Optimal channel and frequency band-based feature selection for motor imagery electroencephalogram classification

Common spatial pattern (CSP) is a widely adopted method for electroencephalogram (EEG) feature extraction in brain-computer interface (BCI) based on motor imagery. Bandpass-filtering EEG into several subbands related to brain activity tasks is an effective approach to improve the performance of CSP based algorithm. However, this approach tends to suffer the over-fitting problem because of the increase in feature dimension. Therefore, we proposed an optimal channel and frequency band-based CSP feature selection method in this paper. Firstly, the correlation coefficient was calculated to select the optimal channels, and these channels were bandpass-filtered into multiple overlapping subbands. The subbands with higher power spectrum density were chosen for CSP feature extraction. Next, the pair-wise relevance was utilized to remove subband features with less difference. And then the screened subband features were combined with features extracted from the broadband signal. The Fisher ratio was exploited to carry out further feature selection. Finally, a support vector machine (SVM) was trained to classify the selected CSP features. An experimental study was implemented on BCI competition III dataset IVa and BCI competition IV dataset 1. The average classification accuracy reached 89.33% and 84.08%, which indicated the rationality and effectiveness of the proposed method.     

Assuring quality of the human–computer interface

The issue of human–computer interface quality has been brought currently into focus due to (a) a change in the character of users who dominate the computer market, (b) the availability of expertise in design for usability and its assurance, and (c) the finally recognized business benefits for vendors of user friendly equipment. Because the underlying human factors expertise belongs to the category of enabling generic quality assurance technologies, the quality management and engineering communities must master this new issue, and related knowledge and methods. The objective of this review article is to aid the quality professionals to respond successfully to this challenge by presenting the fundamentals of human factors engineering, its role in the design for usability process, and the associated methods of assuring quality of the human–computer interface.     

Accident sequence analysis of human–computer interface design

It is important to predict potential accident sequences of human–computer interaction in a safety-critical computing system so that vulnerable points can be disclosed and removed. We address this issue by proposing a Multi-Context human–computer interaction Model along with its analysis techniques, an Augmented Fault Tree Analysis, and a Concurrent Event Tree Analysis. The proposed augmented fault tree can identify the potential weak points in software design that may induce unintended software functions or erroneous human procedures. The concurrent event tree can enumerate possible accident sequences due to these weak points.     

Human–computer interaction in safety critical systems

Increased dependence on computers in safety critical industries means increased dependence on a smaller number of people—both the users of computer systems, and those responsible for their design and production. Reliability and integrity of such systems can be enhanced without large overall increases in costs by looking critically at the human-computer interaction early in the design phase. In this paper, a selection of human factors principles are applied to safety critical system design. This includes making systems easier to learn to use, reducing alarm overload, matching the design of menus to the task, consistency and modality.     

An automatic channel selection method based on the standard deviation of wavelet coefficients for motor imagery based brain–computer interfacing

The redundant data in multichannel electroencephalogram (EEG) signals significantly reduces the performance of brain–computer interface (BCI) systems. By removing redundant channels, a channel selection strategy increases the classification accuracy of BCI systems. In this work, a novel channel selection method (stdWC) based on the standard deviation of wavelet coefficients across channels is proposed to identify Motor Imagery (MI) based EEG signals. The wavelet coefficients are calculated by employing a Continuous Wavelet Transform (CWT) filter bank to decompose each trial from the EEG channel. The wavelet coefficient's standard deviation values are obtained across the channels, and these values are then sorted to determine the EEG channels with the highest standard deviation values. The channels with the largest wavelet coefficient divergence are chosen. MI trials are then spatially filtered with the Common Spatial Pattern (CSP), and CWT filter bank-based 2D images are generated from the spatially filtered trials. These images are then classified using a unique nine-layered convolutional neural network (CNN) model that combines two feature maps acquired with differing filter sizes. The proposed framework (stdWC-CSP-CNN) is evaluated using kappa score and classification accuracy on two publically accessible datasets (BCI Competition III dataset IVa and BCI Competition IV dataset 2a). The suggested framework achieved a mean test classification accuracy of 88.8% for dataset IVa from BCI Competition III and 75.03% for dataset 2a from BCI Competition IV, according to the results. The proposed channel selection method outperforms the other channel selection methods examined, according to the results. By rejecting redundant channels, the whole framework can improve the performance of MI-based BCIs.     

The human error rate assessment and optimizing system HEROS — a new procedure for evaluating and optimizing the man–machine interface in PSA

A new procedure allowing the probabilistic evaluation and optimization of the man–machine system is presented. This procedure and the resulting expert system HEROS, which is an acronym for Human Error Rate Assessment and Optimizing System, is based on the fuzzy set theory. Most of the well-known procedures employed for the probabilistic evaluation of human factors involve the use of vague linguistic statements on performance shaping factors to select and to modify basic human error probabilities from the associated databases. This implies a large portion of subjectivity. Vague statements are expressed here in terms of fuzzy numbers or intervals which allow mathematical operations to be performed on them. A model of the man–machine system is the basis of the procedure. A fuzzy rule-based expert system was derived from ergonomic and psychological studies. Hence, it does not rely on a database, whose transferability to situations different from its origin is questionable. In this way, subjective elements are eliminated to a large extent. HEROS facilitates the importance analysis for the evaluation of human factors, which is necessary for optimizing the man–machine system. HEROS is applied to the analysis of a simple diagnosis of task of the operating personnel in a nuclear power plant.