Search

In this article, a simple yet effective method, called a two-phase learning-based swarm optimizer (TPLSO), is proposed for large-scale optimization. Inspired by the cooperative learning behavior in human society, mass learning and elite learning are involved in TPLSO. In the mass learning phase, TPLSO randomly selects three particles to form a study group and then adopts a competitive mechanism to update the members of the study group. Then, we sort all of the particles in the swarm and pick out the elite particles that have better fitness values. In the elite learning phase, the elite particles learn from each other to further search for more promising areas. The theoretical analysis of TPLSO exploration and exploitation abilities is performed and compared with several popular particle swarm optimizers. Comparative experiments on two widely used large-scale benchmark datasets demonstrate that the proposed TPLSO achieves better performance on diverse large-scale problems than several state-of-the-art algorithms.

In recent years, hashing learning has received increasing attention in supervised video retrieval. However, most existing supervised video hashing approaches design hash functions based on pairwise similarity or triple relationships and focus on local information, which results in low retrieval accuracy. In this work, we propose a novel supervised framework called discriminative codebook hashing (DCH) for large-scale video retrieval. The proposed DCH encourages samples within the same category to converge to the same code word and maximizes the mutual distances among different categories. Specifically, we first propose the discriminative codebook via a predefined distance among intercode words and Bernoulli distributions to handle each hash bit. Then, we use the composite Kullback-Leibler (KL) divergence to align the neighborhood structures between the high-dimensional space and the Hamming space. The proposed DCH is optimized via the gradient descent algorithm. Experimental results on three widely used video datasets verify that our proposed DCH performs better than several state-of-the-art methods., Competing Interests: The authors declare that there are no conflicts of interest in the publication of this paper., (Copyright © 2021 Xiaoman Bian et al.)

A pure acoustic signal can be easy to realize signal analysis and feature extraction. However, the surrounding noises will affect the content of acoustic signals as well as auditory fatigue to the audience. Therefore, it is vital to overcome the problem of noises that affect the acoustic signal. An indoor acoustic signal enhanced method based on image source (IS) method, filtered-x least mean square (FxLMS) algorithm, and the combination of Delaunay triangulation and fuzzy c-means (FCM) clustering algorithm is proposed. In the first stage of the proposed system, the IS method was used to simulate indoor impulse response. Next, the FxLMS algorithm was used to reduce the acoustic signals with noise. Lastly, the quiet areas are optimized and visualized by combining the Delaunay triangulation and FCM clustering algorithm. The experimental analysis results on the proposed system show that better noise reduction can be achieved than the most widely used least mean square algorithm. Visualization was validated with an intuitive understanding of the indoor sound field distribution and the quiet areas., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2021 Suqing Yan et al.)

Rank minimization is a key component of many computer vision and machine learning methods, including robust principal component analysis (RPCA) and low-rank representations (LRR). However, usual methods rely on optimization to produce a point estimate without characterizing uncertainty in this estimate, and also face difficulties in tuning parameter choice. Both of these limitations are potentially overcome with Bayesian methods, but there is currently a lack of general purpose Bayesian approaches for rank penalization. We address this gap using a positive generalized double Pareto prior, illustrating the approach in RPCA and LRR. Posterior computation relies on hybrid Gibbs sampling and geodesic Monte Carlo algorithms. We assess performance in simulation examples, and benchmark data sets., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

Motivation: Diagrams embedded in the biomedical literature convey rich contents, which often concisely and intuitively highlight key thesis of a research article. Despite their vital importance and informative clues for biomedical literature navigation and retrieval; currently, we miss an effective computational method for automatically understanding and accessing these valuable resources., Proposed Method: To address the aforementioned gap, we propose a novel context-based algorithm for estimating the similarity between a pair of biomedical diagrams. The main difference of the proposed algorithm with respect to the existing methods lies in the new algorithm's incorporation of the semantic context associated with diagrams in their source documents into the diagram similarity estimation process. In addition, the new approach also performs a series of advanced image processing and text mining operations to comprehensively extract the semantic content graphically encoded inside diagram images., Results: The new algorithm can be deployed as a reusable component providing a fundamental function for building many advanced, semantic-aware applications on biomedical diagram processing. As a case study, in our experiments, we demonstrate the advantage of the new algorithm for diagram retrieval. A set of biomedical diagram search and ranking experiments were conducted, where the performance of the new method was compared with that of five peer methods. The comparison results demonstrate the performance superiority of the new algorithm with all peer methods with statistical significance.

Background: Images embedded in biomedical publications carry rich information that often concisely summarize key hypotheses adopted, methods employed, or results obtained in a published study. Therefore, they offer valuable clues for understanding main content in a biomedical publication. Prior studies have pointed out the potential of mining images embedded in biomedical publications for automatically understanding and retrieving such images' associated source documents. Within the broad area of biomedical image processing, categorizing biomedical images is a fundamental step for building many advanced image analysis, retrieval, and mining applications. Similar to any automatic categorization effort, discriminative image features can provide the most crucial aid in the process., Method: We observe that many images embedded in biomedical publications carry versatile annotation text. Based on the locations of and the spatial relationships between these text elements in an image, we thus propose some novel image features for image categorization purpose, which quantitatively characterize the spatial positions and distributions of text elements inside a biomedical image. We further adopt a sparse coding representation (SCR) based technique to categorize images embedded in biomedical publications by leveraging our newly proposed image features., Results: we randomly selected 990 images of the JPG format for use in our experiments where 310 images were used as training samples and the rest were used as the testing cases. We first segmented 310 sample images following the our proposed procedure. This step produced a total of 1035 sub-images. We then manually labeled all these sub-images according to the two-level hierarchical image taxonomy proposed by 1. Among our annotation results, 316 are microscopy images, 126 are gel electrophoresis images, 135 are line charts, 156 are bar charts, 52 are spot charts, 25 are tables, 70 are flow charts, and the remaining 155 images are of the type "others". A serial of experimental results are obtained. Firstly, each image categorizing results is presented, and next image categorizing performance indexes such as precision, recall, F-score, are all listed. Different features which include conventional image features and our proposed novel features indicate different categorizing performance, and the results are demonstrated. Thirdly, we conduct an accuracy comparison between support vector machine classification method and our proposed sparse representation classification method. At last, our proposed approach is compared with three peer classification method and experimental results verify our impressively improved performance., Conclusions: Compared with conventional image features that do not exploit characteristics regarding text positions and distributions inside images embedded in biomedical publications, our proposed image features coupled with the SR based representation model exhibit superior performance for classifying biomedical images as demonstrated in our comparative benchmark study.

In challenging scenarios (e.g., small objects and cluttered backgrounds), most existing algorithms suffer from inconsistent results with human visual attention. Since fixation prediction can better model the human visual attention mechanism and has a strong correlation with salient objects. Inspired by this, we proposed a fixation guidance network (FGNet) for salient object detection, which innovatively used fixation prediction to guide both salient object detection and edge detection. Firstly, a multi-branch network structure was designed to achieve multi-task detection. Each branch unit significantly learned the extracted features to accomplish the correct prediction. Secondly, given the strong correlation between the fixation and salient objects, a fixation guidance module was employed to guide salient object detection and edge detection for obtaining more accurate detection results. Finally, to full use the complementary relationship between salient features and edge features, we proposed a multi-resolution feature interaction module to achieve mutual optimization within the same feature and between the different features for suppressing noise and enhancing their representations. The experimental results show that our proposed method performed better in challenging scenes and outperformed existing state-of-the-art algorithms in several metrics on four public benchmark datasets. [ABSTRACT FROM AUTHOR]

To accurately detect small defects in urine test strips, the SK-FMYOLOV3 defect detection algorithm is proposed. First, the prediction box clustering algorithm of YOLOV3 is improved. The fuzzy C-means clustering algorithm is used to generate the initial clustering centers, and then, the clustering center is passed to the K-means algorithm to cluster the prediction boxes. To better detect smaller defects, the YOLOV3 feature map fusion is increased from the original three-scale prediction to a four-scale prediction. At the same time, 23 convolutional layers of size 3 × 3 in the YOLOV3 network are replaced with SkNet structures, so that different feature maps can independently select different convolution kernels for training, improving the accuracy of defect classification. We collected and enhanced urine test strip images in industrial production and labeled the small defects in the images. A total of 11634 image sets were used for training and testing. The experimental results show that the algorithm can obtain an anchor frame with an average cross ratio of 86.57, while the accuracy rate and recall rate of nonconforming products are 96.8 and 94.5, respectively. The algorithm can also accurately identify the category of defects in nonconforming products. [ABSTRACT FROM AUTHOR]

This paper presents a two-stage approach, named Cooperatively Coevolving Competition Swarm Optimiser (C3SO), for large-scale optimisation. C3SO first detects interactions among the original variables by a differential grouping algorithm, therein decomposing a large-scale problem into several sub-components. In the next stage, a new approach is developed using the competition mechanism to independently optimise each sub-component obtained in the first stage. Hence, C3SO takes advantages of both divide-and-conquer and competition strategies, achieving the ability to address large-scale and complex optimisation problems. The proposed method is evaluated by comparing with several state-of-the-art algorithms on different benchmark functions, and the comparative results demonstrated its effectiveness. [ABSTRACT FROM AUTHOR]

Ray-casting algorithm is an important volume rendering algorithm, which is widely used in medical image processing. Aiming to address the shortcomings of the current ray-casting algorithms in 3D reconstruction of medical images, such as slow rendering speed and low sampling efficiency, an improved algorithm based on dynamic adaptive sampling is proposed. By using the central difference gradient method, the corresponding sampling interval is obtained dynamically according to the different sampling points. Meanwhile, a new rendering operator is proposed based on the color value and opacity changes before and after the ray enters the volume element, and the resistance luminosity. Compared with the state of other algorithms, experimental results show that the method proposed in this paper has a faster rendering speed while ensuring the quality of the generated image. [ABSTRACT FROM AUTHOR]

Image Ranking is one of the key problems in information science research area. However, most current methods focus on increasing the performance, leaving the semantic gap problem, which refers to the learned ranking models are hard to be understood, remaining intact. Therefore, in this article, we aim at learning an interpretable ranking model to tackle the semantic gap in fine‐grained image ranking. We propose to combine attribute‐based representation and online passive‐aggressive (PA) learning based ranking models to achieve this goal. Besides, considering the highly localized instances in fine‐grained image ranking, we introduce a supervised constrained clustering method to gather class‐balanced training instances for local PA‐based models, and incorporate the learned local models into a unified probabilistic framework. Extensive experiments on the benchmark demonstrate that the proposed framework outperforms state‐of‐the‐art methods in terms of accuracy and speed. [ABSTRACT FROM AUTHOR]

Attribute-based approaches have recently attracted much attention in visual recognition tasks. These approaches describe images by using semantic attributes as the mid-level feature. However, low recognition accuracy becomes the biggest barrier that limits their practical applications. In this paper, we propose a novel framework termed Boosting Attribute Recognition (BAR) for the image recognition task. Our framework stems from matrix factorization, and can explore latent relationships from the aspect of attribute and image simultaneously. Furthermore, to apply our framework in large-scale visual recognition tasks, we present both offline and online learning implementation of the proposed framework. Extensive experiments on 3 data sets demonstrate that our framework achieves a sound accuracy of attribute recognition. [ABSTRACT FROM AUTHOR]

We propose a new nonrigid registration algorithm which is based on the optimal control approach. In our previously proposed methods, the Jacobian determinant and the curl vector were used as control functions. In this algorithm, we use a new set of control functions. A main advantage of using the new controls is that the positivity and normalization of the Jacobian determinant are satisfied automatically. Numerical results on large deformation brain images are provided to show the accuracy and efficiency of the algorithm. [ABSTRACT FROM AUTHOR]

Abstract: A new progressive compression algorithm for arbitrary topology with highly detailed triangle meshes is proposed in this paper. We firstly parameterize the original triangle mesh to a regular quadrilateral approximation. A wavelet transform is then applied to the approximation to remove a large amount of correlation between neighboring vertices. Finally, we used low cost zerotree coding and subdivision based reconstruction to build a sequence of progressive models. Our method will greatly reduce the cost of transportation with acceptable quality loss as shown in the experimental results. [Copyright &y& Elsevier]

Abstract: We discuss a better higher-order finite difference algorithm for solving dynamic heat and moisture transport equations of fabric. The algorithm is fourth-order accurate in spatial dimensions and second-order in time derivatives. We use central-difference operator for the second space derivatives in the 2D model. It is similar to that used in the standard second-order algorithms, such as the Crank–Nicolson algorithm. Numerical simulation results agree with the real case. [Copyright &y& Elsevier]

Abstract: This paper presents a new algorithm to simulate 2D transient heat and moisture transport behavior through fabric. We established a 3D geometric fiber model first, and the fibers are anisotropic. The new model is deduced by the mass and energy conservation, capillary phenomenon. We use finite-difference time-domain to solve the partial differential equations. It describes the physical mechanisms of heat and moisture transfer in fabric, providing detailed information of the transferring process in fibrous media. The simulation results demonstrate that the new method is relatively accurate and easily implemented. [Copyright &y& Elsevier]

Small scale face detection is a very difficult problem. In order to achieve a higher detection accuracy, we propose a novel method, termed SE-IYOLOV3, for small scale face in this work. In SE-IYOLOV3, we improve the YOLOV3 first, in which the anchorage box with a higher average intersection ratio is obtained by combining niche technology on the basis of the k-means algorithm. An upsampling scale is added to form a face network structure that is suitable for detecting dense small scale faces. The number of prediction boxes is five times more than the YOLOV3 network. To further improve the detection performance, we adopt the SENet structure to enhance the global receptive field of the network. The experimental results on the WIDERFACEdataset show that the IYOLOV3 network embedded in the SENet structure can significantly improve the detection accuracy of dense small scale faces. [ABSTRACT FROM AUTHOR]

At present, most Chinese text summarization algorithms use the sequence-to-sequence model, but this model is prone to the problems of unknown words and incomplete content generation. To address these problems, we propose a new two-stage automatic text summarization method using keyword information and adversarial learning in this paper. On the one hand, the proposed method integrates the keyword information into the sequence-to-sequence model. The main information and keywords of the article are considered simultaneously through the attention mechanism to improve the information of summary generation. On the other hand, adversarial learning is introduced into the proposed model to avoid the problem that the semantic vector after passing through the encoder cannot save the context information better. Experiments are carried out on the Chinese dataset LCSTS, and the comparison results show that the proposed method has advantages in abstractive summarization. [ABSTRACT FROM AUTHOR]

Abstract: In this paper we present a novel fast mesh parameterization algorithm based on subdivision scheme. First, an algorithm of approximating a given triangular mesh by the 4-point interpolatory subdivision is proposed, then a mesh parameterization method is developed based on the subdivision surface approximation algorithm. The novel mesh parameterization method is a generalization of the chordal parameterization to surface case, and it is more computationally efficient than previous methods because it obviates any computation of linear system of equations. Some numerical experiments show the efficiency of the novel algorithm. [Copyright &y& Elsevier]