Self-organizing Map System Research Articles

Cognitive CAMSA: an ecological proposal to integrate cognitive performance into motor competence assessment.

To profile the participants using a system of self-organizing maps (SOM) based on their motor and cognitive performance during a dual-task version of the Canadian Agility and Movement Skill Assessment (Cognitive CAMSA). A total of 169 secondary school students (39.3% girls) volunteered to participate. The original CAMSA, cognitive CAMSA, the Corsi and Digit Span tests were used to assess (a) motor competence, (b) motor competence with cognitive load, and (c) cognitive performance, respectively. SOMs and the k-means clustering algorithm were used to establish the adolescents' dual-task performance profiles. Including decision making based on verbal and visual cues in the original CAMSA significantly increased the participants' total scores but also the time required to complete the test, while the skill score remained unchanged. However, not all the participants showed changes in their performance in the same direction during the cognitive CAMSA. Person-centered analyses by SOMs and k-means clustering identified six performance profiles with variations in the cognitive, motor skill, and time scores (H5 = 146.15, H5 = 102.68, and H5 = 108.07, respectively; all p < 0.01). The cognitive CAMSA was shown to be a feasible field-motor test for assessing motor competence with a cognitive load in an ecological setting. Some of the profiles identified in the SOM approach represented adolescents with similar motor and cognitive performance in dual-task or single-task contexts, although other participants obtained high motor competence in single and dual-tasking while their cognitive performance declined or rose more in dual-task than in single task situations. The cognitive CAMSA emerges as a tool of great potential, applicable in educational and sports environments, to know subjects' characteristics and try to individualize the interventions accordingly with their dual-task profile.

Self-Organizing Maps for Learning the Edit Costs in Graph Matching

Although graph matching and graph edit distance computation have become areas of intensive research recently, the automatic inference of the cost of edit operations has remained an open problem. In the present paper, we address the issue of learning graph edit distance cost functions for numerically labeled graphs from a corpus of sample graphs. We propose a system of self-organizing maps (SOMs) that represent the distance measuring spaces of node and edge labels. Our learning process is based on the concept of self-organization. It adapts the edit costs in such a way that the similarity of graphs from the same class is increased, whereas the similarity of graphs from different classes decreases. The learning procedure is demonstrated on two different applications involving line drawing graphs and graphs representing diatoms, respectively.