An investigation was conducted on the sample of primary school students in urban area with the aim of analyzing the anthropometric parameters between boys and girls entering 1st-9th grade. The main objective is to determine the frequency and causes of obesity in the population of school children with the intention of preventing the risks of developing the 'modern man' diseases (diabetes, hypertension, hypercholesterolemia, the development of metabolic syndromes, coronary heart disease, etc). The basic anthropometric parameters were measured: body weight and height, chest, waist and hips circumference, and from the obtained values the following were calculated: body mass index, ratio of waist circumference to body height and ratio of waist circumference to hips circumference. The comparison of the results according to age and sex of the pupils is expected to give the values that might answer some questions, such as: the degree of development and nutritional status of schoolchildren according to age and sex in relation to the environment in which they live, the annual increment of the measured parameters value, the differences between age and gender groups. Results were compared with parameters of growth and development of the children of same age in rural areas based on earlier research. The goal of the study is to confirm or reject the existence of a linear regression in correlation to some anthropometric parameters in relation to sex and age of the pupils from urban and rural areas, by means of the allometric method.

This paper presents a visual/motor behavior learning approach, based on neural networks. We propose Behavior Chain Model (BCM) in order to create a way of behavior learning. Our behavior-based system evolution task is a mobile robot detecting a target and driving/acting towards it. First, the mapping relations between the image feature domain of the object and the robot action domain are derived. Second, a multilayer neural network for offline learning of the mapping relations is used. This learning structure through neural network training process represents a connection between the visual perceptions and motor sequence of actions in order to grip a target. Last, using behavior learning through a noticed action chain, we can predict mobile robot behavior for a variety of similar tasks in similar environment. Prediction results suggest that the methodology is adequate and could be recognized as an idea for designing different mobile robot behaviour assistance.