A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization.

Edge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always accessible. Therefore, a specialized detector that is optimized for the image particularities can help improve edge detection performance. In this paper, we apply transfer learning to optimize cellular automata (CA) rules for edge detection using particle swarm optimization (PSO). Cellular automata provide fast computation, while rule optimization provides adaptability to the properties of the target images. We use transfer learning from synthetic to medical images because expert-annotated medical data is typically difficult to obtain. We show that our method is tunable for medical images with different properties, and we show that, for more difficult edge detection tasks, batch optimization can be used to boost the quality of the edges. Our method is suitable for the identification of structures, such as cardiac cavities on medical images, and could be used as a component of an automatic radiology decision support tool.

Fitness-Related Self-Conscious Emotions and Risk for Exercise Addiction: Examining the Mediating Role of Passion.

Fitness-related self-conscious emotions (SCEs) have been proposed as antecedents of exercise addiction (EA). However, the potential mechanisms underlying such a relationship remain unexplored. The present study examined the relationship between fitness-related SCEs and risk of EA, as well as the mediating role of passion for exercise. A total of 296 male runners (M = 40.35 years, SD = 10.69) completed a survey assessing weekly exercise frequency/hours, fitness-related SCEs, passion for exercise, and the risk of EA. The relationships between the study variables were examined using structural equation modeling. After controlling for age and weekly exercise frequency/hours, fitness-related SCEs of shame, guilt, and hubristic pride were positively associated with risk of EA. However, while guilt had direct effects on risk of EA, shame and hubristic pride showed indirect effects via obsessive passion. The results of the study are discussed, and some practical implications and future research directions are presented.

Examining the relationship between fitness-related self-conscious emotions, disordered eating symptoms, and morbid exercise behavior: An exploratory study.

BACKGROUND AND AIMS: Theoretical models of morbid exercise behavior (MEB) suggest that it may emerge as a result of complex interactions between a range of psychosocial factors. However, in spite of fitness-related self-conscious emotions involving such factors, their relationship with the risk of MEB has never been investigated. Consequently, this study had two objectives. First, to explore the relationship that fitness-related self-conscious emotions have with (a) symptoms reflecting MEB as assessed by the Exercise Addiction Inventory (EAI) and the Exercise Dependence Scale-Revised (EDS-R) and (b) exercise frequency. Second, to examine whether these relationships might vary according to disordered eating symptoms. METHODS: A sample of 646 undergraduate students (59% males; Mage = 21.25; SDage = 2.94) completed a self-reported questionnaire. RESULTS: After controlling for age, sex, and disordered eating symptoms, it was found that shame, hubristic pride, and authentic pride positively explained MEB; for their part, guilt (negatively) and authentic pride (positively) explained exercise frequency. The positive relationships between pride and MEB were weaker (in the case of the hubristic facet) or stronger (in the case of the authentic facet) under higher levels of disordered eating symptoms. The independent variables explained 29% (EAI), 28% (EDS-R), and 27% (exercise frequency) of the variance in dependent variables. DISCUSSION: Tempering fitness-related emotions of shame, guilt, hubristic pride, and authentic pride may contribute to healthier exercise behavior.

The Relationship between Goal Orientations, Motivational Climate and Selfreported Discipline in Physical Education.

The purpose of this study was to test a motivational model on the links between situational and dispositional motivation and self-reported indiscipline/discipline based on the achievement goals theory. The model postulates that a task-involving motivational climate facilitates self-reported discipline, either directly or mediated by task orientation. In contrast, an ego-involving motivational climate favors self-reported indiscipline, either directly or by means of ego orientation. An additional purpose was to examine gender differences according to the motivational model proposed. Children (n = 565) from a large Spanish metropolitan school district were participants in this study and completed questionnaires assessing goal orientations, motivational climates and self-reported discipline. The results from the analysis of structural equation model showed the direct effect of motivational climates on self-reported discipline and provided support to the model. Furthermore, the gender differences found in self-reported discipline were associated with the differences found in the students' dispositional and situational motivation pursuant to the model tested. The implications of these results with regard to teaching instructional actions in physical education classes are discussed. Key pointsA task-involving motivational climate predicts self-reported discipline behaviors, either directly or mediated by task orientation.An ego-involving motivational climate favors self-reported undisciplined, either directly or mediated by ego orientation.A significant gender difference was found in the motivational disposition perceived climate and self-reported discipline.