Intelligent decision method for stability assessment of shield tunnel based on multi-objective data mining.

Due to improper operation of the shield construction process and unknown geological surveys, shield construction faces many risks in passing through complex strata, among which the excavation face instability is the most serious, potentially leading to disastrous accidents. To address these issues, this research focuses on the limit support pressure and the excavation face stability in the soil when crossing the Yangtze River. First, an analytical formula for the limit support pressure of the excavation face is established through the wedge model. The support safety coefficient is used to assess the excavation face stability quantitatively. Then the rough set algorithm is used to analyse the sensitivity of each index to establish the reduced evaluation index system for the excavation face stability. The back propagation (BP) neural network is used to train the learning data, and a neural network evaluation model with a prediction error of 5.7675 × 10-4 is established. The prediction performance of BP is verified by comparison with the TOPSIS prediction model and the cloud model. The evaluation method proposed in this paper provides an essential reference for evaluating the underwater shield tunnel excavation face stability. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Pattern Recognition of Cognitive Load Using EEG and ECG Signals.

The matching of cognitive load and working memory is the key for effective learning, and cognitive effort in the learning process has nervous responses which can be quantified in various physiological parameters. Therefore, it is meaningful to explore automatic cognitive load pattern recognition by using physiological measures. Firstly, this work extracted 33 commonly used physiological features to quantify autonomic and central nervous activities. Secondly, we selected a critical feature subset for cognitive load recognition by sequential backward selection and particle swarm optimization algorithms. Finally, pattern recognition models of cognitive load conditions were constructed by a performance comparison of several classifiers. We grouped the samples in an open dataset to form two binary classification problems: (1) cognitive load state vs. baseline state; (2) cognitive load mismatching state vs. cognitive load matching state. The decision tree classifier obtained 96.3% accuracy for the cognitive load vs. baseline classification, and the support vector machine obtained 97.2% accuracy for the cognitive load mismatching vs. cognitive load matching classification. The cognitive load and baseline states are distinguishable in the level of active state of mind and three activity features of the autonomic nervous system. The cognitive load mismatching and matching states are distinguishable in the level of active state of mind and two activity features of the autonomic nervous system.