In this paper, we investigate the effect of chemical reaction on peristaltic flow of a Jeffrey fluid in a tapered asymmetric channel with induced magnetic field and thermal radiation. The flow is analysed by long wavelength and low Reynolds number approximations. The reduced equations are solved by using the Adomian Decomposition Method and the expressions for velocity, stream function axial induced magnetic field and pressure gradient are obtained. The effect of pertinent parameters are illustrated graphically.

Short term traffic flow prediction is of great significance for traffic management, early guidance and dispersion, avoiding congestion and improving safety. Traffic flow is affected by multiple factors and exists strong time dependency. Therefore, it is very meaningful to establish a prediction model with multiple features, such as time-day-week-biweekly, holiday and weather situation, etc. In this paper, a TCN- LSTM model with causal convolution block is proposed, which is composed of two subnets: LSTM subnetwork is used to extract feature from original traffic flow data sequence, three TCN+LSTM subnetworks are used to extract features from traffic flow data with day-week-biweekly, holiday and weather. TCN is embedded to maintain causation of the input traffic flow data. Finally, features extracted from the two sub networks are merged and imported into top-level full connection network. The prediction sequence of the future short-term traffic flow is obtained at the output layer of FCN. Experimental results show that the proposed TCN-LSTM model has high accuracy and stability in short-term traffic flow prediction.

Dynamic behavior of the fractional order hyperchaotic Chen system is discussed. According to linear system stability judgment method, general projective synchronization method of hyperchaotic system with fractional order is introduced. By constructing constant full rank matrix, via designing response system, projective synchronization between it and the corresponding drive system can be achieved along with sufficient conditions being obtained. The proposed scheme is simple and easy to be implemented. To verify the effectiveness of the addressed method, numerical simulations are demonstrated.

In the rumor propagation model, different people have different attitudes towards a rumor. This article considers the four attitudes of different people to rumors: unknown (S), hesitation (H), spread (I), and resistance (R)’s rumor spreading model, on this basis, considers impulsive supervision by the government. Under impulsive intervention, that is, the government’s role in refuting rumors, both hesitating and disseminating will tend to zero, and the number of people resisting rumors will increase and tend to increase rapidly. It is stable, and the rate of increase of resisters is proportional to the correlation coefficient p of impulse supervision. The numerical simulation results have taken different p values, and the conclusions drawn also well confirm that the larger the p value, the speed of the increase of resisters is also Faster.

Real time series data sets are often composed of multiple variables. For the future trend of data, not only the historical value of the variables but also other implicit influence factors should be considered. In this paper, a deep neural network prediction model based on multivariable input multi-step output named CNN-BLSTM is proposed. CNN-BLSTM is mainly composed of convolutional neural network (CNN) and bi-directional long short memory network (Bi-LSTM). CNN is used to extract spatial features between variables of multivariate raw data, and Bi-LSTM is used to extract and encode features in time direction. The proposed CNN-BLSTM is able to predict the temperature based on a real-life meteorological data. The experimental results show that the prediction accuracy of the proposed CNN-BLSTM model is significantly better than several state-of-the-art baseline methods.

With superior real-time and storage performance, outdoor computer vision systems have high application value in traffic, public security, identification detection and other fields, but the captured images are affected by environmental factors such as outdoor rainfall, which have obscuration or missing problems and are not conducive to the processing and application of post-level systems. To this end, this paper proposes a tensor model based on total variation regularization low-rank decomposition for video rain streaks removal. Considering the influence of moving objects in the video image on the low-rank structure of the video background, the rainy video is decomposed into static background, dynamic objects and rain streaks, and their a priori characteristics are analyzed separately, combined with the corresponding low-rank characteristics or sparse characteristics to construct a tensor model, and the targets are extracted through low-rank decomposition, and then the rain removal is completed. The proposed tensor model is solved by the alternating direction multiplier method (ADMM), and extensive experiments are carried out on synthetic and real data sets. The results show that the proposed method can effectively remove rain streaks from video images while retaining more background details under dynamic background conditions. Compared with related advanced methods, the proposed method has advantages in three comprehensive quantifiers, namely, peak signal-to-noise ratio, structural similarity and residuals.

Let $n=p^k$, where $p$ is a prime and $k\ge 2.$ In this paper, a construction for weakly pandiagonal strongly symmetric self-orthogonal diagonal Latin squares of order $n$ is given by using frequency squares over finite field of order $p.$ It is proved that there exists a weakly pandiagonal strongly symmetric selforthogonal diagonal Latin square of order $n$ for $n> 4.$

In this paper, we proposed Galerkin method for the numerical solution of boundary value problems using Boubaker wavelets. Here, we used weight functions as Boubaker wavelets that are assumed bases elements which allow us to obtain the numerical solutions of the boundary value problems. Obtained numerical results using this method are compared with the existing method and exact solution. Some test problems are considered to demonstrate the validity and applicability of the proposed method.

In this paper, the Empirical Orthogonal Teleconnection (EOT) analysis is applied to extract the leading modes of summer precipitation from 1951 to 2010 over the Yangtze-Huai River Basin. To analyze the time period of precipitation, the spectrum analysis is performed on the time series of EOT modes. Furthermore, the correlation analysis is used to discuss their drivers, and the major drivers are introduced to construct the forecasting model of summer precipitation. Results show that, the first three leading EOTs can explain about 63% variability of precipitation. The inter-annual, nearly decadal and decadal period signals of the EOT time series (T1-T3) are most significant, respectively. The East Asian summer monsoon (EASM), East Asia/Pacific pattern (EAP), Nino3.4 and Southern Annular Mode (SAM) indices are correlated with T1; the Nino3.4, the Northern Annular Mode (NAM) and SAM indices are correlated with T2, and Indian Ocean Dipole mode (IOD) is correlated with T3. The forecasting model can well capture the main characteristic of summer precipitation.