Traffic forecasting is an important part of Intelligent Transportation System (ITS). The traffic prediction results provide data support for traffic guidance and traffic information release system. Research on traffic forecasting is of great significance to alleviate traffic congestion and increase traffic flow. However, the road network is complex and dynamic. The accuracy of multi-step traffic forecasting decreases rapidly with the increase of time steps, and other performances such as RMSE, MAE, ACC and R2are getting worse and worse, which seriously affects the prediction results. Therefore, we proposes a traffic prediction model based on two-stage stacked graph convolution network ( ED2GCN ) , in which EDGCN is used in both encoder and decoder stages. EDGCN includes a GRU and two stacked AGCN modules. A single AGCN module is composed of GCN, GLU and Attention mechanism. In order to capture the spatial dependence between distant points, two AGCNS are superimposed by residual connection to form a deep AGCN structure. In this paper, PEMS08 data set is used for experimental verification. The experimental results show that the prediction effect of ED2GCN proposed in this paper is better than that of the baselines. Among them, RMSE, MAE, ACC and R2are optimized by at least 7.8%, 10.8%, 0.9% and 0.7% respectively compared with A3T-GCN.

This paper deals with the problem of complex spatio-temporal networks, which is modeled by coupled partial integro-differential equations (PIDEs). A spatial proportional-integral-derivative (SPID) state-feedback controller is studied. With Laypunov direct method, a sufficient condition on synchronization of the complex PIDE network is investigated in terms of linear matrix inequality (LMIs). Finally, a numerical example shows the effectiveness of the proposed results.

A variety of data-driven models focused on remaining lifetime prediction have been developed under condition-based monitoring framework. These models either assume an analytical formula for the underlying degradation path is known, or the number of degradation states could be determined subjectively. This paper proposes an adaptive discrete-state model to estimate system remaining lifetime based on Bayesian Belief Network (BBN) theory. The model consists of three steps: degradation state identification, degradation state characterization, and remaining life prediction. Our approach does not require an explicit distribution function to characterize the fault evolutionary process. Because the BBN model leverages the validity measures to determine the optimum state number, it avoids the state identification errors under limited feature data. The performance of the BBN model is validated and verified by actual and simulated bearing life data. Numerical examples show that the Bayesian degradation model outperforms a time-based maintenance policy both in cost and reliability.

The distance between a straight line and a straight line segment in the image space is proposed in this paper. Based on this distance, the neighborhood of a straight line segment is defined and mapped into the parameter space to obtain the parameter space neighborhood of the straight line segment. The neighborhood mapping between the image space and parameter space is a one to one reversible map. The mapped region in the parameter space is analytically derived and it is proved that it can be efficiently approximated by a quadrangle. The proposed straight line segment neighborhood technique for the HT outperforms conventional straight line neighborhood methods currently used with existing HT variations. In contrast to the straight line neighborhoods used in existing HT variations, the proposed straight line segment neighborhood has several advantages including: 1) the detection error of the proposed neighborhood is not affected by the length of the straight line segments; 2) a precision requirement in the image space described using the proposed distance can be explicitly resolved using the proposed formulation; 3) the proposed neighborhood has the ability to distinguish between segments belonging to the same straight line. A variety of experiments are executed to demonstrate that the proposed neighborhood has a variety of interesting properties of high practical value.

Original Hebbian encoding scheme of bidirectional associative memory (BAM) provides a poor pattern capacity and recall performance. Based on Rosenblatt's perceptron learning algorithm, the pattern capacity of BAM is enlarged, and perfect recall of all training pattern pairs is guaranteed. However, these methods put their emphases on pattern capacity, rather than error correction capability which is another critical point of BAM. This paper analyzes the sensitivity to noise in BAM and obtains an interesting idea to improve noise immunity of BAM. Some researchers have found that the noise sensitivity of BAM relates to the minimum absolute value of net inputs (MAV). However, in this paper, the analysis on failure association shows that it is related not only to MAV but also to the variance of weights associated with synapse connections. In fact, it is a positive monotone increasing function of the quotient of MAV divided by the variance of weights. This idea provides an useful principle of improving error correction capability of BAM. Some revised encoding schemes, such as small variance learning for BAM (SVBAM), evolutionary pseudorelaxation learning for BAM (EPRLAB) and evolutionary bidirectional learning (EBL), have been introduced to illustrate the performance of this principle. All these methods perform better than their original versions in noise immunity. Moreover, these methods have no negative effect on the pattern capacity of BAM. The convergence of these methods is also discussed in this paper. If there exist solutions, EPRLAB and EBL always converge to a global optimal solution in the senses of both pattern capacity and noise immunity. However, the convergence of SVBAM may be affected by a preset function.