Deep learning for cognitive load monitoring: a comparative evaluation

The Cognitive Load Monitoring Challenge organized in the UbiTtention 2020 workshop tasked the research community with the problem of inferring a user's cognitive load from physiological measurements recorded by a low-cost wearable. This is challenging due to the subjective nature of these physiological characteristics: In contrast to related problems involving objective measurements of physical phenomena (e.g., Activity Recognition from smartphone sensors), subjects' physiological response patterns under cognitive load may be highly individual, i.e., expose significant inter-subject variance. However, models trained on datasets compiled in laboratory settings should also deliver accurate classifications when applied to measurements from novel subjects. In this work, we study the applicability of established Deep Learning models for time series classification on this challenging problem. We examine different kinds of data normalization and investigate a variant of data augmentation.

[1]  Jani Bizjak,et al.  A New Frontier for Activity Recognition: The Sussex-Huawei Locomotion Challenge , 2018, UbiComp/ISWC Adjunct.

[2]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[3]  Niels van Berkel,et al.  UbiTtention 2020: 5th International Workshop on Smart & Ambient Notification and Attention Management , 2020, UbiComp/ISWC Adjunct.

[4]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[5]  Veljko Pejovic,et al.  My Watch Says I'm Busy: Inferring Cognitive Load with Low-Cost Wearables , 2018, UbiComp/ISWC Adjunct.

[6]  Jason Lines,et al.  HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles for Time Series Classification , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[7]  James Large,et al.  A tale of two toolkits, report the third: on the usage and performance of HIVE-COTE v1.0 , 2020, ArXiv.

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  M. Gams,et al.  Datasets for Cognitive Load Inference Using Wearable Sensors and Psychological Traits , 2020, Applied Sciences.

[10]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[11]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[12]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[13]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[14]  Eamonn J. Keogh,et al.  The UCR time series archive , 2018, IEEE/CAA Journal of Automatica Sinica.

[15]  Jani Bizjak,et al.  Classical and deep learning methods for recognizing human activities and modes of transportation with smartphone sensors , 2020, Inf. Fusion.

[16]  Germain Forestier,et al.  Deep learning for time series classification: a review , 2018, Data Mining and Knowledge Discovery.

[17]  Franz J. Király,et al.  sktime: A Unified Interface for Machine Learning with Time Series , 2019, ArXiv.