Traffic prediction is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, such as spatial dependency of complicated road networks and temporal dynamics, and many more. The factors make traffic prediction a challenging task due to the uncertainty and complexity of traffic states. In the literature, many research works have applied deep learning methods on traffic prediction problems combining convolutional neural networks (CNNs) with recurrent neural networks (RNNs), which CNNs are utilized for spatial dependency and RNNs for temporal dynamics. However, such combinations cannot capture the connectivity and globality of traffic networks. In this paper, we first propose to adopt residual recurrent graph neural networks (Res-RGNN) that can capture graph-based spatial dependencies and temporal dynamics jointly. Due to gradient vanishing, RNNs are hard to capture periodic temporal correlations. Hence, we further propose a novel hop scheme into Res-RGNN to utilize the periodic temporal dependencies. Based on Res-RGNN and hop Res-RGNN, we finally propose a novel end-to-end multiple Res-RGNNs framework, referred to as “MRes-RGNN”, for traffic prediction. Experimental results on two traffic datasets have demonstrated that the proposed MRes-RGNN outperforms state-of-the-art methods significantly.

No abstract

Motion vector sensors play an important role in artificial intelligence and internet of things. Here, a triboelectric vector sensor (TVS) based on a directcurrent triboelectric nanogenerator is reported, for self-powered measuring various motion parameters, including displacement, velocity, acceleration, angular, and angular velocity. Based on the working mechanism of the contact-electrification effect and electrostatic breakdown, a continuous DC signal can be collected to directly monitor moving objects free from environmental electromagnetic signal interference existing in conventional self-powered TVSs with an alternative-current signal output, which not only enhances the sensitivity of sensors, but also provides a simple solution to miniaturize the sensors. Its sensitivity is demonstrated to be equivalent to state-of-the-art photoelectric technology by a comparative experiment in an intelligent mouse. Notably, an intelligent pen based on the miniaturized TVS is designed to realize motion trajectory tracing, mapping, and writing on the curved surface. This work provides a new paradigm shift to design motion vector sensors and self-powered sensors in artificial intelligent and internet of things.

No abstract

No abstract