A low complexity system based on multiple weighted decision trees for indoor localization

[EN] Indoor position estimation has become an attractive research topic due to growing interest in location-aware services. Nevertheless, satisfying solutions have not been found with the considerations of both accuracy and system complexity. From the perspective of lightweight mobile devices, they are extremely important characteristics, because both the processor power and energy availability are limited. Hence, an indoor localization system with high computational complexity can cause complete battery drain within a few hours. In our research, we use a data mining technique named boosting to develop a localization system based on multiple weighted decision trees to predict the device location, since it has high accuracy and low computational complexity.

Adiposity and age explain most of the association between physical activity and fitness in physically active men

[EN] BACKGROUND: To determine if there is an association between physical activity assessed by the short version of the International Physical Activity Questionnaire (IPAQ) and cardiorespiratory and muscular fitness. METHODOLOGY/PRINCIPAL FINDINGS: One hundred and eighty-two young males (age range: 20-55 years) completed the short form of the IPAQ to assess physical activity. Body composition (dual-energy X-Ray absorptiometry), muscular fitness (static and dynamic muscle force and power, vertical jump height, running speed [30 m sprint], anaerobic capacity [300 m running test]) and cardiorespiratory fitness (estimated VO(2)max: 20 m shuttle run test) were also determined in all subjects. Activity-related energy expenditure of moderate and vigorous intensity (EEPA(moderate) and EEPA(vigorous), respectively) was inversely associated with indices of adiposity (r = -0.21 to -0.37, P<0.05). Cardiorespiratory fitness (VO(2)max) was positively associated with LogEEPA(moderate) (r = 0.26, P<0.05) and LogEEPA(vigorous) (r = 0.27). However, no association between VO(2)max with LogEEPA(moderate), LogEPPA(vigorous) and LogEEPA(total) was observed after adjusting for the percentage of body fat. Multiple stepwise regression analysis to predict VO(2)max from LogEEPA(walking), LogEEPA(moderate), LogEEPA(vigorous), LogEEPA(total), age and percentage of body fat (%fat) showed that the %fat alone explained 62% of the variance in VO(2)max and that the age added another 10%, while the other variables did not add predictive value to the model [VO(2)max = 129.6-(25.1x Log %fat) - (34.0x Log age); SEE: 4.3 ml.kg(-1). min(-1); R(2) = 0.72 (P<0.05)]. No positive association between muscular fitness-related variables and physical activity was observed, even after adjusting for body fat or body fat and age. CONCLUSIONS/SIGNIFICANCE: Adiposity and age are the strongest predictors of VO(2)max in healthy men. The energy expended in moderate and vigorous physical activities is inversely associated with adiposity. Muscular fitness does not appear to be associated with physical activity as assessed by the IPAQ.