Search

Low-cost miniaturized laser sintering equipment remains lacking at present; therefore, the development of laser sintering technology and its widespread applications are significantly hindered. Traditional laser sintering equipment is composed of a carbon dioxide laser, water cooling system, powder-box-heating device, and thermal insulation device. Such requirements are the main factors limiting the miniaturization and economic efficiency of laser sintering equipment. Herein, a laser-sintered material was fabricated by sintering using a near-infrared laser light source with a wavelength of 1064 nm without heating, and its microstructure and properties were systematically studied. Polyether sulfone (PES) and carbon black (CB) powders were selected as the raw materials for preparing PES/CB composites by mechanical mixing. For synthesizing the PES/CB composite powders, the CB powder content was varied within the range of 0.25%–1.5%. The PES/CB powders with different component ratios were subjected to laser sintering treatment, and the corresponding microstructural evolutions of the sintered parts were analyzed. The effects of different component ratios on the mechanical properties and dimensional accuracy of the sintered part were investigated, and the optimal content of CB powders of the PES/CB composite material was determined. Additionally, the effects of laser power (10–18 W), scanning speed (1200–1600 mm/s), and scanning spacing (0.04–0.08 mm) on the forming quality of the sintered parts of the PES/CB composite powders were evaluated. The processing parameters of the laser sintering of PES/CB composite powders were explored using orthogonal experimental tests and optimized using the comprehensive weighted method. [ABSTRACT FROM AUTHOR]

• Producing customized electronic components using the 3D printing. • SiO 2 could improve the conductivity of carbonized laser sintering parts and reduce their shrinkage. • A new way to produce electronic components by laser sintering. laser sintering (LS), can be used to develop customized electronic components for wearable electronic devices. However, the conductivity and molding performance of carbonized LS parts has limitations. Thus, this study evaluates the effect of adding silicon dioxide (SiO 2) to composites to enhance the electrical conductivity and molding performance of graphene oxide/thermoplastic polyurethane carbonized parts prepared by laser sintering. In particular, the effect of SiO 2 content from 0 wt% to 2 wt% on the carbonized parts was investigated through scanning electron microscopy, resistivity tests, and shrinkage measurements. The results show that under specific quantities, adding SiO 2 can effectively improve the electrical conductivity of carbonized sintered parts and shrinkage due to carbonization. Thus, the results provide new ideas for developing customized electronic components. [ABSTRACT FROM AUTHOR]

Recent advances in various fields such as telecommunications, biomedicine and economics, among others, have created enormous amount of data that are often characterized by their huge size and high dimensionality. It has become evident, from research in the past couple of decades, that sparsity is a flexible and powerful notion when dealing with these data, both from empirical and theoretical viewpoints. In this survey, we review some of the most popular techniques to exploit sparsity, for analyzing high-dimensional vectors, matrices and higher-order tensors. [ABSTRACT FROM AUTHOR]

We propose an effective online background subtraction method, which can be robustly applied to practical videos that have variations in both foreground and background. Different from previous methods which often model the foreground as Gaussian or Laplacian distributions, we model the foreground for each frame with a specific mixture of Gaussians (MoG) distribution, which is updated online frame by frame. Particularly, our MoG model in each frame is regularized by the learned foreground/background knowledge in previous frames. This makes our online MoG model highly robust, stable and adaptive to practical foreground and background variations. The proposed model can be formulated as a concise probabilistic MAP model, which can be readily solved by EM algorithm. We further embed an affine transformation operator into the proposed model, which can be automatically adjusted to fit a wide range of video background transformations and make the method more robust to camera movements. With using the sub-sampling technique, the proposed method can be accelerated to execute more than 250 frames per second on average, meeting the requirement of real-time background subtraction for practical video processing tasks. The superiority of the proposed method is substantiated by extensive experiments implemented on synthetic and real videos, as compared with state-of-the-art online and offline background subtraction methods. [ABSTRACT FROM AUTHOR]

Addressing the current complexities, costs, and adherence issues in the detection of forward head posture (FHP), our study conducted an exhaustive epidemiologic investigation, incorporating a comprehensive posture screening process for each participant in China. This research introduces an avant-garde, machine learning-based non-contact method for the accurate discernment of FHP. Our approach elevates detection accuracy by leveraging body landmarks identified from human images, followed by the application of a genetic algorithm for precise feature identification and posture estimation. Observational data corroborates the superior efficacy of the Extra Tree Classifier technique in FHP detection, attaining an accuracy of 82.4%, a specificity of 85.5%, and a positive predictive value of 90.2%. Our model affords a rapid, effective solution for FHP identification, spotlighting the transformative potential of the convergence of feature point recognition and genetic algorithms in non-contact posture detection. The expansive potential and paramount importance of these applications in this niche field are therefore underscored. [ABSTRACT FROM AUTHOR]

As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects from a group of images. On one hand, traditional co-saliency detection approaches rely heavily on human knowledge for designing hand-crafted metrics to possibly reflect the faithful properties of the co-salient regions. Such strategies, however, always suffer from poor generalization capability to flexibly adapt various scenarios in real applications. On the other hand, most current methods pursue co-saliency detection in unsupervised fashions. This, however, tends to weaken their performance in real complex scenarios because they are lack of robust learning mechanism to make full use of the weak labels of each image. To alleviate these two problems, this paper proposes a new SP-MIL framework for co-saliency detection, which integrates both multiple instance learning (MIL) and self-paced learning (SPL) into a unified learning framework. Specifically, for the first problem, we formulate the co-saliency detection problem as a MIL paradigm to learn the discriminative classifiers to detect the co-saliency object in the “instance-level”. The formulated MIL component facilitates our method capable of automatically producing the proper metrics to measure the intra-image contrast and the inter-image consistency for detecting co-saliency in a purely self-learning way. For the second problem, the embedded SPL paradigm is able to alleviate the data ambiguity under the weak supervision of co-saliency detection and guide a robust learning manner in complex scenarios. Experiments on benchmark datasets together with multiple extended computer vision applications demonstrate the superiority of the proposed framework beyond the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Graph-based semi-supervised learning (GSSL) attracts considerable attention in recent years. The performance of a general GSSL method relies on the quality of Laplacian weighted graph (LWR) composed of the similarity imposed on input examples. A key for constructing an effective LWR is on the proper selection of the neighborhood size K or ε on the construction of KNN graph or ε -neighbor graph on training samples, which constitutes the fundamental elements in LWR. Specifically, too large K or ε will result in “shortcut” phenomenon while too small ones cannot guarantee to represent a complete manifold structure underlying data. To this issue, this study attempts to propose a method, called adaptive Laplacian graph trimming (ALGT), to make an automatic tuning to cut improper inter-cluster shortcut edges while enhance the connection between intra-cluster samples, so as to adaptively fit a proper LWR from data. The superiority of the proposed method is substantiated by experimental results implemented on synthetic and UCI data sets. [ABSTRACT FROM AUTHOR]

There are mainly two methodologies utilized in current sparse PCA calculation, the greedy approach and the block approach. While the greedy approach tends to be incrementally invalidated in sequentially generating sparse PCs due to the cumulation of computational errors, the block approach is difficult to elaborately rectify individual sparse PCs under certain practical sparsity or nonnegative constraints. In this paper, a simple while effective block coordinate descent (BCD) method is proposed for solving the sparse PCA problem. The main idea is to separate the original sparse PCA problem into a series of simple sub-problems, each having a closed-form solution. By cyclically solving these sub-problems in an analytical way, the BCD algorithm can be easily constructed. Despite its simplicity, the proposed method performs surprisingly well in extensive experiments implemented on a series of synthetic and real data. In specific, as compared to the greedy approach, the proposed method can iteratively ameliorate the deviation errors of all computed sparse PCs and avoid the problem of accumulating errors; as compared to the block approach, the proposed method can easily handle the constraints imposed on each individual sparse PC, such as certain sparsity and/or nonnegativity constraints. Besides, the proposed method converges to a stationary point of the problem, and its computational complexity is approximately linear in both data size and dimensionality, which makes it well suited to handle large-scale problems of sparse PCA. [ABSTRACT FROM AUTHOR]

Recently, genetic algorithm (GA) has been introduced as an effective method to solve the registration problem. It maintains a population of candidate solutions for the problem and evolves by iteratively applying a set of stochastic operators. Accordingly, a key question is how to reduce the population size. In this study, the authors present two techniques for reducing the population size in the GA for registration of partially overlapping point sets. Based on the trimmed iterative closest point algorithm, they introduce a growth operator into the GA. The growth operator, which is also inspired by the biological evolution, can improve the GA efficiency for registration. Furthermore, they present a technique called centre alignment to confirm the value range of all the registration parameters, which can reduce the search space and allow the well‐designed GA to directly solve the registration problem. Experimental results carried out with the m‐dimensional point sets illustrate its advantages over previous approaches. [ABSTRACT FROM AUTHOR]

The robust detection of small targets is one of the key techniques in infrared search and tracking applications. A novel small target detection method in a single infrared image is proposed in this paper. Initially, the traditional infrared image model is generalized to a new infrared patch-image model using local patch construction. Then, because of the non-local self-correlation property of the infrared background image, based on the new model small target detection is formulated as an optimization problem of recovering low-rank and sparse matrices, which is effectively solved using stable principle component pursuit. Finally, a simple adaptive segmentation method is used to segment the target image and the segmentation result can be refined by post-processing. Extensive synthetic and real data experiments show that under different clutter backgrounds the proposed method not only works more stably for different target sizes and signal-to-clutter ratio values, but also has better detection performance compared with conventional baseline methods. [ABSTRACT FROM AUTHOR]

Abstract: A new method is proposed in this paper to learn overcomplete dictionary from signals. Differing from the current methods that enforce uniform sparsity constraint on the coefficients of each input signal, the proposed method attempts to impose global sparsity constraint on the coefficient matrix of the entire signal set. This enables the proposed method to fittingly assign the atoms of the dictionary to represent various signals and optimally adapt to the complicated structures underlying the entire signal set. By virtue of the sparse coding and sparse PCA techniques, a simple algorithm is designed for the implementation of the method. The efficiency and the convergence of the proposed algorithm are also theoretically analyzed. Based on the experimental results implemented on a series of signal and image data sets, the capability of the proposed method is substantiated in original dictionary recovering, signal reconstructing and salient signal structure revealing. [Copyright &y& Elsevier]

Abstract: In this paper we derive an algorithm to follow the entire solution path of the sparse principal component analysis (PCA) problem. The core idea is to iteratively identify the pairwise variables along which the objective function of the sparse PCA model can be largely increased, and then incrementally update the coefficients of the two variables so selected by a small stepsize. The new algorithm dominates on its capability of providing a computational shortcut to attain the entire spectrum of solutions of the sparse PCA problem, which is always beneficial to real applications. The proposed algorithm is simple and easy to be implemented. The effectiveness of our algorithm is empirically verified by a series of experiments implemented on synthetic and real problems, as compared with other typical sparse PCA methods. [Copyright &y& Elsevier]

We propose the concept of intrinsic spatial distance ( ISD) for the study of a spatial relationship between any two points in space. ISD is a distance measure that takes into account the separation of two points with respect to their physical and attribute closeness. We construct an algorithm to implement this concept as an ISD measurement. Based on the ISD concept, two points in space are related through a transitional path linking one to the other. As an ISD measurement decreases, the spatial relationship between two points becomes increasingly stronger. We argue theoretically and demonstrate empirically that the ISD concept is not predisposed in favor of the first law of geography, but directly considers variance of nearness in physical distance and attribute distance to derive the extent to which two points are spatially associated. Specifically, in single attribute cases, the information uncovered by an ISD measurement is more elaborate than that revealed by Moran's I, local Moran's I, and a semivariogram, giving a meticulous account of relatedness in both local and global contexts. The ISD concept is also sufficiently general to be used to study multiple attributes of relationships. Proponemos el concepto de distancia espacial intrínseca ( intrinsic spatial distance -ISD) para el estudio de la relación espacial entre dos puntos en el espacio. La ISD es una medición de distancia que tiene en cuenta la separación de dos puntos con respecto a su cercanía física y de atributo. Construimos un algoritmo para aplicar este concepto y crear una medición ISD. De acuerdo con en el concepto ISD, dos puntos en el espacio están relacionadas a través de un camino de transición que los vincula uno al otro. A medida que la medición ISD disminuye, la relación espacial entre dos puntos se refuerza. Argumentamos teóricamente y demostramos empíricamente que el concepto ISD no está predispuesto a favor de la primera ley de la geografía (de Tobler), pero considera directamente la varianza de la cercanía de la distancia física y la distancia del valor del atributo para derivar una medición que cuantifica el grado en el que dos puntos están asociados espacialmente. En concreto, en los casos de atributos individuales, la información revelada por una medición ISD es más sofisticada que la que proporcionada por el índice de Moran, el índice de Moran local, y el semivariograma, pues da cuanta minuciosa de la relación espacial y de atributo en contextos locales y globales. El concepto de ISD también es lo suficientemente general para ser usado en el estudio de relaciones entre múltiples atributos. 本文提出了内蕴空间距离(ISD)来研究空间中任意两点之间的空间关系。ISD是考虑空间上分离的两点各自物理和属性接近度的一种距离度量。通过构造一个算法将该概念转变为ISD可度量方式。基于ISD概念，空间上的两点通过连接两者迁移路径相关联。当ISD度量减小时，两点之间空间关系变得越来越强。理论论证和实例演示表明ISD概念并不倾向于符合地理学第一定律，但直接考虑两点间物理距离和属性距离临近性的变化可以推导两点在空间上的联系程度。特别是在单一属性案例中，相比于Moran's I,局部Moran's I和半方差图，ISD度量揭示了全局与局部环境中详尽的空间相关信息。同时，ISD概念在研究多属性的空间关系中也是足够通用的。 [ABSTRACT FROM AUTHOR]

Abstract: Nonlinear dimensionality reduction of data lying on multi-cluster manifolds is a crucial issue in manifold learning research. An effective method, called the passage method, is proposed in this paper to alleviate the disconnectivity, short-circuit, and roughness problems ordinarily encountered by the existing methods. The specific characteristic of the proposed method is that it constructs a globally connected neighborhood graph superimposed on the data set through technically building the smooth passages between separate clusters, instead of supplementing some rough inter-cluster connections like some existing methods. The neighborhood graph so constructed is naturally configured as a smooth manifold, and hence complies with the effectiveness condition underlying manifold learning. This theoretical argument is supported by a series of experiments performed on the synthetic and real data sets residing on multi-cluster manifolds. [Copyright &y& Elsevier]

Detecting intrinsic loop structures of a data manifold is the necessary prestep for the proper employment of the manifold learning techniques and of fundamental importance in the discovery of the essential representational features underlying the data lying on the loopy manifold. An effective strategy is proposed to solve this problem in this study. In line with our intuition, a formal definition of a loop residing on a manifold is first given. Based on this definition, theoretical properties of loopy manifolds are rigorously derived. In particular, a necessary and sufficient condition for detecting essential loops of a manifold is derived. An effective algorithm for loop detection is then constructed. The soundness of the proposed theory and algorithm is validated by a series of experiments performed on synthetic and real-life data sets. In each of the experiments, the essential loops underlying the data manifold can be properly detected, and the intrinsic representational features of the data manifold can be revealed along the loop structure so detected. Particularly, some of these features can hardly be discovered by the conventional manifold learning methods. [ABSTRACT FROM AUTHOR]

Abstract: Various sparse principal component analysis (PCA) methods have recently been proposed to enhance the interpretability of the classical PCA technique by extracting principal components (PCs) of the given data with sparse non-zero loadings. However, the performance of these methods is prone to be adversely affected by the presence of outliers and noises. To alleviate this problem, a new sparse PCA method is proposed in this paper. Instead of maximizing the L 2-norm variance of the input data as the conventional sparse PCA methods, the new method attempts to capture the maximal L 1-norm variance of the data, which is intrinsically less sensitive to noises and outliers. A simple algorithm for the method is specifically designed, which is easy to be implemented and converges to a local optimum of the problem. The efficiency and the robustness of the proposed method are theoretically analyzed and empirically verified by a series of experiments implemented on multiple synthetic and face reconstruction problems, as compared with the classical PCA method and other typical sparse PCA methods. [Copyright &y& Elsevier]

Abstract: A new quality assessment criterion for evaluating the performance of the nonlinear dimensionality reduction (NLDR) methods is proposed in this paper. Differing from the current quality assessment criteria focusing on the local-neighborhood-preserving performance of the NLDR methods, the proposed criterion capitalizes on a new aspect, the global-structure-holding performance, of the NLDR methods. By taking both properties into consideration, the intrinsic capability of the NLDR methods can be more faithfully reflected, and hence more rational measurement for the proper selection of NLDR methods in real-life applications can be offered. The theoretical argument is supported by experiment results implemented on a series of benchmark data sets. [Copyright &y& Elsevier]

Abstract: Geodesic distance estimation for data lying on a manifold is an important issue in many applications of nonlinear dimensionality reduction. In this paper, a method aiming at improving the precision of geodesic distance estimation is proposed. The method is constructed on the basic principle, locally linear assumption, underlying the manifold data. It presumes that the locally linear patch, expressed as a convex combination of neighbors of a vertex, approximately resides on the manifold, as well as the local neighborhood edge does. The proposed method essentially extends the search area from local edges, employed by existing methods, to local patches. This naturally leads to a more accurate geodesic distance estimation. An efficient algorithm for the method is constructed, and its computational complexity is also analyzed. Experiment results also show that the proposed method outperforms the existing methods in geodesic distance estimation. [Copyright &y& Elsevier]

Deep autoencoder-based approaches have achieved significant improvements on restoring damaged images, yet they still suffer from artifacts due to the inadequate representation and inaccurate regularization of existing features. In this paper, we propose a dual-pyramidal inpainting framework called DPNet to address these two limitations, which seamlessly integrates sufficient feature learning and dynamic regularization within an autoencoder network. Specifically, to exhaustively extract multi-scale features, we adopt layer-wise pyramidal convolution in encoder, which provides an arbitrary combination pool of various receptive fields. Subsequently, to tackle the patch deterioration problem in previous cross-scale non-local schemes, we further propose a Pyramidal Attention Mechanism (PAM) in decoder to acquire finer patches directly from learned layers. Mutually benefited with pyramidal features extraction in encoder, the dissemination space for non-local pixels in our PAM is notably enlarged to pyramidal level, thus significantly benefiting the feature representation. Moreover, to avoid the mask error accumulation in existing works, a dynamic normalization mechanism utilizing the spatial mask information updated in encoder is introduced, which further ensures the feature integrity and consistency. Such a dual-pyramidal structure along with dynamic normalization significantly improve the inpainting quality, outperforming existing competitors. Comprehensive experiments conducted on three benchmark datasets demonstrate that our DPNet performs favorably against the state-of-the-arts. [ABSTRACT FROM AUTHOR]

• Proposed a novel self-determine sequence intervention strategy based on the individual preference of the participants. • Used machine learning algorithms to predict the effects of interventions. • Used explainable artificial intelligence to quantify and visualize the contribution of the intervention program. • Used the SHAP values to quantify and visualize the contribution of each feature to the prediction outcome. To improve and even reverse sarcopenia in elderly people, this study developed a self-determined sequence exercise program consisting of strength training exercise, Yijinjing exercise (a traditional Chinese exercise), and hybrid strength training with Yijinjing exercise. Ninety-four community-dwelling older adults screened for sarcopenia using the Asian Working Group for Sarcopenia criteria were randomly assigned to 24 weeks of a control group (CG, n = 30), self-determined sequence exercise program group (SDSG, n = 34) or strength training group (STG, n = 30). The study examined the effects of three interventions on participantsL3 skeletal muscle fat density, L3 skeletal muscle fat area, L3 skeletal muscle density, L3 skeletal muscle area, muscle fat infiltration, relative skeletal muscle mass index, and grip strength using a repeated-measures ANOVA to evaluate the experimental data. To evaluate the real effect of this model in reversing sarcopenia after the intervention, nine classification models were trained. Significant interaction effects were observed with grip strength, RSMI, L3 SMD, and L3 SMA. At the 24th week, participants' grip strength, L3 SMFA, L3 SMA, and RSMI were improved significantly in the SDSG and STG. The SDSG achieved significantly greater RSMI and grip strength than the STG and CG after the intervention. The self-determined sequence exercise program exhibited better performance than the single type of exercise modality in reversing sarcopenia and improving older adults' skeletal muscle area. Consequently, the stacking model is feasible to make a prediction as to whether or not sarcopenia may be reversed in older adults. [ABSTRACT FROM AUTHOR]

This paper presents a novel accelerated exact $k$ k -means called as “Ball $k$ k -means” by using the ball to describe each cluster, which focus on reducing the point-centroid distance computation. The “Ball $k$ k -means” can exactly find its neighbor clusters for each cluster, resulting distance computations only between a point and its neighbor clusters’ centroids instead of all centroids. What’s more, each cluster can be divided into “stable area” and “active area”, and the latter one is further divided into some exact “annular area”. The assignment of the points in the “stable area” is not changed while the points in each “annular area” will be adjusted within a few neighbor clusters. There are no upper or lower bounds in the whole process. Moreover, ball $k$ k -means uses ball clusters and neighbor searching along with multiple novel stratagems for reducing centroid distance computations. In comparison with the current state-of-the art accelerated exact bounded methods, the Yinyang algorithm and the Exponion algorithm, as well as other top-of-the-line tree-based and bounded methods, the ball $k$ k -means attains both higher performance and performs fewer distance calculations, especially for large-k problems. The faster speed, no extra parameters and simpler design of “Ball $k$ k -means” make it an all-around replacement of the naive $k$ k -means. [ABSTRACT FROM AUTHOR]

Background. Concern has been expressed regarding the risk of carcinogenesis from medical computed tomography (CT) radiation. Lowering radiation in CT without appropriate modifications often leads to severe noise-induced artifacts in the images. The utilization of deep learning (DL) techniques has achieved promising reconstruction performance in low-dose CT (LDCT) imaging. However, most DL-based algorithms require the pre-collection of a large set of image pairs (low-dose/standard-dose) and the training of networks in an end-to-end supervised manner. Meanwhile, securing such a large volume of paired, well-registered training data in clinical practice is challenging. Moreover, these algorithms often overlook the potential to utilize the abundant information in a large collection of LDCT-only images/sinograms. Methods. In this paper, we introduce a semi-supervised iterative adaptive network (SIA-Net) for LDCT imaging, utilizing both labeled and unlabeled sinograms in a cohesive network framework, integrating supervised and unsupervised learning processes. Specifically, the supervised process captures critical features (i.e. noise distribution and tissue characteristics) latent in the paired sinograms, while the unsupervised process effectively learns these features in the unlabeled low-dose sinograms, employing a conventional weighted least-squares model with a regularization term. Furthermore, the SIA-Net method is designed to adaptively transfer the learned feature distribution from the supervised to the unsupervised process, thereby obtaining a high-fidelity sinogram through iterative adaptive learning. Finally, high-quality CT images can be reconstructed from the refined sinogram using the filtered back-projection algorithm. Results. Experimental results on two clinical datasets indicate that the proposed SIA-Net method achieves competitive performance in terms of noise reduction and structure preservation in LDCT imaging, when compared to traditional supervised learning methods. [ABSTRACT FROM AUTHOR]

Purpose: Selective laser sintering (SLS) is an essential technology in the field of additive manufacturing. However, SLS technology is limited by the traditional point-laser sintering method and has reached the bottleneck of efficiency improvement. This study aims to develop an image-shaped laser sintering (ISLS) system based on a digital micromirror device (DMD) to address this problem. The ISLS system uses an image-shaped laser light source with a size of 16 mm × 25.6 mm instead of the traditional SLS point-laser light source. Design/methodology/approach: The ISLS system achieves large-area image-shaped sintering of polymer powder materials by moving the laser light source continuously in the x-direction and updating the sintering pattern synchronously, as well as by overlapping the splicing of adjacent sintering areas in the y-direction. A low-cost composite powder suitable for the ISLS system was prepared using polyether sulfone (PES), pinewood and carbon black (CB) powders as raw materials. Large-sized samples were fabricated using composite powder, and the microstructure, dimensional accuracy, geometric deviation, density, mechanical properties and feasible feature sizes were evaluated. Findings: The experimental results demonstrate that the ISLS system is feasible and can print large-sized parts with good dimensional accuracy, acceptable geometric deviations, specific small-scale features and certain density and mechanical properties. Originality/value: This study has achieved the transition from traditional point sintering mode to image-shaped surface sintering mode. It has provided a new approach to enhance the system performance of traditional SLS. [ABSTRACT FROM AUTHOR]

Estimating the geographic positions in GPS-denied environments is of great significance to the safe flight of unmanned aerial vehicles (UAVs). In this paper, we propose a novel geographic position estimation method for UAVs after road network alignment. We discuss the generally overlooked issue, namely, how to estimate the geographic position of the UAV after successful road network alignment, and propose a precise robust solution. In our method, the optimal initial solution of the geographic position of the UAV is first estimated from the road network alignment result, which is typically presented as a homography transformation between the observed road map and the reference one. The geographic position estimation is then modeled as an optimization problem to align the observed road with the reference one to improve the estimation accuracy further. Experiments on synthetic and real flight aerial image datasets show that the proposed algorithm can estimate more accurate geographic position of the UAV in real time and is robust to the errors from homography transformation estimation compared to the currently commonly-used method. [ABSTRACT FROM AUTHOR]

This article addresses the problem of semantic segmentation with limited cross-modality data in large-scale urban scenes. Most prior works have attempted to address this issue by using multimodal deep neural networks (DNNs). However, their ability to effectively blending different properties across multimodalities and robustly learning representations from complex scenes remains limited, particularly in the absence of sufficient and well-annotated training images. This leads to a challenge related to cross-modality learning with multimodal DNNs. To this end, we introduce two novel plug-and-play units in the network: self-generative adversarial networks (GANs) module and mutual-GANs module, to learn perturbation-insensitive feature representations and to eliminate the gap between multimodalities, respectively, yielding more effective and robust information transfer. Furthermore, a patchwise progressive training strategy is devised to enable effective network learning with limited samples. We evaluate the proposed network on two multimodal (hyperspectral and multispectral) overhead image data sets and achieve a significant improvement in comparison with several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Identifying task-relevant structures is important for molecular property prediction. In a graph neural network (GNN), graph pooling can group nodes and hierarchically represent the molecular graph. However, previous pooling methods either drop out node information or lose the connection of the original graph; therefore, it is difficult to identify continuous subtructures. Importantly, they lacked interpretability on molecular graphs. To this end, we proposed a novel Molecular Edge Shrinkage Pooling (MESPool) method, which is based on edges (or chemical bonds). MESPool preserves crucial edges and shrinks others inside the functional groups and is able to search for key structures without breaking the original connection. We compared MESPool with various well-known pooling methods on different benchmarks and showed that MESPool outperforms the previous methods. Furthermore, we explained the rationality of MESPool on some datasets, including a COVID-19 drug dataset. [ABSTRACT FROM AUTHOR]

Background: Immune checkpoint inhibitors-induced myocarditis presents unique clinical challenges. Here, we assessed post-marketing safety of cytotoxic T-lymphocyte-associated protein-4 (CTLA-4), programmed cell death-1 (PD-1), and programmed death-ligand 1 (PD-L1) inhibitors by mining the real-world data reported in two international pharmacovigilance databases.Methods: We analyzed immune checkpoint inhibitors (ICIs)-associated fatal adverse drug events (ADEs) reports from the US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) collected from July 1, 2014 to December 31, 2019 and data from EudraVigilance (EV) database accessed on February 29, 2020. Three different data mining approaches were used to detect the signal of fatal myocarditis caused by ICIs.Results: Based on 7613 ICIs-related ADEs reported to the EV database and 5786 ICIs-associated ADEs submitted to the FAERS database, the most frequently reported ADE was ipilimumab-related colitis. For myocarditis, nivolumab-associated myocarditis was the most common. Among the five fatal toxic effects associated with ICIs, the lethality rate of myocarditis was the highest. Therefore, we further analyzed ICI-associated myocarditis and found that elderly patients and male patients were more likely to develop ICIs-related myocarditis. The results of signal detection showed that the risk signal of avelumab-related myocarditis detected by reporting odds ratio (ROR) method and proportional reporting ratios (PRR) method was the highest, whereas the signal strength of ipilimumab-related myocarditis detected by Bayesian confidence propagation neural networks (BCPNN) method was the strongest.Conclusion: The findings of this study indicated the potential safety issues of developing myocarditis when using ICIs, which were consistent with the results of previous clinical trials and could provide a reference for clinical workers when using ICIs. [ABSTRACT FROM AUTHOR]

Haze appearing in natural scene images generally contains nonhomogeneous characteristics such as filaments, masses, and mist. The high-frequency part of hazy images contains variable background textures and haze shapes, whereas regions with mostly uniform distribution are dominated by low-frequency information. Although existing methods based on convolutional neural networks have achieved remarkable progress in single image dehazing, the intrinsic hazy image patterns have been neglected in most models. We propose a frequency division dehazing network to leverage prior knowledge characterizing hazy images. The proposed network processes shallow feature maps through high-, medium-, and low-frequency branches. This separation facilitates a flexible architecture, whose branch handling lower-frequency components is less redundant given its relatively simpler background and haze shapes. Then, by integrating knowledge extracted from all the network branches using feature fusion, the proposed network fully exploits the variety of frequency characteristics in hazy images and achieves 39.51 PSNR and 0.9931 SSIM on the RESIDE dataset. Experiments on both synthetic and real hazy images demonstrate the superiority of the proposed network over several existing state-of-the-art methods, demonstrating the effectiveness of exploiting prior knowledge in hazy images. [ABSTRACT FROM AUTHOR]

In the laser sintering (LS) printing process, a printed part is formed by sintering layer-by-layer on the powder bed. Thus, it is necessary to consider the dimensional accuracy of the laser-sintered powder bed as an important evaluation index. In this paper, a generalized powder bed–size accuracy compensation model is proposed for non-crystalline thermoplastic polymer materials. Taking polyethersulfone (PES) material as an example, the main factors influencing powder bed dimensional accuracy during LS printing are modeled and analyzed experimentally in this study, including four important factors: laser reference deviation, temperature deviation, density deviation, and secondary sintering deviation. In this study, CX_A200 LS equipment is used for prototyping and verification, a 3D scanning method is used to measure the printed parts, and the measurement results are digitally compared and analyzed. On this basis, the relationship of each influencing factor in the proposed compensation model is determined experimentally, and the experimental results demonstrate that the proposed compensation model is approximately 95% effective in terms of correcting the deviation of powder bed dimensional accuracy. [ABSTRACT FROM AUTHOR]

Early diagnosis and continuous monitoring of patients suffering from eye diseases have been major concerns in the computer-aided detection techniques. Detecting one or several specific types of retinal lesions has made a significant breakthrough in computer-aided screen in the past few decades. However, due to the variety of retinal lesions and complex normal anatomical structures, automatic detection of lesions with unknown and diverse types from a retina remains a challenging task. In this paper, a weakly supervised method, requiring only a series of normal and abnormal retinal images without need to specifically annotate their locations and types, is proposed for this task. Specifically, a fundus image is understood as a superposition of background, blood vessels, and background noise (lesions included for abnormal images). Background is formulated as a low-rank structure after a series of simple preprocessing steps, including spatial alignment, color normalization, and blood vessels removal. Background noise is regarded as stochastic variable and modeled through Gaussian for normal images and mixture of Gaussian for abnormal images, respectively. The proposed method encodes both the background knowledge of fundus images and the background noise into one unique model, and corporately optimizes the model using normal and abnormal images, which fully depict the low-rank subspace of the background and distinguish the lesions from the background noise in abnormal fundus images. Experimental results demonstrate that the proposed method is of fine arts accuracy and outperforms the previous related methods. [ABSTRACT FROM AUTHOR]

As a promising way for analyzing data, sparse modeling has achieved great success throughout science and engineering. It is well known that the sparsity/low-rank of a vector/matrix can be rationally measured by nonzero-entries-number ( $l_0$ norm)/nonzero- singular-values-number (rank), respectively. However, data from real applications are often generated by the interaction of multiple factors, which obviously cannot be sufficiently represented by a vector/matrix, while a high order tensor is expected to provide more faithful representation to deliver the intrinsic structure underlying such data ensembles. Unlike the vector/matrix case, constructing a rational high order sparsity measure for tensor is a relatively harder task. To this aim, in this paper we propose a measure for tensor sparsity, called Kronecker-basis-representation based tensor sparsity measure (KBR briefly), which encodes both sparsity insights delivered by Tucker and CANDECOMP/PARAFAC (CP) low-rank decompositions for a general tensor. Then we study the KBR regularization minimization (KBRM) problem, and design an effective ADMM algorithm for solving it, where each involved parameter can be updated with closed-form equations. Such an efficient solver makes it possible to extend KBR to various tasks like tensor completion and tensor robust principal component analysis. A series of experiments, including multispectral image (MSI) denoising, MSI completion and background subtraction, substantiate the superiority of the proposed methods beyond state-of-the-arts. [ABSTRACT FROM AUTHOR]

This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert recertification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the “instructor-student-collaborative” learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://hcp.sysu.edu.cn/projects/aspl/. [ABSTRACT FROM AUTHOR]

Accurate wind power forecasting has great practical significance for the safe and economical operation of power systems. In reality, wind power data are recorded at high time resolution (5 s, etc.). The original high-resolution data are averaged to produce the low-resolution time series (10 min, etc.) used in wind power forecasts. Therefore, the current wind power forecasting models neglect certain information in the high-resolution data. Moreover, the common Gaussian assumption used for the error term in the current wind power forecasting model is not consistent with the real, complex wind power forecasting error distribution. In this paper, an adaptive robust multi-kernel regression model is proposed to deal with the two disadvantages mentioned above. First, a multi-kernel regression model is constructed to process the multi-resolution wind power data. Second, a Gaussian mixture model is employed to model the complex wind power forecasting error. Finally, a variational Bayesian method is introduced to optimize the proposed model and to cause the simultaneous output of both the deterministic and probabilistic forecasts. Two case studies have been conducted on real wind power data from Chinese wind farms. The results show that the proposed model provides more accurate deterministic forecasts and more useful probabilistic forecasts, and has great potential for practical application in power systems. [ABSTRACT FROM AUTHOR]

Existing convolutional neural network (CNN)-based and vision Transformer (ViT)-based image restoration methods are usually explored in the spatial domain. However, we employ Fourier analysis to show that these spatial domain models cannot perceive the entire frequency spectrum of images, i.e., mainly focus on either high-frequency (CNN-based models) or low-frequency components (ViT-based models). This intrinsic limitation results in the partial missing of semantic information and the appearance of artifacts. To address this limitation, we propose a novel uncertainty-guided hierarchical frequency domain Transformer named HFDT to effectively learn both high and low-frequency information while perceiving local and global features. Specifically, to aggregate semantic information from various frequency levels, we propose a dual-domain feature interaction mechanism, in which the global frequency information and local spatial features are extracted by corresponding branches. The frequency domain branch adopts the Fast Fourier Transform (FFT) to convert the features from the spatial domain to the frequency domain, where the global low and high-frequency components are learned with Log-linear complexity. Complementarily, an efficient convolution group is employed in the spatial domain branch to capture local high-frequency details. Moreover, we introduce an uncertainty degradation-guided strategy to efficiently represent degraded prior information, rather than simply distinguishing degraded/non-degraded regions in binary form. Our approach achieves competitive results in several degraded scenarios, including rain streaks, raindrops, motion blur, and defocus blur. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is one of the fundamental tasks in HSI analysis. Recently, many approaches have been extensively studied to improve the classification performance, among which integrating the spatial information underlying HSIs is a simple yet effective way. However, most of the current approaches haven't fully exploited the spatial information prior. They usually consider this prior either in the step of extracting spatial feature before classification or in the step of post-processing label map after classification, while don't integratively employ the prior in both steps, which thus leaves a room for further enhancing their performance. In this paper, we propose a novel spectral-spatial HSI classification method, which fully utilizes the spatial information in both steps. Firstly, the spatial feature is extracted by applying the 3-dimensional discrete wavelet transform (3D-DWT). Secondly, the local spatial correlation of neighboring pixels is modeled using Markov random field (MRF) based on the probabilistic classification map obtained by applying probabilistic support vector machine (SVM) to the extracted 3D-DWT feature in the first step, and then a maximum a posterior (MAP) classification problem can be formulated in a Bayesian perspective. Finally, α -Expansion min-cut-based optimization algorithm is adopted to solve this MAP problem efficiently. Experimental results on two benchmark HSIs show that the proposed method achieves a significant performance gain beyond state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As a convex relaxation of the rank minimization model, the nuclear norm minimization (NNM) problem has been attracting significant research interest in recent years. The standard NNM regularizes each singular value equally, composing an easily calculated convex norm. However, this restricts its capability and flexibility in dealing with many practical problems, where the singular values have clear physical meanings and should be treated differently. In this paper we study the weighted nuclear norm minimization (WNNM) problem, which adaptively assigns weights on different singular values. As the key step of solving general WNNM models, the theoretical properties of the weighted nuclear norm proximal (WNNP) operator are investigated. Albeit nonconvex, we prove that WNNP is equivalent to a standard quadratic programming problem with linear constrains, which facilitates solving the original problem with off-the-shelf convex optimization solvers. In particular, when the weights are sorted in a non-descending order, its optimal solution can be easily obtained in closed-form. With WNNP, the solving strategies for multiple extensions of WNNM, including robust PCA and matrix completion, can be readily constructed under the alternating direction method of multipliers paradigm. Furthermore, inspired by the reweighted sparse coding scheme, we present an automatic weight setting method, which greatly facilitates the practical implementation of WNNM. The proposed WNNM methods achieve state-of-the-art performance in typical low level vision tasks, including image denoising, background subtraction and image inpainting. [ABSTRACT FROM AUTHOR]

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. A list of important papers discussed in this survey, corresponding codes, and additional resources on BLOs are publicly available at: https://github.com/vis-opt-group/BLO. [ABSTRACT FROM AUTHOR]

A dynamically weighted directed network (DWDN) is frequently encountered in various big data-related applications like a terminal interaction pattern analysis system (TIPAS) concerned in this study. It consists of large-scale dynamic interactions among numerous nodes. As the involved nodes increase drastically, it becomes impossible to observe their full interactions at each time slot, making a resultant DWDN High Dimensional and Incomplete (HDI). An HDI DWDN, in spite of its incompleteness, contains rich knowledge regarding involved nodes’ various behavior patterns. To extract such knowledge from an HDI DWDN, this paper proposes a novel Alternating direction method of multipliers (ADMM)-based Nonnegative Latent-factorization of Tensors (ANLT) model. It adopts three-fold ideas: a) building a data density-oriented augmented Lagrangian function for efficiently handling an HDI tensor's incompleteness and nonnegativity; b) splitting the optimization task in each iteration into an elaborately designed subtask series where each one is solved based on the previously solved ones following the ADMM principle to achieve fast convergence; and c) theoretically proving that its convergence is guaranteed with its efficient learning scheme. Experimental results on six DWDNs from real applications demonstrate that the proposed ANLT outperforms state-of-the-art models significantly in both computational efficiency and prediction accuracy for missing links of an HDI DWDN. Hence, this study proposes a novel and efficient approach to large-scale DWDN representation. [ABSTRACT FROM AUTHOR]

A dynamically weighted directed network (DWDN) is frequently encountered in various big data-related applications like a terminal interaction pattern analysis system (TIPAS) concerned in this study. It consists of large-scale dynamic interactions among numerous nodes. As the involved nodes increase drastically, it becomes impossible to observe their full interactions at each time slot, making a resultant DWDN High Dimensional and Incomplete (HDI). An HDI DWDN, in spite of its incompleteness, contains rich knowledge regarding involved nodes’ various behavior patterns. To extract such knowledge from an HDI DWDN, this paper proposes a novel Alternating direction method of multipliers (ADMM)-based Nonnegative Latent-factorization of Tensors (ANLT) model. It adopts three-fold ideas: a) building a data density-oriented augmented Lagrangian function for efficiently handling an HDI tensor's incompleteness and nonnegativity; b) splitting the optimization task in each iteration into an elaborately designed subtask series where each one is solved based on the previously solved ones following the ADMM principle to achieve fast convergence; and c) theoretically proving that its convergence is guaranteed with its efficient learning scheme. Experimental results on six DWDNs from real applications demonstrate that the proposed ANLT outperforms state-of-the-art models significantly in both computational efficiency and prediction accuracy for missing links of an HDI DWDN. Hence, this study proposes a novel and efficient approach to large-scale DWDN representation. [ABSTRACT FROM AUTHOR]

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. A list of important papers discussed in this survey, corresponding codes, and additional resources on BLOs are publicly available at: https://github.com/vis-opt-group/BLO. [ABSTRACT FROM AUTHOR]

Tobacco is a cash crop throughout the world, and its growth and development are affected by abiotic stresses including drought stress; therefore, drought-tolerant breeding may help to improve tobacco yield and quality under drought stress conditions. Considering that the plant hormone ABA (abscisic acid) is able to regulate plant responses to abiotic stresses via activating ABA response genes, the characterization of ABA response genes may enable the identification of genes that can be used for molecular breeding to improve drought tolerance in tobacco. We report here the identification of NtAITRs (Nicotiana tabacum ABA-induced transcription repressors) as a family of novel regulators of drought tolerance in tobacco. Bioinformatics analysis shows that there are a total of eight NtAITR genes in tobacco, and all the NtAITRs have a partially conserved LxLxL motif at their C-terminus. RT-PCR results show that the expression levels of at least some NtAITRs were increased in response to ABA and drought treatments, and NtAITRs, when recruited to the Gal4 promoter via a fused GD (Gal4 DNA-binding domain), were able to repress transcription activator LD-VP activated expression of the LexA-Gal4-GUS reporter gene. Roles of NtAITRs in regulating drought tolerance in tobacco were analyzed by generating CRISPR/Cas9 gene-edited mutants. A total of three Cas9-free ntaitr12356 quintuple mutants were obtained, and drought treatment assays show that drought tolerance was increased in the ntaitr12356 quintuple mutants. On the other hand, results of seed germination and seedling greening assays show that ABA sensitivity was increased in the ntaitr12356 quintuple mutants, and the expression levels of some ABA signaling key regulator genes were altered in the ntaitr12356-c3 mutant. Taken together, our results suggest that NtAITRs are ABA-responsive genes, and that NtAITRs function as transcription repressors and negatively regulate drought tolerance in tobacco, possibly by affecting plant ABA response via affecting the expression of ABA signaling key regulator genes. [ABSTRACT FROM AUTHOR]

Tissue segmentation is an essential task in computational pathology. However, relevant datasets for such a pixel-level classification task are hard to obtain due to the difficulty of annotation, bringing obstacles for training a deep learning-based segmentation model. Recently, contrastive learning has provided a feasible solution for mitigating the heavy reliance of deep learning models on annotation. Nevertheless, applying contrastive loss to the most abstract image representations, existing contrastive learning frameworks focus on global features, therefore, are less capable of encoding finer-grained features (e.g., pixel-level discrimination) for the tissue segmentation task. Enlightened by domain knowledge, we design three contrastive learning tasks with multi-granularity views (from global to local) for encoding necessary features into representations without accessing annotations. Specifically, we construct: (1) an image-level task to capture the difference between tissue components, i.e., encoding the component discrimination; (2) a superpixel-level task to learn discriminative representations of local regions with different tissue components, i.e., encoding the prototype discrimination; (3) a pixel-level task to encourage similar representations of different tissue components within a local region, i.e., encoding the spatial smoothness. Through our global-to-local pre-training strategy, the learned representations can reasonably capture the domain-specific and fine-grained patterns, making them easily transferable to various tissue segmentation tasks in histopathological images. We conduct extensive experiments on two tissue segmentation datasets, while considering two real-world scenarios with limited or sparse annotations. The experimental results demonstrate that our framework is superior to existing contrastive learning methods and can be easily combined with weakly supervised and semi-supervised segmentation methods. [ABSTRACT FROM AUTHOR]