Cognitive radio (CR) is the enabling technology for supporting dynamic spectrum access: the policy that addresses the spectrum scarcity problem that is encountered in many countries. Thus, CR is widely regarded as one of the most promising technologies for future wireless communications. To make radios and wireless networks truly cognitive, however, is by no means a simple task, and it requires collaborative effort from various research communities, including communications theory, networking engineering, signal processing, game theory, software-hardware joint design, and reconfigurable antenna and radio-frequency design. In this paper, we provide a systematic overview on CR networking and communications by looking at the key functions of the physical (PHY), medium access control (MAC), and network layers involved in a CR design and how these layers are crossly related. In particular, for the PHY layer, we will address signal processing techniques for spectrum sensing, cooperative spectrum sensing, and transceiver design for cognitive spectrum access. For the MAC layer, we review sensing scheduling schemes, sensing-access tradeoff design, spectrum-aware access MAC, and CR MAC protocols. In the network layer, cognitive radio network (CRN) tomography, spectrum-aware routing, and quality-of-service (QoS) control will be addressed. Emerging CRNs that are actively developed by various standardization committees and spectrum-sharing economics will also be reviewed. Finally, we point out several open questions and challenges that are related to the CRN design.

Cognitive radio networking and communications: an overview

With the popular use of high-resolution satellite images, more and more research efforts have been placed on remote sensing scene classification/recognition. In scene classification, effective feature selection can significantly boost the final performance. In this letter, a novel deep-learning-based feature-selection method is proposed, which formulates the feature-selection problem as a feature reconstruction problem. Note that the popular deep-learning technique, i.e., the deep belief network (DBN), achieves feature abstraction by minimizing the reconstruction error over the whole feature set, and features with smaller reconstruction errors would hold more feature intrinsics for image representation. Therefore, the proposed method selects features that are more reconstructible as the discriminative features. Specifically, an iterative algorithm is developed to adapt the DBN to produce the inquired reconstruction weights. In the experiments, 2800 remote sensing scene images of seven categories are collected for performance evaluation. Experimental results demonstrate the effectiveness of the proposed method.

Deep Learning Based Feature Selection for Remote Sensing Scene Classification

It is of great interest in exploiting texture information for classification of hyperspectral imagery (HSI) at high spatial resolution. In this paper, a classification paradigm to exploit rich texture information of HSI is proposed. The proposed framework employs local binary patterns (LBPs) to extract local image features, such as edges, corners, and spots. Two levels of fusion (i.e., feature-level fusion and decision-level fusion) are applied to the extracted LBP features along with global Gabor features and original spectral features, where feature-level fusion involves concatenation of multiple features before the pattern classification process while decision-level fusion performs on probability outputs of each individual classification pipeline and soft-decision fusion rule is adopted to merge results from the classifier ensemble. Moreover, the efficient extreme learning machine with a very simple structure is employed as the classifier. Experimental results on several HSI data sets demonstrate that the proposed framework is superior to some traditional alternatives.

Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification

Saliency detection has been a hot topic in recent years, and many efforts have been devoted in this area. Unfortunately, the results of saliency detection can hardly be utilized in general applications. The primary reason, we think, is unspecific definition of salient objects, which makes that the previously published methods cannot extend to practical applications. To solve this problem, we claim that saliency should be defined in a context and the salient band selection in hyperspectral image (HSI) is introduced as an example. Unfortunately, the traditional salient band selection methods suffer from the problem of inappropriate measurement of band difference. To tackle this problem, we propose to eliminate the drawbacks of traditional salient band selection methods by manifold ranking. It puts the band vectors in the more accurate manifold space and treats the saliency problem from a novel ranking perspective, which is considered to be the main contributions of this paper. To justify the effectiveness of the proposed method, experiments are conducted on three HSIs, and our method is compared with the six existing competitors. Results show that the proposed method is very effective and can achieve the best performance among the competitors.

Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking

Hyperspectral sensors record the reflectance from the Earth's surface over the full range of solar wavelengths with high spectral resolution. The resulting high-dimensional data contain rich information for a wide range of applications. However, for a specific application, not all the measurements are important and useful. The original feature space may not be the most effective space for representing the data. Feature mining, which includes feature generation, feature selection (FS), and feature extraction (FE), is a critical task for hyperspectral data classification. Significant research effort has focused on this issue since hyperspectral data became available in the late 1980s. The feature mining techniques which have been developed include supervised and unsupervised, parametric and nonparametric, linear and nonlinear methods, which all seek to identify the informative subspace. This paper provides an overview of both conventional and advanced feature reduction methods, with details on a few techniques that are commonly used for analysis of hyperspectral data. A general form that represents several linear and nonlinear FE methods is also presented. Experiments using two widely available hyperspectral data sets are included to illustrate selected FS and FE methods.

Feature Mining for Hyperspectral Image Classification

Band selection is a common approach to reduce the data dimensionality of hyperspectral imagery. It extracts several bands of importance in some sense by taking advantage of high spectral correlation. Driven by detection or classification accuracy, one would expect that, using a subset of original bands, the accuracy is unchanged or tolerably degraded, whereas computational burden is significantly relaxed. When the desired object information is known, this task can be achieved by finding the bands that contain the most information about these objects. When the desired object information is unknown, i.e., unsupervised band selection, the objective is to select the most distinctive and informative bands. It is expected that these bands can provide an overall satisfactory detection and classification performance. In this letter, we propose unsupervised band selection algorithms based on band similarity measurement. The experimental result shows that our approach can yield a better result in terms of information conservation and class separability than other widely used techniques.

https://my.ece.msstate.edu/faculty/du/GRSL-BS.pdf

Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis

Band selection is often applied to reduce the dimensionality of hyperspectral imagery. When the desired object information is known, it can be achieved by finding the bands that contain the most object information. It is expected that these bands can provide an overall satisfactory detection and classification performance. In this letter, we propose a new supervised band-selection algorithm that uses the known class signatures only without examining the original bands or the need of class training samples. Thus, it can complete the task much faster than traditional methods that test bands or band combinations. The experimental result shows that our approach can generally yield better results than other popular supervised band-selection methods in the literature.

An Efficient Method for Supervised Hyperspectral Band Selection

We propose a joint optical flow and principal component analysis (PCA) method for motion detection. PCA is used to analyze optical flows so that major optical flows corresponding to moving objects in a local window can be better extracted. This joint approach can efficiently detect moving objects and more successfully suppress small turbulence. It is particularly useful for motion detection from outdoor videos with low quality. It can also effectively delineate moving objects in both static and dynamic background. Experimental results demonstrate that this approach outperforms other existing methods by extracting the moving objects more completely with lower false alarms.

/pdf/optical-flow-and-principal-component-analysis-based-motion-uihfpcnyp2.pdf

Optical flow and principal component analysis-based motion detection in outdoor videos

A particle swarm optimization (PSO)-based dimensionality reduction approach is proposed to use a simple searching criterion function, called minimum estimated abundance covariance (MEAC), requiring class signatures only. It has low computational cost, and the selected bands are independent of the detector or classifiers used in the following data analysis step. With such an efficient criterion, PSO can find a global optimal solution much more efficiently, compared with other frequently used searching strategies. Its performance is evaluated by support vector machine (SVM)-based classification for urban land cover mapping. In our experiments, SVM classification accuracy using PSO-selected bands is greatly higher than using all of the original bands or dimensionality-reduced data from principal component analysis (PCA) or linear discriminant analysis (LDA). In addition, the improvement on SVM accuracy can bring out even more significant improvement in classifier fusion.

Particle Swarm Optimization-Based Hyperspectral Dimensionality Reduction for Urban Land Cover Classification

The high dimensionality of hyperspectral imagery challenges image processing and analysis. Band selection is a common technique for dimensionality reduction. When the desired object information is unknown, an unsupervised band selection approach is employed to select the most distinctive and informative bands. Although band selection can significantly alleviate the computational burden in the following data processing and analysis, the process itself may induce additional computation complexity, especially when the image spatial size is large; it may be time-consuming for unsupervised band selection methods that need to take all pixels into consideration. Parallel computing techniques are widely adopted to alleviate the computational burden and to achieve real-time processing of data with vast volume. In this paper, we propose parallel implementations via emerging general-purpose graphics processing units (GPUs) for band selection without changing band selection result. Its speedup performance is comparable to the cluster-based parallel implementation. We also propose an approach to using several selected pixels for unsupervised band selection and the number of pixels needed can be equal to the number of selected bands minus one. With whitened pixel signatures (not the original pixels), band selection performance can be comparable to or even better than that from using all the pixels. For this approach, parallel computing is implemented for pixel selection only, since computational complexity in band selection has been greatly reduced.

/pdf/unsupervised-hyperspectral-band-selection-using-graphics-4ivdyzh95i.pdf

He Yang

Papers

Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis

An Efficient Method for Supervised Hyperspectral Band Selection

Optical flow and principal component analysis-based motion detection in outdoor videos

Particle Swarm Optimization-Based Hyperspectral Dimensionality Reduction for Urban Land Cover Classification

Unsupervised Hyperspectral Band Selection Using Graphics Processing Units