Search

An error-related potential (ErrP) occurs when people’s expectations are not consistent with the actual outcome. Accurately detecting ErrP when a human interacts with a BCI is the key to improving these BCI systems. In this paper, we propose a multi-channel method for error-related potential detection using a 2D convolutional neural network. Multiple channel classifiers are integrated to make final decisions. Specifically, every 1D EEG signal from the anterior cingulate cortex (ACC) is transformed into a 2D waveform image; then, a model named attention-based convolutional neural network (AT-CNN) is proposed to classify it. In addition, we propose a multi-channel ensemble approach to effectively integrate the decisions of each channel classifier. Our proposed ensemble approach can learn the nonlinear relationship between each channel and the label, which obtains 5.27% higher accuracy than the majority voting ensemble approach. We conduct a new experiment and validate our proposed method on a Monitoring Error-Related Potential dataset and our dataset. With the method proposed in this paper, the accuracy, sensitivity and specificity were 86.46%, 72.46% and 90.17%, respectively. The result shows that the AT-CNNs-2D proposed in this paper can effectively improve the accuracy of ErrP classification, and provides new ideas for the study of classification of ErrP brain–computer interfaces.

The construction of desert railways inevitably destructs the environment and aggravates the wind–sand damage along the line. A reasonable railway route is an effective measure to avoid blown sand hazards, save construction costs, and reduce environmental damage. Currently, the selection methods for the railway route scheme are to analyze the qualitative indicators and quantitative indicators separately, and there are few decision-making models for the desert railway scheme. Therefore, this study aims to propose a comprehensive quantitative optimization model of the route scheme for the desert railway. Based on the design principles of hazard reduction, the evaluation index system of the desert railway route is first constructed, including railway design factors, wind-blown sand hazard factors, environmental impact factors, and operation condition factors. Subsequently, the subjective weights and objective weights are combined to obtain the comprehensive weights of the index by utilizing the principle of minimum discrimination information. Finally, the interval number is employed to quantify the linguistic fuzzy number of qualitative indicators, and the optimization model of the route scheme for the desert railway is constructed based on the technique for order preference by similarity to an ideal solution (TOPSIS). The model is verified using the Minfeng-Yuhu section in the Hotan–Ruoqiang railway as the case study. The achieved results reveal that this model enhances the accuracy and efficiency of the railway scheme decision-making and provides a theoretical basis for the optimal design and sand damage control of the desert railway.