Search

Tasks with high mental workload often involve higher cognitive functions of the human brain and complex information flow involving multiple brain regions. However, the dynamics of functional connectivity between brain regions during high mental workload have not been well-studied. We use an analysis approach designed to find repeating network states from gamma-band phase locking value networks built from electroencephalograph data collected while participants engaged in tasks with different levels of mental workload. First, we define network states as results of clustering based on the closeness centrality node-level network metric. Second, we found that the transition between network states is not completely random. And, we found significant differences in network state statistics between low and high mental workload. Third, we found significant correlation between features calculated from the network state sequence and behavioral performance. Finally, we use dynamic network features as input to a support vector machine classifier and obtain cross-participant average decoding accuracy of 69.6%. Our methods provide a new perspective for analyzing the dynamics of electroencephalograph signals and have potential application to the decoding of mental workload level. [ABSTRACT FROM AUTHOR]

Thrombocytopenia is one of the most common hematological adverse reactions in chronic myeloid leukemia (CML) patients receiving tyrosine kinase inhibitors (TKI) therapy, causing life-threatening bleeding cases. However, there are fewer therapeutic drugs for TKI-induced thrombocytopenia. Eltrombopag is a non-peptide thrombopoietin receptor agonist used for the treatment of immune thrombocytopenia， aplastic anemia, and hepatitis C-associated thrombocytopenia. Nevertheless, studies of eltrombopag for TKI-induced thrombocytopenia are still lacking. This study retrospectively analyzed the clinical and test data of 21 CML patients with TKI-related thrombocytopenia. The results demonstrated that the median baseline value of thrombocytopenia in the 21 CML patients was 15.57 × 109/L [2–28 × 109/L]. Following treatment with eltrombopag, 16 patients had a significant increase in their platelet levels. The peak median for platelet increase in effective responders was 145.12 × 109/L (51–460 × 109/L). However, 5 patients failed to respond to eltrombopag. Moreover, 4 of the 21 patients enrolled had adverse reactions, including reversible liver function impairment, palpitation, headache, insomnia, and loss of appetite. Nonetheless, no cases of disease progression, thrombotic events, or myelofibrosis were observed. Hence, eltrombopag may be a useful adjunctive therapy for relieving TKI-related thrombocytopenia in patients with CML. [ABSTRACT FROM AUTHOR]

The article aims to explore certain reliability probability models using a Hamiltonian Monte Carlo (HMC) sampler. There are some concerns with the classic HMC samplers. A notable aspect of the method comes from its acceptance probability whose value is constant, “1,” in theory. One practical problem is the possibility of divergence. A further issue emerges from the simulation trajectory, which essentially traverses on the last principal component. Also, the method is extremely sensitive to run-time parameters. As an improvement, Riemann Manifold HMC can travel along the first principal component. However, its overall accuracy on other components remains unclear. The no-U-turn sampler can adjust the distance traveled, but it may also suffer from excessive simulation steps. To address these concerns, this article proposes: to implement the conservation of energy by virtual collision among particles; to adopt constant simulation steps and adjust the acceptance probability and step size; and to alternate two kinds of trajectories to reconcile all principal components. Experiments show that the proposed algorithm is able to estimate the reliability and remaining useful life of the probability models. To bridge theory and practice, algorithm fragment is demonstrated with Mathematica language. [ABSTRACT FROM AUTHOR]

Zero-shot learning (ZSL) aims to recognize unseen objects using disjoint seen objects via sharing attributes. The generalization performance of ZSL is governed by the attributes, which transfer semantic information from seen classes to unseen classes. To take full advantage of the knowledge transferred by attributes, in this paper, we introduce the notion of the complementary attributes (CAs), as a supplement to the original attributes, to enhance the semantic representation ability. Theoretical analyses demonstrate that CAs can improve the PAC-style generalization bound of the original ZSL model. Since the proposed CA focuses on enhancing the semantic representation, CA can be easily applied to any existing attribute-based ZSL methods, including the label-embedding strategy-based ZSL (LEZSL) and the probability-prediction strategy-based ZSL (PPZSL). In PPZSL, there is a strong assumption that all attributes are independent of each other, which is arguably unrealistic in practice. To solve this problem, a novel rank aggregation (RA) framework is proposed to circumvent the assumption. Extensive experiments on five ZSL benchmark datasets and the large-scale ImageNet dataset demonstrate that the proposed CA and RA can significantly and robustly improve the existing ZSL methods and achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes) by sharing information of attributes between different objects. Attributes are artificially annotated for objects and treated equally in recent ZSL tasks. However, some inferior attributes with poor predictability or poor discriminability may have negative impacts on the ZSL system performance. This letter first derives a generalization error bound for ZSL tasks. Our theoretical analysis verifies that selecting the subset of key attributes can improve the generalization performance of the original ZSL model, which uses all the attributes. Unfortunately, previous attribute selection methods have been conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks. Inspired by learning from pseudo-relevance feedback, this letter introduces out-of-the-box data—pseudo-data generated by an attribute-guided generative model—to mimic the unseen data. We then present an iterative attribute selection (IAS) strategy that iteratively selects key attributes based on the out-of-the-box data. Since the distribution of the generated out-of-the-box data is similar to that of the test data, the key attributes selected by IAS can be effectively generalized to test data. Extensive experiments demonstrate that IAS can significantly improve existing attribute-based ZSL methods and achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Most learning-based hashing algorithms leverage sample-to-sample similarities, such as neighborhood structure, to generate binary codes, which achieve promising results for image retrieval. This type of methods are referred to as instance-level encoding. However, it is nontrivial to define a scalar to represent sample-to-sample similarity encoding the semantic labels and the data structure. To address this issue, in this paper, we seek to use a class-level encoding method, which encodes the class-to-class relationship, to take the semantic information of classes into consideration. Based on these two encodings, we propose a novel framework, error correcting input and output (EC-IO) coding, which does class-level and instance-level encoding under a unified mapping space. Our proposed model contains two major components, which are distribution preservation and error correction. With these two components, our model maps the input feature of samples and the output code of classes into a unified space to encode the intrinsic structure of data and semantic information of classes simultaneously. Under this framework, we present our hashing model, EC-IO hashing (EC-IOH), by approximating the mapping space with the Hamming space. Extensive experiments are conducted to evaluate the retrieval performance, and EC-IOH exhibits superior and competitive performances comparing with popular supervised and unsupervised hashing methods. [ABSTRACT FROM AUTHOR]

Spontaneous generation, natural dissipation, split, and merger of convective cells within the life cycle of the mesoscale convective system (MCS) is the main problem of most existing tracking algorithms. To address this issue, an algorithm called spatio-temporal context and extended maxima transform (SCEMT) is proposed for tracking convective cells using satellite infrared image sequences. In order to track convective cells, the presented method uses the extended maxima transform technique to detect convective cells, learning a spatio-temporal context model, updating scale and variance, and calculating the confidence map of adjacent moments. Case studies demonstrate the effectiveness of the proposed method in different phases of MCS life cycle. The SCEMT method is evaluated utilising contingency table approach on FY-2F data sets. This novel method has a good discrimination skill (probability of detection 90%, false alarm ratio 7%, and critical success index 84%), and provides a correct tracking of convection motion. [ABSTRACT FROM AUTHOR]

Pose tracking is an important task in Augmented Reality (AR), interactive systems, and robotic systems. The frame-by-frame pose tracking that is effective in many cases still faces challenges in complex environments such as occlusions, illumination changes and flipping. In this paper, based on the optimization model offered by Ye et al. J Vis Commun Image Represent 44:72-81 (2017), three improvements are further proposed. First, a feature adjustment strategy based on a group of neighbors is offered to alleviate a sharp reduction of features. Then, when the features are no longer well representing the scene of interest, a score model based on a weighted histogram for result evaluations is presented to realize an adaptive interval. Besides, a forward-backward algorithm is provided to improve the accuracy by replacing the detection method with the tracking method. Experimental results manifest the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose real-time and reliable approaches for pose tracking of a rigid object by feature detection and image matching. We first present a new fast binary descriptor with a double circle structure of overlapping regions, namely double circle structure descriptor (DCSD). DCSD is rotation invariant and robust against blur, illumination changes, Joint Photographic Experts Group (JPEG) compression and orientation changes. Experimental results show that with fewer feature bits, DCSD is still discriminative and faster than the state-of-the-art features in many general situations. We then propose a new matching measure named Hough Voting Matching (HVM), which is based on clustering and Hough voting schemes. HVM can efficiently discriminate between correct and incorrect keypoint correspondences, and can be combined with some descriptors to improve the matching accuracy as an independent part. Experiments are also presented to illustrate that HVM can refine the matching results of DCSD if we embed HVM into a DCSD algorithm. [ABSTRACT FROM AUTHOR]

Tropical cyclones (TCs) are one of nature’s most destructive phenomena, and a key element in forecasting TC tracks is the ability to accurately detect TC centres. In this paper, a novel algorithm has been proposed to objectively detect TC centres using infrared satellite images. Pyramid representation and optical flow technique are utilized to construct the cloud motion wind (CMW) field of each cyclone, and thereafter the centre is determined by analysing the constructed CMW field. Ten TCs formed in the Northwestern Pacific Ocean in 2014 have been tested to evaluate the performance of the present method, and TC Halong and Rammasun were analysed in detail as instances. Experimental results comparing with forecast track derived from Unisys Weather show that the proposed method provides an accurate detection of TC centres. The present algorithm has a potential to be employed to assist forecasters to detect TC centres. [ABSTRACT FROM PUBLISHER]

A novel binning and learning framework is presented for analyzing and applying large data sets that have no explicit knowledge of distribution parameterizations, and can only be assumed generated by the underlying probability density functions (PDFs) lying on a nonparametric statistical manifold. For models' discretization, the uniform sampling-based data space partition is used to bin flat-distributed data sets, while the quantile-based binning is adopted for complex distributed data sets to reduce the number of under-smoothed bins in histograms on average. The compactified histogram embedding is designed so that the Fisher-Riemannian structured multinomial manifold is compatible to the intrinsic geometry of nonparametric statistical manifold, providing a computationally efficient model space for information distance calculation between binned distributions. In particular, without considering histogramming in optimal bin number, we utilize multiple random partitions on data space to embed the associated data sets onto a product multinomial manifold to integrate the complementary bin information with an information metric designed by factor geodesic distances, further alleviating the effect of over-smoothing problem. Using the equipped metric on the embedded submanifold, we improve classical manifold learning and dimension estimation algorithms in metric-adaptive versions to facilitate lower-dimensional Euclidean embedding. The effectiveness of our method is verified by visualization of data sets drawn from known manifolds, visualization and recognition on a subset of ALOI object database, and Gabor feature-based face recognition on the FERET database. [ABSTRACT FROM AUTHOR]

An image descriptor based on the orientation of contrasts is proposed to facilitate image understanding. A mathematical function that satisfies the heat equation is proposed to model the parameters of an ideal edge, including the width, contrast, offset, position, and orientation. A simple method can compute the contrast and width of canny edge features. Inspired by the histogram of oriented gradients method, an image representation is proposed based on a histogram of contrasts. The proposed method encodes the weighted orientation in a sub-window. The weighting is based on the contrast instead of the gradient magnitude. Our experiments showed that the new representation was more robust against noise compared with several state-of-the-art methods. Several sub-window resolutions were also considered, which resulted in a pyramid that incorporated the global and local context. A method based on Bayes' theorem and empirical cumulative distribution function is proposed to predict the probability of correctness for the nearest neighbor classification. The annotation and class label of an image were retrieved using a nearest neighbor method or a support vector machine classifier. This method was tested using several benchmark datasets and toolboxes, which showed that it is suitable for image understanding tasks. [ABSTRACT FROM AUTHOR]

Accurate rapidly developing convection (RDC) detection is an essential part of a severe weather warning. A novel algorithm called object track and identification (OTI) is proposed for detecting RDC using infrared image sequences from geostationary meteorology satellite. Convective cells are computed using extended maxima transform-based region growing algorithm. Firstly, a novel area overlap-based object tracking method is proposed to track convective cells in successive images. Secondly, the lowest 25% of overall brightness temperature of the same convective cloud is averaged in order to preserve the extremum information of evolution of cloud. Thirdly, a new identification criterion, which contains three subcriteria, is developed to detect RDC. Contingency table approach applied to various case studies over China shows that the OTI algorithm is efficient and accurate. [ABSTRACT FROM AUTHOR]

Automatic co-segmentation is a challenging task because it lacks of prior cues. In this paper, an efficient region contrast based method is proposed for salient object detection and segmentation. The coarse location information of the salient object and the background is first estimated based on the distribution of the detected key-points. Histograms of the estimated foreground and background are calculated as their features. An image is then over-segmented into super-pixels and their histograms are computed. The saliency of a super-pixel is obtained according to the similarity coefficients between the super-pixel and the estimated foreground/background. With the saliency map, the salient object in the image is extracted using a graph cut based optimized framework. The proposed method is compared with state-of-the-art methods on the widely used dataset, and the experiments show that it overall obtains more accurate results. [ABSTRACT FROM AUTHOR]

Convective cell detection is a critical step for tracking and forecasting of Mesoscale Convective Systems from geostationary satellite infrared (IR) data. Conventional threshold methods for identifying convective cell depend on the choice of threshold. Adjacent convective cells cannot be well distinguished because of the influence of anvil cloud. To address this problem, a new algorithm called extended maxima transform–based region growing (EMTRG) is proposed. First, EMTRG algorithm uses extended maxima transform to generate seed points of convective cell, and applies neighbourhood criterion to cluster adjacent seed points. Second, the merger and split times of pair-wise seed clusters are counted, and a merger criterion is utilized to decide whether pair-wise seed clusters should be merged. The algorithm is applied to various case studies over China. Experimental results on geostationary satellite IR images show that the proposed algorithm distinguishes adjacent convective cells region efficiently. [ABSTRACT FROM AUTHOR]

This paper introduces a scale-invariant and contrast-invariant multi-scale differential edge detector. The method is a direct consequence of two key discoveries: (1) a precise scale normalization method and (2) a formula to verify scale-invariant detectors. The new scale normalization method provides differential operators with respect to scale, among them the scale-invariant edge detectors. To investigate these differential detectors quantitatively, mathematical functions were used to represent the edges and to solve for the parameters, including position, width, contrast, offset, and orientation, in closed form. Noise is filtered as a low-contrast feature. The method has been tested with various kinds of synthesized edge functions and can extract edge features accurately. It is suitable for real-world images of several kinds of degradation. [ABSTRACT FROM AUTHOR]

In graph-based linear dimensionality reduction algorithms, it is crucial to construct a neighbor graph that can correctly reflect the relationship between samples. This paper presents an improved algorithm called fuzzy local maximal marginal embedding (FLMME) for linear dimensionality reduction. Significantly differing from the existing graph-based algorithms is that two novel fuzzy gradual graphs are constructed in FLMME, which help to pull the near neighbor samples in same class nearer and nearer and repel the far neighbor samples of margin between different classes farther and farther when they are projected to feature subspace. Through the fuzzy gradual graphs, FLMME algorithm has lower sensitivities to the sample variations caused by varying illumination, expression, viewing conditions and shapes. The proposed FLMME algorithm is evaluated through experiments by using the WINE database, the Yale and ORL face image databases and the USPS handwriting digital databases. The results show that the FLMME outperforms PCA, LDA, LPP and local maximal marginal embedding. [ABSTRACT FROM AUTHOR]

Parallax handling is a challenging task for image stitching. Existing image stitching methods are quite sensitive to large parallax. One common phenomenon, e.g. is the ghosting. In this Letter, a flexible building facade stitching method that allows large parallax is proposed. Using the rigidity constraints of the man‐made environment, each view can be aligned to a reference view. Excellent stitching performance demonstrates that the proposed method is superior to the state‐of‐the‐art ones. [ABSTRACT FROM AUTHOR]