Search

Background and purpose: Thrombus red blood cell (RBC) content has been shown to be a significant factor influencing the efficacy of acute ischemic stroke treatment. In this study, our objective was to evaluate the ability of convolutional neural networks (CNNs) to predict ischemic stroke thrombus RBC content using multiparametric MR images. Materials and methods: Retrieved stroke thrombi were scanned ex vivo using a three-dimensional multi-echo gradient echo sequence and histologically analyzed. 188 thrombus R2*, quantitative susceptibility mapping and late-echo GRE magnitude image slices were used to train and test a 3-layer CNN through cross-validation. Data augmentation techniques involving input equalization and random image transformation were employed to improve network performance. The network was assessed for its ability to quantitatively predict RBC content and to classify thrombi into RBC-rich and RBC-poor groups. Results: The CNN predicted thrombus RBC content with an accuracy of 62% (95% CI 48–76%) when trained on the original dataset and improved to 72% (95% CI 60–84%) on the augmented dataset. The network classified thrombi as RBC-rich or poor with an accuracy of 71% (95% CI 58–84%) and an area under the curve of 0.72 (95% CI 0.57–0.87) when trained on the original dataset and improved to 80% (95% CI 69–91%) and 0.84 (95% CI 0.73–0.95), respectively, on the augmented dataset. Conclusions: The CNN was able to accurately predict thrombus RBC content using multiparametric MR images, and could provide a means to guide treatment strategy in acute ischemic stroke. [ABSTRACT FROM AUTHOR]

This article investigates the experiences of Yi migrant workers in Shenzhen factories through a conceptual framework that focuses on three dimensions of home in migration. Examining industrial dormitories, the foreman system, and governmental attention, it uncovers the intricate ways migrants negotiate their sense of belonging. The spatial dimension is evident in dormitories offering a semblance of home while reflecting broader societal and economic influences. The relational aspect emerges through the evolution of the foreman system, highlighting the interplay between traditional social bonds and modern labour demands. The sensorial dimension becomes apparent in the limited recognition migrants receive despite their contributions. This study underscores the multifaceted nature of migrant experiences as well as the need for comprehensive understandings of home that encompass spatial, relational, and sensorial elements within the dynamic context of migration. [ABSTRACT FROM AUTHOR]

Suxiu, "Suzhou embroidery," is one of the major styles of traditional Chinese embroidery. In 2006, Suxiu was listed as the National Intangible Cultural Heritage (ICH) of China. Although the official media highlight the glory of Suxiu and its cultural significance as ICH, the industry has encountered great difficulties and challenges for the last 20 years. This paper explores the predicament of Suxiu and the far-reaching impacts of the China's ICH policies on the embroidery industry. It argues that the state policies fail to provide community members with equal participatory opportunities in the heritage industry. Instead, it creates intragroup hierarchy and classification, favoring certain members while excluding others. More specifically, it examines local embroiderers' different attitudes and reactions toward the ICH system, thus illustrating how the top-down policies affect the sociocultural process of recognition. It aims to offer a critical reflection on how China's industrialization and ICH policies have transformed the nation's handicraft industry. [ABSTRACT FROM AUTHOR]

There is a growing application of machine learning methods to predict socioeconomic and environmental attributes in computational social science, where big data are usually presented in tabular format. However, it is still a challenge to develop novel deep learning models to deal with tabular data, fill missing value, improve prediction accuracy, and enhance interpretability. In this study, we for the first time apply a tabular deep learning methodology (TabNet) to predict socioeconomic and environmental attributes (number of population and companies, volume of consumption, poker players' behaviors, forest cover, etc.). Furthermore, we develop a new network architecture, referred to as improved TabNet (iTabNet), that can simultaneously learn local and global features in the tabular data to improve prediction accuracy. We also introduce a difference loss to constrain the feature selection process in iTabNet so that the model can use different features at different steps to enhance interpretability. To deal with missing values, we introduce a fusion strategy based on data mean and Auto-Encoder network to efficiently complete a more reasonable value filling. Experimental results demonstrate that the proposed iTabNet achieves competitive performances in the application to predict socioeconomic and environmental attributes based on tabular data, iTabNet using the proposed fusion strategy significantly outperforms other machine learning models when tabular data have missing values. [ABSTRACT FROM AUTHOR]

• A light-weight UAV formation control algorithm based on inner and outer loop control is proposed. • An improving ADRC based on prescribed-time extended state observer and broad learning is proposed. • The broad learning is used to dynamically optimize the weights according to the different wind disturbances. Considering that the formation composed of light-weight UAVs is highly susceptible to the interference, which may from the changes in the external environment and the uncertainty of system, a formation control method based on the inner and outer loops is proposed. In the inner loop, the single UAV stable flight can be achieved via controlling the state variables of UAV angles. In the outer loop, we can achieve multi-UAVs cooperative flight through the leader-follower strategy. In this paper, we mainly focus on the stability control of each member UAV, which is the basic composition of formation control. For this purpose, an optimized active disturbance rejection control (ADRC) is proposed which combined an improved prescribed-time extended state observer (PTESO) and weight optimization module based on broad learning. In this way, the single UAV can dynamically adjust the control weights according to different wind degrees, so that the influence of environmental changes on the control system is reduced. Then, the effectiveness and superiority of the proposed formation control methods are verified by simulations. The stability enhancement control method proposed in this paper provides a new and effective theoretical support for the actual control of the light-weight UAV formation, which has a well engineering application prospect. [ABSTRACT FROM AUTHOR]

Pansharpening is a special image fusion task of reconstructing a high-resolution multispectral (HRMS) image by integrating a panchromatic (PAN) image of high spatial resolution and a low-resolution multispectral (LRMS) image. To handle such an ill-posed multimodal fusion task, in this article, we propose a novel pansharpening method, referred to as model-driven and data-driven network (MD3Net), which combines model-driven and data-driven approaches. The architecture design of MD3Net is inspired from the traditional model constructed based on domain knowledge and thus making its network topology explainable and its input-output predictable. To further explore the powerful learning ability of deep-learning-based approaches, we introduce the deep prior into the MD3Net as its implicit regularization, thus improving its data adaptability and representation capability. Comprehensive experiments conducted on both reduced and full resolution of several acknowledged datasets have qualitatively and quantitatively verified the superiority of our network compared with a benchmark consisting of several state-of-the-art approaches. The code can be downloaded from https://github.com/YinsongYan/M3DNet. [ABSTRACT FROM AUTHOR]

Purpose: To address whether Curcumin has synergistic effect with cytarabine (Ara-C) in treating acute myeloid leukemia (AML). Methods: A xenograft AML mouse model was established by injecting HL-60 cells into tail vein of mice to assess the function of Curcumin. Mononuclear cells (MNCs) isolated from AML mice and AML cell lines were used to examine the effect of Curcumin. Metagenomics and metabolomics were used to evaluate the alteration of intestinal microbiota and the change of metabolites in MNCs. Results: Curcumin treatment sensitized response to Ara-C in MNCs of AML mice, but had no direct effect on AML cell lines. Metagenomics revealed an alteration of intestinal microbiota with Curcumin treatment, which contributes to sensitized response to Ara-C. Curcumin treatment led to enhanced intestinal intact to sensitize response to Ara-C in AML mice, through reducing mucus degrading bacteria. Metabolomics demonstrated that Curcumin treatment led to decreased cholesterol in MNCs of AML mice. Further study proved that Curcumin treatment resulted in inhibition of SQLE, a key enzyme of cholesterol biosynthesis, to increase sensitivity to Ara-C. Conclusion: Curcumin sensitizes response to Ara-C through regulating microbiota, highlighting the importance of intestinal intact strengthening in chemoresistant therapy. Moreover, aiming at cholesterol synthesis is promising in AML treatment. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF) has been one of the most widely used techniques for hyperspectral unmixing (HU), which aims at decomposing each mixed pixel into a set of endmembers and their corresponding fractional abundances. However, the standard NMF model is ill-posed with only considering the non-negativity constraint. Therefore, many kinds of regularization (e.g. Tikhonov or sparsity regularization) have been imposed into NMF to well-define the model. Different from the general regularization, we introduce the entropy regularization into the NMF and propose an entropy regularized NMF (ERNMF) model for HU. In ERNMF, we minimize the entropy of that abundances on each pixel, which can achieve the sparsity of abundances. We also introduce a strategy to adaptively adjust the regularization parameter. In addition, we explore the proposed ERNMF with two optimization algorithms and provide the corresponding convergence and complexity analysis. Experimental results on both simulated and real-world data sets demonstrate the effectiveness of our proposed model and algorithms in comparison to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Research on the interfacial instability of two‐phase systems can help in gaining a better understanding of various hydrodynamic instabilities in nature. However, owing to the nonlinear and complex spatiotemporal dynamics of the unstable interface, the instability is challenging to control and suppress. This paper presents a novel interfacial instability of the magnetic microswarm induced by the competition between the destabilizing effect of magnetic field and the stabilizing effect of acoustic field. The physics underlying this novel phenomenon is discussed by analyzing the contributions of the external fields. Unlike previous studies, this study demonstrates that the instability is independent of the interfacial force or diffusion effect and can persist without dissipation over time. The manipulation of the unstable interface is further achieved by adjusting the configuration of the magneto‐acoustic system. This approach can be used in thermal encoding metamaterials and has great potential applications in systems where the instability is detrimental. [ABSTRACT FROM AUTHOR]

Hybrid neural network models are effective in analyzing time-series data by combining the strengths of neural networks and differential equation models. Although most studies have focused on linear hybrid models, few have examined nonlinear problems. This work explores the potential of a hybrid nonlinear epidemic neural network in predicting the correct infection function of an epidemic model. We design a novel loss function by combining bifurcation theory and mean-squared error loss to ensure the trainability of the hybrid model. Additionally, we identify unique existence conditions that support ordinary differential equations for estimating the correct infection function. Moreover, numerical experiments using the Runge–Kutta method confirm our proposed model's soundness both on our synthetic data and the real COVID-19 data. [ABSTRACT FROM AUTHOR]

Abstract Vector light beams (VLBs), manifesting as the non-uniform spatial distribution of polarization states, have shown broad applications in increasing communication capacity. Here, we propose and experimentally demonstrate a spatial phase cross-polarized method for achieving a mode coded modulation of VLBs. By employing the polarization sensitivity of the spatial light modulators (SLMs), the left and the right-handed circularly polarized parts of light beams are modulated with opposite spatial spiral phase to produce VLBs by the coherent combination. Manipulating the spatial phase distribution of the left and the right-handed circularly polarized light beams, the VLBs with 16 modes ([m; l]=[2, 3, 4, 5, 3, 4, 5, 6, 4, 5, 6, 7, 5, 6, 7, 8; 0, −1, −2, −3, 1, 0, −1, −2, 2, 1, 0, −1, 3, 2, 1, 0]) are obtained and used to code digital signals. In the experiment, a 60 × 60 pixels flower gray image with 14 400 quaternary numbers are then coded to the 16 modes and decoded successfully after 1 m transmission in free space. And the flower gray image is also recovered accordingly. [ABSTRACT FROM AUTHOR]

We report the design and realization of yolk–shell structured nanospheres with periodic mesoporous organosilica (PMO) nanospheres or noble metal nanoparticles encapsulated in mesoporous silica shells via a selective etching method. These architectures have well controlled structure, size and morphology. The yolk–shell structured PMO@SiO2 nanoparticles can be precisely functionalized with different catalytic functionalities, even incompatible acidic and basic groups: the PMO core with amino (–NH2) groups and the mesoporous silica shell with sulfonic acid (–SO3H) groups. As a nanoreactor, the as-synthesized Au@SiO2 nanospheres show faster reduction of 4-nitrophenol than that of nitrobenzene. Furthermore, the prepared PMO-NH2@SiO2-SO3H nanoparticles can be used as bifunctional catalysts with highly efficient catalytic performance for catalyzing the deacetalization-Henry cascade reaction. [ABSTRACT FROM AUTHOR]

Multi-echo gradient echo (mGRE) sequences have been widely adapted in clinical and scientific practice for different purposes to their capability of performing Dixon MRI, generating multi-contrast images and extracting multi-parametric maps. This work aims to extend mGRE-based techniques for imaging whole head, where further technical developments are required due to the co-existence of fat and large B0 inhomogeneity in regions such as the skull base and neck. Specifically, bipolar mGRE data were acquired with a single sequence that contains both a short echo-spacing (ΔTE) echo train to capture water-fat and B0 phase shifts (for proton density fat-fraction (FF) and B0 mapping) and a longer ΔTE echo train (and long echo times) to capture subtle susceptibility variations and R2* information. The mGRE images covering the whole head (spatial resolution 1.0 × 1.0 × 2.0 mm 3 ) were acquired in 5 min. An automated processing pipeline was implemented to use the FF and B0 maps determined from the short-TE train to compensate for the effects of fat, remove the background phase for whole-head quantitative susceptibility mapping, and reduce the difficulty of spatial phase unwrapping of the long echo-time data. Data from healthy volunteers imaged on a 3 T scanner along with phantom validation are presented. Co-registered quantitative multi-parametric maps (FF, B0 inhomogeneity, R2*, local frequency shift and quantitative susceptibility) and multi-contrast images covering the whole head were successfully generated in processing times of several minutes. [ABSTRACT FROM AUTHOR]

Concept factorization (CF) has been a powerful data representation method, which has been widely applied in image processing and document clustering. However, traditional CF cannot guarantee the decomposition results of CF to be sparse in theory and do not consider the geometric structure of the databases. In this paper, we propose a graph-regularized CF with local coordinate (LGCF) method, which enforces the learned coefficients to be sparse by using the local coordinate constraint meanwhile preserving the intrinsic geometric structure of the data space by incorporating graph regularization. An iterative optimization method is also proposed to solve the objective function of LGCF. By comparing with the state-of-the-arts algorithms (Kmeans, NMF, CF, LCCF, LCF), experimental results on four popular databases show that the proposed LGCF method has better performance in terms of average accuracy and mutual information. [ABSTRACT FROM AUTHOR]

Background: Recently, sparse unmixing has been successfully applied to spectral mixture analysis of remotely sensed hyperspectral images. Based on the assumption that the observed image signatures can be expressed in the form of linear combinations of a number of pure spectral signatures known in advance, unmixing of each mixed pixel in the scene is to find an optimal subset of signatures in a very large spectral library, which is cast into the framework of sparse regression. However, traditional sparse regression models, such as collaborative sparse regression, ignore the intrinsic geometric structure in the hyperspectral data. Results: In this paper, we propose a novel model, called manifold regularized collaborative sparse regression, by introducing a manifold regularization to the collaborative sparse regression model. The manifold regularization utilizes a graph Laplacian to incorporate the locally geometrical structure of the hyperspectral data. An algorithm based on alternating direction method of multipliers has been developed for the manifold regularized collaborative sparse regression model. Conclusions: Experimental results on both the simulated and real hyperspectral data sets have demonstrated the effectiveness of our proposed model. [ABSTRACT FROM AUTHOR]

Purpose To develop and evaluate a rapid spherical navigator echo (SNAV) motion correction technique, then apply it for retrospective correction of brain images. Methods The pre-rotated, template matching SNAV method (preRot-SNAV) was developed in combination with a novel hybrid baseline strategy, which includes acquired and interpolated templates. Specifically, the SNAV templates are only rotated around X- and Y-axis; for each rotated SNAV, simulated baseline templates that mimic object rotation about the Z-axis were interpolated. The new method was first evaluated with phantom experiments. Then, a customized SNAV-interleaved gradient echo sequence was used to image three volunteers performing directed head motion. The SNAV motion measurements were used to retrospectively correct the brain images. Experiments were performed using a 3.0 T whole-body MRI scanner and both single and 8-channel head coils. Results Phantom rotations and translations measured using the hybrid baselines agreed to within 0.9° and 1 mm compared to those measured with the original preRot-SNAV method. Retrospective motion correction of in vivo images using the hybrid preRot-SNAV effectively corrected for head rotation up to 4 ° and 4 mm. Conclusions The presented hybrid approach enables the acquisition of pre-rotated baseline templates in as little as 2.5 s, and results in accurate measurement of rotations and translations. Retrospective 3D motion correction successfully reduced motion artifacts in vivo. [ABSTRACT FROM AUTHOR]

Pan-sharpening aims to integrate the spatial details of a high-resolution panchromatic (Pan) image with the spectral information of low-resolution multispectral (MS) images to produce high-resolution MS images. The key is to appropriately estimate the missing spatial details of the MS images while preserving their spectral contents. However, many existing methods extract the spatial details from the Pan image without fully considering the structures of the MS images, resulting in spectral distortion due to redundant detail injection. A guided filter can transfer the structures of the MS images into the intensity component or the low-pass approximation of the Pan image. Using the guided filter, we propose two novel pan-sharpening methods to reduce the redundant details among the MS and Pan images. Specifically, we extract the missing spatial details of the MS images by minimizing the difference between the Pan image and its corresponding filtering output, with the help of the MS images. Two different ways of using the MS images as guided images lead to two proposed methods, which can be grouped into component substitution (CS) family. Extensive experimental results over three data sets collected by different satellite sensors demonstrate the effectiveness of the proposed methods. [ABSTRACT FROM PUBLISHER]

Direct synthesis of ethanol from syngas derived from coal, natural gas, or biomass is one of the most promising routes for renewable energy production. In this work, Ce-promoted highly-dispersed Rh catalyst on TiO 2 support was prepared by the deposition–precipitation method, which exhibits largely enhanced catalytic activity and selectivity for ethanol production from syngas. XRD and TEM reveal a high dispersion of Rh nanoparticles (~1 nm) on the surface of TiO 2 support by the introduction of CeO 2. It was found that the relative content of Rh and CeO 2 imposes significant influence on the catalytic behavior, and the sample of 1 wt% Rh–1 wt% CeO 2/TiO 2 exhibits the highest CO conversion (32 %) and the largest ethanol selectivity (33 %) under the conditions of 573 K, 3 MPa, H 2:CO = 2:1. H 2-TPR and XPS results confirm a gradually enhanced electron interaction between Rh and CeO 2 with the increase of Ce content; CO-TPD further reveals that the Rh–CeO 2 interaction generates a new adsorption site for CO, accounting for the improved selectivity towards ethanol. Therefore, this work provides a facile and effective method for the preparation of Rh–CeO 2/TiO 2 catalysts with high catalytic behavior, which can be potentially used in syngas conversion to ethanol. Graphical Abstract: A series of CeO 2 promoted Rh/TiO 2 catalysts with low Rh loading (1 wt%) were prepared by the deposition–precipitation method, which exhibit largely enhanced catalytic activity and selectivity towards ethanol production from syngas [Figure not available: see fulltext.]. [ABSTRACT FROM AUTHOR]

Based on deep learning, various pan-sharpening models have achieved excellent results. However, most of them adopt simple addition or concatenation operations to merge the information of low spatial resolution multi-spectral (LRMS) images and panchromatic (PAN) images, which may cause a loss of detailed information. To tackle this issue, inspired by capsule networks, we propose a plug-and-play layer named modified dynamic routing layer (MDRL), which modifies the information transmission mode of capsules to effectively fuse LRMS images and PAN images. Concretely, the lower-level capsules are generated by applying transform operation to the features of LRMS images and PAN images, which preserve the spatial location information. Then, the dynamic routing algorithm is modified to adaptively select the lower-level capsules to generate the higher-level capsule features to represent the fusion of LRMS images and PAN images, which can effectively avoid the loss of detailed information. In addition, the previous addition and concatenation operations are illustrated as special cases of our MDRL. Based on MIPSM with addition operations and DRPNN with concatenation operations, two modified dynamic routing models named MDR–MIPSM and MDR–DRPNN are further proposed for pan-sharpening. Extensive experimental results demonstrate that the proposed method can achieve remarkable spectral and spatial quality. [ABSTRACT FROM AUTHOR]

Under a linear mixture model with non-negativity and sum-to-one constraints, the spectral unmixing problem can be seen as a convex geometry problem. This article first analyses three commonly used endmember extraction criteria including the extreme projection criterion, the maximum simplex volume criterion and the minimum volume enclosing simplex criterion, which are derived from the geometrical explanation of the linear mixture model. And then an acceleration strategy is introduced to shorten the computing time of endmember extraction algorithms. The acceleration strategy exploits two facts: (1) the endmembers corresponding to the vertices of a simplex composed of the mixed pixels can be determined only by the boundary points, with little or no affect by the interior points; (2) the boundary points can be found in a series of two-dimensional subspace. Experiments using simulated data on eight popular endmember extraction algorithms show that the proposed acceleration strategy can reduce the computing time and then improve the speed of endmember extraction, while maintaining the same results or little sacrifice of computing precision. [ABSTRACT FROM AUTHOR]

Abstract: Calix[n]arenes (n =4,5) comprising 4-(2,2′:6′,2″-terpyridyl)-phenyl substituents at the upper rim were synthesized for the first time, employing Suzuki-type coupling reactions. All calix[n]arene derivatives were prepared as cone conformers. The single crystal X-ray structure of cone-5,11,17,23-tetra{4-(2,2′:6′,2″-terpyridyl)-phenyl}-25,26,27,28-tetrabutoxycalix[4]arene 4 is analyzed in terms of structural rigidity and potential use of these ligands as novel synthons of cage-type metallosupramolecular assemblies. [Copyright &y& Elsevier]

• A novel method DPP-VSE is designed to construct good variable selection ensembles. • Discrete DPPs are utilized to infer a probability distribution of model size. • A sample from the distribution specifies the number of variables selected by each member. • The simulated and real experiments are conducted to study DPP-VSE's performance. • DPP-VSE outperforms its rivals in most cases and has fewer parameters to specify. As an effective tool to analyze high-dimensional data, variable selection is playing an increasingly important role in many fields. In recent years, variable selection ensembles (VSEs) have gained much interest of researchers due to their great potential to improve selection accuracy and to stabilize the results of traditional selection methods. Inspired by one common practice of Bayesian methods, we propose in this paper a novel technique named DPP-VSE to build a VSE by utilizing determinantal point processes (DPP) to infer a distribution of model size. By sampling from this distribution, DPP-VSE has the advantage that the number of variables for a base learner to select can be automatically determined. In contrast to other VSE strategies, it has fewer parameters for users to specify. The experiments conducted with both synthetic and real data illustrate that DPP-VSE performs best under most circumstances when being evaluated with several metrics. Hence, DPP-VSE can be seen as an effective and easy to use method to solve variable selection problems. [ABSTRACT FROM AUTHOR]

An abstract of the conference paper "Simultaneous wall and blood-flow phase-contrast imaging using a single low VENC," by Junmin Liu and colleagues is presented.

Pansharpening is a typical image fusion problem, which aims to produce a high resolution multispectral (HRMS) image by integrating a high spatial resolution panchromatic (PAN) image with a low spatial resolution multispectral (MS) image. Prior arts have used either component substitution (CS)-based methods or multiresolution analysis (MRA)-based methods for this propose. Although they are simple and easy to implement, they usually suffer from spatial or spectral distortions and could not fully exploit the spatial and/or spectral information existed in PAN and MS images. By considering their complementary performances and with the goal of combining their advantages, we propose a pansharpening weight network (PWNet) to adaptively average the fusion results obtained by different methods. The proposed PWNet works by learning adaptive weight maps for different CS-based and MRA-based methods through an end-to-end trainable neural network (NN). As a result, the proposed PWN inherits the data adaptability or flexibility of NN, while maintaining the advantages of traditional methods. Extensive experiments on data sets acquired by three different kinds of satellites demonstrate the superiority of the proposed PWNet and its competitiveness with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The deep learning method, especially convolution neural networks (CNNs), has recently made ground-breaking advances on object detection in very-high-resolution (VHR) optical remote sensing images. However, as CNN is originally designed for the classification of natural images, these methods are not very suitable for object detection of remote sensing images. First, current CNN-based approaches have difficulty to deal with objects that have large rotation variation, which is widely existed in optical remote sensing images. Second, the detectors based on CNN only have limited receptive fields and, thus, can hardly utilize the global contextual information that is essential for accurate detection of small targets. To address these two issues, this article proposes a novel deep learning-based object detection framework, including a geometric transform module (GTM) and a global contextual feature fusion module (GCFM). Especially, the GTM combines rotation and flip transformation to deal with the multiangle characteristics of objects. The GCFM uses a spatial attention mechanism to adaptively involve global contextual information in feature maps to improve the recognition and location accuracy of targets. We introduce the two modules into the YOLOv3 framework to achieve end-to-end detection with high performance and efficiency. Comprehensive evaluations on three publicly available object detection data sets demonstrate the excellent performance of the proposed methods. [ABSTRACT FROM AUTHOR]

Pansharpening is the process of integrating a high spatial resolution panchromatic image with a low spatial resolution multispectral image to obtain a multispectral image with high spatial and spectral resolution. Over the last decade, several algorithms have been developed for pansharpening. In this paper, a technique, called enhanced back-projection (EBP), is introduced and applied as postprocessing on the pansharpening. The proposed EBP first enhances the spatial details of the pansharpening results by histogram matching and high-pass modulation, followed by a back-projection process, which takes into account the modulation transfer function (MTF) of the satellite sensor such that the pansharpening results obey the consistency property. The EBP is validated on four datasets acquired by different satellites and several commonly used pansharpening methods. The pansharpening results achieve substantial improvements by this postprocessing technique, which is widely applicable and requires no modification of existing pansharpening methods. [ABSTRACT FROM AUTHOR]

In recent years, deep reinforcement learning (DRL) algorithm has been widely used in algorithmic trading. Many fully automated trading systems or strategies have been built using DRL agents, which integrate price prediction and trading signal generation in one system. However, the previous agents extract the current state from the market data without considering the long-term market historical trend when making decisions. Besides, plenty of related and useful information has not been considered. To address these two problems, we propose a novel model named Parallel Multi-Module Deep Reinforcement Learning (PMMRL) algorithm. Here, two parallel modules are used to extract and encode the feature: one module employing Fully Connected (FC) layers is used to learn the current state from the market data of the traded stock and the fundamental data of the issuing company; another module using Long Short-Term Memory (LSTM) layers aims to detect the long-term historical trend of the market. The proposed model can extract features from the whole environment by the above two modules simultaneously, taking the advantages of both LSTM and FC layers. Extensive experiments on China stock market illustrate that the proposed PMMRL algorithm achieves a higher profit and a lower drawdown than several state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Fuzzy c-means with regularization by K–L information (KLFCM) is an objective function method for clustering, which is regarded as a fuzzy counterpart of Gaussian mixture models (GMMs) with EM algorithm when the regularization parameter λ equals 2. However, KLFCM method extracts very close or even coincident clusters in many cases because the K–L information term in its objective function is used to minimize the dissimilarity between the membership degrees and the proportions of data belonging to the clusters. To deal with this problem, we propose a new model called fuzzy c-means clustering with conditional probability based K–L information regularization (CKLFCM) which incorporates the conditional probability distributions and the probabilistic dissimilarity functional into the conventional KLFCM algorithm in order to assign appropriate membership degrees to each data point. CKLFCM technique does not suffer from obtaining the unexpected close or coincident clusters. Several experiments are presented to show the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

3D object recognition is one of the most important tasks in 3D data processing, and has been extensively studied recently. Researchers have proposed various 3D recognition methods based on deep learning, among which a class of view-based approaches is a typical one. However, in the view-based methods, the commonly used view pooling layer to fuse multi-view features causes a loss of visual information. To alleviate this problem, in this paper, we construct a novel layer called Dynamic Routing Layer (DRL) by modifying the dynamic routing algorithm of capsule network, to more effectively fuse the features of each view. Concretely, in DRL, we use rearrangement and affine transformation to convert features, then leverage the modified dynamic routing algorithm to adaptively choose the converted features, instead of ignoring all but the most active feature in view pooling layer. We also illustrate that the view pooling layer is a special case of our DRL. In addition, based on DRL, we further present a Dynamic Routing Convolutional Neural Network (DRCNN) for multi-view 3D object recognition. Our experiments on three 3D benchmark datasets show that our proposed DRCNN outperforms many state-of-the-arts, which demonstrates the efficacy of our method. [ABSTRACT FROM AUTHOR]

Sparse representation (SR)-based pansharpening methods which combine the dictionary and estimated sparse coefficients have achieved visually and quantitatively great results in pansharpening problem these days. And the details injection (ID)-based methods can receive comparable images by sharpening the multispectral bands through adding the proper spatial details from panchromatic (PAN) images. Recently, method based on sparse representation of injected details (SR-D) which combines the SR and ID points out a new way forward for pansharpening. In this direction, manifold regularized sparse representation of injected details (MR-SR-D) which introducing a manifold regularization (MR) into the former SR-D model have improved the quality of pansharpened images greatly utilizing a graph Laplacian to incorporate the locally geometrical structure of the multispectral data. However, due to the lack of spatial information in PAN, and the use of higher-order features similarity with the original multispectral images, the resulting images still have spatial and spectral distortion. Thus, in this paper, we propose a new method to enhance the spatial resolution of aiming image by adding the weighted local geometrical structure of PAN and multispectral images, and improve the spectral resolution by joining the higher-order structure connection between multispectral and aiming images to the MR-SR-D method which can be called as weighted manifold regularized (WMR) sparse representation of featured injected details method (WMR-SR-FD). Experimental results using IKONOS, QuickBird and WorldView2 data show that the proposed method can achieve remarkable spectral and spatial quality. [ABSTRACT FROM AUTHOR]

In the literature of object detection in optical remote sensing images, a popular pipeline is first modifying an off-the-shelf deep neural network, then initializing the modified network by pretrained weights on a source data set, and finally fine-tuning the network on a target data set. The procedure works well in practice but might not make full use of underlying knowledge implied by pretrained weights. In this article, we propose a novel method, referred to as Fisher regularization, for efficient knowledge transferring. Based on Bayes’ theorem, the method stores underlying knowledge into a Fisher information matrix and fine-tunes parameters based on the knowledge. The proposed method would not introduce extra parameters and is less sensitive to hyperparameters than classical weight decay. Experiments on NWPUVHR-10 and DOTA data sets show that the proposed method is effective and works well with different object detectors. [ABSTRACT FROM AUTHOR]

The fusion of hyperspectral image (HSI) and multispectral image (MSI) is one of the most significant topics in remote sensing image processing. Recently, deep learning (DL) has emerged as an important tool for this task. However, existing DL-based methods have two drawbacks, that is, limited ability for feature extraction and suffering from spectral distortion. To address these issues, this article presents a novel neural network, where sophisticated techniques are employed, including network-in-network convolutional unit, batch normalization, and skip connection. To make full use of the MSI, the proposed model fuses HSI and MSI at different scales. Besides, this article presents a new loss function, called RMSE, angle and Laplacian (RAP) loss (the combination of the relative mean squared error, angle loss, and Laplacian loss), to deal with both spatial and spectral distortions. Experiments conducted on four data sets have verified the rationality of network structure and the proposed loss function and demonstrated that the proposed novel model outperforms state-of-the-art counterparts. [ABSTRACT FROM AUTHOR]

Regularization is a very effective algorithm to solve overfitting problem in neural network, which improves the generalization ability of the model. However, their working mechanisms and the impact on the model performance have not been fully explored. In this paper, we study and analyze them using information bottleneck theory and one theory from human brain sensory system. We propose a metric to characterise the encoding length of hidden layers, named as AEntry value. Then, we implement extensive experiments on MNIST and FashionMNIST datasets with several commonly used regularization algorithms, and calculate the corresponding AEntry values. We analyze these results and obtain three conclusions. (1) The introduction of regularization influences the encoding of relative features with prediction task in neural network. The early stopping technique avoids introducing unrelated information with the task into the model by stopping the training process as an appropriate iterations. Laplace, Gaussian and Sparse Response regularizations compress the related representation and improve the performance of neural network by introducing the prior information into the model. In contrast, Dropout, Batch Normalization, and Layer Normalization increase the encoding length of features by adopting redundant representation to improve the performance. (2) The encoding of neural network does not satisfy the data processing inequality of information theory, which is mainly caused by redundant coding of extracted features. (3) The overfitting is caused by introducing irrelative information with the target. These results can give us insight into building more efficient regularization algorithm to improve the performance of neural network model. [ABSTRACT FROM AUTHOR]

Endmember is defined as the spectral signature of pure material present in hyperspectral imagery. Estimation of the number of endmembers (NOE) present in a scene is an important preprocessing step and plays a crucial role in hyperspectral image processing, since over- or under-estimation of the NOE will lead to heavily incorrect results. In this article, we develop a thresholding ridge ratio (TRR) criterion based on eigendecomposition for NOE determination. Different from the widely used eigenvalue difference analysis methods, the TRR seeks an adaptive thresholding operation to the ridge ratio of eigenvalue differences, and ridge ratio combined with adaptive thresholding can theoretically guarantee a consistent estimate even when there are several local minima. Based on the TRR criterion, an algorithm is introduced to perform the estimation of NOE. Experimental results on both the simulated and real hyperspectral data sets have demonstrated that the proposed TRR-based algorithm has comparable and even better performances to several benchmark algorithms in the estimation accuracy of the NOE. [ABSTRACT FROM AUTHOR]

Pansharpening with sparse representation (SR) and details injection (ID) can both produce visually and quantitatively pleasing images. The former constructs pansharpened image by combining the dictionary and estimated sparse coefficients while the later by sharpening the multispectral bands through adding the proper spatial details from panchromatic (Pan) image. The combination of these two methods has been putting forward as the pansharpening method based on sparse representation of injected details (SR-D). Although SR-D has achieved better results both in visual and quantitative parts than many state-of-art methods, it ignores the intrinsic geometric structure connection between the multispectral image (MS) and the corresponding high-resolution MS image. In this paper, we propose a new pansharpening method, called manifold regularized sparse representation of injected details (MR-SR-D) by introducing a manifold regularization (MR) into the former SR-D model. The manifold regularization utilized a graph Laplacian to incorporate the locally geometrical structure of the multispectral data. Experimental results on the IKONOS, QuickBird and WorldView2 data sets show that the proposed method can achieve remarkable spectral and spatial quality on both reduced scale and full scale. [ABSTRACT FROM AUTHOR]

In recent years, convolutional neural networks (CNNs) have gained considerable attention in text classification because of the remarkable good performance they achieved in various situations. The usual practice is to first perform word embedding (i.e., mapping each word into a word vector), and then employ a CNN to perform classification. To improve classification accuracy, term weighting approaches have been proven to be quite effective. But to the best of our knowledge, almost all these methods assign only one weight to each term (word). Considering the fact that one term generally has different importance in documents with different class labels, we propose in this paper a novel term weighting scheme to be combined with word embeddings to enhance the classification performance of CNNs. In the novel method, multiple weights are assigned to each term and these weights are applied to the word embeddings of the words separately. Subsequently, the transformed features are fed into a multi-channel CNN model to predict the label of the sentence. By comparing the novel method with several other baseline methods with five benchmark data sets, the results manifest that the classification accuracy of the proposed method exceeds that of other methods by an amazing margin. Moreover, the weights assigned by different weighting schemes are also analyzed to get more insights of their working mechanism. [ABSTRACT FROM AUTHOR]

An abstract of the conference paper "Simultaneous measurement of blood-flow velocity and regional wall motion with phase unwrapping," by Junmin Liu and colleagues is presented.

Abstract Wasserstein generative adversarial networks (Wasserstein GANs, WGAN) improve the performance of GANs significantly by imposing the Lipschitz constraints on the critic, which is implemented by weight clipping. In this work, we argue that weight clipping could result in a side effect called area collapse by modifying orientations of weights heavily. To fix this issue, a novel method called Lp-WGAN is presented, where l p -norm normalization is employed to impose the constraints. This method restricts the searching space of weights within a low-dimensional manifold and focuses on searching orientations of weights. Experiments on toy datasets show that Lp-WGAN could spread probability mass and find the underlying distribution earlier than WGAN with weight clipping. Results on the LSUN bedroom dataset and CIFAR-10 dataset show that the proposed method could stabilize training better, generate competitive images earlier and get higher evaluation scores. [ABSTRACT FROM AUTHOR]

Recently, concept factorization (CF), which is a variant of nonnegative matrix factorization, has attracted great attentions in image representation. In CF, each concept is modeled as a nonnegative linear combination of the data points, and each data point as a linear combination of the concepts. CF has impressive performances in data representation. However, it is an unsupervised learning method without considering the label information of the data points. In this paper, we propose a novel semi-supervised CF method, called class-driven concept factorization (CDCF), which associates the class labels of data points with their representations by introducing a class-driven constraint. This constraint forces the representations of data points to be more similar within the same class while different between classes. Thus, the discriminative abilities of the representations are enhanced in the image representation. Experimental results on several databases have shown the effectiveness of our proposed method in terms of clustering accuracy and mutual information. [ABSTRACT FROM AUTHOR]

Two novel 2D covalent organic frameworks (TPT-COF-1 and TPT-COF-2) were synthesized from the flexible 2,4,6-triaryloxy-1,3,5-triazine building blocks on a gram scale, which show high crystallinity and large surface area. The controllable formation of highly ordered frameworks is mainly attributed to the self-assembly Piedfort unit of 2,4,6-triaryloxy-1,3,5-triazine. [ABSTRACT FROM AUTHOR]

A series of amino substituted cyclotrianisylene (aCTV)-based covalent organic frameworks (COFs), aCTV-COF1 to aCTV-COF4, have been synthesized. These crystalline analogues showed permanent porosity with BET surface areas from 656 m2 g−1 to 1428 m2 g−1. With the introduction of methoxy groups and hydroxyl groups at the phenyl linker moieties in aCTV-COF3 and aCTV-COF4, their properties (such as color, gas adsorption, hydrolytic stability and so on) have been influenced to a great extent. The CO2 sorption of aCTV-COF4 has increased significantly, and the H2 uptake of aCTV-COF3 is obviously higher than those of aCTV-COF1 and aCTV-COF2. Moreover, the introduction of the methoxy and hydroxyl groups has made aCTV-COF3 and aCTV-COF4 have better hydrolytic stability. [ABSTRACT FROM AUTHOR]

Ti(iv)-based complexes have been demonstrated as candidates for preparing hybrid and functional materials, and have received considerable attention. In this paper, hierarchical hollow titania materials with different surface nanostructures were synthesized successfully using a hydrothermal process via the transformation of a Ti(iv) oxalate complex as a precursor. Different concentrations of ammonia were used to adjust the morphologies and crystalline forms of the hydrothermal products. The hierarchical hollow anatase titania materials, HHTM-1 (cal) and HHTM-2 (cal), have high surface areas of up to 132 m2 g−1 and 84 m2 g−1, respectively, and show superior performance for dye degradation in water. [ABSTRACT FROM AUTHOR]

Purpose: To develop and evaluate a tool for accurate, reproducible, and programmable motion control of imaging phantoms for use in motion sensitive magnetic resonance imaging (MRI) applications. Methods: In this paper, the authors introduce a compact linear motion stage that is made of nonmagnetic material and is actuated with an ultrasonic motor. The stage can be positioned at arbitrary positions and orientations inside the scanner bore to move, push, or pull arbitrary phantoms. Using optical trackers, measuring microscopes, and navigators, the accuracy of the stage in motion control was evaluated. Also, the effect of the stage on image signal-to-noise ratio (SNR), artifacts, and B0 field homogeneity was evaluated. Results: The error of the stage in reaching fixed positions was 0.025±0.021 mm. In execution of dynamic motion profiles, the worst-case normalized root mean squared error was below 7% (for frequencies below 0.33 Hz). Experiments demonstrated that the stage did not introduce artifacts nor did it degrade the image SNR. The effect of the stage on the B0 field was less than 2 ppm. Conclusions: The results of the experiments indicate that the proposed system is MRI-compatible and can create reliable and reproducible motion that may be used for validation and assessment of motion related MRI applications. [ABSTRACT FROM AUTHOR]

The backpropagation (BP) algorithm is the most commonly utilized training strategy for a feed-forward artificial neural network (FFANN). The BP algorithm, however, always leads to the problems of low convergence rate, high energy and poor generalization capability of FFANN. In this paper, motivated by the sparsity property of human neuron’ responses, we introduce a new sparse-response BP (SRBP) to improve the capacity of a FFANN by enforcing sparsity to its hidden units through imposing a supplemental L 1 term on them. The FFANN model learned from our algorithm is closely related to the real human and thus its mechanism fully complies with the human nervous system, i.e., sparse representation and architectural depth. Experiments on several datasets demonstrate that SRBP yields good performances on convergence rate, energy saving and generalization capability. [ABSTRACT FROM AUTHOR]

Guided image denoising recovers clean target images by fusing guidance images and noisy target images. Several deep neural networks have been designed for this task, but they are black-box methods lacking interpretability. To overcome the issue, this paper builds a more interpretable network. To start with, an observation model is proposed to account for modality gap between target and guidance images. Then, this paper formulates a deep prior regularized optimization problem, and solves it by alternating direction method of multipliers (ADMM) algorithm. The update rules are generalized to design the network architecture. Extensive experiments conducted on FAIP and RNS datasets manifest that the novel network outperforms several state-of-the-art and benchmark methods regarding both evaluation metrics and visual inspection. • This is the first paper to raise the concept of modality gap. • This paper profoundly studies the statistical distribution of modality gap. • The proposed networks outperform the SOTA methods. [ABSTRACT FROM AUTHOR]

The demand for improving the activity, durability, and recyclability of metal-organic cages (MOCs) that work as photocatalytic molecular devices in a homogeneous system has promoted research to combine them with other solid materials. An M2L4 type photosensitive metal-organic cage MOC-Q2 with light-harvesting ligands and catalytic Pd2+ centers has been synthesized and further heterogenized with graphitic carbon nitride to prepare a robust direct Z-scheme heterojunction photocatalyst for visible-light-driven hydrogen generation. The optimized g-C3N4/MOC-Q2 (0.7 wt%) sample exhibits a high H2 evolution activity of 6423 μmol g−1 h−1 in 5 h, and a total turnover number of 39,695 after 10 h, significantly superior to the bare MOC-Q2 used in the homogeneous solution and the comparison sample Pd/g-C3N4/L-4. The enhanced performances of g-C3N4/MOC-Q2 can be ascribed to its direct Z-scheme heterostructure, which effectively improves the charge separation and transfer efficiency. This work presents a rational approach of designing a binary photocatalytic system through combing micromolecular MOCs with heterogeneous semiconductors for water splitting. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization(NMF) is a powerful image representation algorithm in pattern recognition and data mining. However, the traditional NMF does not utilize any label information, or fail to guarantee the sparse parts-based representation. In this paper, we put forward a semi-supervised local coordinate NMF (SLNMF) algorithm, which incorporate the available label information and the local coordinate constraint into NMF. Particularly, SLNMF makes the learned coefficients sparse by adding the coordinate constraint, and enhance the discriminative ability of different classes by using the label information constraint. Furthermore, in order to extract the geometric structure of the data space, we propose a new semi-supervised graph regularized NMF with local coordinate constraint (SGLNMF) method, which incorporates the graph regularization into SLNMF to enhance the discriminative abilities of data representations. SGLNMF not only reveals the intrinsic geometrical information of the data space, but also takes into account the local coordinate constraint and the label information. Clustering experiments on several standard image datasets demonstrate the effectiveness of our proposed SLNMF and SGLNMF methods compared to the state-of-the-art methods. • In our proposed SLNMF, which incorporates the label information and the local coordinate constraint into NMF as the additional constraints to enhance the performance of the clustering algorithm. • SGLNMF reveals the intrinsic geometrical information of the data space by constructing the graph regularization, and also takes both the local coordinate constraints and the label information into account, so it can have better performance on the AC and NMI. • We develop the corresponding iterative updating optimization schemes to derive the iterative updating rules of matric factors U and Z. More importantly, the convergence proof of our proposed SGLNMF is provided. [ABSTRACT FROM AUTHOR]

Two composites LaNi4.8Sn0.2/CNTs and NdNi4.8Sn0.2/CNTs were prepared by an impregnation-reduction method. Their hydrogen storage capacity could reach up to 2.96 wt% and 2.88 wt% respectively at room temperature and 1.0 MPa pressure. These values, which might result from the synergetic effect between the alloy nanoparticles and the pretreated CNTs, were three times higher than those of the unsupported MNi4.8Sn0.2(M=La, Nd) alloys under the same conditions. XRD and TEM revealed that the alloy particles were uniformly dispersed on the CNTs and the average particle size was Ca. 30 nm. The composites also showed good stability and the hydrogen storage capacity decreased by less than 6% after 100 adsorption-desorption cycles. Moreover, no noticeable change in crystalline structure was observed for the composites. [ABSTRACT FROM AUTHOR]

A type of novel material with a high hydrogen storage capacity was prepared by supporting PdNi18 alloy nanoparticles, which were synthesized by using a new colloid method, on the surface of pretreated multiwal led carbon nanotubes (MWCNTs). The average PdNi18 alloy particle sizes calculated from XRD patterns were ca. 3 nm, and the high dispersion of these particles on MWCNTs was confirmed by TEM image. Hydrogen storage performance of the composite was investigated under moderate pressure (0.1-1.5 MPa) at room temperature, and a maximum storage capacity of ca. 2.3 wt% was achieved under 1.5 MPa at room temperature, which was much higher than that reported previously under the same conditions. [ABSTRACT FROM AUTHOR]