The influence of context on information processing.

The main research question of this study is how the processing of information relates to different contextual characteristics. More specifically, how the context is associated with efficiency of information processing (success and speed), size of chunks, speed of chunk processing and the recall of a chunk. The research domain was the game of chess. The efficiency of information processing and the chunk characteristics were defined with the reconstruction of sequences of chess moves. Context variables were defined using a slightly adapted chess program. Variables on information dispersion, deviation, complexity and positivity were extracted in each chess position. Overall, the results showed that higher dispersion and complexity and lower positivity of information in a context lead to less efficient information processing. The results support the assumptions of the cognitive load theory about the negative effects of external factors burden on information processing and working memory. Our results also support the ACT-R theory, which suggests that more frequent information has a higher activation level and can therefore be retrieved more easily and quickly. The results are also congruent with the positivity effect, which proposes that it is easier to remember positive information than negative information. The findings of our study can be beneficial for the development of intelligent tutoring systems and the design of human-computer interaction systems.

Elicitation of neurological knowledge with argument-based machine learning.

OBJECTIVE: The paper describes the use of expert's knowledge in practice and the efficiency of a recently developed technique called argument-based machine learning (ABML) in the knowledge elicitation process. We are developing a neurological decision support system to help the neurologists differentiate between three types of tremors: Parkinsonian, essential, and mixed tremor (comorbidity). The system is intended to act as a second opinion for the neurologists, and most importantly to help them reduce the number of patients in the "gray area" that require a very costly further examination (DaTSCAN). We strive to elicit comprehensible and medically meaningful knowledge in such a way that it does not come at the cost of diagnostic accuracy. MATERIALS AND METHODS: To alleviate the difficult problem of knowledge elicitation from data and domain experts, we used ABML. ABML guides the expert to explain critical special cases which cannot be handled automatically by machine learning. This very efficiently reduces the expert's workload, and combines expert's knowledge with learning data. 122 patients were enrolled into the study. RESULTS: The classification accuracy of the final model was 91%. Equally important, the initial and the final models were also evaluated for their comprehensibility by the neurologists. All 13 rules of the final model were deemed as appropriate to be able to support its decisions with good explanations. CONCLUSION: The paper demonstrates ABML's advantage in combining machine learning and expert knowledge. The accuracy of the system is very high with respect to the current state-of-the-art in clinical practice, and the system's knowledge base is assessed to be very consistent from a medical point of view. This opens up the possibility to use the system also as a teaching tool.