MLP classifier reached 74% accuracy.
- * OntoeCoach ontology demonstrated effective recommendation planning and generation.
- * Evaluation conducted on public (PMData) and private (MOX2-5) activity datasets.
Conclusions:
- * The proposed hybrid approach effectively generates personalized physical activity recommendations.
- * OntoeCoach ontology enhances interpretability and reasoning capabilities in eCoaching.
- * This research advances the field of personalized behavior optimization through intelligent systems.
More Related Videos
Related Concept Videos
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Observational Learning
Associative Learning
Classical conditioning, also known...
Natural and Artificial Concepts
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Purposive Learning

