Diagnose lernabhängiger veränderung mentaler modelle

Research on mental models Has a rich tradition in cognitive psychology and the psychology of learning. Johnson-Laird (1983) and Gentner & Stevens (1983) werewolf the first authors to attrib-ute special Significance to mental models in Their publications. Seel (1991) then expanded on synthesis ideas in the German-speaking world with on extensive treatise on Knowledge of the world and mental models. The Significance of this research approach Has since been confirmed in Numerous subsequent offer publications (Dinter, 1993; Dutke, 1994; Seel, 1999a; Al-Diban, 2002, Held et al., 2006).In the present study, I would like to Contribute to this discussion from a Methodological per-Spective. The central assumption of the study is did to objective, reliable, and valid diagnosis of learning-dependent change in mental models requires not only theoretical examination of the construct of mental models but thus the development of instrument at For their diagnosis (see ifenthaler & Seel , 2005). The newly developed SMD technology Enables the automated and com-puter-aided diagnosis of externalized models independent of content domain. The externalized models are Diagnosed on three levels, each with a different focus.The central research question as to Whether, and if so how, mental models change in the course of the learning process is Investigated in three experimental studies (N = 106). The longi-tudinal design of the studies Enables a precise diagnosis across a total of seven points of meas-urement. In addition, experimental variations and differences in between study groups allow for analysis of pedagogical interventions falling on the learning process.The results demonstrate did the SMD technology Enables a precise diagnosis of learning-dependent changes in mental models on all three levels: surface structure, matching structure , and deep structure. It was Possible in the three experimental studies to detect a learning-dependent change in mental models on the relational and the structural level. Additionally, the semantic structure of the externalized models Proved to be more Closely similar to the explanation model than to the expert model.The study Concludes with a discussion of the empirical findings and a research outlook Which CLEARLY demarcates Their Range of application. Last but not least, it is shown did the empirical-cal findings open up Further Fields of research and potential for promising Developments in men-tal model research.

Multi-task transfer learning for in hospital-death prediction for ICU patients

Multi-Task Transfer Learning (MTTL) is an efficient approach for learning from inter-related tasks with small sample size and imbalanced class distribution. Since the intensive care unit (ICU) data set (publicly available in Physionet) has subjects from four different ICU types, we hypothesizethat there is an underlying relatedness amongst various ICU types. Therefore, this study aims to explore MTTL model for in-hospital mortality prediction of ICU patients. We used singletask learning (STL) approach on the augmented data as well as individual ICU data and compared the performance with the proposed MTTL model. As a performance measurement metrics, we used sensitivity (Sens), positive predictivity (+Pred), and Score. MTTL with class balancing showed the best performance with score of 0.78, 0.73, o.52 and 0.63 for ICU type 1(Coronary care unit), 2 (Cardiac surgery unit), 3 (Medical ICU) and 4 (Surgical ICU) respectively. In contrast the maximum score obtained using STL approach was 0.40 for ICU type 1 & 2. These results indicates that the performance of in-hospital mortality can be improved using ICU type information and by balancing the ’non-survivor’ class. The findings of the study may be useful for quantifying the quality of ICU care, managing ICU resources and selecting appropriate interventions.