The advance of remote sensing technology has been capable of providing abundant spatial and contextual information for object detection in optical satellite or aerial imagery, which facilitates subsequent automatic analysis and interpretation of the optical remotes sensing images (RSIs). Most existing object detection approaches suffer from two limitations. First, the feature representation used is insufficiently powerful to capture the spatial and structural patterns of objects and the background regions. Second, a large number of training data with manual annotation of object bounding boxes is required in the supervised learning techniques adopted while the annotation process is generally too expensive and sometimes even unreliable. To tackle these two limitations, a novel and effective geospatial object detection framework is proposed by combining the weakly supervised learning (WSL) and high-level feature learning. First, we employ an unsupervised feature learning approach via Deep Boltzmann Machine (DBM) to infer the spatial and structural information encoded in the low-level and middle-level features, which facilitates good semantic preserving ability for effective describing objects in optical RSIs. Then, we present a novel WSL approach to object detection in optical RSIs where the training sets require only binary labels indicating whether an image contains the target object or not. Based on the learnt high-level features, it jointly integrates saliency, intra-class compactness, and inter-class separability in a Bayesian framework to initialize a set of training examples from weakly labeled images and start iterative learning of the object detector. A novel evaluation criterion is also developed to detect model drift and cease the iterative learning. Comprehensive experiments on three optical RSI datasets with large variations in terms of spatial resolution, and types of objects have demonstrated the efficacy of the proposed approach in benchmarking with several state-of-the-art supervised learning based object detection approaches.

Electroencephalography (EEG)-based brain-computer interfaces (BCIs), particularly those using motor-imagery (MI) data, have the potential to become groundbreaking technologies in both clinical and entertainment settings. MI data is generated when a subject imagines the movement of a limb. This paper reviews state-of-the-art signal processing techniques for MI EEG-based BCIs, with a particular focus on the feature extraction, feature selection and classification techniques used. It also summarizes the main applications of EEG-based BCIs, particularly those based on MI data, and finally presents a detailed discussion of the most prevalent challenges impeding the development and commercialization of EEG-based BCIs.

For the classification of hyperspectral images (HSIs), this paper presents a novel framework to effectively utilize the spectral-spatial information of superpixels via multiple kernels, termed as superpixel-based classification via multiple kernels (SC-MK). In HSI, each superpixel can be regarded as a shape-adaptive region which consists of a number of spatial-neighboring pixels with very similar spectral characteristics. Firstly, the proposed SC-MK method adopts an over-segmentation algorithm to cluster the HSI into many superpixels. Then, three kernels are separately employed for the utilization of the spectral information as well as spatial information within and among superpixels. Finally, the three kernels are combined together and incorporated into a support vector machines classifier. Experimental results on three widely used real HSIs indicate that the proposed SC-MK approach outperforms several well-known classification methods.

It is important to detect breast cancer as early as possible. In this manuscript, a new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced. A new computer aided detection (CAD) system is proposed for classifying benign and malignant mass tumors in breast mammography images. In this CAD system, two segmentation approaches are used. The first approach involves determining the region of interest (ROI) manually, while the second approach uses the technique of threshold and region based. The deep convolutional neural network (DCNN) is used for feature extraction. A well-known DCNN architecture named AlexNet is used and is fine-tuned to classify two classes instead of 1,000 classes. The last fully connected (fc) layer is connected to the support vector machine (SVM) classifier to obtain better accuracy. The results are obtained using the following publicly available datasets (1) the digital database for screening mammography (DDSM); and (2) the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Training on a large number of data gives high accuracy rate. Nevertheless, the biomedical datasets contain a relatively small number of samples due to limited patient volume. Accordingly, data augmentation is a method for increasing the size of the input data by generating new data from the original input data. There are many forms for the data augmentation; the one used here is the rotation. The accuracy of the new-trained DCNN architecture is 71.01% when cropping the ROI manually from the mammogram. The highest area under the curve (AUC) achieved was 0.88 (88%) for the samples obtained from both segmentation techniques. Moreover, when using the samples obtained from the CBIS-DDSM, the accuracy of the DCNN is increased to 73.6%. Consequently, the SVM accuracy becomes 87.2% with an AUC equaling to 0.94 (94%). This is the highest AUC value compared to previous work using the same conditions.

Land-use classification using remote sensing images covers a wide range of applications. With more detailed spatial and textural information provided in very high resolution (VHR) remote sensing images, a greater range of objects and spatial patterns can be observed than ever before. This offers us a new opportunity for advancing the performance of land-use classification. In this paper, we first introduce an effective midlevel visual elements-oriented land-use classification method based on "partlets," which are a library of pretrained part detectors used for midlevel visual elements discovery. Taking advantage of midlevel visual elements rather than low-level image features, a partlets-based method represents images by computing their responses to a large number of part detectors. As the number of part detectors grows, a main obstacle to the broader application of this method is its computational cost. To address this problem, we next propose a novel framework to train coarse-to-fine shared intermediate representations, which are termed "sparselets," from a large number of pretrained part detectors. This is achieved by building a single-hidden-layer autoencoder and a single-hidden-layer neural network with an L0-norm sparsity constraint, respectively. Comprehensive evaluations on a publicly available 21-class VHR land-use data set and comparisons with state-of-the-art approaches demonstrate the effectiveness and superiority of this paper.

Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging.

Feature extraction is of high importance for effective data classification in hyperspectral imaging (HSI). Considering the high correlation among band images, spectral-domain feature extraction is widely employed. For effective spatial information extraction, a 2-D extension to singular spectrum analysis (SSA), a recent technique for generic data mining and temporal signal analysis, is proposed. With 2D-SSA applied to HSI, each band image is decomposed into varying trend, oscillations and noise. Using the trend and selected oscillations as features, the reconstructed signal, with noise highly suppressed, becomes more robust and effective for data classification. Three publicly available data sets for HSI remote sensing data classification are used in our experiments. Comprehensive results using a support vector machine (SVM) classifier have quantitatively evaluated the efficacy of the proposed approach. Benchmarked with several state-of-the-art methods including 2-D empirical mode decomposition (2D-EMD), it is found that our proposed 2D-SSA approach generates the best results in most cases. Unlike 2D-EMD which requires sequential transforms to obtain detailed decomposition, 2D-SSA extracts all components simultaneously. As a result, the executive time in feature extraction can also be dramatically reduced. The superiority in terms of enhanced discrimination ability from 2D-SSA is further validated when a relatively weak classifier, k-nearest neighbor (k-NN), is used for data classification. In addition, the combination of 2D-SSA with 1D-PCA (2D-SSA-PCA) has generated the best results among several other approaches, which has demonstrated the great potential in combining 2D-SSA with other approaches for effective spatial-spectral feature extraction and dimension reduction in HSI. Index Terms-Data classification, feature extraction, hyperspectral imaging (HSI), 2-D empirical mode decomposition (2D-EMD), 2-D singular spectrum analysis (2D-SSA).

Stacked autoencoders (SAEs), as part of the deep learning (DL) framework, have been recently proposed for feature extraction in hyperspectral remote sensing. With the help of hidden nodes in deep layers, a high-level abstraction is achieved for data reduction whilst maintaining the key information of the data. As hidden nodes in SAEs have to deal simultaneously with hundreds of features from hypercubes as inputs, this increases the complexity of the process and leads to limited abstraction and performance. As such, segmented SAE (S-SAE) is proposed by confronting the original features into smaller data segments, which are separately processed by different smaller SAEs. This has resulted in reduced complexity but improved efficacy of data abstraction and accuracy of data classification