In this article, a new type-2 fuzzy-based modeling approach is proposed to assess human operators’ psychophysiological states for both safety and reliability of human–machine interface systems. Such a new modeling technique combines type-2 fuzzy sets with state tracking to update the rule base through a Bayesian process. These new configurations successfully lead to an adaptive, robust, and transparent computational framework that can be utilized to identify dynamic (i.e., real time) features without prior training. The proposed framework is validated on mental arithmetic cognitive real-time experiments with ten participants. It is found that the proposed framework outperforms other paradigms (i.e., an adaptive neuro-fuzzy inference system and an adaptive general type-2 fuzzy c-means modeling approach) in terms of disturbance rejection and learning capabilities. The proposed framework achieved the best performance compared to other models that have been presented in the related literature. Therefore, the new framework can be a promising development in human–machine interface systems. It can be further utilized to develop advanced control mechanisms, investigate the origins of human compromised task performance, and identify and remedy psychophysiological breakdown in the early stages.
We consider the challenge of detecting and clustering point and collective anomalies in streaming data that exhibit significant nonlinearities and seasonal structures. The challenge is motivated by detecting problems in a communications network, where we can measure the throughput of nodes, and wish to rapidly detect anomalous traffic behaviour. Our approach is to train a neural network-based nonlinear autoregressive exogenous model on initial training data, then to use the sequential collective and point anomaly framework to identify anomalies in the residuals generated by comparing one-step-ahead predictions of the fitted model with the observations, and finally, we cluster the detected anomalies with fuzzy c-means clustering using empirical cumulative distribution functions. The autoregressive model is sufficiently general and robust such that it provides the nearly (locally) stationary residuals required by the anomaly detection procedure. The combined methods are successfully implemented to create an adaptive, robust, computational framework that can be used to cluster point and collective anomalies in streaming data. We validate the method on both data from the core of the UK’s national communications network and the multivariate Skoltech anomaly benchmark and find that the proposed method succeeds in dealing with different forms of anomalies within the nonlinear signals and outperforms conventional methods for anomaly detection and clustering.