Search

Exploring the geometric prior in the dimensionality reduction (DR) of hyperspectral image data (HID) is an important issue because it can overcome the possible overclassification of spectrally homogeneous areas in the HID classification. In this paper, the local geometric similarity of hyperspectral vectors is explored in both the manifold domain and image domain, and a semisupervised dual-geometric subspace projection (DGSP) approach is proposed for the DR of HID, by utilizing both labeled and unlabeled samples. First, the geometric information in the manifold domain is captured by a sparse coding-based geometric graph, and then, a local-consistency-constrained geometric matrix is defined to reveal the geometric structure in the image domain. Second, unlabeled samples are used to refine the geometric structure by defining a pairwise similarity matrix. Third, three scatter matrices are then derived from these similarity matrices to find the optimal subspace projection that captures the most important properties of the subspaces with respect to classification. Some experiments are taken on the airborne visible infrared imaging spectrometer (AVIRIS) HID to prove the efficiency of the proposed method. [ABSTRACT FROM PUBLISHER]

The statistical model plays an important role in BAN radio propagation characterization. However, a traditional least-square statistical model is not necessarily the best choice when only limited samples can be collected. This paper proposes the method for improving the density model in BAN radio propagation characterization; the final PDF result validates the correctness of the method. [ABSTRACT FROM AUTHOR]

A finite element mesh aggregating approach is presented to reconstruct images of multiple internal bioluminescence sources. Rather than assuming independence between mesh nodes, the proposed reconstruction strategy exploits spatial structure of nodes and aggregation feature of density distribution on the finite element mesh to adaptively determine the number of sources and to improve the quality of reconstructed images. With the proposed strategy integrated in the regularization-based reconstruction process, reconstruction algorithms need no a priori knowledge of source number; even more importantly, they can automatically reconstruct multiple sources that differ greatly in density or power. [ABSTRACT FROM AUTHOR]

The article presents a retrospective study on the microsurgical treatment of 174 intramedullary spinal cord tumors (IMSCTs). It notes that 48.9% of the tumors are ependymoma while total resection was possible for 60.9% of the patient-respondent. It reveals on the urgent treatment for most IMSCTs and the necessity of radiation therapy for malignant tumors and for those wherein total removal cannot be applied.

Electromagnetic target representation is a common fundamental problem in electromagnetic space situational awareness. Early target representation was based on expert empirical knowledge, which required designers to have strong professional background and prior knowledge, and is performed poorly in complex signal environments. Deep learning, which has been developed in recent years, provides a new way for signal representation in complex electromagnetic environments. It simulates the deep structure of the human brain to build a machine learning model to automatically represent and process target data in an end-to-end manner, and shows good performance in perception tasks such as electromagnetic target detection, classification, identification, parameter estimation, and behavioral cognition. However, deep learning relies heavily on massive amounts of high-quality labelled data, and has certain limitations in the real electromagnetic environment. Incorporating know-ledge into intelligent systems has always been the research direction of artificial intelligence. Combining know-ledge and data for electromagnetic target representation will hopefully improve target perception accuracy and generalization ability, and is becoming a new direction in electromagnetic target representation. This paper reviews the development process of electromagnetic target representation techniques, and provide an outlook on the new paradigm of electromagnetic target perception driven by joint knowledge-data.

The article focuses on a study which determined adult endogenous neurogenesis effects on cognitive function repair and regeneration of neural progenitor cells after varying graded traumatic hippocampal injury. Neurogenesis takes place throughout the lifespan in the dentate gyrus of the rat and adult human hippocampus which is important in memory and learning making it vulnerable to brain trauma. Results showed that endogenous adult neurogenesis repairs the neurological functions to an extent but function recovery remains limited after brain trauma.

Recently, saliency detection has been becoming a popular topic in computer vision. In this paper we propose an object-level saliency detection algorithm which explicitly explores bottom-up visual attention and objectness cues. Firstly, some category-independent object candidates are segmented from the image by the quantized color attributes. Then two metrics, global cues and candidate objectness, are developed to estimate the saliency in the whole image and the object candidates respectively. We use global cues to describe the focusness and spatial distribution of color attributes in the entire image. As supplementary, candidate objectness can reveal the objectness of the object candidates. Finally, we integrate the two saliency cues to derive a saliency map of the image. By explicitly fusing candidate objectness and global cues, our proposed method is more suitable for processing images with complex background. Experimental results on three large benchmark databases demonstrate that the proposed method achieves more favorable performance than 15 recent state-of-the-art methods in terms of three evaluation criterions. [ABSTRACT FROM AUTHOR]