Identification of Mental Workload Using Imbalanced EEG Data and DySMOTE-based Neural Network Approach

Abstract Identifying the temporal changes of mental workload level (MWL) is crucial for enhancing the safety of human-machine (HM) system operations especially when human operators suffer from cognitive overload and inattention. In this paper, we oversampled the EEG data in minority class to dynamically learn a multilayer perceptron (MLP) model based on a dynamical SMOTE (DySMOTE) approach in order to classify the MWL. The proposed approach consists of data sampling and a dynamical selection strategy, in which the probability of each sample being selected to update the weights and thresholds of the MLP is estimated in each epoch to derive an accurate classifier model. The DySMOTE approach was evaluated on the measured EEG data from eight subjects. The results showed that the proposed method outperforms existing methods in terms of several performance metrics including geometric mean (G-mean) and classification accuracy (or correct classification rate) of individual classes of the MWL.

[1]  A.W.K. Gaillard,et al.  Operator Functional State: The Assessment and Prediction of Human Performance Degradation in Complex Tasks , 2003 .

[2]  Zhi-Hua Zhou,et al.  Ieee Transactions on Knowledge and Data Engineering 1 Training Cost-sensitive Neural Networks with Methods Addressing the Class Imbalance Problem , 2022 .

[3]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[4]  Marco Vannucci,et al.  A method for resampling imbalanced datasets in binary classification tasks for real-world problems , 2014, Neurocomputing.

[5]  A. Craig,et al.  A critical review of the psychophysiology of driver fatigue , 2001, Biological Psychology.

[6]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[7]  R. Parasuraman,et al.  Psychophysiology and adaptive automation , 1996, Biological Psychology.

[8]  Andrew K. C. Wong,et al.  Classification of Imbalanced Data: a Review , 2009, Int. J. Pattern Recognit. Artif. Intell..

[9]  Xin Yao,et al.  Dynamic Sampling Approach to Training Neural Networks for Multiclass Imbalance Classification , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Hasan Ayaz,et al.  Optical brain monitoring for operator training and mental workload assessment , 2012, NeuroImage.

[11]  Soumen Chakrabarti,et al.  Data mining for hypertext: a tutorial survey , 2000, SKDD.

[12]  I. Tomek,et al.  Two Modifications of CNN , 1976 .

[13]  Jacek M. Zurada,et al.  Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance , 2008, Neural Networks.

[14]  Yung-Tsan Jou,et al.  Evaluation of operators’ mental workload of human–system interface automation in the advanced nuclear power plants , 2009 .

[15]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..