Abstract-This paper presents a novel application of a hybrid learning approach to the optimisation of membership and non-membership functions of a newly developed interval type-2 intuitionistic fuzzy logic system (IT2 IFLS) of a TakagiSugeno-Kang (TSK) fuzzy inference system with neural network learning capability. The hybrid algorithms consisting of decoupled extended Kalman filter (DEKF) and gradient descent (GD) are used to tune the parameters of the IT2 IFLS for the first time. The DEKF is used to tune the consequent parameters in the forward pass while the GD method is used to tune the antecedents parts during the backward pass of the hybrid learning. The hybrid algorithm is described and evaluated, prediction and identification results together with the runtime are compared with similar existing studies in the literature. Performance comparison is made between the proposed hybrid learning model of IT2 IFLS, a TSK-type-1 intuitionistic fuzzy logic system (IFLS-TSK) and a TSK-type interval type-2 fuzzy logic system (IT2 FLS-TSK) on two instances of the datasets under investigation. The empirical comparison is made on the designed systems using three artificially generated datasets and three real world datasets. Analysis of results reveal that IT2 IFLS outperforms its type-1 variants, IT2 FLS and most of the existing models in the literature. Moreover, the minimal run time of the proposed hybrid learning model for IT2 IFLS also puts this model forward as a good candidate for application in real time systems.Index Terms-Interval type-2 intuitionistic fuzzy logic system; Decoupled extended Kalman filter; Gradient descent algorithm.

Abstract-This paper presents an approach to prediction based on a new interval type-2 intuitionistic fuzzy logic system (IT2IFLS) of Takagi-Sugeno-Kang (TSK) fuzzy inference. The gradient descent algorithm (GDA) is used to adapt the parameters of the IT2IFLS. The empirical comparison is made on the designed system using two synthetic datasets. Analysis of our results reveal that the presence of additional degrees of freedom in terms of non-membership functions and hesitation indexes in IT2IFLS tend to reduce the root mean square error (RMSE) of the system compared to a type-1 fuzzy logic approach and some interval type-2 fuzzy systems.

No abstract

T his paper considers the problem of allocating pushback times to departing aircraft, specifying the time at which they will be given permission to push back from their allocated stand, start their engines, and commence their taxi to the runway. The aim of this research is to first predict the delay (defined as the waiting time at the stand or runway) for each departure, then to use this to calculate a pushback time such that an appropriate amount of the delay is absorbed at the stand, prior to starting the engines. A two-stage approach is used, where the feasibility of the second stage (pushback time allocation) has to be considered within the first stage (takeoff sequencing). The characteristics of this real-world problem and the differences between it and similar problems are thoroughly discussed, along with a consideration of the important effects of these differences. Differences include a nonlinear objective function with a nonconvex component; the integration of two sequence dependent separation problems; separations that can vary over time; and time-slot extensions. Each of these factors has contributed to the design of the solution algorithm. Results predict significant fuelburn benefits from absorbing some of the delay as stand hold, as well as delay benefits from indirectly aiding the runway controllers by reducing runway queue sizes. A system for pushback time allocation at London Heathrow has been developed by NATS (formerly National Air Traffic Services) based upon the algorithm described in this paper.