Jiaqi Zhao

Discriminant deep belief network for high-resolution SAR image classification

Classification plays an important role in many fields of synthetic aperture radar (SAR) image understanding and interpretation. Many scholars have devoted to design features to characterize the content of SAR images. However, it is still a challenge to design discriminative and robust features for SAR image classification. Recently, the deep learning has attracted much attention and has been successfully applied in many fields of computer vision. In this paper, a novel feature learning approach that is called discriminant deep belief network (DisDBN) is proposed to learning high-level features for SAR image classification, in which the discriminant features are learned by combining ensemble learning with a deep belief network in an unsupervised manner. Firstly, some subsets of SAR image patches are selected and marked with pseudo-labels to train weak classifiers. Secondly, the specific SAR image patch is characterized by a set of projection vectors that are obtained by projecting the SAR image patch onto each weak decision space spanned by each weak classifier. Finally, the discriminant features are generated by feeding the projection vectors to a DBN for SAR image classification. Experimental results demonstrate that better classification performance can be achieved by the proposed approach than the other state-of-the-art approaches. HighlightsA DisDBN is proposed to characterize SAR image patches in an unsupervised manner.Both the CPL and IPL are investigated to produce prototypes of SAR image patches.Some weak decision spaces are constructed based on the learned prototypes.A high-level feature is learned for the SAR image patch in a hierarchy manner.We show that our method can achieve a better classification performance.

Quantum-behaved discrete multi-objective particle swarm optimization for complex network clustering

Abstract Complex network research has attracted lots of attention in both academic community and various application fields. Complex network clustering, as one of the key issues in complex network, explores the internal organization of the nodes in a complex network. The discrete particle swarm optimization strategy has been successfully proposed for network clustering, while the existing method works with weak robust. In this paper, we model the task of complex network clustering as a multi-objective optimization problem and solve the problem with the quantum mechanism based particle swarm optimization algorithm, which is a parallel algorithm. To our knowledge, this is the first attempt to apply the quantum mechanism based discrete particle swarm optimization algorithm into network clustering. In addition, the non-dominant sorting selection operation is employed for individual replacement. Consequently, a quantum-behaved discrete multi-objective particle swarm optimization algorithm is proposed for complex network clustering. The experimental results demonstrate that the proposed algorithm performs effectively and achieves competitive performance with the state-of-the-art approaches on the extension of Girvan and Newman benchmarks and real-world networks, especially on large-scale networks.

Multiobjective optimization of classifiers by means of 3D convex-hull-based evolutionary algorithms

The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves are frequently used in the machine learning community to analyze the performance of binary classifiers. Recently, the convex-hull-based multiobjective genetic programming algorithm was proposed and successfully applied to maximize the convex hull area for binary classification problems by minimizing false positive rate and maximizing true positive rate at the same time using indicator-based evolutionary algorithms. The area under the ROC curve was used for the performance assessment and to guide the search. Here we extend this research and propose two major advancements: Firstly we formulate the algorithm in detection error tradeoff space, minimizing false positives and false negatives, with the advantage that misclassification cost tradeoff can be assessed directly. Secondly, we add complexity as an objective function, which gives rise to a 3D objective space (as opposed to a 2D previous ROC space). A domain specific performance indicator for 3D Pareto front approximations, the volume above DET surface, is introduced, and used to guide the indicator-based evolutionary algorithm to find optimal approximation sets. We assess the performance of the new algorithm on designed theoretical problems with different geometries of Pareto fronts and DET surfaces, and two application-oriented benchmarks: (1) Designing spam filters with low numbers of false rejects, false accepts, and low computational cost using rule ensembles, and (2) finding sparse neural networks for binary classification of test data from the UCI machine learning benchmark. The results show a high performance of the new algorithm as compared to conventional methods for multicriteria optimization.

Semisupervised Discriminant Feature Learning for SAR Image Category via Sparse Ensemble

Terrain scene classification plays an important role in various synthetic aperture radar (SAR) image understanding and interpretation. This paper presents a novel approach to characterize SAR image content by addressing category with a limited number of labeled samples. In the proposed approach, each SAR image patch is characterize by a discriminant feature which is generated in a semisupervised manner by utilizing a spare ensemble learning procedure. In particular, a nonnegative sparse coding procedure is applied on the given SAR image patch set to generate the feature descriptors first. The set is combined with a limited number of labeled SAR image patches and an abundant number of unlabeled ones. Then, a semisupervised sampling approach is proposed to construct a set of weak learners, in which each one is modeled by a logistic regression procedure. The discriminant information can be introduced by projecting SAR image patch on each weak learner. Finally, the features of SAR image patches are produced by a sparse ensemble procedure which can reduce the redundancy of multiple weak learners. Experimental results show that the proposed discriminant feature learning approach can achieve a higher classification accuracy than several state-of-the-art approaches.

A spam filtering multi-objective optimization study covering parsimony maximization and three-way classification

Display Omitted Advances on applications of multi-objective optimization to anti-SPAM filtering.Parsimony maximization of rule-based SPAM classifiers.Three-way classification balancing user effort and confidence level.Indicator-based/machine learning/decomposition-based evolutionary optimization. Classifier performance optimization in machine learning can be stated as a multi-objective optimization problem. In this context, recent works have shown the utility of simple evolutionary multi-objective algorithms (NSGA-II, SPEA2) to conveniently optimize the global performance of different anti-spam filters. The present work extends existing contributions in the spam filtering domain by using three novel indicator-based (SMS-EMOA, CH-EMOA) and decomposition-based (MOEA/D) evolutionary multi-objective algorithms. The proposed approaches are used to optimize the performance of a heterogeneous ensemble of classifiers into two different but complementary scenarios: parsimony maximization and e-mail classification under low confidence level. Experimental results using a publicly available standard corpus allowed us to identify interesting conclusions regarding both the utility of rule-based classification filters and the appropriateness of a three-way classification system in the spam filtering domain.

Sparse learning based fuzzy c-means clustering

Recently sparse representation (SR) based clustering has attracted a growing interests in the field of image processing and pattern recognition. Since the SR technology has favorable category distinguishing ability, we introduce it into the fuzzy clustering in this paper, and propose a new clustering algorithm, called sparse learning based fuzzy c-means (SL_FCM). Firstly, to reduce the computation complexity of the SR based FCM method, most energy of discriminant feature obtained by solving a SR model is reserved and the remainder is discarded. By this way, some redundant information (i.e. the correlation among samples of different classes) in the discriminant feature can be also removed, which can improve the clustering quality. Furthermore, to further enhance the clustering performance, the position information of valid values in discriminant feature is also used to re-define the distance between sample and clustering center in SL_FCM. The weighted distance in SL_FCM can enhance the similarity of the samples from the same class and the difference of the samples of different classes, thus to improve the clustering result. In addition, as the dimension of stored discriminant feature of each sample is different, we use set operations to formulate the distance and cluster center in SL_FCM. The comparisons on several datasets and images demonstrate that SL_FCM performs better than other state-of-art methods with higher accuracy, while keeps low spatial and computational complexity, especially for the large scale dataset and image.

Superpixel-Based Multiple Local CNN for Panchromatic and Multispectral Image Classification

Recently, very high resolution (VHR) panchromatic and multispectral (MS) remote-sensing images can be acquired easily. However, it is still a challenging task to fuse and classify these VHR images. Generally, there are two ways for the fusion and classification of panchromatic and MS images. One way is to use a panchromatic image to sharpen an MS image, and then classify a pan-sharpened MS image. Another way is to extract features from panchromatic and MS images, respectively, and then combine these features for classification. In this paper, we propose a superpixel-based multiple local convolution neural network (SML-CNN) model for panchromatic and MS images classification. In order to reduce the amount of input data for the CNN, we extend simple linear iterative clustering algorithm for segmenting MS images and generating superpixels. Superpixels are taken as the basic analysis unit instead of pixels. To make full advantage of the spatial-spectral and environment information of superpixels, a superpixel-based multiple local regions joint representation method is proposed. Then, an SML-CNN model is established to extract an efficient joint feature representation. A softmax layer is used to classify these features learned by multiple local CNN into different categories. Finally, in order to eliminate the adverse effects on the classification results within and between superpixels, we propose a multi-information modification strategy that combines the detailed information and semantic information to improve the classification performance. Experiments on the classification of Vancouver and Xi’an panchromatic and MS image data sets have demonstrated the effectiveness of the proposed approach.

Semi-supervised double sparse graphs based discriminant analysis for dimensionality reduction

Abstract Discriminant analysis (DA) is a well-known dimensionality reduction tool in pattern classification. With enough efficient labeled samples, the optimal projections could be found by maximizing the between-class scatter variance meanwhile minimizing the within-class scatter variance. However, the acquisition of label information is difficult in practice. So, semi-supervised discriminant analysis has attracted much attention in recent years, where both few labeled samples and many unlabeled samples are utilized during learning process. Sparse graph learned by sparse representation contains local structure information about data and is widely employed in dimensionality reduction. In this paper, semi-supervised double sparse graphs (sDSG) based dimensionality reduction is proposed, which considers both the positive and negative structure relationship of data points by using double sparse graphs. Aiming to explore the discriminant information among unlabeled samples, joint k nearest neighbor selection strategy is proposed to select pseudo-labeled samples which contain some precise discriminant information. In the following procedures, the data subset consisting of labeled samples and pseudo-labeled samples are used instead of the original data. Based on two different criterions, two sDSG based discriminant analysis methods are designed and denoted by sDSG-dDA (distance-based DA) and sDSG-rDA (reconstruction-based DA), which also use different strategies to reduce the effect of pseudo-labels’ inaccuracy. Finally, the experimental results both on UCI datasets and hyperspectral images validate the effectiveness and advantage of the proposed methods compared with some classical dimensionality reduction methods.

Dimensionality Reduction of Hyperspectral Imagery Using Sparse Graph Learning

Combining with sparse representation, the sparse graph can adaptively capture the intrinsic structural information of the specified data. In this paper, an unsupervised sparse-graph-learning-based dimensionality reduction (SGL-DR) method is proposed for hyperspectral image. In SGL-DR, the sparse graph construction and projection learning are combined together in a unified framework and influence each other. During sparse graph learning, projected features are utilized to enhance the discriminant information in sparse graph. Likewise, in projection learning, the enhanced sparse graph could make projected features have high discriminant capacity. Besides, the spatial–spectral information in the original space combined with the structure information in the projected space is also exploited to learn the imprecise discriminant information. With the imprecise discriminant information, the projected space that is spanned by the projection matrix of the constructed sparse graph would contain abundant discriminant information, which is beneficial for hyperspectral image classification. Experimental results over two hyperspectral image datasets demonstrate that the proposed approach outperforms the other state-of-the-art unsupervised approaches with a 10% improvement of the classification accuracy. Furthermore, it also outperforms those graph-based supervised methods with acceptable computational cost.

Locality-constraint discriminant feature learning for high-resolution SAR image classification

It remains one of the most challenging tasks to distinguish different terrain materials from a single SAR image. With the increase of ground resolution, it allows us to model the SAR image directly by exploiting spatial structures and texture information that are extracted by several machine learning approaches. In this paper, a novel feature learning approach is proposed to capture discriminant features of high-resolution SAR images. In the first stage, a weighted discriminant filter bank is learned from some labeled SAR image patches to generate low-level features. Then, the locality constraint is introduced to produce the high-level features in both the encoding and the spatial pooling procedure. In this work, the superpixels are employed as the basic operational units instead of the pixels for terrain classification. With some learned domain patterns which are learned from all of the high-level features of each pixel, the superpixel is characterized by a hyper-feature. In the last stage, a linear-kernel support vector machine is utilized to classify all of these hyper-features which are generated for each superpixel. The experimental results show a better classification performance of the proposed approach than several available state-of-the-art approaches.