Social anxiety disorder has been widely recognised as one of the most commonly diagnosed mental disorders. Individuals with social anxiety disorder experience difficulties during social interactions that are essential in the regular functioning of daily routines; perpetually motivating research into the aetiology, maintenance and treatment methods. Traditionally, social and clinical neuroscience studies incorporated protocols testing one participant at a time. However, it has been recently suggested that such protocols are unable to directly assess social interaction performance, which can be revealed by testing multiple individuals simultaneously. The principle of two-person neuroscience highlights the interpersonal aspect of social interactions that observes behaviour and brain activity from both (or all) constituents of the interaction, rather than analysing on an individual level or an individual observation of a social situation. Therefore, two-person neuroscience could be a promising direction for assessment and intervention of the social anxiety disorder. In this paper, we propose a novel paradigm which integrates two-person neuroscience in a neurofeedback protocol. Neurofeedback and interbrain synchrony, a branch of two-person neuroscience, are discussed in their own capacities for their relationship with social anxiety disorder and relevance to the paradigm. The newly proposed paradigm sets out to assess the social interaction performance using interbrain synchrony between interacting individuals, and to employ a multi-user neurofeedback protocol for intervention of the social anxiety.

Class imbalance is a common challenge when dealing with pattern classification of real-world medical data-sets. An effective countermeasure typically used is a method known as re-sampling. In this paper we implement an ANN with different re-sampling techniques to subsequently compare and evaluate the performances. Re-sampling strategies included a control, under-sampling, over-sampling, and a combination of the two. We found that over-sampling and the combination of under-and over-sampling both led to a significantly superior classifier performance compared to under-sampling only in correctly predicting labelled classes.

No abstract

Re-sampling methods to solve class imbalance problems have shown to improve classification accuracy by mitigating the bias introduced by differences in class size. However, it is possible that a model which uses a specific re-sampling technique prior to Artificial neural networks (ANN) training may not be suitable for aid in classifying varied datasets from the healthcare industry. Five healthcare-related datasets were used across three re-sampling conditions: under-sampling, over-sampling and combi-sampling. Within each condition, different algorithmic approaches were applied to the dataset and the results were statistically analysed for a significant difference in ANN performance. The combi-sampling condition showed that four out of the five datasets did not show significant consistency for the optimal re-sampling technique between the f1-score and Area Under the Receiver Operating Characteristic Curve performance evaluation methods. Contrarily, the over-sampling and under-sampling condition showed all five datasets put forward the same optimal algorithmic approach across performance evaluation methods. Furthermore, the optimal combi-sampling technique (under-, over-sampling and convergence point), were found to be consistent across evaluation measures in only two of the five datasets. This study exemplifies how discrete ANN performances on datasets from the same industry can occur in two ways: how the same re-sampling technique can generate varying ANN performance on different datasets, and how different re-sampling techniques can generate varying ANN performance on the same dataset.