Asymmetric Network Research Articles

APAFNet: Single-Frame Infrared Small Target Detection by Asymmetric Patch Attention Fusion

Single-frame infrared small target (SIRST) detection has been applied in many civilian and military applications and has greatly developed since deep-learning methods grow in recent years. However, the contradiction between semantic information and spatial details limits detection performance, especially for dim and small targets with complex interference. To overcome the restrictions, we propose an asymmetric patch attention fusion network (APAFNet) in this letter to merge high-level semantics and low-level spatial details, which consists of an APAF module based on a patch channel attention branch and a dilation context block, guiding the network to collect local semantics and spatial details. The experimental results on the NUAA-SIRST dataset and IRSTD-1k dataset show that the proposed APAFNet can achieve excellent performance under complex backgrounds.

An End-to-End Approach for Rigid-Body Target Micro-Doppler Analysis Based on the Asymmetrical Autoencoding Network

Micro-Doppler analysis of rigid-body target is significant for attitude estimation and recognition of space objects. The traditional micro-Doppler analysis method for rigid-body targets includes two sequential steps. First, the time-frequency analysis is performed on the radar echo data of the target, and then the micro-Doppler curve of each scattering center is separated and extracted from the time-frequency map. The second step depends on the micro motion model of the target. In the micro-Doppler analysis of real rigid-body target, there are some problems such as the mismatch of the micro motion model, the incidence angle dependence of the scattering center position, and the partial occlusion of the scattering center. Therefore, it is very difficult to correctly extract the micro-Doppler curves of multiple scatterers. In this paper, an end-to-end micro-Doppler analysis method for rigid-body target based on deep learning network is proposed, which can directly separate and extract the micro-Doppler curves of multiple scatterers from the target echo data. Specifically, an Asymmetrical AutoEncoding (A2E) network equipped with a Data Pre-Processing (DP2) module is developed to extract Time-Frequency Curves (TFCs) from radar echos. Considering the sparseness of Time-Frequency Distribution (TFDs), we then develop a novel Energy-Concentration Objective (ECO) function based on Min-Max game to enhance curves energy while suppress the background energy. In practice, measured TFDs are rarely annotated, it restricts the generalization capability of the A2E from the simulation to the measurement. To bridge the gap, two-fold modifications are finally constructed: i) we insert a partial-shared branch of decoder to reconstruct the TFD from the DP2 module; ii) we regularize the ECO function with a knowledge preservation based reconstruction bound to further capture the characteristics of measured echos in a semi-supervised way at test time to relieve the domain-shift problem.

ИССЛЕДОВАНИЕ ХАРАКТЕРИСТИК РАЗВЕРТЫВАЕМОЙ КОСМИЧЕСКОЙ ЗЕРКАЛЬНОЙ АНТЕННЫ С РАЗРЕЖЕННОЙ ОТРАЖАЮЩЕЙ ПОВЕРХНОСТЬЮ

The article presents the results of a study of the characteristics of a space parabolic mirror with a deployable reflector. A model of the reflector truss structure formed by two asymmetric parabolic networks with tension cables is presented. Three variants of the sparse structure of the reflecting film of the reflector are presented, differing in periodically repeating hexagonal holes with different sizes. A complex electrodynamic modeling of the radiation characteristics of a parabolic mirror antenna with a developed model of a truss-bearing structure and the proposed structures of reflective films, allowing to reduce the mass of the reflector and increase the reliability of the antenna system, are carried out. The estimation of the frequency dependences of the characteristics of the variants of the parabolic mirror antenna model is given. Recommendations on the use of sparse reflective films for small, medium and large apertures of deployable reflectors are proposed.

Asymmetric Cascade Fusion Network for Building Extraction

Asymmetric Cascade Fusion Network for Building Extraction

AMFFNet: Asymmetric Multiscale Feature Fusion Network of RGB-NIR for Solid Waste Detection

AMFFNet: Asymmetric Multiscale Feature Fusion Network of RGB-NIR for Solid Waste Detection

A-RetinaNet: A novel RetinaNet with an asymmetric attention fusion mechanism for dim and small drone detection in infrared images.

To solve the problems of texture lacking and resolution coarseness in the detection of dim and small drone targets in infrared images, we propose a novel RetinaNet with an asymmetric attention fusion mechanism for dim and small drone detection. First, we propose a super-resolution texture-enhancement network as an effective solution for the lack of texture-related information on small infrared targets. The network generates super-resolution images and enhances the texture features of the targets. Second, considering the inadequacy of feature pyramids in the feature fusion stage, we use an asymmetric attention fusion mechanism to constitute an asymmetric attention fusion pyramid network for cross-layer feature fusion in a bidirectional manner; it achieves high-quality semantic and location detail information interaction between scale features. Third, a global average pooling layer is employed to capture global spatial-sensitive information, thus effectively identifying features and achieving classification. Experiments were conducted by using a publicly available infrared image dim-small drone target detection dataset; the results show that the proposed method achieves an AP of 95.43% and a recall of 80.6%, which is a significant improvement over the current mainstream target detection algorithms.

Validation of genome information in real time, including illness mapping and polymorphism

The world of genetics is on the threshold of a new era. With real-time genetic sequencing, researchers can quickly and accurately verify genetic sequences in real time, providing rich information for disease diagnosis and treatment. This technology, combined with disease mapping and genetic polymorphism analysis, is the key to unlocking the mysteries of genetic disorders and developing more effective treatments. This article explores the exciting opportunities and challenges of real-time genetic sequencing and provides a glimpse into the future of personalized medicine and precision medicine. In the present framework, gene dependency networks often change in response to differences in disease types. A main goal of genomic research is to determine if and how these networks are formed between the two disease states. An innovative asymmetric network inference method is proposed to detect the alteration of gene networks by integrating information about gene expression and mutations. The subgroup bridge penalty mechanism is used to distinguish commonalities and differences between different data types. The goal of the modification process is to identify individuals at high risk of disease and then recommend either a specific diet or other natural remedies based on the results of the genetic screening procedure.

TheLR531v1 – A deep learning multi-branch CNN architecture for day-night automatic segmentation of horticultural crops

There is an increasing need for crop management practices to improve the day-night segmentation efficiency of crops grown in the open-field or in the greenhouse, in soil or in hydroponic environments, or both. We propose an asymmetric TheLR531v1 network with a multi-branch structure with powerful feature representation to recover plants, plant leaf or canopy (horticultural crops) from the background in real-time. The multi-branch structure of the network successfully extracts various image features from the input images and classifies them into leaf and background classes. We evaluated the network performance by using over 55,992 augmented images (tomato, eggplant, and lettuce) and obtained 94.55% training and 95.89% validation accuracy. The total parameters of TheLR531v1 are only 4.5 M, which is significantly lower than other state-of-the-art models. But realise that in addition, the proposed network achieves an average BF score of 89.00%, an IoU of 87.00%, and a GA of 96.00% to distinguish plants or plant canopy pixels from background pixels. Overall, TheLR531v1 can replace the laborious manual image segmentation tasks, analyze variability in stress conditions (temperature), and visualize stress related changes in plants, leaves or canopy (pixel area), which can improve crop management practices and yield.

Topology design for leader-follower coherence in noisy asymmetric networks

In this paper, we aim to study the effect of the leader’s positions in leader-follower coherence quantified by the spectrum in noisy asymmetric networks with a set of hub nodes. In order to compare the impact of leader selection in different ways on the studied coherence, we choose a family of ring-trees networks to conveniently assign the leaders and hubs. Based on the regular network topology and matrix theories, we obtain analytical solutions for the leader-follower coherence regarding network parameters and the number of leaders. Using these expressions, we then obtain exact relations among the coherences and show that the leader’s positions and network parameters have a profound impact on the coherence. More specifically, the network with one hub displays better coherence than the networks with two hubs. In addition, two adjacent and nonadjacent hubs lead to distinct performance of leader-follower consensus dynamics that depends on network parameters and assigned leaders in the ring or the tree network.

A lightweight multi-dimension dynamic convolutional network for real-time semantic segmentation.

Semantic segmentation can address the perceived needs of autonomous driving and micro-robots and is one of the challenging tasks in computer vision. From the application point of view, the difficulty faced by semantic segmentation is how to satisfy inference speed, network parameters, and segmentation accuracy at the same time. This paper proposes a lightweight multi-dimensional dynamic convolutional network (LMDCNet) for real-time semantic segmentation to address this problem. At the core of our architecture is Multidimensional Dynamic Convolution (MDy-Conv), which uses an attention mechanism and factorial convolution to remain efficient while maintaining remarkable accuracy. Specifically, LMDCNet belongs to an asymmetric network architecture. Therefore, we design an encoder module containing MDy-Conv convolution: MS-DAB. The success of this module is attributed to the use of MDy-Conv convolution, which increases the utilization of local and contextual information of features. Furthermore, we design a decoder module containing a feature pyramid and attention: SC-FP, which performs a multi-scale fusion of features accompanied by feature selection. On the Cityscapes and CamVid datasets, LMDCNet achieves accuracies of 73.8 mIoU and 69.6 mIoU at 71.2 FPS and 92.4 FPS, respectively, without pre-training or post-processing. Our designed LMDCNet is trained and inferred only on one 1080Ti GPU. Our experiments show that LMDCNet achieves a good balance between segmentation accuracy and network parameters with only 1.05 M.

3D-MASNet: 3D mixed-scale asymmetric convolutional segmentation network for 6-month-old infant brain MR images.

Precise segmentation of infant brain magnetic resonance (MR) images into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) are essential for studying neuroanatomical hallmarks of early brain development. However, for 6-month-old infants, the extremely low-intensity contrast caused by inherent myelination hinders accurate tissue segmentation. Existing convolutional neural networks (CNNs) based segmentation models for this task generally employ single-scale symmetric convolutions, which are inefficient for encoding the isointense tissue boundaries in baby brain images. Here, we propose a 3D mixed-scale asymmetric convolutional segmentation network (3D-MASNet) framework for brain MR images of 6-month-old infants. We replaced the traditional convolutional layer of an existing to-be-trained network with a 3D mixed-scale convolution block consisting of asymmetric kernels (MixACB) during the training phase and then equivalently converted it into the original network. Five canonical CNN segmentation models were evaluated using both T1- and T2-weighted images of 23 6-month-old infants from iSeg-2019 datasets, which contained manual labels as ground truth. MixACB significantly enhanced the average accuracy of all five models and obtained the most considerable improvement in the fully convolutional network model (CC-3D-FCN) and the highest performance in the Dense U-Net model. This approach further obtained Dice coefficient accuracies of 0.931, 0.912, and 0.961 in GM, WM, and CSF, respectively, ranking first among 30 teams on the validation dataset of the iSeg-2019 Grand Challenge. Thus, the proposed 3D-MASNet can improve the accuracy of existing CNNs-based segmentation models as a plug-and-play solution that offers a promising technique for future infant brain MRI studies.

Detection and Analysis of Microtubule Nucleator γ-Tubulin Ring Complex.

Golgi-derived microtubules constitute an asymmetrical microtubule network that drives polarized transport of vesicles to support cell polarization and directional migration. Golgi-based microtubule nucleation requires the γ-tubulin ring complex (γTuRC), the principal microtubule nucleator in animal cells. In this chapter, we present methods for detecting γTuRC components and associated proteins on the Golgi, examining Golgi-based microtubule nucleation, and measuring the microtubule-nucleating activity of isolated γTuRCs. These approaches have been demonstrated to be effective for assessing the microtubule-organizing function of the Golgi complex.

Fault Phase Selection Method Based on Single-Phase Flexible Arc Suppression Device for Asymmetric Distribution Networks

The phase-to-ground admittance in distribution networks is asymmetric. This asymmetry is aggravated by the arc suppression coil, resulting in zero-sequence overvoltage. The magnitude of zero-sequence overvoltage can exceed the line-to-ground voltage, endangering the operation of electrical equipment. Moreover, after the occurrence of a single-line-to-ground fault, the change law of the three-phase voltage is affected by the zero-sequence overvoltage, leading to misjudgment of the fault phase. Accordingly, this paper proposes a fault phase selection method based on active current injection that can adapt to asymmetric distribution networks. The fault phase is selected by injecting current and calculating the equivalent power supply voltage of the faulty line without increasing the ground-fault current. The high sensitivity of the proposed fault phase selection method was verified for high impedance faults through software simulations and prototype experiments. Moreover, the zero-sequence overvoltage can be suppressed by a single-phase flexible arc suppression device during the normal operation of distribution networks. The ground-fault current can be quickly suppressed at different ground-fault locations and resistance values, ensuring the extinguishment of the ground-fault arc.

State Estimation of Asymmetrical Distribution Networks by μ-PMU Allocation: A Novel Stochastic Two-stage Programming

• The WLS-based state estimation algorithm developed in this research can simulate large-scale asymmetric distribution networks. • An effective DSSE model is implemented based on a limited number of μ-PMUs and ZINs for determining the state variables. • Using the ZIN characteristics to minimize the μ-PMUs number in the system and keep the system fully observable. • The linear approximations are applied to model the linear DSSE. Distribution system state estimation provides essential data for the system monitoring and control, which some uncertain parameters such as the intermittent and varying output of distributed generation (DG), random meter errors, and inaccurate network parameters make situational awareness (SA) of distribution systems a challenging issue. To address these issues, this paper develops an innovative two-stage stochastic programming model, where in the first stage, optimal μ-PMU placement is implemented aiming at minimizing the installation cost of μ-PMU and maximizing the number of measurement redundancy and the system observability in the presence of partially zero injection nodes (PZIN), while in the second stage state estimation of three-phase asymmetric DG-integrated distribution systems is performed to enhance SA. By applying the proposed model, the optimal locations of μ-PMUs in the presence of PZINs and various contingencies were achieved, and the distribution system state estimation was obtained with high accuracy and low error percentage. The feasibility of the proposed methodology is verified on the modified IEEE 85-bus distribution system.

${l}\,^2$-MPTCP: A Learning-Driven Latency-Aware Multipath Transport Scheme for Industrial Internet Applications

With various industrial wireless networks greeting booming development, modern industrial devices configured with several network interfaces increasingly become the norm. Such multihomed industrial devices can increase application throughput by making use of multiple network paths, enabled by the multipath transmission control protocol (MTCP) (MPTCP). However, MPTCP might be challenged in the heterogeneous industrial networks because concurrent transmitting industrial application data over asymmetric network paths with different delays is almost bound to the receive buffer blocking problem, which is caused by out-of-order packet arrival and is harmful to the performance of the multipath transmission. The existing MPTCP solutions generally use static mathematical models to evaluate path quality and prohibit transmission on paths with poor quality, which are unable to perform efficiently under highly dynamic and complex network environments. Therefore, in this article, we propose a learning-driven latency-aware MPTCP variant, called <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${l}\,^2$</tex-math></inline-formula> -MPTCP, which seeks to possibly mitigate the out-of-order packet arrival and receive buffer blocking problems associated with the network heterogeneity in the industrial Internet. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${l}\,^2$</tex-math></inline-formula> -MPTCP accurately computes each MPTCP path’s forward delay and assigns application data to multiple paths according to their calculated forward delay differences by using a novel multiexpert learning-enabled forward delay estimator. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${l}\,^2$</tex-math></inline-formula> -MPTCP dynamically manages path usage and chooses the optimal path collection for bandwidth aggregation and multipath transmission by using a promising reinforcement learning-empowered multipath manager. Experimental results demonstrate that <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${l}\,^2$</tex-math></inline-formula> -MPTCP outperforms the current MPTCP solutions in terms of multipathing service quality.

Memristor-coupled asymmetric neural networks: Bionic modeling, chaotic dynamics analysis and encryption application

With the rapid development of artificial intelligence, it has important theoretical and practical significance to construct neural network models and study their dynamical behaviors. This article mainly focuses on the bionic model and chaotic dynamics of the asymmetric neural network as well as its engineering application. We first construct a memristor-coupled asymmetric neural network (MANN) utilizing two asymmetrical sub-neural networks and a coupled multi-piecewise memristor synapse. Then, the chaotic dynamics of the proposed MANN is studied and analyzed by using basic dynamics methods like equilibrium stability, bifurcation diagrams, Lyapunov exponents, and Poincare mappings. Research results show that the proposed MANN exhibits multiple complex dynamical characteristics including infinitely wide hyperchaos with amplitude control, hyperchaotic initial-boosted behavior, and arbitrary number of hyperchaotic multi-structure attractors. More importantly, the phenomena of the infinitely wide hyperchaos and the hyperchaotic multi-structure attractors are observed in neural networks for the first time. Meanwhile, applying the hyperchaotic multi-structure attractors, a color image encryption scheme is designed based on the proposed MANN. Performance analyses show that the designed encryption scheme has some merits in correlation, information entropy, and key sensitivity. Finally, a physical circuit of the MANN is implemented and various typical dynamical behaviors are verified by hardware experiments.

Regime-Switching Fractionally Integrated Asymmetric Power Neural Network Modeling of Nonlinear Contagion for Chaotic Oil and Precious Metal Volatilities

This paper aims at analyzing nonlinear dependence between fractionally integrated, chaotic precious metal and oil prices and volatilities. With this respect, the Markov regime-switching fractionally integrated asymmetric power versions of generalized autoregressive conditional volatility copula (MS-FIAPGARCH-copula) method are further extended to multi-layer perceptron (MLP)-based neural networks copula (MS-FIAPGARCH-MLP-copula). The models are utilized for modeling dependence between daily oil, copper, gold, platinum and silver prices, covering a period from 1 January 1990–25 March 2022. Kolmogorov and Shannon entropy and the largest Lyapunov exponents reveal uncertainty and chaos. Empirical findings show that: i. neural network-augmented nonlinear MS-FIAPGARCH-MLP-copula displayed significant gains in terms of forecasts; ii. asymmetric and nonlinear processes are modeled effectively with the proposed model, iii. important insights are derived with the proposed method, which highlight nonlinear tail dependence. Results suggest, given long memory and chaotic structures, that policy interventions must be kept at lowest levels.

Undirected graphical model of adjacency matrix for dynamic elasticity in polyelectrolyte hydrogels

Molecular network plays a critical role in determining dynamic elasticity of soft condensed polymers, e.g., their varied cross-linking densities and end-to-end distances with changed Young's moduli. Although it has been studied for decades, the coupling relationship between vertices and edges of molecular networks is not well understood, mainly because the degree of the crosslinking points and asymmetry molecular networks have not been considered in the previously models. In this study, a graph theory was employed to formulate an undirected graphical model and describe the coupling between vertices and edges in molecular networks, based on which the dynamic elasticity of polyelectrolyte hydrogel was modeled. From the Kirchhoff graph theory and bead-spring model, the coupling relationship between vertices and edges was obtained using end-to-end distance and viscosity parameters. Combining the Watts–Strogatz model and kinetic probability, the coupling between vertices and edges for the polyelectrolyte network was studied. Furthermore, an adjacency matrix with eigenvalue, number of vertices and mean degree was proposed to formulate constitutive relationships including dynamic elasticity and stress-strain, according to rubber elasticity theory and Mooney-Rivlin model, respectively. The linking between the vertices and edges determines the network structure and dynamic elasticity of the polyelectrolyte hydrogel. Based on the graph theory, the vertices and edges are encoded by adjacency matrix, which is proposed to describe the dynamic elasticity of symmetric and asymmetric network structures using the crosslinking density and end-to-end distance. Finally, effectiveness of the undirected graphical model was verified using both finite element analysis and experimental results of polyelectrolyte hydrogels reported in literature.

Outer-synchronization criterions for asymmetric recurrent time-varying neural networks described by differential-algebraic system via data-sampling principles.

Asymmetric recurrent time-varying neural networks (ARTNNs) can enable realistic brain-like models to help scholars explore the mechanisms of the human brain and thus realize the applications of artificial intelligence, whose dynamical behaviors such as synchronization has attracted extensive research interest due to its superior applicability and flexibility. In this paper, we examined the outer-synchronization of ARTNNs, which are described by the differential-algebraic system (DAS). By designing appropriate centralized and decentralized data-sampling approaches which fully account for information gathering at the times t k and . Using the characteristics of integral inequalities and the theory of differential equations, several novel suitable outer-synchronization conditions were established. Those conditions facilitate the analysis and applications of dynamical behaviors of ARTNNs. The superiority of the theoretical results was then demonstrated by using a numerical example.

Asymmetric Network Connectedness of Fears

Abstract This paper introduces forward-looking measures of the network connectedness of fears in the financial system arising due to the good and bad beliefs of market participants about uncertainty that spreads unequally across a network of banks. We argue that this asymmetric network structure extracted from call and put traded option prices of the main U.S. banks contains valuable information for predicting macroeconomic conditions and economic uncertainty, and it can serve as a tool for forward-looking systemic risk monitoring.