Learn More
Human actions can be represented by the trajectories of skeleton joints. Traditional methods generally model the spatial structure and temporal dynamics of human skeleton with hand-crafted features and recognize human actions by well-designed classifiers. In this paper, considering that recurrent neural network (RNN) can model the long-term contextual(More)
The radiometric normalization of multi-temporal satellite optical images of the same terrain is necessary for land cover change detection e.g. relative differences. In previous studies, ground reference data or pseudo invariant features (PIFs) were used in the radiometric rectification of multi-temporal images. Ground reference data are costly and difficult(More)
Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN). In this paper, we propose a novel convolutional neural networks (CNN) based framework for both action classification and detection. Raw skeleton coordinates as well as skeleton motion are fed directly into CNN for label prediction. A(More)
Rough set theory has been extensively discussed in the domain of machine learning and data mining. Pawlak's rough set theory offers a formal theoretical framework for attribute reduction and rule learning from nominal data. However, this model is not applicable to numerical data, which widely exist in real-world applications. In this work, we extend this(More)
Numerous studies have demonstrated that neuroinflammation is associated with depression-like symptoms and neuropsychological disturbances, and cysteinyl leukotriene receptor 1 (CysLT1R) was reported to be involved in neuroinflammation. The pathophysiological role of CysLT1R has been reported in several types of brain damage. However, the role of CysLT1R in(More)
Partial volume (PV) effects degrade the quantitative accuracy of SPECT brain images. In this paper, we extended a PV compensation (PVC) method originally developed for brain PET, the geometric transfer matrix (GTM) method, to brain SPECT using iterative reconstruction-based compensations. In the GTM method a linear transform between the true regional(More)
Oxidative stress is implicated in tissue inflammation, and plays an important role in the pathogenesis of immune-mediated nephritis. Using the anti-glomerular basement membrane antibody-induced glomerulonephritis (anti-GBM-GN) mouse model, we found that increased expression of glutathione S-transferase Mu 2 (GSTM2) was related to reduced renal damage caused(More)
MicroRNAs (miRNAs) are a class of small, noncoding RNA molecules capable of regulating gene expression translationally and/or transcriptionally. A large number of evidence have demonstrated that miRNAs have a functional role in both physiological and pathological processes by regulating the expression of their target genes. Recently, the functionalities of(More)