Cyclic Network Research Articles

Accuracy analysis for distributed dynamic state estimation in large-scale systems with a cyclic network graph

Accuracy analysis for distributed dynamic state estimation in large-scale systems with a cyclic network graph

Cyclic Generative Attention-Adversarial Network for Low-Light Image Enhancement.

Images captured under complex conditions frequently have low quality, and image performance obtained under low-light conditions is poor and does not satisfy subsequent engineering processing. The goal of low-light image enhancement is to restore low-light images to normal illumination levels. Although many methods have emerged in this field, they are inadequate for dealing with noise, color deviation, and exposure issues. To address these issues, we present CGAAN, a new unsupervised generative adversarial network that combines a new attention module and a new normalization function based on cycle generative adversarial networks and employs a global-local discriminator trained with unpaired low-light and normal-light images and stylized region loss. Our attention generates feature maps via global and average pooling, and the weights of different feature maps are calculated by multiplying learnable parameters and feature maps in the appropriate order. These weights indicate the significance of corresponding features. Specifically, our attention is a feature map attention mechanism that improves the network's feature-extraction ability by distinguishing the normal light domain from the low-light domain to obtain an attention map to solve the color bias and exposure problems. The style region loss guides the network to more effectively eliminate the effects of noise. The new normalization function we present preserves more semantic information while normalizing the image, which can guide the model to recover more details and improve image quality even further. The experimental results demonstrate that the proposed method can produce good results that are useful for practical applications.

3D Domain Adaptive Instance Segmentation via Cyclic Segmentation GANs.

3D instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying pre-trained models optimized on diverse training data or sequentially conducting image translation and segmentation with two relatively independent networks. In this work, we propose a novel Cyclic Segmentation Generative Adversarial Network (CySGAN) that conducts image translation and instance segmentation simultaneously using a unified network with weight sharing. Since the image translation layer can be removed at inference time, our proposed model does not introduce additional computational cost upon a standard segmentation model. For optimizing CySGAN, besides the CycleGAN losses for image translation and supervised losses for the annotated source domain, we also utilize self-supervised and segmentation-based adversarial objectives to enhance the model performance by leveraging unlabeled target domain images. We benchmark our approach on the task of 3D neuronal nuclei segmentation with annotated electron microscopy (EM) images and unlabeled expansion microscopy (ExM) data. The proposed CySGAN outperforms pre-trained generalist models, feature-level domain adaptation models, and the baselines that conduct image translation and segmentation sequentially. Our implementation and the newly collected, densely annotated ExM zebrafish brain nuclei dataset, named NucExM, are publicly available at https://connectomics-bazaar.github.io/proj/CySGAN/index.html.

Multi-load short-term prediction of an integrated energy system based on GAN-LSTM

An integrated energy system’s load consists of diverse forms, including electric load, cooling load, heat load, and more. Due to its strong randomness and volatility, traditional load forecasting methods are not suitable for the integrated energy system. To address the issue of short-term forecasting for multiple loads of the integrated energy system, the proposed paper utilizes generating adversarial networks (GAN). The proposed method analyzes the characteristics of comprehensive energy multi-load and combines meteorological factors with multi-load historical data to form the input dataset for the prediction model. To further improve the accuracy of the short-term forecasting of comprehensive energy multiple loads, the model employs a generator and a discriminator constructed based on the cyclic neural network of long- and short-term memory (LSTM). The example results demonstrate that the proposed method is effective in predicting multiple loads, with significantly better accuracy than traditional methods.

Multi-scroll attractor and its broken coexisting attractors in cyclic memristive neural network

This paper proposes a simple-structured memristive neural network, which incorporates self-connections of memristor synapses alongside both unidirectional and bidirectional connections. Different from other multi-scroll chaotic systems, this network structure has a more concise three-neuron structure. This simple memristive neural network can generate a number of multi-scroll attractors in manageable quantities and shows the characteristics of the coexisting attractors and amplitude control. In particular, when the parameters are changed, the coexisting attractors break up around the center of gravity into two centrosymmetric chaotic attractors. Abundant dynamic behaviors are studied through phase portraits, bifurcation diagrams, Lyapunov exponents, and attraction basins. The feasibility of the system is demonstrated by building a circuit realization platform.

Video Super-Resolution Network with Gated High-Low Resolution Frames

In scenes with large inter-frame motion variations, distant targets, and blurred targets, the lack of inter-frame alignment can greatly affect the effectiveness of subsequent video super-resolution reconstruction. How to perform inter-frame alignment in such scenes is the key to super-resolution reconstruction. In this paper, a new motion compensation method is proposed to design an alignment network based on gated high-low resolution frames. The core idea is to introduce a gating mechanism while using the information of high-low resolution neighboring frames to perform motion compensation adaptively. Meanwhile, within this alignment framework, we further introduce a pre-initial hidden state network and a local scale hierarchical salient feature fusion network. The pre-initial hidden state network is mainly used to reduce the impact of unbalanced quality effects between frames that occur in one-way cyclical networks; the local scale hierarchical salient feature fusion network is used to fuse the features of aligned video frames to extract contextual information and locally salient features to improve the reconstruction quality of the video. Compared with existing video super-resolution methods, this method achieves good performance and clearer edge and texture details.

Hydration Rearrangement in the 4-Aminobenzonitrile-(H2 O)2 Cluster Induced by Photoionization: The Effect of Solvent-Solvent Interactions.

The interplay between solute-solvent and solvent-solvent interactions plays an essential role in solvation dynamics that has important effects on the mechanism and dynamics of chemical reactions in solution. In this study, the rearrangement of the hydration shell induced by photoionization of a solute molecule is probed in a state- and isomer-specific manner by resonant multiphoton ionization detected IR spectroscopy of the prototypical 4-aminobenzonitrile-(H2 O)2 cluster produced in a molecular beam. IR spectra reveal that the water molecules form a cyclic solvent network around the CN group in the initial neutral state (S0 ). Different from the singly-hydrated cluster, in which either the CN or the NH2 group is hydrated, hydration of the NH2 group is not observed in the dihydrated cluster. IR spectra obtained after ionizing the solute molecule into the cation ground state (D0 ) exhibit features ascribed to both NH-bound and CN-bound isomers, indicating that water molecules migrate from the CN to the NH site upon ionization with a yield depending on the ionization excess energy. Analysis of the IR spectra as a function of the excess energy shows that migration produces two different NH2 solvated structures, namely (i) the most stable structure in which both N-H bonds are singly hydrated and (ii) the second most stable isomer in which one of the N-H bonds is hydrated by a H-bonded (H2 O)2 dimer. The product branching ratio of the two isomers depends on the excess energy. The role of the water-water interaction in the hydration rearrangement is discussed based on the potential energy landscape. Solvation dynamics plays an important role in reaction mechanisms in the condensed phase, where not only solute-solvent solvation but also solvent-solvent interactions have a significant influence on the dynamics. Thus, the investigation of solvation dynamics at the molecular level substantially contributes to our understanding of the reaction mechanism. In this study, the dihydrated cluster of 4ABN was utilized as a model for the first solvation layer to elucidate solvent motions induced by ionization of the solute and the role of W-W interactions for the solvent relaxation.

Few-shot temporal knowledge graph completion based on meta-optimization

Knowledge Graphs (KGs) have become an increasingly important part of artificial intelligence, and KGs have been widely used in artificial intelligence fields such as intelligent answering questions and personalized recommendation. Previous knowledge graph completion methods require a large number of samples for each relation. But in fact, in KGs, many relationships are long-tail relationships, and the existing researches on few-shot completion mainly focus on static knowledge graphs. In this paper, we consider few-shot completion in Temporal Knowledge Graphs (TKGs) where the event may only hold for a specific timestamp, and propose a model abbreviated as FTMO based on meta-optimization. In this model, we combine the time-based relational-aware heterogeneous neighbor encoder, the cyclic automatic aggregation network, and the matching network to complete the few-shot temporal knowledge graph. We compare our model with the baseline models, and the experimental results demostrate the performance advantages of our model.

Simple cyclic memristive neural networks with coexisting attractors and large-scale amplitude control.

The memristor's unique memory function and non-volatile nature make it an ideal electronic bionic device for artificial neural synapses. This paper aims to construct a class of memristive neural networks (MNNs) with a simple circular connection relationship and complex dynamics by introducing a generic memristor as synapse. For placing the memristive synapse in different coupling positions, three MNNs with the same coupling cyclic connection are yielded. One remarkable feature of the proposed MNNs is that they can yield complex dynamics, in particular, abundant coexisting attractors and large-scale parameter-relied amplitude control, by comparing with some existing MNNs. Taking one of the MNNs as an example, the complex dynamics (including chaos, period-doubling bifurcation, symmetric coexisting attractors, large-scale amplitude control) and circuit implementation are studied . The number of equilibria and their stabilities are discussed. The parameter-relied dynamic evolution and the coexisting attractors are numerically shown by using bifurcations and phase portraits. A microcontroller-based hardware circuit is given to realize the network, which verifies the correctness of the numerical results and experimental results.

Evolution of cyclic di-GMP signalling on a short and long term time scale.

Diversifying radiation of domain families within specific lineages of life indicates the importance of their functionality for the organisms. The foundation for the diversifying radiation of the cyclic di-GMP signalling network that occurred within the bacterial kingdom is most likely based in the outmost adaptability, flexibility and plasticity of the system. Integrative sensing of multiple diverse extra- and intracellular signals is made possible by the N-terminal sensory domains of the modular cyclic di-GMP turnover proteins, mutations in the protein scaffolds and subsequent signal reception by diverse receptors, which eventually rewires opposite host-associated as well as environmental life styles including parallel regulated target outputs. Natural, laboratory and microcosm derived microbial variants often with an altered multicellular biofilm behaviour as reading output demonstrated single amino acid substitutions to substantially alter catalytic activity including substrate specificity. Truncations and domain swapping of cyclic di-GMP signalling genes and horizontal gene transfer suggest rewiring of the network. Presence of cyclic di-GMP signalling genes on horizontally transferable elements in particular observed in extreme acidophilic bacteria indicates that cyclic di-GMP signalling and biofilm components are under selective pressure in these types of environments. On a short and long term evolutionary scale, within a species and in families within bacterial orders, respectively, the cyclic di-GMP signalling network can also rapidly disappear. To investigate variability of the cyclic di-GMP signalling system on various levels will give clues about evolutionary forces and discover novel physiological and metabolic pathways affected by this intriguing second messenger signalling system.

Overflow Capacity Prediction of Pumping Station Based on Data Drive

In recent years, the information requirements of pumping stations have become higher and higher. The prediction of overflow capacity can provide important reference for flood carrying capacity, water resource scheduling and water safety. In order to improve the accuracy, stability and generalization ability of the model, a BiGRU–ARIMA data-driven method based on self-attention mechanism is proposed to predict the flow capacity of the pump station. Bidirectional gated recurrent unit (BiGRU), a variant of cyclic neural network (RNN), can not only deal with nonlinear components well, but also deal with the problem of insufficient dependence over long distances and has a simple structure. Autoregressive integrated moving average (ARIMA) has the advantage of being sensitive to linear components. Firstly, the characteristics of the pre-processed pump station data are selected and screened through Pearson correlation coefficient and a self-attention mechanism. Then, a bi-directional gated recurrent unit (BiGRU) is used to process the nonlinear components of the data, and a dropout layer is added to avoid overfitting phenomena. We extract the linear features of the obtained error terms using the ARIMA model and use them as correction items to correct the prediction results of the BiGRU model. Finally, we obtain the prediction results of the overflow and water level. The variation characteristics of overdischarge are analyzed by the relation of flow and water level. In this paper, the actual production data of a Grade 9 pumping station of Miyun Reservoir is taken as an example to verify the validity of the model. Model performance is evaluated according to mean absolute error (MAE), mean absolute percentage error (MAPE) and linear regression correlation coefficient (R2). The experimental results show that, compared with the single ARIMAX, BiGRU model and BP neural network, the SA–BiGRU–ARIMA hybrid prediction model has a better prediction effect than other data-driven models.

Cross-Modal Sentiment Analysis of Text and Video Based on Bi-GRU Cyclic Network and Correlation Enhancement

Cross-modal sentiment analysis is an emerging research area in natural language processing. The core task of cross-modal fusion lies in cross-modal relationship extraction and joint feature learning. The existing research methods of cross-modal sentiment analysis focus on static text, video, audio, and other modality data but ignore the fact that different modality data are often unaligned in practical applications. There is a long-term time dependence among unaligned data sequences, and it is difficult to explore the interaction between different modalities. The paper proposes a sentiment analysis model (UA-BFET) based on feature enhancement technology in unaligned data scenarios, which can perform sentiment analysis on unaligned text and video modality data in social media. Firstly, the model adds a cyclic memory enhancement network across time steps. Then, the obtained cross-modal fusion features with interaction are applied to the unimodal feature extraction process of the next time step in the Bi-directional Gated Recurrent Unit (Bi-GRU) so that the progressively enhanced unimodal features and cross-modal fusion features continuously complement each other. Secondly, the extracted unimodal text and video features taken jointly from the enhanced cross-modal fusion features are subjected to canonical correlation analysis (CCA) and input into the fully connected layer and Softmax function for sentiment analysis. Through experiments executed on unaligned public datasets MOSI and MOSEI, the UA-BFET model has achieved or even exceeded the sentiment analysis effect of text, video, and audio modality fusion and has outstanding advantages in solving cross-modal sentiment analysis in unaligned data scenarios.

Systematic Exploration of Structural Topologies in Hydrogen-Bonded Supramolecular Assemblies of Citric Acid with Different Heterocyclic Compounds.

Hydrogen-bonded supramolecular assemblies of citric acid, CA, with some heterocyclic compounds (N-donor and N-oxide)-acridine (acr), phenazine (phenz), 1,10-phenanthroline (110phen), 1,7-phenanthroline (17phen), 4,7-phenanthroline (47phen), 1,4-diazabicyclo[2.2.2]octane (dabco), and 4,4'-bipyridyl-N,N'-dioxide (bpydo)-have been reported. Among these, only the N-donors phenz and N-oxide (bpydo) form neutral co-crystals, while the others form salts owing to the deprotonation of -COOH. Thus, depending on the nature of the aggregate (salt/co-crystal), recognition between the co-formers is established through O-H···N/N+-H···O/N+H···O-heteromeric hydrogen bonding. Additionally, CA molecules establish homomeric interactions mediated by O-H···O hydrogen bonds. Moreover, CA forms a cyclic network with the co-formers or on its own, with a noteworthy feature of formation of host-guest networks in the assemblies with acr and phenz (solvated). In the assembly of acr, the CA molecules form a host network and captivate acr molecules as guest species, while in the case of phenz assembly, both the co-formers together encapsulate the solvent in the channels. However, the observed cyclic networks in the other structures form three-dimensional topologies in the form of ladders, a sandwich, lamellar layers, and interpenetrated networks. The structural features of the ensembles are evaluated unequivocally by the single-crystal X-ray diffraction method, while the homogeneity and phase purity are evaluated by using the powder X-ray diffraction method and differential scanning calorimetry. Further, conformational analysis of CA molecules reveals three types of conformations-T-shape (type I), syn-anti (type II), and syn (type III) as also observed in the literature for other CA co-crystals. In addition, the strength of the intermolecular interactions is quantified by performing Hirshfeld analysis.

An Exploit Traffic Detection Method Based on Reverse Shell

As the most crucial link in the network kill chain, exploiting a vulnerability is viewed as one of the most popular attack vectors to get the control authority of the system, which is dangerous for legal users. Therefore, an effective exploit traffic detection method is urgent. However, current methods are almost based on pattern matching, invalid for encrypted traffic. To address this problem, we propose a reverse shell-based exploit traffic detection method, ETDetector. Our key insight is that the reverse shell attack often coexists with vulnerability exploitation as one of the most popular exploit behaviors. So, we first extract the fusion information feature from original features, such as the packet delay sequence, as input of a decision tree model to identify reverse shell traffic in the shellcode execution stage. Then, we trace suspicious traffic in the shellcode delivery stage by reconstructing the session relationship of the two stages above. Compared with Blatta, using a cyclic neural network to detect early exploit traffic, the detection rate of ETDetector is increased by 50% and valid for encrypted exploit traffic. In addition, we propose a traffic stratification method based on a bisecting K-means algorithm, which can intuitively show the traffic communication behavior and improve the interpretability of ETDetector.

A Novel Periodic Cyclic Sparse Network With Entire Domain Adaptation for Deep Transfer Fault Diagnosis of Rolling Bearing

In recent years, rolling bearing fault diagnosis technique based on deep learning provides a more intelligent and reliable way for the safe operation of mechanical system. However, this technique still exists the problems of high model complexity and poor generalization ability in application. To solve the above problem, a novel periodic cyclic sparse network with entire domain adaptation (PcsNet-EDA) for deep transfer fault diagnosis of rolling bearing is proposed in this paper. The proposed periodic cyclic sparse design pattern makes the weight matrices of the convolutional layer and the fully-connected layer contain a large number of zero-weight parameters with regular arrangement, which effectively reduces the complexity of the model. The proposed EDA simultaneously considers the alignment of both global and local discrepancy, which further enhances the generalization ability of the model. In experimental validation, this paper firstly analyzes the basic diagnostic performance of PcsNet. Then, the transfer diagnostic performance of PcsNet within single-source domain scenarios based on EDA is explored, including the influence of different pre-defined sparse structures on the transfer diagnostic accuracy. The validation shows that the proposed PcsNet and the corresponding transfer model PcsNet-EDA can achieve satisfactory results on different bearing fault datasets for fault diagnosis.

Comparison of ARIMA and LSTM in Predicting Structural Deformation of Tunnels during Operation Period

Accurately predicting the structural deformation trend of tunnels during operation is significant to improve the scientificity of tunnel safety maintenance. With the development of data science, structural deformation prediction methods based on time-series data have attracted attention. Auto Regressive Integrated Moving Average model (ARIMA) is a classical statistical analysis model, which is suitable for processing non-stationary time-series data. Long- and Short-Term Memory (LSTM) is a special cyclic neural network that can learn long-term dependent information in time series. Both are widely used in the field of temporal prediction. In view of the lack of time-series prediction in the tunnel deformation field, the body of this paper uses historical data of the Xinjian Road and the Dalian Road tunnel in Shanghai to propose a new way of modeling based on single points and road sections. ARIMA and LSTM models are applied in comprehensive experiments, and the results show that: (1) Both LSTM and ARIMA models have great performance for settlement and convergence deformation. (2) The overall robustness of ARIMA is better than that of LSTM, and it is more adaptable to the datasets. (3) The model prediction performance is closely related to the data quality. ARIMA has more stable performance under the lack of data volume, while LSTM has better performance with high-quality data and higher upper limit.

Cyclic Convolutional Neural Network Model Based on Artificial Intelligence

Abstract This paper mainly discusses the internal correlation between meshless discrete data and learning samples, meshless dynamic analysis recursive operation and information transmission mode in cyclic convolutional neural networks. This paper establishes a cyclic convolutional neural network based on the meshless method. This paper demonstrates an agent model of cyclic convolutional neural network based on dynamic characteristics. This method combines the advantages of the flexible configuration of meshless nodes in the discrete model. The universality and adaptability of cyclic convolutional neural networks are improved. In addition, because of the unique historical memory characteristics of the periodic module, it can analyze continuous data efficiently. The solution of dynamic analysis is accelerated without affecting the calculation accuracy. Based on a group of examples, the accuracy and effectiveness of this method are studied experimentally.

Domination Number and Secure Resolving Sets in Cyclic Networks

Consider a robot that is navigating a graph-based space and is attempting to determine where it is right now. To determine how distant it is from each group of fixed landmarks, it can send a signal. We discuss the problem of determining the minimum number of landmarks necessary and their optimal placement to ensure that the robot can always locate itself. The number of landmarks is referred to as the graph's metric dimension, and the set of nodes on which they are distributed is known as the graph's metric basis. On the other hand, the metric dimension of a graph <I>G</I> is the minimum size of a set <i>w</i> of vertices that can identify each vertex pair of <I>G </I>by the shortest-path distance to a particular vertex in <i>w</i>. It is an NP-complete problem to determine the metric dimension for any network. The metric dimension is also used in a variety of applications, including geographic routing protocols, network discovery and verification, pattern recognition, image processing, and combinatorial optimization. In this paper, we investigate the exact value of the secure resolving set of some networks, such as trapezoid network, <I>Z</I>-(<i>P_n</i>) network, open ladder network, tortoise network and <img width="40" height="15" src="http://article.sciencepublishinggroup.com/journal/147/1471683/image001.png" /> network. We also determine the domination number of the networks, such as the twig network <i>T_m</i>, double fan network <i>F_2,n</i>, bistar network <i>B_n,n </i>and linear <i>kc</i>₄ – snake network.

TCM disease diagnosis based on convolutional cyclic neural network algorithm

The unique diagnosis and treatment mode of traditional Chinese medicine provides a lot of diagnostic basis with reference value for modern medicine, which is welcomed by people all over the world and has attracted extensive attention of medical researchers. However, the unique diagnosis and treatment method of traditional Chinese medicine also brings difficulties to the dissemination of traditional Chinese medicine. The diagnosis method of traditional Chinese medicine is difficult to objectively and quantitatively express, and the diagnosis process is also closely related to the subjective experience of traditional Chinese medicine doctors. , lacking established standards. In view of the above-mentioned difficulties in the modernization of traditional Chinese medicine, the development of modern information science and technology has brought a turning point to the intelligentization of disease differentiation in traditional Chinese medicine. The core of traditional Chinese medicine diagnosis and treatment is diagnosis and classification. How to convert the difficult to describe disease diagnosis and treatment process of traditional Chinese medicine into language that can be distinguished and understood by ordinary doctors, and build an auxiliary diagnosis and treatment model to provide reference for Chinese doctors to see a doctor is the main problem to be solved in this paper.

SiamCMN: Jointing cycle memory and correlation network for Siamese object tracking

In heterogeneous scenes with latent non-deterministic states, template features determine the performance of the Siamese network-based trackers, however, background noise is easily introduced in the search area matching process, which causes the trackers lack sufficient discrimination. To solve this problem, this paper proposes an object tracking algorithm based on the cyclic memory module. Firstly, the extracted primary features are mapped to the cyclic spatial memory network, the spatial memory unit is used to store the interference components. On this basis, the cyclic structure is used to filter out the interference components and refine the template features. Then a channel correlation network is introduced into the proposed method, which can mine semantic complementary information and capture global contextual relevance by modeling the positive and the negative correlation between the channels. The experimental results on tracking benchmarks such as OTB50, OTB100, UAV123, VOT2018, GOT10k, and LaSOT have shown that the proposed method outperforms recent representative algorithms in tracking accuracy in challenging scenarios.