Evaluating the performance of the cognitive workload model with subjective endorsement in addition to EEG.

The aptitude-oriented exercises from almost all domains impose cognitive load on their operators. Evaluating such load poses several challenges owing to many factors like measurement mode and complexity, nature of the load, overloading conditions, etc. Nevertheless, the physiological measurement of a specific genre of cognitive load and subjective measurement have not been reported along with each other. In this study, the electroencephalography (EEG)-driven machine learning (Support Vector Machine (SVM)) model is sought along with the support of NASA's Task Load Index (NASA-TLX) rating scale for a novel purpose in workload exploration of operators. The Cognitive Load Theory (CLT) was used as the foundation to design the intrinsic stimulus (Spot the Difference task), as most workloads operators are exposed to are notably intrinsic. The SVM-based three-level classification accuracy ranged from 85.4 to 97.4% (p < 0.05), and the NASA-TLX-based three-level classification accuracy ranged from 88.33 to 97.33%. The t-test results show that the neurometric indices contributing to the classification significantly differed (p < 0.05) for every level. The NASA-TLX scale was utilised for validation in its basic form after the validity (Pearson correlation coefficients 0.338 to 0.805 (p < 0.05)) and reliability (Cronbach's α = 0.753) test. This modeling is beneficial to phase out particular-level cognitive exercises from the curriculum during under or overload workload (critical) conditions.

Towards a versatile mental workload modeling using neurometric indices.

Researchers have been working to magnify mental workload (MWL) modeling for a long time. An important aspect of its modeling is feature selection as it interprets bulky and high-dimensional EEG data and enhances the accuracy of the classification model. In this study, a feature selection technique is proposed to obtain an optimized feature set with multiple domain features that can contribute to classifying the MWL at three distinct levels. The brain signals from thirteen healthy subjects were examined while they attended an intrinsic MWL of spotting differences in a set of similar pictures. The Recursive Feature Elimination (RFE) technique selects the robust features from the feature matrix by eliminating all the least contributing features. Along with the Support Vector Machine (SVM), the overall classification accuracy with the proposed RFE reached 0.913 from 0.791 surpassing the other techniques mentioned. The results of the study also significantly display the variation in the mean values of the selected features at the three workload levels (p<0.05). This model can become the principle for defining the workload level quantification applicable to diverse fields like neuroergonomics study, intelligent assistive devices (ADs) development, blue-chip technology exploration, cognitive evaluation of students, power plant operators, traffic operators, etc.

A comparative study of classification methods for designing a pictorial P300-based authentication system.

The response of the P300-based speller is associated with factors like matrix size, inter-stimulus interval, and flashing period. This study proposes the comparison of the novel 2 × 2 image-based speller with the traditional 6 × 6 character-based speller to analyze the effects of the stimulus on the accuracy and information transfer rates. To determine the best classification methodology for the approach suggested, a comparative study was performed using linear and quadratic discrimination analysis, K-nearest neighbor, and support vector machine. In the proposed paradigm, four pictures (objects, special symbols, geometrical shapes, and colors) were randomly placed at four corners of the monitor. Subjects were asked to focus on the target image while ignoring all other images. The proposed method outperformed the traditional method, with an average accuracy of 96.99 ± 1.64% and 86.74 ± 5.19%, respectively, and information transfer rates of 33.82 ± 0.57 bits/min and 23.35 ± 0.79 bits/min, respectively. Results show that a modified speller can play a significant role in optimizing brain-computer interface-driven applications. A repeated measure ANOVA test was performed, which concluded that the improved results are obtained using QDA classifiers in terms of mean accuracy, speed, and error rates.

A novel approach for designing authentication system using a picture based P300 speller.

Due to great advances in the field of information technology, the need for a more reliable authentication system has been growing rapidly for protecting the individual or organizational assets from online frauds. In the past, many authentication techniques have been proposed like password and tokens but these techniques suffer from many shortcomings such as offline attacks (guessing) and theft. To overcome these shortcomings, in this paper brain signal based authentication system is proposed. A Brain-Computer Interface (BCI) is a tool that provides direct human-computer interaction by analyzing brain signals. In this study, a person authentication approach that can effectively recognize users by generating unique brain signal features in response to pictures of different objects is presented. This study focuses on a P300 BCI for authentication system design. Also, three classifiers were tested: Quadratic Discriminant Analysis (QDA), K-Nearest Neighbor, and Quadratic Support Vector Machine. The results showed that the proposed visual stimuli with pictures as selection attributes obtained significantly higher classification accuracies (97%) and information transfer rates (37.14 bits/min) as compared to the conventional paradigm. The best performance was observed with the QDA as compare to other classifiers. This method is advantageous for developing brain signal based authentication application as it cannot be forged (like Shoulder surfing) and can still be used for disabled users with a brain in good running condition. The results show that reduced matrix size and modified visual stimulus typically affects the accuracy and communication speed of P300 BCI performance.