Hyperspectral anomaly detection using spectral–spatial features based on the human visual system

ABSTRACT

Anomaly detection (AD) is one of the most attracting topics within the recent 10 years in hyperspectral imagery (HSI). The goal of the AD is to label the pixels with significant spectral or spatial differences to their neighbours, as targets. In this paper, we propose a method that uses both spectral and spatial information of HSI based on human visual system (HVS). By inspiring the retina and the visual cortex functionality, the multiscale multiresolution analysis is applied to some principal components of hyperspectral data, to extract features from different spatial levels of the image. Then the global and local relations between features are considered based on inspiring the visual attention mechanism and inferotemporal (IT) part of the visual cortex. The effects of the attention mechanism are implemented using the logarithmic function which well highlights, small variations in pixels’ grey levels in global features. Also, the maximum operation is used over the local features for imitating the function of IT. Finally, the information theory concept is used for generating the final detection map by weighting the global and local detection maps to obtain the final anomaly map. The result of the proposed method is compared with some state-of-the-art methods such as SSRAD, FLD, PCA, RX, KPCA, and AED for two well-known real hyperspectral data which are San Diego airport and Pavia city, and a synthetic hyperspectral data. The results demonstrate that the proposed method effectively improves the AD capabilities, such as enhancement of the detection rate, reducing the false alarm rate and the computation complexity.     

Evaluating students’ learning achievement based on the eigenvector method

In this paper, we present a new method for students’ learning achievement evaluation based on the eigenvector method. The proposed method considers the “accuracy rate”, the “time rate”, the “importance” and the “complexity” for evaluating students’ learning achievement. First, the proposed method transforms the attributes “accuracy rate” and “time rate” into the “effect of accuracy rate” and the “effect of time rate”, respectively. Then, it generates the relative importance degrees of the attributes “effect of accuracy rate”, “effect of time rate”, “importance” and “complexity” based on the eigenvector method. Then, it uses the correlation coefficients between the attribute vectors and the standard deviations of the elements in the attribute vectors to calculate the fitness degrees of the attributes, where the attribute vectors represent the relationships between the attributes and the questions. Then, it generates the weights of the attributes based on the relative importance degrees of the attributes and the fitness degrees of the attributes. Then, it generates the importance degrees of the questions according to the weights of the attributes and the relation matrix representing the relationships between the questions and the attributes. Finally, based on the importance degrees vector of the questions, the grade matrix, the accuracy rate matrix, it calculates the learning achievement index of each student having the same original total score for students’ learning achievement evaluation. The proposed method provides us with a useful way for students’ learning achievement evaluation based on the eigenvector method.     

Software defect prediction model based on LASSO–SVM

Neural Computing and Applications - A software defect report is a bug in the software system that developers and users submit to the software defect library during software development and...     

Parallel eigenvalue calculation based on multiple shift–invert Lanczos and contour integral based spectral projection method

We discuss the possibility of using multiple shift–invert Lanczos and contour integral based spectral projection method to compute a relatively large number of eigenvalues of a large sparse and symmetric matrix on distributed memory parallel computers. The key to achieving high parallel efficiency in this type of computation is to divide the spectrum into several intervals in a way that leads to optimal use of computational resources. We discuss strategies for dividing the spectrum. Our strategies make use of an eigenvalue distribution profile that can be estimated through inertial counts and cubic spline fitting. Parallel sparse direct methods are used in both approaches. We use a simple cost model that describes the cost of computing k eigenvalues within a single interval in terms of the asymptotic cost of sparse matrix factorization and triangular substitutions. Several computational experiments are performed to demonstrate the effect of different spectrum division strategies on the overall performance of both multiple shift–invert Lanczos and the contour integral based method. We also show the parallel scalability of both approaches in the strong and weak scaling sense. In addition, we compare the performance of multiple shift–invert Lanczos and the contour integral based spectral projection method on a set of problems from density functional theory (DFT).     

Fast local image inpainting based on the Allen–Cahn model

In this paper, we propose a fast local image inpainting algorithm based on the Allen–Cahn model. The proposed algorithm is applied only on the inpainting domain and has two features. The first feature is that the pixel values in the inpainting domain are obtained by curvature-driven diffusions and utilizing the image information from the outside of the inpainting region. The second feature is that the pixel values outside of the inpainting region are the same as those in the original input image since we do not compute the outside of the inpainting region. Thus the proposed method is computationally efficient. We split the governing equation into one linear equation and one nonlinear equation by using an operator splitting technique. The linear equation is discretized by using a fully implicit scheme and the nonlinear equation is solved analytically. We prove the unconditional stability of the proposed scheme. To demonstrate the robustness and accuracy of the proposed method, various numerical results on real and synthetic images are presented.     

T–S fuzzy model identification based on a novel fuzzy c-regression model clustering algorithm

This paper proposes a novel approach for identification of Takagi–Sugeno (T–S) fuzzy model, which is based on a new fuzzy c-regression model (FCRM) clustering algorithm. The clustering prototype in fuzzy space partition is hyper-plane, so FCRM clustering technique is more suitable to be applied in premise parameters identification of T–S fuzzy model. A new FCRM clustering algorithm (NFCRMA) is presented, which is deduced from the fuzzy clustering objective function of FCRM with Lagrange multiplier rule, possessing integrative and concise structure. The proposed approach consists mainly of two steps: premise parameter identification and consequent parameter identification. The NFCRMA is utilized to partition the input–output data and identify the premise parameters, which can discover the real structure of the training data; on the other hand, orthogonal least square is exploited to identify the consequent parameters. Finally, some examples are given to verify the validity of the proposed modeling approach, and the results show the new approach is very efficient and of high accuracy.     

Abnormality detection based on the Kullback–Leibler divergence for generalized Gaussian data

This paper is on abnormality detection, where the observed data under the normal condition is assumed to be independent and identically distributed (i.i.d.) and follow the generalized Gaussian distribution (GGD) with shape parameter greater than 1. The Kullback–Leibler divergence (KLD) between the estimated GGD of the observed data and the normal one is used as the test statistic. An analytical expression of the KLD is derived under the normal condition when the number of samples is large; then, two algorithms with constant and adaptive thresholds are proposed. Extensive simulated and industrial case studies are conducted to verify the analytical results and to show the effectiveness of the proposed algorithms.     

Automatic detection of erythemato-squamous diseases using PSO–SVM based on association rules

In this paper, we develop a diagnosis model based on particle swarm optimization (PSO), support vector machines (SVMs) and association rules (ARs) to diagnose erythemato-squamous diseases. The proposed model consists of two stages: first, AR is used to select the optimal feature subset from the original feature set; then a PSO based approach for parameter determination of SVM is developed to find the best parameters of kernel function (based on the fact that kernel parameter setting in the SVM training procedure significantly influences the classification accuracy, and PSO is a promising tool for global searching). Experimental results show that the proposed AR_PSO–SVM model achieves 98.91% classification accuracy using 24 features of the erythemato-squamous diseases dataset taken from UCI (University of California at Irvine) machine learning database. Therefore, we can conclude that our proposed method is very promising compared to the previously reported results.     

Dynamic modeling of SOFC based on a T–S fuzzy model

The operating temperature and voltage are the key parameters affecting the performance of Solid Oxide Fuel Cell (SOFC). In this article a Takagi–Sugeno (T–S) fuzzy model is proposed to describe the nonlinear temperature and voltage dynamic properties of the SOFC system. During the process of modeling, a Fuzzy Clustering Means (FCM) method is used to determine the nonlinear antecedent parameters, and the linear consequent parameters are identified by a recursive least squares algorithm. The validity and accuracy of modeling are tested by simulations. The simulation results show that it is feasible to establish the dynamic model of SOFC by using the T–S fuzzy identification method.     

Evolving Takagi–Sugeno fuzzy model based on switching to neighboring models

In this paper, we propose a new online identification approach for evolving Takagi–Sugeno (TS) fuzzy models. Here, for a TS model, a certain number of models as neighboring models are defined and then the TS model switches to one of them at each stage of evolving. We define neighboring models for an in-progress (current) TS model as its fairly evolved versions, which are different with it just in two fuzzy rules. To generate neighboring models for the current model, we apply specially designed split and merge operations. By each split operation, a fuzzy rule is replaced with two rules; while by each merge operation, two fuzzy rules combine to one rule. Among neighboring models, the one with the minimum sum of squared errors – on certain time intervals – replaces the current model.To reduce the computational load of the proposed evolving TS model, straightforward relations between outputs of neighboring models and that of current model are established. Also, to reduce the number of rules, we define and use first-order TS fuzzy models whose generated local linear models can be localized in flexible fuzzy subspaces. To demonstrate the improved performance of the proposed identification approach, the efficiency of the evolving TS model is studied in prediction of monthly sunspot number and forecast of daily electrical power consumption. The prediction and modeling results are compared with that of some important existing evolving fuzzy systems.     

Graphical model construction based on evolutionary algorithms

1 Introduction Evolutionary algorithms(EAs) [1～5] are stochastic search and optimization techniques, which were inspired by the analogy of evolution and population genetics. They have been demonstrated to be effective and robust in searching very large, varied, spaces in a wide range of applications, including classification, machine learning, ecological, so- cial systems and so on. However, most of the common evo- lutionary algorithms using simple operators are incapable of learning the reg…     

Study of multiple moving targets’ detection in fisheye video based on the moving blob model

Multimedia Tools and Applications - This paper discussed some improved algorithms for multiple moving targets detection and tracking in fisheye video sequences which based on the moving blob model....     

Research on Hyperspectral Imagery Land Cover ClassificationMethod based on AdaBoost Improved Random Forest

In order to improve the classification accuracy of hyperspectral images,a new weighted random forest method based on AdaBoost is proposed.In this method,the concept of sample weight is introduced,and then the weight of each sample will be adjusted according to whether the sample is correctly classified.Those misclassified samples will be given higher weight value,to attract more attention of the classifier to improve the classification.Furthermore,the method gives the voting weight to every basic classifier according to their classification error rate.The basic classifier with higher classification accuracy will obtain larger voting weight.Two sets of Hyperspectral data(The CASI Hyperspectral Data acquired in Heihe region and CHRIS Hyperspectral Data acquired in the Yellow River Estuary) are used to verify the validity of the method.The results show that the weighted random forest has a better performance than the equal weight random forest and the SVM method in the overall classification accuracy,the average classification accuracy and the Kappa coefficient,which proves the efficiency of the proposed method.     

Object-oriented change detection based on the Kolmogorov–Smirnov test using high-resolution multispectral imagery

In this article, we propose a novel method of object-oriented change detection for high-resolution remote-sensing imagery. The method consists of three main parts: image segmentation, object adjusting and change detection. We use the Fractal Net Evolution Approach to segment the multi-temporal images. Then we adjust the object maps. By merging the objects in relatively large areas, the object -adjusting algorithm aims to obtain a set of objects with different sizes, which coincide better with the real ground objects than the single-scale results. In the third part, the Kolmogorov–Smirnov two-sample test detects each pair of objects in the multi-temporal object maps with multi-scale. The calculated value of the D-statistic is compared to the threshold of a user-defined significance level. Through these three processes, we can make full use of the spatial and spectral features in high- resolution images to detect changes. According to our experiments in two study areas employing QuickBird imagery, the overall errors of our method decreased by more than 1000 pixels compared with the conventional object-oriented change vector analysis. The proposed method can also avoid the errors resulting from classification in the method of post-classification comparison.     

Anomaly detection of network traffic based on autocorrelation principle

Network anomalies caused by network attacks can significantly degrade or even terminate network services. A Real-time and reliable detection of anomalies is essential to rapid anomaly diagnosis, anomaly mitigation, and malfunction recovering. Unlike most detection methods based on the statistical analysis of the packet headers （Such as IP addresses and ports）, a new approach only using network traffic volumes is proposed to detect anomalies reliably. Our method is based on autocorrelation function to judge whether anomalies have happened. In details, the correlation coefficients of normal and anomaly data fluctuate slightly respectively, while those of the overlapped data composed of them fluctuate greatly. Experimental results on network traffic volumes transformed from 1999 DARPA intrusion evaluation data set show that this method can effectively detect network anomalies, while avoiding the high false alarms rate.     

Mean–variance portfolio selection based on a generalized BNS stochastic volatility model

We study a mean–variance portfolio selection problem via optimal feedback control based on a generalized Barndorff-Nielsen and Shephard stochastic volatility model, where an investor trades in a generalized Black–Scholes market. The random coefficients of the market are driven by non-Gaussian Ornstein–Uhlenbeck processes that are independent of the underlying multi-dimensional Brownian motion. Our contribution is to explicitly compute and justify optimal portfolios over an admissible set that is large enough to cover some important classes of strategies such as the class of feedback controls of Markov type. Concretely, the mean–variance efficient portfolios and efficient frontiers are explicitly calculated through the method of generalized linear-quadratic control and explicitly constructed solutions to three integro-partial differential equations under a quite mild condition that only requires one stock whose appreciation-rate process is different from the interest-rate process. Related minimum variance issue is also addressed via our main results.     

Real-time state-of-health monitoring of lithium-ion battery with anomaly detection,Levenberg–Marquardt algorithm,and multiphase exponential regression model

Neural Computing and Applications - The state of health (SOH) of lithium-ion (Li+) battery prediction plays significant roles in battery management and the determination of the durability of the...     

The prediction model of worsted yarn quality based on CNN–GRNN neural network

Neural Computing and Applications - It is key indexes of worsted yarn quality such as worsted yarn strength index, etc., and it can well control worsted yarn quality by predicting yarn strength...     

A new arc detection method based on fuzzy logic using S-transform for pantograph–catenary systems

pantograph–catenary system is one of the critical components used in electrical trains. It ensures the transmission of the electrical energy to the train taken from the substation that is required for electrical trains. The condition monitoring and early diagnosis for pantograph–catenary systems are very important in terms of rail transport disruption. In this study, a new method is proposed for arc detection in the pantograph–catenary system based signal processing and S-transform. Arc detection and condition monitoring were achieved by using current signals received from a real pantograph–catenary system. Firstly, model based current data for pantograph–catenary system is obtained from Mayr arc model. The method with S-transform is developed by using this current data. Noises on the current signal are eliminated by applying a low pass filter to the current signal. The peak values of the noiseless signals are determined by taking absolute values of these signals in a certain frequency range. After the data of the peak points has been normalized, a new signal will be obtained by combining these points via a linear interpolation method. The frequency-time analysis was realized by applying S-transform on the signal obtained from peak values. Feature extraction that obtained by S-matrix was used in the fuzzy system. The current signal is detected the contdition as healthy or faulty by using the outputs of the fuzzy system. Furthermore the real-time processing of the proposed method is examined by applying to the current signal received from a locomotive.     

GMAT: Glottal closure instants detection based on the Multiresolution Absolute Teager–Kaiser energy operator

Glottal Closure Instants (GCIs) detection is important to many speech applications. However, most existing algorithms cannot achieve computational efficiency and accuracy simultaneously. In this paper, we present the Glottal closure instants detection based on the Multiresolution Absolute TKEO (GMAT) that can detect GCIs with high accuracy and low computational cost. Considering the nonlinearity in speech production, the Teager–Kaiser Energy Operator (TKEO) is utilized to detect GCIs and an instant with a high absolute TKEO value often indicates a GCI. To enhance robustness, three multiscale pooling techniques, which are max pooling, multiscale product, and mean pooling, are applied to fuse absolute TKEOs of several scales. Finally, GCIs are detected based on the fused results. In the performance evaluation, GMAT is compared with three state-of-the-art methods, MSM (Most Singular Manifold-based approach), ZFR (Zero Frequency Resonator-based method), and SEDREAMS (Speech Event Detection using the Residual Excitation And a Mean-based Signal). On clean speech, experiments show that GMAT can attain higher identification rate and accuracy than MSM. Comparing with ZFR and SEDREAMS, GMAT gives almost the same reliability and higher accuracy. In addition, on noisy speech, GMAT demonstrates the highest robustness for most SNR levels. Additional comparison shows that GMAT is less sensitive to the choice of scale in multiscale processing and it has low computational cost. Finally, pathological speech identification, which is a concrete application of GCIs, is included to show the efficacy of GMAT in practice. Through this paper, we investigate the potential of TKEO for GCI detection and the proposed algorithm GMAT can detect GCIs with high accuracy and low computational cost. Due to the superiority of GMAT, it will be a promising choice for GCI detection, particularly in real-time scenarios. Hence, this work may contribute to systems relying on GCIs, where both accuracy and computational cost are crucial.