In this day and age, Association football is the global sport worldwide, whether as hobbies, careers, or a part of fitness regimens, because they are uniquely democratic team sports. It is inconsequential whether footballer’s height, color skin, financial status and age are different. According to FIFA, there are 270 million people play association football, which is four percent of the world’s population. The association footballer is repeatedly endangered by musculoskeletal injuries, some of the injuries are due to the overload of their training program.
In this research project, the project team research and find a solution to prevent these injuries by using sensor technology and machine learning techniques to detect and analyse the signs and symptoms of overtraining syndrome in footballers.
The project focus on the research question “How can we develop an effectively applicable tool that can validly measure the external and internal training load and help medical staff and physical trainer detect (potential) overload, and thus help to make the right intervention to prevent injuries”.
The project’s goal was created a machine learning framework, which can run a pre-season health examination based on footballer’s training data with high accuracy. Therefore, this framework could be developed, optimized and extended in the future. The mandatory requirements for this framework are easy to configure without complicit programming via Python API, the result of pre-season health examination from machine learning framework had the high accuracy and reliability.
In this chapter the literatures with information about internal stress are described.
Effect of hot environmental conditions on physical activity patterns and temperature response of soccer players (2010, pp. 140-147) was published in Scandinavian journal of medicine & science in sports. This research was funded and supported by Turkish Football Federation and FIFA Football Medicine and Research Centre (FMARC). The main purpose of this research was evaluated thermal responses and physical activities of footballers during matches through hot environmental conditions. To evaluate the results, GPS monitor and Heart rate value are the two main variables.
As reported, the Garma watch gathered data from the start to the end of match. These data will be explored and analyzed to discover the effect of environment on the player performance. The following physical activities were applied to the GPS data: standing (0-0.4 km/h), walking (0.5-7.5 km/h), jogging (7.6-14.5 km/h), low-moderate intensity running (14.6-19.5km/h), high-intensity running (19.6-25.5 km/h) and sprinting (42.56 km/h). Therefore, the heart rated data will be measured and marked with the time period for further analysis of heart rate and speed.
From June to July 2007 in the city of Adana, the mean temperature range was around 35°C (moderate heat) and 49°C (high heat). The highest core temperature of footballers was reached 40.2 in high heat match (HH). However, after the warm-up session, the core temperature of footballers was recorded between 37.6 °C to 37.7 °C in moderate heat match (MH).
The average heart rate in the first half of the game was lower than the MH match with around 171 beats/ minute and higher in the second half with 164 beats/minute. Concerning HH match, the mean heart rate was lower than MH which were 169 beats/minutes in the first half and 155 beats/minute in the rest. In whatever way, the higher sweat rate and dehydration were the evidence for the core body temperature increased with the higher distance covered.
This research is valuable because it determined the relationship between heart rate and temperature. However, the current data set is not containing the temperature value. In the future, the weather feature could be added to FC Twente data to improve the accuracy of machine learning model in the future.
👋 Hi! I’m your smart assistant Amy!
Don’t know where to start? Type your requirements and I’ll connect you to an academic expert within 3 minutes.get help with your assignment