Executive cognitive functions like working memory determine the success or failure of a wide variety of different cognitive tasks. Estimation of constructs like working memory load or memory capacity from neurophysiological or psychophysiological signals would enable adaptive systems to respond to cognitive states experienced by an operator and trigger responses designed to support task performance (e.g. by simplifying the exercises of a tutor system, or by shutting down distractions from the mobile phone). The determination of cognitive states like working memory load is also useful for automated testing/assessment, for usability evaluation and for tutoring applications. While there exists a huge body of research work on neural and physiological correlates of cognitive functions like working memory activity, fewer publications deal with the application of this research with respect to single-trial detection and real-time estimation of cognitive functions in complex, realistic scenarios. Single-trial classifiers based on brain activity measurements such as EEG, fNIRS or physiological signals such as EDA, ECG, BVP or Eyetracking have the potential to classify affective or cognitive states based upon short segments of data. For this purpose, signal processing and machine learning techniques need to be developed and transferred to real-world user interfaces.
In this research topic, we are looking for: (1) studies in complex, realistic scenarios that specifically deal with cognitive states or cognitive processes (memory-related or other), (2) classification and estimation of cognitive states and processes like working memory activity, and (3) applications to Brain-Computer Interfaces and Human-Computer Interaction in general. Central open research questions which we would like to see approached in this research topic comprise:
* How can working memory load be quantified with regression or classification models which are robust to perturbations common to realistic recording conditions and natural brain signal fluctuations?
* How can detection and classification of cognitive states be used in Brain-Computer Interfaces (BCIs)?
* How can multiple types of features or signal types be combined to achieve a more robust classification of working memory load?
* How can working memory activity be differentiated from other types of cognitive or affective activity which co-vary with, but are not related to memory?
* How well can insights from offline, average-analysis studies on memory activity be transferred to online, single-trial BCIs?
* How can models of working memory load be calibrated to account for individual differences, for example in working memory capacity?
* How can approaches from computational cognitive modeling be combined with physiological signals to assess memory processes?
* How can working memory load be classified, for example according to modality (spatial memory, semantic memory, ...) or type of activity (encoding, retrieval, rehearsal, ...)?
* How to design user-independent memory load estimators? Is that even feasible?
* How can memory load estimators from a given context or modality be transferred to another modality and/or context?
* How can working memory activity be classified to predict the outcome of the activity, for example by differentiating successful from failed encoding attempts?
Additionally, we are also interested in other relevant submissions related to the research topic. We also sincerely invite manuscripts dealing with applications of memory-related interfaces (e.g. adaptive human-computer interfaces for memory-intensive tasks). Comprehensive review articles which critically reflect the state-of-the-art on a certain aspect of the topic are also welcome.
Executive cognitive functions like working memory determine the success or failure of a wide variety of different cognitive tasks. Estimation of constructs like working memory load or memory capacity from neurophysiological or psychophysiological signals would enable adaptive systems to respond to cognitive states experienced by an operator and trigger responses designed to support task performance (e.g. by simplifying the exercises of a tutor system, or by shutting down distractions from the mobile phone). The determination of cognitive states like working memory load is also useful for automated testing/assessment, for usability evaluation and for tutoring applications. While there exists a huge body of research work on neural and physiological correlates of cognitive functions like working memory activity, fewer publications deal with the application of this research with respect to single-trial detection and real-time estimation of cognitive functions in complex, realistic scenarios. Single-trial classifiers based on brain activity measurements such as EEG, fNIRS or physiological signals such as EDA, ECG, BVP or Eyetracking have the potential to classify affective or cognitive states based upon short segments of data. For this purpose, signal processing and machine learning techniques need to be developed and transferred to real-world user interfaces.
In this research topic, we are looking for: (1) studies in complex, realistic scenarios that specifically deal with cognitive states or cognitive processes (memory-related or other), (2) classification and estimation of cognitive states and processes like working memory activity, and (3) applications to Brain-Computer Interfaces and Human-Computer Interaction in general. Central open research questions which we would like to see approached in this research topic comprise:
* How can working memory load be quantified with regression or classification models which are robust to perturbations common to realistic recording conditions and natural brain signal fluctuations?
* How can detection and classification of cognitive states be used in Brain-Computer Interfaces (BCIs)?
* How can multiple types of features or signal types be combined to achieve a more robust classification of working memory load?
* How can working memory activity be differentiated from other types of cognitive or affective activity which co-vary with, but are not related to memory?
* How well can insights from offline, average-analysis studies on memory activity be transferred to online, single-trial BCIs?
* How can models of working memory load be calibrated to account for individual differences, for example in working memory capacity?
* How can approaches from computational cognitive modeling be combined with physiological signals to assess memory processes?
* How can working memory load be classified, for example according to modality (spatial memory, semantic memory, ...) or type of activity (encoding, retrieval, rehearsal, ...)?
* How to design user-independent memory load estimators? Is that even feasible?
* How can memory load estimators from a given context or modality be transferred to another modality and/or context?
* How can working memory activity be classified to predict the outcome of the activity, for example by differentiating successful from failed encoding attempts?
Additionally, we are also interested in other relevant submissions related to the research topic. We also sincerely invite manuscripts dealing with applications of memory-related interfaces (e.g. adaptive human-computer interfaces for memory-intensive tasks). Comprehensive review articles which critically reflect the state-of-the-art on a certain aspect of the topic are also welcome.