Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Launch Supplement

University of Alberta

$12,500.00

Beyond Trial and Error: A Data-Driven Framework for Personalized Human-in-the-Loop Training Optimization

EF 2024-25

Résumé
Motivation for Developing a Data-Driven Framework for Enhancing Training Efficiency Skill learning is essential in our daily lives, with implications for healthcare, sports, and professional training. The "Optimal Challenge Point" framework is an accepted model that explains the influencing factors in learning efficiency. This framework suggests that learning is maximized when the training challenge lies within the "sweet spot" for the learner's current abilities. However, the Optimal Challenge Point framework does not provide systematic ways of changing the training regimens. This is particularly important when training with a robot or a simulator, where we can measure data to quantify training efficiency. Proposed Program Objectives The long-term goal of this NSERC DG program is to develop fundamental knowledge to implement a data-driven framework for enhancing training efficiency. We aim to optimize the training schedule, difficulty, and feedback with minimum reliance on pre-recorded data. To achieve this long-term goal, we will pursue four short-term objectives: (1) quantify learners' overall skill level when learning multiple tasks through performance metrics; (2) determine learners' Optimal Challenge Point by combining their skill and engagement levels; (3) optimize training schedule and difficulty by predicting learners' performance for various training scenarios; and (4) provide interpretable information to guide the training based on individuals' learning stage. To achieve these objectives, we will employ advanced data processing methods and (un)supervised Machine Learning within three Subprograms. While the real-world applications are diverse, as an example, we will focus on learning robotic games in young, healthy individuals.  Impact of the Proposed Research Given its data-driven nature, the proposed training optimization framework can, in the future, be customized for diverse settings. Beyond its fundamental scientific contributions, which will pave the way for future innovations in various domains, the proposed program has substantial socio-economic impacts and addresses Canada's priorities in the following areas: Healthcare: Delivering cost-effective and efficient personalized therapy and personnel training using robotic systems, aligned with the CIHR's Strategic Action Plan on Training. Sports: Developing personalized training regimens using sports simulators (e.g., skiing, motor racing, rowing) aligned with the Canadian High-Performance Sport Strategy. Defence: Boosting personnel training in using specialized equipment (e.g., flight simulators) aligned with the Strong, Secure, and Engaged defence policy. Social: Providing technical, scientific, and soft skill training for Highly Qualified Personnel, making them attractive for advanced career opportunities in industry and academia.
Programme
Discovery Launch Supplement
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
DGECR-2024-00324
Name nom
Nazarahari, Milad
Department département
Department of Mechanical Engineering
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
12500
Program id
DGECR
Program name en
Discovery Launch Supplement
Program name fr
Supplément Tremplin vers la découverte
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1512
Committee name en
Mechanical Engineering
Committee name fr
Génie mécanique
Area of application code
1102
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Biomedical engineering
Area of application fr
Génie biomédical
Research subject code
1901
Research subject group en
Biomedical engineering
Research subject group fr
Génie biomédical
Research subject en
Biomedical technology
Research subject fr
Technologie biomédicale
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Beyond Trial and Error: A Data-Driven Framework for Personalized Human-in-the-Loop Training Optimization
Keywords
optimal challenge point; human-in-the-loop training optimization; phenomenological modelling; functional task difficulty; performance metrics; engagement level; augmented feedback; machine learning; fuzzy inference systems; statistical methods
Application summary
Motivation for Developing a Data-Driven Framework for Enhancing Training Efficiency Skill learning is essential in our daily lives, with implications for healthcare, sports, and professional training. The "Optimal Challenge Point" framework is an accepted model that explains the influencing factors in learning efficiency. This framework suggests that learning is maximized when the training challenge lies within the "sweet spot" for the learner's current abilities. However, the Optimal Challenge Point framework does not provide systematic ways of changing the training regimens. This is particularly important when training with a robot or a simulator, where we can measure data to quantify training efficiency. Proposed Program Objectives The long-term goal of this NSERC DG program is to develop fundamental knowledge to implement a data-driven framework for enhancing training efficiency. We aim to optimize the training schedule, difficulty, and feedback with minimum reliance on pre-recorded data. To achieve this long-term goal, we will pursue four short-term objectives: (1) quantify learners' overall skill level when learning multiple tasks through performance metrics; (2) determine learners' Optimal Challenge Point by combining their skill and engagement levels; (3) optimize training schedule and difficulty by predicting learners' performance for various training scenarios; and (4) provide interpretable information to guide the training based on individuals' learning stage. To achieve these objectives, we will employ advanced data processing methods and (un)supervised Machine Learning within three Subprograms. While the real-world applications are diverse, as an example, we will focus on learning robotic games in young, healthy individuals.  Impact of the Proposed Research Given its data-driven nature, the proposed training optimization framework can, in the future, be customized for diverse settings. Beyond its fundamental scientific contributions, which will pave the way for future innovations in various domains, the proposed program has substantial socio-economic impacts and addresses Canada's priorities in the following areas: Healthcare: Delivering cost-effective and efficient personalized therapy and personnel training using robotic systems, aligned with the CIHR's Strategic Action Plan on Training. Sports: Developing personalized training regimens using sports simulators (e.g., skiing, motor racing, rowing) aligned with the Canadian High-Performance Sport Strategy. Defence: Boosting personnel training in using specialized equipment (e.g., flight simulators) aligned with the Strong, Secure, and Engaged defence policy. Social: Providing technical, scientific, and soft skill training for Highly Qualified Personnel, making them attractive for advanced career opportunities in industry and academia.