International Journal of Pattern Recognition and Artificial Intelligence

In this paper, the combination of nonlinear gradient iteration and crossing method is presented in order to analyze high precision remote sensing images of solar magnetic field in extreme ultraviolet (EUV) wavelengths which are usually affected by solar magnetic evolution, satellite attitude changes and random satellite jitter, and to reduce structural complexity the complicated correlation tracker is normally adopted. Using crossing method which better approached the inefficiency by computing full-scale solar magnetic field images, nine point areas are uniformly selected in full-scale solar magnetic field images which solves the problem of low-computing efficiency. Meanwhile, nonlinear gradient iteration algorithm through numerical simulation experiments is adopted to analyze displacement of solar magnetic field images in EUV wavelengths, which reduces the errors due to the solar intensity changing and tiny deformation of solar magnetic field compared to traditional algorithms. The results clearly indicate that the precision of mean error field and square deviation field for deformed displacement are both less than 5% of pixel by solar magnetic field images of Solar Dynamics Observatory (SDO).

Since edge detection is a field of study used by various disciplines, it is of vital importance to calculate it accuretly. In addition, an edge detection algorithm may be involved in many image processing phases. A recent and contemporary approach, neutrosophy is based on neutrosophic logic, neutrosophic probability, neutrosophic set and neutrosophic statistics. This method yields better results compared to various other optimization methods. Neutrosophic Set (NS) is based on the origin, nature and scope of neutralities. In NS, problems are separated into true, false and indeterminacy subsets. It helps solve indeterminate situations effectively. It has recently been used in the field of image processing as indeterminate situations are also encountered in this field. Chan–Vese (CV) model is one of the successful region-based segmentation methods. The present study proposes a new NS-based edge detection method using CV algorithm. The proposed method combines the philosophical view of NS with successful segmentation characteristics of CV model. Obtained edge detection results are compared with different edge detection methods. The performances of each method are analyzed by using Figure of Merit (FOM) and Peak Signal-To-Noise Ratio (PSNR). The results suggest that the proposed method displays a better performance assessment compared to the used well-known methods.

Long-term exposure to seriously polluted atmospheric environment is closely related to a variety of human diseases. The long-term and continuous monitoring of PM${}_{2.5}$ (the aerodynamic particle diameter is less than or equal to 2.5$\mu$m) is of great significance as it is one of the major air pollutants. Because of the small number of PM${}_{2.5}$ monitoring stations in China, it is very difficult to accurately estimate the continuous scale of air pollution, but PM${}_{2.5}$ concentration can be acquired by using the aerosol products inversed by remote sensing data. However, due to the limitation of the inversion algorithm, the traditionally used moderate resolution imaging spectroradiometer (MODIS) aerosol products cannot meet the precision and practical requirements in both spatial resolution and effective numerical coverage. This paper adopts MAIAC AOD, i.e. the aerosol optical depth (AOD) products produced by using the new multi-angle implementation of atmospheric correction (MAIAC) algorithm, and we take the Beijing–Tianjin–Hebei region in China as the research area. Based on the neural network algorithm, the MAIAC AOD data is mainly used and the meteorological parameter data is supplemented to establish the PM${}_{2.5}$ concentration prediction model to obtain the PM${}_{2.5}$ concentration distribution map. The prediction accuracy, the effective numerical coverage and spatial resolution have been greatly improved.

An adaptive region-segmentation based multi-focus image fusion method is presented using a Laplacian pyramid transform which decomposes the pre-registered source images into approximate and detail coefficients. In order to avoid the disadvantage of fixed-size blocks, the adaptive differential evolution scheme is designed to compute the optimal-size block. Firstly, with approximate coefficients, the optimal-size blocks are iteratively calculated by an adaptive differential evolution algorithm. The initial decision diagram is then completed by comparing the regional sum-modified Laplacian energy of two corresponding blocks after the regional sum-modified Laplacian energy is calculated. Secondly, the initial decision diagram is optimized by the guided image filter to obtain the final decision diagram in order to avoid the block effect of boundary. With the decision diagram, the approximate coefficients are fused using the weighted mean rules, while the detail coefficients are fused using the regional gradient energy method. Finally, an inverse Laplacian pyramid transform is used to reconstruct the fused approximate coefficients and fused detail coefficients, and to acquire the fused image where all objects are clear. The experimental result proves that the proposed method produces fusion images of fewer artifacts or additional noise, with higher computational efficiency. The proposed method is also superior to the other state-of-the-art methods in both subjective visual effect and objective quantitative evaluation indicators.

A contrast enhancement method based on the adaptive noise threshold estimation and logarithmic function in nonsubsampled contourlet transform (NSCT) domain is proposed, which can improve the defects segmentation accuracy of the elevator compensation chain. After extracting region of interest (ROI) according to the spatial location of defects, it is transformed into NSCT domain, where the high-frequency subband coefficients corresponding to noise is suppressed by the adaptive noise threshold estimation. Then, the logarithmic function transformation is used to enhance the image edges to a variable extent. Finally, the enhanced image is segmented by watershed algorithm based on laws texture analysis. Experimental results demonstrate that the performance of the proposed method is superior to the existing methods in terms of both the quality of contrast enhancement and the segmentation accuracy.

Integrating spatial information into the sparse subspace clustering (SSC) models for hyperspectral images (HSIs) is an effective way to improve clustering accuracy. Since HSI is a three-dimensional (3D) cube datum, 3D spectral-spatial filtering becomes a simple method for extracting the spectral-spatial information. In this paper, a novel spectral-spatial SSC framework based on 3D edge-preserving filtering (EPF) is proposed to improve the clustering accuracy of HSI. First, the initial sparse coefficient matrix is obtained in the sparse representation process of the classical SSC model. Then, a 3D EPF is conducted on the initial sparse coefficient matrix to obtain a more accurate coefficient matrix by solving an optimization problem based on ADMM, which is used to build the similarity graph. Finally, the clustering result of HSI data is achieved by applying the spectral clustering algorithm to the similarity graph. Specifically, the filtered matrix can not only capture the spectral-spatial information but the intensity differences. The experimental results on three real-world HSI datasets demonstrated that the potential of including the proposed 3D EPF into the SSC framework can improve the clustering accuracy.

This paper focused on the illumination model of machined surface based on micro-image. According to micro-image forming condition, the theory that the image brightness is related to the microfacet topography and surface reflection characteristics is presented. The distribution rule of micro-topography and reflection characteristics of sample surface is analyzed according to the measured data. An illumination mode of machined surface is established based on the analysis result, and the model parameters are obtained by using the simulated annealing algorithm. Verification results show that this proposed model can improve the simulation accuracy significantly and describe the lighting effect of machined surface. The research will provide a new idea and method for the 3D reconstruction.

Graph signal processing (GSP) is an emerging field in the signal processing community. Novel GSP-based transforms, such as graph Fourier transform and graph wavelet filter banks, have been successfully utilized in image processing and pattern recognition. As a rapidly developing research area, graph signal processing aims to extend classical signal processing techniques to signals with irregular underlying structures. One of the hot topics in GSP is to develop multi-scale transforms such that novel GSP-based techniques can be applied in image processing or other related areas. For designing graph signal multi-scale frameworks, downsampling operations that ensuring multi-level downsampling should be specifically constructed. Among the existing downsampling methods in graph signal processing, the state-of-the-art method was constructed based on the maximum spanning tree (MST). However, when using this method for multi-level downsampling of graph signals defined on unweighted densely connected graphs, such as social network data, the sampling rates are not close to $\frac{1}{2}$. This phenomenon is summarized as a new problem and called downsampling unbalance problem in this paper. Due to the unbalance, MST-based downsampling method cannot be applied to construct graph signal multi-scale transforms. In this paper, we propose a novel and efficient method to detect and reduce the downsampling unbalance generated by the MST-based method. For any given graph signal, we apply the graph density to construct a measurement of the downsampling unbalance generated by the MST-based method. If a graph signal has large unbalance possibility, the multi-level downsampling is conducted after the MST is improved. The experimental results on synthetic and real-world social network data show that downsampling unbalance can be efficiently detected and then reduced by our method.

Due to the functionality of dynamic mapping for nonlinear complex data, BP neural network (BP-NN) as a typical neural network has increasingly been applied to a variety of applications. Although it has been successfully applied, its prominent shortcoming, such as the local optimum problem and the setting problem for the initial parameter of neural network, have not been completely eliminated. In this paper, an optimization algorithm for the architecture, weights and thresholds of neural networks using an improved gene expression programming (IGEP) was presented. The algorithm effectively combines the global search ability of GEP and the local search ability of BP-NN. To obtain a better efficiency, the basic GEP was improved by the dynamic adjustment of the fitness function, genetic operators and the number of evolutionary generations. The experimental results show that the IGEP-BP algorithm is an effective method for evolving neural network.

The performance of the traditional Pareto-based evolutionary algorithms sharply reduces for many-objective optimization problems, one of the main reasons is that Pareto dominance could not provide sufficient selection pressure to make progress in a given population. To increase the selection pressure toward the global optimal solutions and better maintain the quality of selected solutions, in this paper, a new dominance method based on expanding dominated area is proposed. This dominance method skillfully combines the advantages of two existing popular dominance methods to further expand the dominated area and better maintain the quality of selected solutions. Besides, through dynamically adjusting its parameter with the iteration, our proposed dominance method can timely adjust the selection pressure in the process of evolution. To demonstrate the quality of selected solutions by our proposed dominance method, the experiments on a number of well-known benchmark problems with 5–25 objectives are conducted and compared with that of the four state-of-the-art dominance methods based on expanding dominated area. Experimental results show that the new dominance method not only enhances the selection pressure but also better maintains the quality of selected solutions.

The ultimate direction of intelligent vehicle management is to achieve artificial intelligence (AI), and data mining is an important supporting technology for AI. The adoption of new AI technology can effectively improve operational efficiency and safety, especially in terms of performance. This paper takes the researches on traffic jam as an example and proposes one algorithm for combination forecasting model based on a segmentation algorithm for traffic flow sequence and BP neural network prediction. In this paper, it also introduces the traffic flow clustering analysis and mining algorithms for congestion events at the intersections. The blocking point algorithm is improved, and experimental analysis is performed through samples. Experimental results show that the algorithm use for combination forecasting model can greatly improve the real-time performance of short-term traffic flow prediction and significantly reduce the prediction error rate. Therefore, this algorithm has practical and innovative significance in the field of intelligent vehicle management.

This paper corrects some mistakes about three theorems, two figures and some expressions on “finite field” in a literature, and then it analyzes the digraphs and period properties of the logistic map on residue class rings $Z(3^n)$ and $Z(p^n)$. Some theorems and conjectures are proved or given. To validate these properties, we make some numeral experiments and draw the relative figures and tables. So the theoretical analysis and numeral experiments show that there exists periods in the logistic map on $Z(3^n)$ and on $Z(p^n)$ and it can be applied in the pseudo-random generators, cryptography, spread spectrum communications and so on.

Batch processes and phenomena in traffic video data processing, such as traffic video image processing and intelligent transportation, are commonly used. The application of batch processing can increase the efficiency of resource conservation. However, owing to limited research on traffic video data processing conditions, batch processing activities in this area remain minimally examined. By employing database functional dependency mining, we developed in this study a workflow system. Meanwhile, the Bayesian network is a focus area of data mining. It provides an intuitive means for users to comply with causality expression approaches. Moreover, graph theory is also used in data mining area. In this study, the proposed approach depends on relational database functions to remove redundant attributes, reduce interference, and select a property order. The restoration of selective hidden naive Bayesian (SHNB) affects this property order when it is used only once. With consideration of the hidden naive Bayes (HNB) influence, rather than using one pair of HNB, it is introduced twice. We additionally designed and implemented mining dependencies from a batch traffic video processing log for data execution algorithms.