This article is dedicated to developing a robust data-based predictive iterative learning control (PILC) framework for linear time-varying (LTV) systems via a behavioral approach. By investigating the properties of the admissible behaviors of LTV systems, an input/output representation is constructed from data, based upon which a data-based trackability criterion is developed for iterative learning control (ILC) systems. Moreover, in the presence of measurement noises, a robust PILC framework is constructed from noisy data through adopting a slack-variable-based strategy. Consequently, even in the absence of model information, ILC systems can achieve robust tracking performance with a faster convergence speed of tracking errors. To validate the effectiveness of the proposed PILC framework, simulation tests are performed on a permanent magnet synchronous motor (PMSM).

This paper deals with sideslip angle estimation problems of autonomous ground vehicles that repeatedly perform the specific tasks in the absence of model knowledge for their lateral dynamics. By designing appropriate estimators, the equivalence between estimator auxiliary input synthesis and output feedback stabilization along the iteration axis is established. Moreover, we propose an innovative data-based output feedback stabilization framework that leverages insufficient sampled data to formulate an output feedback controller without the need of identification. To be specific, with the application of some helpful linear matrix inequality (LMI) techniques, the data-based synthesis of required output feedback controller is transformed into solving the equivalent LMI conditions. By employing the proposed data-based estimation strategy and partial lateral dynamics information of ground vehicles, accurate estimation of sideslip angles over the entire estimation duration can be achieved even in the presence of disturbances. Experiments on an Ackermann steering intelligent vehicle are provided to demonstrate the effectiveness of the proposed estimation strategy.

Location-based recommendation has become a significant method to help people locate fascinating and appealing points of interest (POIs) with the rapid popularity of smart mobile devices and the prevalence of location-based social networks (LBSN). However, the sparsity of the user-POI matrix and the cold-start issue have generated serious challenges, resulting in a substantial decrease in collaborative filtering methods’ recommendation results. In reality, location-based recommendation demands spatiotemporal context awareness. In order to overcome these challenges, we develop an embedding model based on the heterogeneous graph attention network. Geographic influence, social relation and historical check-in influence are captured in a unified way by constructing a user-POI heterogeneous graph. Subsequently, we use the LSTM-based model to learn the category weight of the next POI to select. We are developing a score function to recommend the next POI for users by integrating category weights, user preferences and time impact. We conduct experiments on existing large-scale datasets to evaluate the performance of our model. The results demonstrate our proposal is superior to other rivals. Additionally, our method has been significantly improved compared with other competitive approaches in terms of recommending cold-start POI.

Unsupervised image-to-image translation is to learn a mapping function from one image domain to another with unpaired samples, which is an important task of computer vision. However, current unsupervised image-to-image translation methods only perform well on certain datasets. To handle the limitation, this paper proposes a novel framework termed as CSAGAN which contains a new discriminator structure, a novel attention module, and a new normalized function. The discriminator is an attention-guided feature pyramid discriminator which makes use of low-level and high-level features to determine an image’s realness. The new attention module integrating channel attention and spatial attention can guide generators focus on the most discriminative regions of feature maps to generate high-quality translated images. Moreover, our attention module embedded into generators requires less computation compared with other self-attention methods. In addition, the new normalized function helps generators limberly control the variation of shape, color, and texture through learning parameters. Experimental results indicate that our approach performs better than the current state-of-the-art methods.