Search

As a kind of time series, the export volume of foreign trade has the characteristics of randomness, complexity, strong nonlinearity and noise, so it is difficult to describe it by using the traditional time series model algorithm. Support vector neural network (SVNN) has many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition problems. This paper uses the method of support vector neural network to predict and analyze China's foreign trade export and uses principal component analysis and regression analysis to analyze the contribution rate of different influencing factors to foreign trade export. The results show that:(1) the contribution rate of domestic economic factors to China's foreign trade export is the largest, reaching 59.65%, which also reflects the necessity and correctness of China's insistence on supply-side reform. (2) The nonlinear prediction results of the support vector neural network have a good fitting with the actual value of China's foreign trade export, and the prediction error of the support vector neural network is controlled within 10%, showing a good prediction effect; (3) neural network method has good modeling and generalization ability for nonstationary small sample import and export time series data and can achieve high prediction accuracy and decision judgment accuracy, especially for the prediction of its development trend, and the model has a high degree of fitting.

With the frequent occurrence of natural disasters, timely warning of flood disasters has become an issue of concern. This research mainly discusses flood disaster risk assessment based on random forest algorithm. This study uses the special functions of GIS to collect, manage, and analyze data to propose a method of flood disaster risk assessment based on GIS. This method is based on the characteristics of natural disaster-causing factors in the study area, selects an appropriate grid size, and finally realizes the function of visual expression of regional disaster risk. First, use ArcGIS10.1 to analyze and integrate each hazard factor into the flood disaster report index model. Second, the random forest algorithm is used as the weight of each parameter of the flood disaster index model. Finally, use ArcGIS spatial analysis tool map algebra function to model, carry out flood risk assessment in different periods, and use spatial analysis function to extract the median value to point function to extract the flood inundation depth of the study area in a specific scenario. In the experimental part, this research uses layer overlay to determine the number and types of affected areas. Using the natural break point method of ArcGIS 10.1 platform, the study area is divided according to the magnitude of the flood disaster risk value. At the same time, there are a total of 85 samples that have experienced flood disasters, of which only six have been misjudged as no flood disasters. Generally speaking, the model prediction accuracy is high. The research results show that the combination of random forest algorithm and GIS technology is convenient for analyzing the spatial pattern and internal laws of flood risk, and has good applicability.

Aiming at the problem that blog texts are the streaming data captured by different acquisition modality, each kind of which has its particular quality evaluation mode, this paper proposes a text quality evaluation (TQA) model based on 3D CNN correlated with blog text data. In order to achieve accurate TQA value, the model adopted a Bi-LSTM-based architecture to process video-related blog text as auxiliary part to provide additional information for our TQA architecture. First, the auxiliary part constructs feature vector for each video-related text by the model originating from Bi-LSTM and Seq2Seq. Then, the feature vector was feed to a well-trained decoder to reconstruct the original input data. Then, the feature vector complied with the blog textual data are inputted into end-to-end TQA modal based on the 3D CNN straightly. Comprehensive experimental results on the blog text/video dataset from the well-known truism website “ http://www.mafengwo.cn/ ” have shown that the proposed model reflects the subjective quality of online texts more accurately, and has better overall blog TQA assessment performance than the other state-of-the-art non-reference methods.

For the problems of inconsistent sample duration and unbalance of sample categories in the speech emotion corpus, this paper proposes a speech emotion recognition model based on Bi-GRU (Bidirection Gated Recurrent Unit) and Focal Loss. The model has been improved on the basis of learning CRNN (Convolutional Recurrent Neural Network) deeply. In CRNN, Bi-GRU is used to effectively lengthen the samples of the speech with short duration, and Focal Loss function is used to deal with the difficulties in classification caused by the imbalance of emotional categories of the samples. Through different methods for experimental comparison, weighted average recall (WAR), unweighted average recall (UAR) and confusion matrix (CM) are used as evaluation index of the algorithm. The experimental results show that the speech emotion recognition model proposed in this paper improves the recognition accuracy and the imbalance of IEMOCAP database samples, and can effectively prove that the improvement of speech emotion recognition performance is not due to the adjustment of model parameters or the change of the model topology.

The emergence of the Internet has brought great convenience to people, changing the way of life in many fields, such as food, clothing, housing and transportation. With the increasing popularity of the Internet and the rapid development of network technology, the Internet has become the main communication tool and information sharing channel for people. Network users bring not only convenience but also great challenges to network. The purpose is to study the practicability of statistical protocol recognition methods in network environment and to develop new solutions based on the existing protocol recognition methods. Based on the method step by step to study the identification of a complex application (CA) problems, usability issues, put forward the solution, and the solution of complex application, puts forward a set of perfect CA identification and analysis framework, greatly improved the accuracy and efficiency of complex application, to more than 80%. While promoting the development of recognition technology, it solves problems and finally implements a recognition and analysis system for complex applications. The complex private network mining technology proposed in this paper solves many difficulties and challenges of CA identification and analysis in network environment and can effectively improve the network management capability of network operators.

With the leaps and bounds of computer performance and the advent of the era of big data, deep learning has drawn more and more attention from all walks of life. It can combine low-level features to form more abstract high-level features and describe the data more essentially. Therefore, it is widely used in various fields such as computer vision. Image segmentation is one of the most basic research topics in the field of computer vision. The main purpose is to extract regions of interest from images for later image processing research. In 3D reconstruction based on sequence images, the segmentation accuracy and speed of sequence images determine the quality and efficiency of target reconstruction. Therefore, when facing large-scale sequence images, the biggest problem is how to improve the segmentation speed while ensuring accuracy. Based on the above background, the research content of this article is an indoor scene segmentation algorithm based on full convolutional neural network. According to the characteristics of indoor application scenes, this paper proposes a fast convolutional neural network image segmentation method to segment the indoor scene image and construct the fast fully convolutional networks (FFCN) for indoor scene image segmentation uses inter-layer fusion to reduce the amount of network calculation parameters and avoid the loss of picture feature information by continuous convolution. In order to verify the effectiveness of the network, in this paper, a basic living object data set (XAUT data set) in an indoor environment is created. The XAUT data set is used to train the FFCN network under the Caffe framework to obtain an indoor scene segmentation model. In order to compare the effectiveness of the model, the structure of the worn FCN8s, FCN16s, and FCN32s models was fine-tuned, and the corresponding algorithm model for indoor scene segmentation was obtained by training with the XAUT data set. The experimental results show that the pixel recognition accuracy of all types of networks has reached 86%, and the mean IU ratio has reached more than 63%. The mean IU of the FCN8s network is the highest at 70.38%, but its segmentation speed is only 1/5 of FFCN. On the premise that other types of indicators are not much different, the average segmentation speed on FFCN fast segmentation convolutional neural network reaches 40 fps. It can be seen that the scale fusion technology can well avoid the loss of image feature information in the network convolution and reddening process. Compared with other FCN networks, it has a faster speed and is conducive to real-time image preprocessing.

ViBe algorithm is an efficient pixel level video background modeling algorithm. Aiming at the problem of ghost and dynamic background false detection in traditional ViBe algorithm, an improved algorithm based on improved ViBe algorithm is proposed. Firstly, the initial background model and the background update algorithm of three frame difference are constructed based on the time information to solve the problem of ghost elimination in the ViBe algorithm. Aiming at the problem of false detection in the process of dynamic background detection in the ViBe algorithm, an adaptive threshold dynamic background motion detection algorithm combined with the three frame difference method is proposed, Three frame difference method is used to determine the dynamic interference area, and adaptive threshold motion detection is used to detect the dynamic interference area. The algorithm can quickly remove ghosts and reduce the probability of false detection in dynamic background. Experimental results show that the algorithm is effective and robust.

Multi-label sorting learning has been successful in many fields. It can not only express the complex semantic information of learning objects, but also present good generalization ability in dealing with complex things. This paper proposes age estimation algorithm of facial images based on multi-label sorting. This estimation algorithm is for the lack of facial age dataset, and it changes the traditional multi-valued classification method, simplified the problem of tedious steps to estimate age and shortened the time for model training. A series of experiments on two age datasets shows that the algorithm has achieved very good results in evaluating indicators, and these indicators include MAE (mean absolute error), CS (cumulative score), and convergence rate. When compared with some classic algorithms of age estimation, the efficiency and accuracy of the algorithm are verified.

In order to solve the inaccuracy of age estimation dataset and the imbalance of age distribution, this paper proposes an age estimation model based on the structured sparse learning. Firstly, the Multi-label representation of facial images is performed by age, and the age estimation model is trained by solving the model matrix. Finally, the correlation with all age labels is calculated according to the facial images and age estimation model to be tested, and the most correlated age is taken as the predicted age. This paper sets up a series of verification experiments, and analyzes the structured sparse age estimation model from several perspectives. The proposed algorithm has achieved good results in the evaluation of indexes such as the mean absolute error, accumulation index curve and convergence rate, and has designed the demo system to put the model into use. Facts prove that the age estimation model proposed in this paper may achieve a good estimation effect.