Semi-supervised dimensionality reduction based on partial least squares for visual analysis of high dimensional data

Dimensionality reduction is employed for visual data analysis as a way to obtaining reduced spaces for high dimensional data or to mapping data directly into 2D or 3D spaces. Although techniques have evolved to improve data segregation on reduced or visual spaces, they have limited capabilities for adjusting the results according to user's knowledge. In this paper, we propose a novel approach to handling both dimensionality reduction and visualization of high dimensional data, taking into account user's input. It employs Partial Least Squares (PLS), a statistical tool to perform retrieval of latent spaces focusing on the discriminability of the data. The method employs a training set for building a highly precise model that can then be applied to a much larger data set very effectively. The reduced data set can be exhibited using various existing visualization techniques. The training data is important to code user's knowledge into the loop. However, this work also devises a strategy for calculating PLS reduced spaces when no training data is available. The approach produces increasingly precise visual mappings as the user feeds back his or her knowledge and is capable of working with small and unbalanced training sets.

Similar health benefits of endurance and high-intensity interval training in obese children

Purpose: To compare two modalities of exercise training (i.e., Endurance Training [ET] and High-Intensity Interval Training [HIT]) on health-related parameters in obese children aged between 8 and 12 years. Methods: Thirty obese children were randomly allocated into either the ET or HIT group. The ET group performed a 30 to 60-minute continuous exercise at 80% of the peak heart rate (HR). The HIT group training performed 3 to 6 sets of 60-s sprint at 100% of the peak velocity interspersed by a 3-min active recovery period at 50% of the exercise velocity. HIT sessions last similar to 70% less than ET sessions. At baseline and after 12 weeks of intervention, aerobic fitness, body composition and metabolic parameters were assessed. Results: Both the absolute (ET: 26.0%; HIT: 19.0%) and the relative VO2 peak (ET: 13.1%; HIT: 14.6%) were significantly increased in both groups after the intervention. Additionally, the total time of exercise (ET: 19.5%; HIT: 16.4%) and the peak velocity during the maximal graded cardiorespiratory test (ET: 16.9%; HIT: 13.4%) were significantly improved across interventions. Insulinemia (ET: 29.4%; HIT: 30.5%) and HOMA-index (ET: 42.8%; HIT: 37.0%) were significantly lower for both groups at POST when compared to PRE. Body mass was significantly reduced in the HIT (2.6%), but not in the ET group (1.2%). A significant reduction in BMI was observed for both groups after the intervention (ET: 3.0%; HIT: 5.0%). The responsiveness analysis revealed a very similar pattern of the most responsive variables among groups. Conclusion: HIT and ET were equally effective in improving important health related parameters in obese youth.

Comparison between multiple sets and half-pyramid resistance exercise bouts for muscle damage profile

The present study compared the changes in markers of muscle damage after bouts of resistance exercise employing the Multiple-sets (MS) and Half-pyramid (HP) training systems. Ten healthy men (26.1 +/- 6.3 years), who had been involved in regular resistance training, performed MS and HP bouts, 14 days apart, in a randomised, counter-balanced manner. For the MS bout, participants performed three sets of maximum repetitions at 75%-1RM (i.e. 75% of a One Repetition Maximum) for the three exercises, starting with the bench press, followed by pec deck and decline bench press. For the HP bout, the participants performed three sets of maximum repetitions with 67%-1RM, 74%-1RM and 80%-1RM for the first, second and third sets, respectively, for the same three exercise sequences as the MS bout. The total volume of load lifted was equated between both bouts. Muscle soreness, plasma creatine kinase (CK) activity, myoglobin (Mb) and C-reactive protein (CRP) concentrations were assessed before and for three days after each exercise bout, and the changes over time were compared between MS and HP using two-way repeated measures ANOVA. Muscle soreness developed significantly (P<0.01) after both bouts, but no significant difference was observed between MS and HP. Plasma CK activity and Mb concentration increased significantly (P<0.01) without significant differences between bouts, and CRP concentration did not change significantly after either bout. These results suggest that the muscle damage profile is similar for MS and HP, probably due to the similar total volume of load lifted.