Multi-resolution Network Research Articles

Single\u2010cell transcriptomic landscape reveals the differences in cell differentiation and immune microenvironment of papillary thyroid carcinoma between genders

BackgroundPapillary thyroid carcinoma (PTC) is the main pathological type of thyroid carcinoma (TC). Gender is a prominent background parameter for patients with PTC. Here, we aimed to delineate the differences in cell clusters and immune microenvironment in relation to gender in PTC.Methods We generated 6720, 14,666, and 33,373 single-cell transcriptomes that were pooled from the tissues of four male patients with PTC, seven female patients with PTC, and three patients with nodular goiter, respectively. We performed single-cell RNA-sequencing (scRNA-seq) based on BD Rhapsody and characterized the first single-cell transcriptomic landscape of PTC involving gender. The differential cell clusters and their gene profiles were identified and analyzed via a multi-resolution network in male and female patients. The interactions of fibroblasts and endothelial cells with malignant epithelial cells and the difference in the immune infiltration of B and T lymphocytes according to gender were assessed.ResultsMalignant epithelial cells were divided into two distinct subsets in male and female patients with PTC. Moreover, significant differences involving inferred copy-number variations (CNVs), gene profiles, and cell differentiation were detected between male and female patients. Regarding the interactions of fibroblasts and endothelial cells with malignant epithelial cells, members of the human leukocyte antigen (HLA) family and their receptors were considered as typical in female patients with PTC, while transforming growth factor beta 1 (TGFB1) and its receptors were typical of male patients with PTC. The characteristics of B cells, including cell clusters, cell differentiation, and dominant gene sets, were significantly different between genders.ConclusionsOur data revealed the detailed differences in cell clusters and immune microenvironment in PTC according to gender at the single-cell level, which provided new insights into the understanding of the impact of gender on PTC.

A multi-channel uncertainty-aware multi-resolution network for MR to CT synthesis.

Synthesising computed tomography (CT) images from magnetic resonance images (MRI) plays an important role in the field of medical image analysis, both for quantification and diagnostic purposes. Convolutional neural networks (CNNs) have achieved state-of-the-art results in image-to-image translation for brain applications. However, synthesising whole-body images remains largely uncharted territory involving many challenges, including large image size and limited field of view, complex spatial context, and anatomical differences between images acquired at different times. We propose the use of an uncertainty-aware multi-channel multi-resolution 3D cascade network specifically aiming for whole-body MR to CT synthesis. The Mean Absolute Error on the synthetic CT generated with the MultiResunc network (73.90 HU) is compared to multiple baseline CNNs like 3D U-Net (92.89 HU), HighRes3DNet (89.05 HU) and deep boosted regression (77.58 HU) and shows superior synthesis performance. We ultimately exploit the extrapolation properties of the MultiRes networks on sub-regions of the body.

Method for Bridge Crack Detection Based on Multiresolution Network

Method for Bridge Crack Detection Based on Multiresolution Network

A multiresolution mixture generative adversarial network for video super-resolution.

Generative adversarial networks (GANs) have been used to obtain super-resolution (SR) videos that have improved visual perception quality and more coherent details. However, the latest methods perform poorly in areas with dense textures. To better recover the areas with dense textures in video frames and improve the visual perception quality and coherence in videos, this paper proposes a multiresolution mixture generative adversarial network for video super-resolution (MRMVSR). We propose a multiresolution mixture network (MRMNet) as the generative network that can simultaneously generate multiresolution feature maps. In MRMNet, the high-resolution (HR) feature maps can continuously extract information from low-resolution (LR) feature maps to supplement information. In addition, we propose a residual fluctuation loss function for video super-resolution. The residual fluctuation loss function is used to reduce the overall residual fluctuation on SR and HR video frames to avoid a scenario where local differences are too large. Experimental results on the public benchmark dataset show that our method outperforms the state-of-the-art methods for the majority of the test sets.

An Efficient Multiresolution Clustering for Motif Discovery in Complex Networks.

Motif discovery and network clustering in complex networks have received a lot of attention in recent years, also they are still challenging tasks in bioinformatics, big data analytics and data mining applications. Motif discovery in big data networks has a lot of important applications in different domains such as engineering, bioinformatics, cheminformatics, genomics, sociology and ecology for revealing hidden frequent structures, functional building blocks, or knowledge discovery. In this paper, a motif localization method based on a novel clustering algorithm in complex networks is presented. In our method, for each complex network, a novel structure so-called Augmented Multiresolution Network (AMN) is generated, then it is adaptively partitioned into several clusters and their corresponding subnets. Then top ranked subnets are chosen to discover network motifs. We show that the proposed method provides an efficient solution for clustering and motif discovery; It speeds up current motif discovery algorithms by pruning non-promising regions of complex networks. Experimental results show our algorithm efficiently deals with complex networks representing large datasets with high-dimensionality such as big scientific data. Our method also provides motivations for future studies in big data and complex networks.

Deep Binary Classification via Multi-Resolution Network and Stochastic Orthogonality for Subcompact Vehicle Recognition.

To encourage people to save energy, subcompact cars have several benefits of discount on parking or toll road charge. However, manual classification of the subcompact car is highly labor intensive. To solve this problem, automatic vehicle classification systems are good candidates. Since a general pattern-based classification technique can not successfully recognize the ambiguous features of a vehicle, we present a new multi-resolution convolutional neural network (CNN) and stochastic orthogonal learning method to train the network. We first extract the region of a bonnet in the vehicle image. Next, both extracted and input image are engaged to low and high resolution layers in the CNN model. The proposed network is then optimized based on stochastic orthogonality. We also built a novel subcompact vehicle dataset that will be open for a public use. Experimental results show that the proposed model outperforms state-of-the-art approaches in term of accuracy, which means that the proposed method can efficiently classify the ambiguous features between subcompact and non-subcompact vehicles.

An image super-resolution method for better cognition of images in cognition computing system

Data cognition plays an important role in cognitive computing. Cognition of low-resolution (LR) image is a long-stand problem because LR images have insufficient information about objects. For better cognition of LR images, a multi-resolution residual network (MRRN) is proposed to improve image resolution in this paper for cognitive computing systems. In MRRN, a multi-resolution feature learning (MRFL) strategy is introduced to achieve satisfying performance with low computational costs. Inspired by image pyramids, a feature pyramid is designed to implement multi-resolution feature learning in the building unit of the proposed MRRN. Specifically, multi-resolution residual units (MRRUs) are introduced as the building units of the proposed network, which consist of a feature pyramid decomposition stage and a feature reconstruction stage. To obtain informative features, transferred skip links (TSLs) are utilized to transfer fine-grain residual features in the pyramid decomposition stage to the reconstruction stage. The effectiveness of MRFL and TSL is demonstrated by ablation experiments. Also, the tests on standard benchmarks indicate the superiority of the proposed MRRN over other state-of-the-art methods.

Multiresolution Multiplex Network for Analyzing Multichannel Fluid Flow Signals

Gas-liquid two-phase flow widely exists in chemical industries and natural gas industries. But characterizing the nonlinear flow behaviors underlying such flow remains a challenge of great importance. In this brief, we first carry out the vertical gas-liquid two-phase flow experiment in a 50mm-inner-diameter pipe to acquire signals via the four-sector conductance measurement system. Then, we develop a multiresolution multiplex network (MMN) to analyze multichannel measurements. In particular, we employ average edge overlap to quantitatively characterize the derived network corresponding to different flow patterns. Results show that our method allows to effectively uncover the evolution from bubble flow to slug flow. In addition, we calculate the approximate entropy of different flow patterns to verify the findings from our network analysis. All the results demonstrate that our proposed method allows characterizing the nonlinear flow behaviors from multichannel measurements and also provides a novel way for multivariate time series analysis.

Gender classification using mesh networks on multiresolution multitask fMRI data.

Brain connectivity networks have been shown to represent gender differences under a number of cognitive tasks. Recently, it has been conjectured that fMRI signals decomposed into different resolutions embed different types of cognitive information. In this paper, we combine multiresolution analysis and connectivity networks to study gender differences under a variety of cognitive tasks, and propose a machine learning framework to discriminate individuals according to their gender. For this purpose, we estimate a set of brain networks, formed at different resolutions while the subjects perform different cognitive tasks. First, we decompose fMRI signals recorded under a sequence of cognitive stimuli into its frequency subbands using Discrete Wavelet Transform (DWT). Next, we represent the fMRI signals by mesh networks formed among the anatomic regions for each task experiment at each subband. The mesh networks are constructed by ensembling a set of local meshes, each of which represents the relationship of an anatomical region as a weighted linear combination of its neighbors. Then, we estimate the edge weights of each mesh by ridge regression. The proposed approach yields 2CL functional mesh networks for each subject, where C is the number of cognitive tasks and L is the number of subband signals obtained after wavelet decomposition. This approach enables one to classify gender under different cognitive tasks and different frequency subbands. The final step of the suggested framework is to fuse the complementary information of the mesh networks for each subject to discriminate the gender. We fuse the information embedded in mesh networks formed for different tasks and resolutions under a three-level fuzzy stacked generalization (FSG) architecture. In this architecture, different layers are responsible for fusion of diverse information obtained from different cognitive tasks and resolutions. In the experimental analyses, we use Human Connectome Project task fMRI dataset. Results reflect that fusing the mesh network representations computed at multiple resolutions for multiple tasks provides the best gender classification accuracy compared to the single subband task mesh networks or fusion of representations obtained using only multitask or only multiresolution data. Besides, mesh edge weights slightly outperform pairwise correlations between regions, and significantly outperform raw fMRI signals. In addition, we analyze the gender discriminative power of mesh edge weights for different tasks and resolutions.

Multiresolution Network Models

ABSTRACTMany existing statistical and machine learning tools for social network analysis focus on a single level of analysis. Methods designed for clustering optimize a global partition of the graph, whereas projection-based approaches (e.g., the latent space model in the statistics literature) represent in rich detail the roles of individuals. Many pertinent questions in sociology and economics, however, span multiple scales of analysis. Further, many questions involve comparisons across disconnected graphs that will, inevitably be of different sizes, either due to missing data or the inherent heterogeneity in real-world networks. We propose a class of network models that represent network structure on multiple scales and facilitate comparison across graphs with different numbers of individuals. These models differentially invest modeling effort within subgraphs of high density, often termed communities, while maintaining a parsimonious structure between said subgraphs. We show that our model class is projective, highlighting an ongoing discussion in the social network modeling literature on the dependence of inference paradigms on the size of the observed graph. We illustrate the utility of our method using data on household relations from Karnataka, India. Supplementary material for this article is available online.

Cumulative inhibition in neural networks

We show how a multi-resolution network can model the development of acuity and coarse-to-fine processing in the mammalian visual cortex. The network adapts to input statistics in an unsupervised manner, and learns a coarse-to-fine representation by using cumulative inhibition of nodes within a network layer. We show that a system of such layers can represent input by hierarchically composing larger parts from smaller components. It can also model aspects of top-down processes, such as image regeneration.

Multi-resolution networks for ship detection in infrared remote sensing images

Ship detection is a hot point of remote sensing image processing and analysis. Most current methods merely utilize a single resolution image and cannot take full advantage of registered multi-resolution images. In this paper, we proposed a novel ship detection method for multi-resolution infrared remote sensing images based on convolutional neural networks. With a specially designed layer of various size kernels, our net takes in registered multi-resolution images simultaneously, extracting more robust features and gives a more accurate detection result. Besides, as ship targets only occupy a few pixels in an infrared remote sensing image, to handle the extreme background-foreground imbalance problem in infrared remote sensing images, we introduce the focal loss to train our net. Compared with classical methods, experiments on visible bands and infrared bands of Landsat-8 satellite images demonstrate the effectiveness of our method.

Identification of multi-resolution network structures with multi-objective immune algorithm

Community structure is one of the most important properties in complex networks, and the field of community detection has received an enormous amount of attention in the past several years. Many quality metrics and methods have been proposed for revealing community structures at multiple resolution levels, while most existing methods need a tunable parameter in their quality metrics to determine the resolution level in advance. In this study, a multi-objective evolutionary algorithm (MOEA) for revealing multi-resolution community structures is proposed. The proposed MOEA-based community detection algorithm aims to find a set of tradeoff solutions which represent network partitions at different resolution levels in a single run. It adopts an efficient multi-objective immune algorithm to simultaneously optimize two contradictory objective functions, Modified Ratio Association and Ratio Cut. The optimization of Modified Ratio Association tends to divide a network into small communities, while the optimization of Ratio Cut tends to divide a network into large communities. The simultaneous optimization of these two contradictory objectives returns a set of tradeoff solutions between the two objectives. Each of these solutions corresponds to a network partition at one resolution level. Experiments on artificial and real-world networks show that the proposed method has the ability to reveal community structures of networks at different resolution levels in a single run.

Multiresolution Network Temporal and Spatial Scheduling Model of Scenic Spot

Tourism is one of pillar industries of the world economy. Low-carbon tourism will be the mainstream direction of the scenic spots' development, and theωpath of low-carbon tourism development is to develop economy and protect environment simultaneously. However, as the tourists' quantity is increasing, the loads of scenic spots are out of control. And the instantaneous overload in some spots caused the image phenomenon of full capacity of the whole scenic spot. Therefore, realizing the real-time schedule becomes the primary purpose of scenic spot’s management. This paper divides the tourism distribution system into several logically related subsystems and constructs a temporal and spatial multiresolution network scheduling model according to the regularity of scenic spots’ overload phenomenon in time and space. It also defines dynamic distribution probability and equivalent dynamic demand to realize the real-time prediction. We define gravitational function between fields and takes it as the utility of schedule, after resolving the transportation model of each resolution, it achieves hierarchical balance between demand and capacity of the system. The last part of the paper analyzes the time complexity of constructing a multiresolution distribution system.

Detecting hidden spatial and spatio-temporal structures in glasses and complex physical systems by multiresolution network clustering

We elaborate on a general method that we recently introduced for characterizing the "natural" structures in complex physical systems via multi-scale network analysis. The method is based on "community detection" wherein interacting particles are partitioned into an "ideal gas" of optimally decoupled groups of particles. Specifically, we construct a set of network representations ("replicas") of the physical system based on interatomic potentials and apply a multiscale clustering ("multiresolution community detection") analysis using information-based correlations among the replicas. Replicas may i) be different representations of an identical static system, ii) embody dynamics by considering replicas to be time separated snapshots of the system (with a tunable time separation), or iii) encode general correlations when different replicas correspond to different representations of the entire history of the system as it evolves in space-time. Inputs for our method are the inter-particle potentials or experimentally measured two (or higher order) particle correlations. We apply our method to computer simulations of a binary Kob-Andersen Lennard-Jones system in a mixture ratio of A(80)B(20) , a ternary model system with components "A", "B", and "C" in ratios of A(88)B(7)C(5) (as in Al(88)Y(7)Fe(5) , and to atomic coordinates in a Zr(80)Pt(20) system as gleaned by reverse Monte Carlo analysis of experimentally determined structure factors. We identify the dominant structures (disjoint or overlapping) and general length scales by analyzing extrema of the information theory measures. We speculate on possible links between i) physical transitions or crossovers and ii) changes in structures found by this method as well as phase transitions associated with the computational complexity of the community detection problem. We also briefly consider continuum approaches and discuss rigidity and the shear penetration depth in amorphous systems; this latter length scale increases as the system becomes progressively rigid.

A New Multi-Resolution Wavelet Neural Network For Bridge Health Monitoring

Abstract Anew multi-resolution wavelet network for bridge health monitoring is proposed in this paper, which has one hidden layer and multiple outputs. In this network, training data and forecasting data collected from bridge health monitoring are important factors in determining structure. By learning algorithm the finite wavelets and scaling functions are selected for the active function. All outputs vary from the coarsest resolution to the finest one. The theoretical analysis shows that the finest output convergence becomes uniformly.

A new directional multi-resolution ridgelet network

In this paper, a directional multi-resolution ridgelet network (DMRN) is proposed based on ridgelet theory. By using ridgelet as the activation function, DMRN has great capabilities in catching essential features of "direction-rich" data for its multi-resolution property in direction besides scale and position. It proves to be able to approximate any multivariate function in a more stable and efficient way, and is optimal in approximating functions with spatial inhomogeneities. Using binary ridgelet frame for its design, DMRN is characteristic of more flexible structure. Possibilities of applications to regression and recognition are included to demonstrate its superiority.

Geometrical multi-resolution network based on ridgelet frame

Ridgelet has multi-resolution properties in direction besides scale and position. This paper proposes a geometrical multi-resolution network (GMN) based on ridgelet frame by taking ridgelet as the activation function in the hidden layer. For ridgelet is efficient in describing line, hyperplane, and other non-point like structures in high dimension, the network is capable of catching essential features in ‘direction-rich’ signals and thus representing high-dimensional data sparsely. With the binary ridgelet frame providing the foundation for designation, the network is characteristic of more flexible structure and more accurate description of directions. The construction and learning of the network are presented, as well as a theoretical analysis on its approximation property. At last, the superiority of GMN is demonstrated by simulation results of regression and classification.

Multiresolution edge detection based on modified bubble function and SWT

A new way based on a modified bubble function and stationary wavelet transform (SWT) is proposed to solve the problem that the conventional edge detection algorithms are sensitive to the noises. Firstly, the traditional bubble function is modified in order to get different time-frequency domain responses and to get filtering effects through adjusting the parameters. Secondly, the modified bubble function is combined with SWT to construct a multiresolution network. By using the modified bubble function to enhance the edges and by using SWT to reduce the noises, the edges can be extracted accurately, effectively and quickly with lower noise. Finally, the experimental results of the proposed edge detection algorithm are verified to be better than that with the traditional bubble function.

Network flow optimization for restoration of images

The network flow optimization approach is offered for restoration of gray‐scale and color images corrupted by noise. The Ising models are used as a statistical background of the proposed method. We present the new multiresolution network flow minimum cut algorithm, which is especially efficient in identification of the maximum a posteriori (MAP) estimates of corrupted images. The algorithm is able to compute the MAP estimates of large‐size images and can be used in a concurrent mode. We also consider the problem of integer minimization of two functions, U1(x) = λ∑i|yi − xi|+∑i,j βi,j|xi − xj| and , with parameters λ, λi, βi,j > 0 and vectors x = (x1, …, xn), y = (y1, …, yn) ∈ {0,…,L−1}n. Those functions constitute the energy ones for the Ising model of color and gray‐scale images. In the case L = 2, they coincide, determining the energy function of the Ising model of binary images, and their minimization becomes equivalent to the network flow minimum cut problem. The efficient integer minimization of U1(x), U2(x) by the network flow algorithms is described.