This paper presents the cognitive architecture Con-SCIS (conceptual space based cognitive imitation system), which tightly links low-level data processing with knowledge representation in the context of imitation learning. We use the word imitate to refer to the paradigm of program-level imitation: we are interested in the final effects of actions on objects, and not on the particular kinematic or dynamic properties of the motion. The same architecture is used both to analyze and represent the task to be imitated, and to perform the imitation by generalizing in novel and different circumstances. The implemented experimental scenario is a simplified two-dimensional world populated with various objects in which observation/imitation takes place. During the observation phase, the user shows her/his hand while performing arbitrary tasks of manipulating objects in front of a single calibrated camera. The task is then segmented into meaningful units and its properties (objects' color and shape, their absolute position and orientation, relations between objects) are represented into high-level symbolic terms. In the imitation phase, the symbolic information is employed to drive the robot's actions. To validate our approach, we report some results concerned with the problem of teaching a humanoid hand/arm robotic system tasks of assembling different workspace objects

AIM To compare perinatal and maternal outcomes in Tuzla Canton during the 1992-1995 war in Bosnia and Herzegovina with those before (1988-1991) and after (2000-2003) the war. METHODS We retrospectively collected data on a total of 59,707 liveborn infants and their mothers from the databases of Tuzla University Department for Gynecology and Obstetrics and Tuzla Institute for Public Health. Data on the number of live births, stillbirths, early neonatal deaths, causes of death, gestational age, and birth weights were collected. We also collected data on the number of medically unattended deliveries, examinations during pregnancy, preterm deliveries, and causes of maternal deaths. Perinatal and maternal outcomes were determined for each study period. RESULTS There were 23,194 live births in the prewar, 18,302 in the war, and 18,211 in the postwar period. Prewar perinatal mortality of 23.3 per 1000 live births increased to 25.8 per 1000 live births during the war (P<0.001), due to a significant increase in early neonatal mortality (10.3 per thousand before vs 15.1 per thousand after the war, P<0.001). After the war, both perinatal mortality (14.4 per thousand) and early neonatal mortality (6.6 per thousand) decreased (P<0.001 for both). The most frequent cause of early neonatal death during the war was prematurity (55.7%), with newborns most often dying within the first 24 hours after birth. During the war, there were more newborns with low birth weight (<2500 g), while term newborns had lower average body weight. Women underwent 2.4 examinations during pregnancy (5.4 before and 6.3 after the war, P<0.001 for both) and 75.9% had delivery attended by a health care professional (99.1% before and 99.8% after the war; P<0.001 for both). Maternal mortality rate of 65 per 100,000 deliveries during the war was significantly higher than that before (39 per 100,000 deliveries) and after (12 per 100,000 deliveries) the war (P<0.001 for both). CONCLUSION Perinatal and maternal mortality in Tuzla Canton were significantly higher during the war, mainly due to lower adequacy and accessibility of perinatal and maternal health care.