ABSTRACT
Knowledge of internal load is essential to understand the effect of training and competition on athletes. The aim of this study was to analyse the validity of the rate of perceived exertion (RPE) scale as an indicator of intensity in amateur female basketball players during a relegation play-off. The heart rate and RPE of 10 players (age: 21.30 ± 2.71 years, weight: 68.84 ± 11.21 kg, body fat: 20.74 ± 3.51%) from a Copa Catalunya team while competing over a 10-day period were analysed. The mean heart rate of each match was registered with the Suunto Team Pack™ heart rate monitors. The RPE values were obtained once the match ended, completing the original Borg scale. The mean RPE ranged from 15.20 ± 2.39 to 18.00 ± 1.07 AU, whereas the mean heart rate (MHR) ranged from 132.35 ± 12.37 to 147.33 ± 10.61 bpm. There was also an improvement in the statistical correlation between the two variables as the days progressed. Regression equations were calculated for the total number of registered matches and the last five matches, obtaining the following regression equations: MHR = 6.23 × RPE20 + 36.8 (R2 = 0.56) for all games and MHR = 30.95 + 6.73 × RPE (R2 = 0.73) for the last five games. The results suggest that RPE could be seen as an indicator of intensity in amateur basketball players during a relegation play-off, improving their relationship with MHR as the weeks went by, which could suggest a learning process.
ABSTRACT
The urban population is growing at such a rate that by 2050 it is estimated that 84% of the world's population will live in cities, with flats being the most common living place. Moreover, WiFi technology is present in most developed country urban areas, with a quick growth in developing countries. New Ambient-Assisted Living applications will be developed in the near future having user positioning as ground technology: elderly tele-care, energy consumption, security and the like are strongly based on indoor positioning information. We present an Indoor Positioning System for wearable devices based on WiFi fingerprinting. Smart-watch wearable devices are used to acquire the WiFi strength signals of the surrounding Wireless Access Points used to build an ensemble of Machine Learning classification algorithms. Once built, the ensemble algorithm is used to locate a user based on the WiFi strength signals provided by the wearable device. Experimental results for five different urban flats are reported, showing that the system is robust and reliable enough for locating a user at room level into his/her home. Another interesting characteristic of the presented system is that it does not require deployment of any infrastructure, and it is unobtrusive, the only device required for it to work is a smart-watch.
