Identifying highly talented athletes: Conception and design of an expert system

Specific to track and field

Diploma Thesis , 2007 , 157 Pages , Grade: 1,7

Sport - Kinematics and Training Theory

This work deals with the conception of an Expert System for the identification of talented athletes for athletic sprinting.
Expert Systems are a sub domain of Artificial Intelligence. They are a class of programs which simulate the reasoning capabilities of a human expert in the solution of complex, narrowly defined problems. Unlike conventional algorithms, they are capable of solving problems on the basis of incomplete or vague data, similar to a human expert. A key characteristic of Expert Systems is the strict separation of the problem-specific knowledge and the inference engine.
The short distance sprint is one of the oldest and most exciting athletic disciplines, dating back as far as the first Olympic Games. In spite of the relatively simple goal of this sport, to cover the given distance in the shortest possible time, this task demands highly complex technical and physical skills. These are presented in the second chapter together with an overview of the different phases of a sprint race (start, acceleration, maximum velocity).
This forms the basis of the talent identification methods presented in chapter three. A talent is a person that exhibits above average abilities or skills in a certain field or area. Talent search is usually restricted to the assessment of physical abilities. This is a gross reduction of the complexity of talent, as chapter three points out.
Based on this knowledge, a five phase engineering process was devised. This work presents this process, and this discourse is as such a concrete documentation of the work performed.
The first phase is characterized by planning and organizational activities, and is known as requirements analysis.
In the second phase, the requirements are concretized and elaborated. Within this work, the knowledge acquisition was performed during this stage.
In the third phase, the system architecture was designed. The shell d3web was presented and the major features of the front- and back-end were introduced.
This tool was then utilized in the fourth phase, the implementation phase, for the creation of a system prototype. The findings of phase two were used to construct the knowledge base.
The fifth phase is known as the deployment phase. Here the product is handed to the customer, and from this point on the developmental tasks are replaced by maintenance work.
The work is rounded off by a conclusion and a possible outlook regarding the future use of Expert Systems in sports.

Inhaltsverzeichnis (Table of Contents)

• 1 Introduction
• 2 Track and Field Sprint
• 2.1 History, Overview and Classification
• 2.2 The Skill of Running
• 2.2.1 Stride Length and Stride Frequency
• 2.2.2 The Race Sections
• 2.2.3 The Start and Acceleration Phase
• 2.2.4 Running at Maximum Velocity
• 2.3 Performance Structure
• 2.3.1 Emotional and Mental Attributes
• 2.3.2 Physical Fitness
• 2.3.2.1 Strength
• 2.3.2.2 Endurance
• 2.3.2.3 Flexibility
• 2.3.2.4 Speed
• 2.3.3 Technique and Coordinative Abilities
• 2.3.4 Other Factors
• 2.3.4.1 Physique
• 2.3.4.2 Tactical Abilities
• 3 The Search for Talent
• 3.1 The Elements of Talent
• 3.1.1 Distinctive Performance
• 3.1.2 Rate of Progression
• 3.1.3 Utilization
• 3.1.4 Physical Tolerance
• 3.1.5 Conclusion and Consequences
• 3.2 Successful Talent Identification Schemes
• 3.3 Talent Search with the Help of an Expert System
• 3.3.1 Goal
• 3.3.2 Limitations
• 3.3.3 Testing Procedures
• 3.3.3.1 Vertical Jump
• 3.3.3.2 40m Sprint
• 3.3.3.3 50m Bounding
• 3.3.4 Evaluation and Selection
• 4 Introduction to Expert Systems
• 4.1 Artificial Intelligence and the Emergence of Expert Systems
• 4.2 What are Expert Systems?
• 4.3 How do Expert Systems Work?
• 4.4 Expert Systems in Sports
• 4.4.1 RunCoach
• 4.4.2 Expert System for Tactical Player Positioning in Soccer
• 4.4.3 TESSY
• 5 An Expert System for Talent Identification
• 5.1 Phase 1 – Requirements Analysis and Planning
• 5.1.1 Project Management
• 5.1.2 Requirements Definition
• 5.1.3 Requirements Specification
• 5.2 Phase 2 - System Components Definition
• 5.2.1 Knowledge Acquisition
• 5.2.2 Evaluation of the Vertical Jump
• 5.2.3 Evaluation of the 40m Sprint
• 5.2.4 Evaluation of the 50m Bounding
• 5.2.5 Diagnoses
• 5.3 Phase 3 – Design
• 5.3.1 Prototyping the Shell
• 5.3.2 Introduction to d3web
• 5.3.2.1 The Back-End
• 5.3.2.2 The Front-End
• 5.4 Phase 4-Implementation
• 5.4.1 Setting Up the Knowledge Base
• 5.4.1.1 Diagnoses Set
• 5.4.1.2 Question Hierarchy
• 5.4.2 The Knowledge Implementation
• 5.4.2.1 The Rule Editor
• 5.4.2.2 Heuristic Decision Table
• 5.4.3 The User Interface
• 5.5 Phase 5 – Deployment and Maintenance
• 6 Summary

Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)

This thesis examines the potential of using an Expert System for identifying talented young athletes in track and field. The work aims to demonstrate the feasibility and limitations of this approach, drawing on existing research and case studies.

• Talent identification in track and field
• Expert systems in sports
• Development of an Expert System for talent identification
• Testing procedures for talent assessment
• Knowledge acquisition and representation

Zusammenfassung der Kapitel (Chapter Summaries)

• Chapter 1: Introduction This chapter introduces the topic of talent identification in track and field, highlighting the importance of identifying talented athletes at an early stage. It also provides a background on the history of track and field and the modern Olympic Games.
• Chapter 2: Track and Field Sprint This chapter focuses on the sprint events in track and field, providing an overview of the sport's history, classification, and key skills. It also discusses the physical, emotional, and mental attributes needed for success in sprinting.
• Chapter 3: The Search for Talent This chapter delves into the topic of talent identification, exploring different approaches and methods used to identify talented athletes. It also examines the elements of talent, including distinctive performance, rate of progression, and physical tolerance.
• Chapter 4: Introduction to Expert Systems This chapter introduces the concept of expert systems, outlining their history, development, and applications in various fields, particularly in sports.
• Chapter 5: An Expert System for Talent Identification This chapter details the process of designing and implementing an Expert System specifically for talent identification in track and field. It covers the different stages of the project, including requirements analysis, system components definition, design, implementation, and deployment.

Schlüsselwörter (Keywords)

This work focuses on the application of Expert Systems for talent identification in track and field, utilizing key concepts such as artificial intelligence, knowledge acquisition, testing procedures, and performance evaluation.

• College: Technical University of Darmstadt (Institut für Sportwissenschaft)
• Grade: 1,7
• Author: Johannes Chun (Author)
• Publication Year: 2007
• Pages: 157
• Catalog Number: V73598
• ISBN (eBook): 9783638678636
• ISBN (Book): 9783638680813
• Language: English
• Tags: Identifying, Conception