Classification Of Multisource Data Research Articles

Cross-Scene Joint Classification of Multisource Data With Multilevel Domain Adaption Network.

Domain adaption (DA) is a challenging task that integrates knowledge from source domain (SD) to perform data analysis for target domain. Most of the existing DA approaches only focus on single-source-single-target setting. In contrast, multisource (MS) data collaborative utilization has been extensively used in various applications, while how to integrate DA with MS collaboration still faces great challenges. In this article, we propose a multilevel DA network (MDA-NET) for promoting information collaboration and cross-scene (CS) classification based on hyperspectral image (HSI) and light detection and ranging (LiDAR) data. In this framework, modality-related adapters are built, and then a mutual-aid classifier is used to aggregate all the discriminative information captured from different modalities for boosting CS classification performance. Experimental results on two cross-domain datasets show that the proposed method consistently provides better performance than other state-of-the-art DA approaches.

Relationship Learning from Multisource Images via Spatial-spectral Perception Network.

Advances in multisource remote sensing have allowed for the development of more comprehensive observation. The adoption of deep convolutional neural networks (CNN) naturally includes spatial-spectral information, which has achieved promising performance in multisource data classification. However, challenges are still found with the extraction of spatial distribution and spectrum relationships, which eventually limit the classification performance. To solve the issue, a spatial-spectral perception network (S2PNet) is proposed to extract the advantages of different data sources and the cross information between data sources in a targeted manner. Specifically, the spatial perception network is developed to build the spatial distribution relationship from high-resolution images, while the spectral perception network extracts the spectrum relationship from spectral images. For perceiving cross information, a memory unit is utilized to store the features from different data sources in succession. In addition, the distance loss and reconstruction loss are introduced to keep the feature integrity, and the cross-entropy loss ensures that features can distinguish different classes. The comprehensive experiments are conducted on several datasets to validate the superiority of the proposed algorithm. The proposed S2PNet outperforms the considered classifiers with an average improvement of +0.77%, +5.62%, +1.58%, and +1.79% for overall accuracy values.

Performance analysis of feature selection and classification in Big Data Information extraction

Purpose: Information extraction from big data is improved by either reducing the number of features in a data set or selecting features using intelligent data analysis. Generally, big data sets are complex to process using traditional approaches. Feature selection is highly essential in big data information extraction because it chooses the subset of features that influence the final classification. Reducing the number of selected features in the data leads to enhanced accuracy and efficiency of data extraction with other attributes used in the mathematical model. This work aims to improve the performance of the classifier using an enhanced binary bat algorithm-based effective feature selection model. formulated to enhance accuracy, efficiency of data extraction with other attributes. An enhanced binary bat algorithm (EBBA) proposed to solve the mentioned problem using local optimization and global optimization factor which improves the performance of optimization. Experiment carried out with different datasets selected to test effective performance of proposed algorithm and demonstrated performance is better with other algorithms. Design: The purpose of this paper is to provide, an effective feature selection model for big data information extraction. An enhanced binary bat algorithm has been proposed to improve attribute selection using local optimization and global optimization methods. Classification of multisource data using selected features using labeled approach. Particular Information extraction for multi view multi label (PIMM) approach is compared with EBBA algorithm. Further to enhance effectiveness of shared and specific information in big data [3] by setting the delta and omega factors in order to fuse different information from different view point, Online analysis of relevance with any redundancy analysis also been incorporated. Findings: All the experiments were carried out with different datasets on the number of iterations and fitness of the attributes to validate the effective performance of the proposed algorithm. Experimental results and graphs show that the proposed methodology improves the overall performance of optimization using PIMM models. Originality: A feature selection model based on the binary bat algorithm has been the focus of this paper. Subset selection and feature ranking are the two important methods used in this approach. Experiments were conducted on datasets to analyze the patterns in the number of iterations and fitness of the attributes over selection. The improvement in feature selection leads to better classification accuracy of the proposed model compared to other nature inspired techniques.

Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data Classification

The joint hyperspectral image (HSI) and light detection and ranging (LiDAR) data classification aims to interpret ground objects at more detailed and precise level. Although deep learning methods have shown remarkable success in the multisource data classification task, self-supervised learning has rarely been explored. It is commonly nontrivial to build a robust self-supervised learning model for multisource data classification, due to the fact that the semantic similarities of neighborhood regions are not exploited in the existing contrastive learning framework. Furthermore, the heterogeneous gap induced by the inconsistent distribution of multisource data impedes the classification performance. To overcome these disadvantages, we propose a nearest neighbor-based contrastive learning network (NNCNet), which takes full advantage of large amounts of unlabeled data to learn discriminative feature representations. Specifically, we propose a nearest neighbor-based data augmentation scheme to use enhanced semantic relationships among nearby regions. The intermodal semantic alignments can be captured more accurately. In addition, we design a bilinear attention module to exploit the second-order and even high-order feature interactions between the HSI and LiDAR data. Extensive experiments on four public datasets demonstrate the superiority of our NNCNet over state-of-the-art methods. The source codes are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/summitgao/NNCNet</uri> .

OptFus: Optical Sensor Fusion for the Classification of Multisource Data: Application to Mineralogical Mapping

We propose a new fusion-based classification technique for optical multisource remote-sensing images called OptFus. OptFus is developed to merge and process optical imagery having different spatial and spectral resolutions. The spatial features are extracted using morphological filters from the RGB data containing high spatial resolution. A feature fusion technique is developed to combine all the sensor data in a subspace using a common set of representative features. Finally, the fused features are classified using a support vector machine to ensure a robust supervised spectral classification. The proposed method is designed to allocate varying weights to the data from various imaging sensors in the fusion process. OptFus is applied to two multisource optical datasets captured from geological drill-core samples. The classification accuracy demonstrates considerable improvements compared to the state-of-the-art. A MATLAB implementation of OptFus is available online: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/BehnoodRasti/OptFus</uri> .

Joint feature extraction for multi-source data using similar double-concentrated network

Joint classification of multi-source data is often better than single-source data in application scenes, but it is difficult to ensure effective feature extraction of multi-source information. In this paper, a similar double-concentrate network, denoted as SDCN, is proposed for extracting features effectively and classifying more accurately based on hyperspectral imagery (HSI) and Light Detection and Ranging (LiDAR) data. Specifically, the dual-concentrate network is first developed to capture spectral and spatial features from HSI, and then expanding the connection of LiDAR information based on the trained HSI branch. Each branch of the designed network is similar, which includes two convolutional layers, one maximum pooling layer, one batch normalization layer and two activation layers. After the network of HSI is fully trained, similar network is deployed to distinguish spatial features and ‘band’ difference of LiDAR data, and different features are also combined with multi-source associations. The absolute symmetry network structure and specific multi-source connection can ensure the orderly and balance of features extracted in this model, and adjust the direction of feature extraction constantly. Experimental results on several real data demonstrate that the proposed SDCN outperforms other relevant state-of-the-art methods.

An ensemble method based on rotation calibrated least squares support vector machine for multi-source data classification

ABSTRACT This paper proposed an extended rotation-based ensemble method for the classification of a multi-source optical-radar data. The proposed method was actually inspired by the rotation-based support vector machine ensemble (RoSVM) with several fundamental refinements. In the first modification, a least squares support vector machine was used rather than the support vector machine due to its higher speed. The second modification was to apply a Platt calibrated version instead of a classical non-probabilistic version in order to consider more suitable probabilities for the classes. In the third modification, a filter-based feature selection algorithm was used rather than a wrapper algorithm in order to further speed up the proposed method. In the final modification, instead of a classical majority voting, an objective majority voting, which has better performance and less ambiguity, was employed for fusing the single classifiers. Accordingly, the proposed method was entitled rotation calibrated least squares support vector machine (RoCLSSVM). Then, it was compared to other SVM-based versions and also the RoSVM. The results implied higher accuracy, efficiency and diversity of the RoCLSSVM than the RoSVM for the classification of the data set of this paper. Furthermore, the RoCLSSVM had lower sensitivity to the training size than the RoSVM.

Fusion of RADARSAT-2 and multispectral optical remote sensing data for LULC extraction in a tropical agricultural area

In this study, we investigated the performance of different fusion and classification techniques for land cover mapping in Hilir Perak, Peninsula Malaysia using RADAR and Landsat-8 images in a predominantly agricultural area. The fusion methods used are Brovey Transform, Wavelet Transform, Ehlers and Layer Stacking and their results classified into seven different land cover classes which include (1) pixel-based classifiers (spectral angle mapper (SAM), maximum likelihood (ML), support vector machine (SVM)) and (2) Object-based (rule-based and standard nearest neighbour (NN)) classifiers. The result shows that pixel-based classification achieved maximum accuracy of the optical data classification using SVM in Landsat-8 with 74.96% accuracy compared to SAM and ML. For multisource data classification, the highest overall accuracy recorded for layer stacking (SVM) was 79.78%, Ehlers fusion (SVM) with 45.57%, Brovey fusion (SVM) with 63.70% and Wavelet fusion (SVM) 61.16%. And for object-based classifiers, the overall classification accuracy is 95.35% for rule-based and 76.33% for NN classifier, respectively. Based on the analysis of their performances, object-based and the rule-based classifiers produced the best classification accuracy from the fused images.

Combining the matter element model with the associated function of probability transformation for multi-source remote sensing data classification in mountainous regions

That the multi-source remote sensing information integrates knowledge-based geospatial constraints to develop efficient and practical Land cover classification algorithm has become one of the most important developing directions in the field of remote sensing ground object classification. Remote sensing classification is a strictly incompatible problem, but the spectra distribution of remote sensing data has compatible attributes especially in mountainous regions, and such contradiction is one of the main reasons leading to uncertainties in remote sensing classification. In this paper, the remote sensing spectra feature compatible information is transformed into the probability of the association degree firstly, and then the matter-element theory is introduced to establish models to achieve the integrated classification of multi-source data to fuse knowledge-based geographical constrained condition probability. Taking the grassland–wetland fragile ecosystem in Ruoergai plateau of China as a case study, this paper selected the multi-source data including images of Landsat TM and CBERS, ASTER-GDEM and MODIS-NDVI to construct a comprehensive classifier, in which the relationship between topography and land cover, and the prior knowledge on vegetation growth difference were taken as constraints to support the decision-making. The classification accuracy was evaluated by a field investigation and existing land cover map. The test result shows that, the overall accuracy (89.89%) and Kappa coefficient (0.8870) are better than those derived by the Maximum Likelihood method. It indicates that the proposed classification method is not subject to the dimensionality and form of data sources, and it can integrate the data source information to improve the classification accuracy, so that it is very useful to apply multi-source data and prior knowledge to land cover classification in mountainous regions.

Characterization of groups using composite kernels and multi-source fMRI analysis data: Application to schizophrenia

Pattern classification of brain imaging data can enable the automatic detection of differences in cognitive processes of specific groups of interest. Furthermore, it can also give neuroanatomical information related to the regions of the brain that are most relevant to detect these differences by means of feature selection procedures, which are also well-suited to deal with the high dimensionality of brain imaging data. This work proposes the application of recursive feature elimination using a machine learning algorithm based on composite kernels to the classification of healthy controls and patients with schizophrenia. This framework, which evaluates nonlinear relationships between voxels, analyzes whole-brain fMRI data from an auditory task experiment that is segmented into anatomical regions and recursively eliminates the uninformative ones based on their relevance estimates, thus yielding the set of most discriminative brain areas for group classification. The collected data was processed using two analysis methods: the general linear model (GLM) and independent component analysis (ICA). GLM spatial maps as well as ICA temporal lobe and default mode component maps were then input to the classifier. A mean classification accuracy of up to 95% estimated with a leave-two-out cross-validation procedure was achieved by doing multi-source data classification. In addition, it is shown that the classification accuracy rate obtained by using multi-source data surpasses that reached by using single-source data, hence showing that this algorithm takes advantage of the complimentary nature of GLM and ICA.

Multisource data classification with dependence trees

In order to apply a statistical approach to the classification of multisource remote-sensing data, one of the main problems to face lies in the estimation of probability distribution functions. This problem arises out of the difficulty of defining a common statistical model for such heterogeneous data. A possible solution is to adopt nonparametric approaches, which rely on the availability of training samples without any assumption about the related statistical distributions. The purpose of this paper is to investigate the suitability of the concept of dependence trees for the integration of multisource information through estimation of probability distributions. First, this concept, introduced by Chow and Liu (1968), is used to provide an approximation of a probability distribution defined in an N-dimensional space by a product of N-1 probability distributions defined in two-dimensional (2-D) spaces; this approximation corresponds, in terms of graph theoretical interpretation, to a tree of dependence. For each land cover class, a dependence tree is generated by minimizing an appropriate closeness measure. Then, a nonparametric estimation of the second-order probability distributions is carried out through the Parzen window approach, based on the implementation of 2-D Gaussian kernels. In this way, it is possible to reduce the complexity of the estimation, while capturing a significant part of the interdependence among variables. A comparison with other multisource data fusion methods, namely, the multilayer perceptron (MLP) method, the k-nearest neighbor (k-NN) method, and a Bayesian hierarchical classifier (BHC), is made. Experimental results obtained on multisensor [airborne thematic mapper (ATM) and synthetic aperture radar (SAR)] and multisource (experimental synthetic aperture radar (E-SAR) and a textural feature) data sets show that the proposed fusion method based on dependence trees is able to provide a classification accuracy similar to those of the other methods considered, but with the advantage of a reduced computational load.

Optimisation of multisource data analysis: an example using evidential reasoning for GIS data classification

The classification of integrated data from multiple sources represents a powerful and synergistic approach to deriving important geoscience information from diverse data sets. These data often reside on Geographical Information Systems (GIS) and encompass a variety of sources and properties such as thematic data, remote sensing imagery, topographic data, or environmental map information in raster or vector formats in point, line or polygon representations. Multisource data classification algorithms often require the specification of user-defined parameters to guide data processing, however, these inputs can be numerous or difficult to determine, resulting in less than optimal results. This paper presents three methods for optimising the specification of user-defined inputs based on different levels of empirical testing and computational efficiency: (i) Exhaustive search by recursion, (ii) isolated independent search, and (iii) sequential dependent search. These methods have been implemented in an optimisation software program which is suitable for use with any data classification or analysis algorithm for which user specified inputs are required. In an example application of classifying sub-Arctic mountain permafrost in the Yukon Territory of northern Canada, these optimisation methods were compared in terms of classification accuracy, memory resources and run-time performance using a multisource evidential reasoning classifier, which has been shown to provide improved classification of multisource data compared to neural network, linear discriminant analysis, and maximum likelihood approaches. Using the optimisation software, higher evidential reasoning classification accuracies were achieved without excessive additional computing time. A two-stage approach was recommended for general use to ensure maximum efficiency. It was concluded that these methods are applicable to a wide variety of classification and data analysis algorithms and represent a useful approach to optimising user inputs which otherwise may be difficult or impractical to derive.

Feature extraction for multisource data classification with artificial neural networks

Classification of multisource remote sensing and geographic data by neural networks is discussed with respect to feature extraction. Several feature extraction methods are reviewed, including principal component analysis, discriminant analysis, and the recently proposed decision boundary feature extraction method. The feature extraction methods are then applied in experiments in conjunction with classification by multilayer neural networks. The decision boundary feature extraction method shows excellent performance in the experiments.

Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images

Proposes a new method for statistical classification of multisource data. The method is suited for land-use classification based on the fusion of remotely sensed images of the same scene captured at different dates from multiple sources. It incorporates a priori information about the likelihood of changes between the acquisition of the different images to be fused. A framework for the fusion of remotely sensed data based on a Bayesian formulation is presented. First, a simple fusion model is given, and then the basic model is extended to take into account the temporal attribute if the different data sources are acquired at different dates. The performance of the model is evaluated by fusing Landsat TM images and ERS-1-SAR images for land-use classification. The fusion model gives significant improvements in the classification error rates compared to the conventional single-source classifiers. >

Conjugate-gradient neural networks in classification of multisource and very-high-dimensional remote sensing data

Application of neural networks to classification of remote sensing data is discussed. Conventional two-layer backpropagation is found to give good results in classification of remote sensing data but is not efficient in training. A more efficient variant, based on conjugate-gradient optimization, is used for classification of multisource remote sensing and geographic data and very-high-dimensional data. The conjugate-gradient neural networks give excellent performance in classification of multisource data, but do not compare as well with statistical methods in classification of very-high-dimentional data.

Classification of permafrost active layer depth from remotely sensed and topographic evidence

The remote detection of permafrost (perennially frozen ground) has important implications to environmental resource development, engineering studies, natural hazard prediction, and climate change research. In this study, we present results from two experiments into the classification of permafrost active layer depth within the zone of discontinuous permafrost in northern Canada. A new software system (MERCURY⊕) based on evidential reasoning was implemented to permit the integrated classification of multisource data consisting of landcover, terrain aspect, and equivalent latitude (potential insolation), each of which possessed different formats, data types, or statistical properties that could not be handled by conventional classification algorithms available to this study. In the first experiment, four active layer depth classes were classified using ground based measurements of the three variables with an accuracy of 83 % compared to in situ soil probe determination of permafrost active layer depth at over 500 field sites. This confirmed the environmental significance of the variables selected, and provided a baseline result to which a remote sensing classification could be compared. In the second experiment, evidence for each input variable was obtained from image processing of digital SPOT imagery and a photogrammetric digital elevation model, and used to classify active layer depth with an accuracy of 79%. These results suggest the classification of evidence from remotely sensed measures of spectral response and topography may provide suitable indicators of permafrost active layer depth.