Abstract
Assessing physical activity (PA) is a challenging task and many different approaches have been proposed. Direct observation (DO) techniques can objectively code both the behavior and the context in which it occurred, however, they have significant limitations such as the cost and burden associated with collecting and processing data. Therefore, this study evaluated the utility of an automated video analysis system (CAM) designed to record and discriminate the intensity of PA using a subject tracking methodology. The relative utility of the CAM system and DO were compared with criterion data from an objective accelerometry-based device (Actigraph GT3X+). Eight 10 year old children (three girls and five boys) wore the GT3X+ during a standard basketball session. PA was analyzed by two observers using the SOPLAY instrument and by the CAM system. The GT3X+ and the CAM were both set up to collect data at 30 Hz while the DO was performed every two minutes, with 10s of observation for each gender. The GT3X+ was processed using cut points by Evanson and the outcome measure was the percentage of time spent in different intensities of PA. The CAM data were processed similarly using the same speed thresholds as were used in establishing the Evenson cut-off points (light: <2 mph; walking: 2-4 mph; very active: >4 mph). Similar outcomes were computed from the SOPLAY default analyses. A chi-square test was used to test differences in the percentage of time at the three intensity zones (light, walking and very active). The Yates' correction was used to prevent overestimation of statistical significance for small data. When compared with GT3X+, the CAM had better results than the SOPLAY. The chi-square test yielded the following pairwise comparisons: CAM versus GT3x+ was chi(2) (5) = 24.18, p < .001; SOPLAY2 versus GT3x+ was chi(2) (5) = 144.44, p < .001; SOPLAY1 versus GT3x+ was chi(2) (5) = 119.55, p < .001. The differences were smaller between CAM and GT3x+, suggesting that the video tracking system provided better agreement than DO. The small sample size precludes a definitive evaluation but the results show that the CAM video system may have promise for automated coding of physical activity behavior.

Abstract

Abstract

Abstract
Developing software agents that play incomplete information games is a demanding task: it is required they incorporate strategies capable of dealing with hidden information and deception and risk management. In Poker, these issues are commonly addressed by estimating opponents' gameplay using a variety of techniques such as Expected Hand Strength (E[HS]) or Hand Potential. In this paper, we propose criteria which can be applied when assessing such techniques, and we have also run benchmark tests which demonstrate their pertinence. We have, however, been faced with a clear gap in terms of the methods' efficiency. While this is not a problem in theoretical models, when implementing such methods in real world applications, they can prove to be painfully slow. In order to address this issue, we propose the Average Rank Strength (ARS) method. It can calculate the strength of a hand of any size through the hand's rank width negligible error, when compared to the original method. Still, the greatest contribution of this method lies in the speed-up factor of about 1000 times over E[HS]. Since most successful agents in the literature use their game abstraction based on E[HS], this breakthrough will significantly contribute towards a much lighter strategy computation, since this routine must be called billions of times. By saving computation time, we believe that future integration of ARS with current game playing algorithms will allow for creating agents with smaller abstraction levels, thus making room for improvement in their overall performance.

Abstract
Hand gesture recognition for human computer interaction, being a natural way of human computer interaction, is an area of active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them to convey information or for device control. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. In this study we try to identify hand features that, isolated, respond better in various situations in human-computer interaction. The extracted features are used to train a set of classifiers with the help of RapidMiner in order to find the best learner. A dataset with our own gesture vocabulary consisted of 10 gestures, recorded from 20 users was created for later processing. Experimental results show that the radial signature and the centroid distance are the features that when used separately obtain better results, with an accuracy of 91 % and 90,1 % respectively obtained with a Neural Network classifier. These to methods have also the advantage of being simple in terms of computational complexity, which make them good candidates for real-time hand gesture recognition.

Abstract