Crime prediction is crucial for sustainable urban development and protecting citizens’ quality of life. However, there exist some challenges in this regard. First, the spatio-temporal correlations in crime data are relatively complex and are heterogenous in time and space, hence it is difficult to model the spatio-temporal correlation in crime data adequately. Second, crime prediction at fine spatial temporal scales can be applied to micro patrol command; however, crime data are sparse in both time and space, making crime prediction very challenging. To overcome these challenges, based on the deep spatio-temporal 3D convolutional neural networks (ST-3DNet), we devise an improved ST-3DNet framework for crime prediction at fine spatial temporal scales (ST3DNetCrime). The framework utilizes diurnal periodic integral mapping to solve the problem of sparse and irregular crime data at fine spatial temporal scales. ST3DNetCrime can, respectively, capture the spatio-temporal correlations of recent crime data, near historical crime data and distant historical crime data as well as describe the difference in the correlations’ contributions in space. Extensive experiments on real-world datasets from Los Angeles demonstrated that the proposed ST3DNetCrime framework has better prediction performance and enhanced robustness compared with baseline methods. In additon, we verify that each component of ST3DNetCrime is helpful in improving prediction performance.

In this paper, two iterative learning control methods are proposed for the different high-order systems with arbitrary initial shifts. The tracking errors caused by nonzero initial shifts are easily detected when applying conventional learning algorithms. But this defect is overcome through applying a step-bystep rectifying controller with initial initial rectifying action introduced in a small interval. It demonstrates the improvement of tracking performance and shows the robustness with respect to the stochastic initial shifts. Finally, simulation results are presented to illustrate the effectiveness of the stated algorithms.

In this paper, two iterative learning control methods are proposed for the different high-order systems with arbitrary initial shifts. The tracking errors caused by nonzero initial shifts are easily detected when applying conventional learning algorithms. But this defect is overcome through applying a step-by-step rectifying controller with initial initial rectifying action introduced in a small interval. It demonstrates the improvement of tracking performance and shows the robustness with respect to the stochastic initial shifts. Finally, simulation results are presented to illustrate the effectiveness of the stated algorithms.

This paper introduces three types of controllers: a PID-type iterative learning controller, an adaptive iterative learning controller, and an optimal iterative learning controller, and reviews the history and research status of initial shifts rectifying algorithms. Initial state shifts have attracted research attention because they affect both the tracking performance and system stability. This study focuses on the current common initial shifts rectifying methods and analyzes the underlying mechanism in detail. To verify the effectiveness of the presented initial shifts rectifying algorithms, we simulated those using ideal first- and second-order systems. Finally, directions for the future development of iterative learning control (ILC) and some challenging topics related to initial shifts rectifying for ILC are presented. This article aims to introduce recent developments and advances in initial shifts rectifying algorithms and discuss the directions for their further exploration.