Cyclic Network Research Articles

Salient instance segmentation with region and box-level annotations

In the field of saliency detection, salient instance segmentation is a novel challenging task that has received widespread attention. Due to the limited scale of the available dataset and the high cost of mask annotations, a substantial quantity of supervision sources is urgently required to train a high-performing salient instance model. To this end, we aim to train a novel salient instance segmentation model by weak supervisions that make full use of the existing salient object detection dataset. In this paper, we present a cyclic global context salient instance segmentation network (CGCNet) supervised by the combination of salient regions and bounding boxes from ready-made salient object detection datasets. To locate salient instances more accurately, a global feature refining layer is designed to expand the size of the features from the region of interest (ROI) to the global field in a scene. Moreover, a labeling updating scheme is embedded in the proposed framework to iteratively update the weak labels. Extensive experimental results demonstrate that our CGCNet trained by weak labels is competitive with the existing fully-supervised state-of-the-art methods.

Dance Action Generation Model Based on Recurrent Neural Network

In recent years, modeling methods based on Deep Learning and Recurrent Neural Network (RNN) have achieved rapid development in various tasks in the field of computer vision, and video generation technology has also achieved remarkable results on this basis, with boosting effect. This paper analyzes the requirements and system design of the dance generation system based on cyclic neural network and clearly puts forward the specific functional requirements and nonfunctional requirements. Design, test each function of the system, and show the graphs generated by our application during training and testing, and visualize the specific value of the loss function during training. Combining the latest image generation technology and the most effective open source gesture detection project, a dance generation algorithm is completed, which can generate a video of the target person completing the specified dance action.

Cyclic Learning-Based Lightweight Network for Inverse Tone Mapping

Recent studies on inverse tone mapping (iTM) have moved toward indirect mapping, which generates a stack of low dynamic range (LDR) images with multiple exposure values (multi-EV stack) and then merges them. In order to generate multi-EV stack(s), several large-scale networks with more than 20 M parameters have been proposed, but their high dynamic range (HDR) reconstruction and multi-EV stack generation performance were not acceptable. Also, some previous methods using cycle consistency should even have trained additional networks that are not used for multi-EV stack generation, which results in large memory for training. Thus, this paper proposes novel cyclic learning based on cycle consistency to reduce the memory burden in training. In detail, we eliminated networks used only for training, so the proposed method enables efficient learning in terms of training-purpose memory. In addition, this paper presents a lightweight iTM network that dramatically reduces the network sizes of the existing networks. Actually, the proposed lightweight network requires only a small parameter size of 1/100 compared to the state-of-the-art (SOTA) method. The lightweight network contributes to the practical use of iTM. Therefore, the proposed method based on a lightweight network reliably generates a multi-EV stack. Experimental results show that the proposed method achieves quantitatively SOTA performance and is qualitatively comparable to conventional indirect iTM methods.

3D GAN image synthesis and dataset quality assessment for bacterial biofilm.

Data-driven deep learning techniques usually require a large quantity of labeled training data to achieve reliable solutions in bioimage analysis. However, noisy image conditions and high cell density in bacterial biofilm images make 3D cell annotations difficult to obtain. Alternatively, data augmentation via synthetic data generation is attempted, but current methods fail to produce realistic images. This article presents a bioimage synthesis and assessment workflow with application to augment bacterial biofilm images. 3D cyclic generative adversarial networks (GAN) with unbalanced cycle consistency loss functions are exploited in order to synthesize 3D biofilm images from binary cell labels. Then, a stochastic synthetic dataset quality assessment (SSQA) measure that compares statistical appearance similarity between random patches from random images in two datasets is proposed. Both SSQA scores and other existing image quality measures indicate that the proposed 3D Cyclic GAN, along with the unbalanced loss function, provides a reliably realistic (as measured by mean opinion score) 3D synthetic biofilm image. In 3D cell segmentation experiments, a GAN-augmented training model also presents more realistic signal-to-background intensity ratio and improved cell counting accuracy. https://github.com/jwang-c/DeepBiofilm. Supplementary data are available at Bioinformatics online.

Cyclic Gate Recurrent Neural Networks for Time Series Data with Missing Values

Gated Recurrent Neural Networks (RNNs) such as LSTM and GRU have been highly effective in handling sequential time series data in recent years. Although Gated RNNs have an inherent ability to learn complex temporal dynamics, there is potential for further enhancement by enabling these deep learning networks to directly use time information to recognise time-dependent patterns in data and identify important segments of time. Synonymous with time series data in real-world applications are missing values, which often reduce a model’s ability to perform predictive tasks. Historically, missing values have been handled by simple or complex imputation techniques as well as machine learning models, which manage the missing values in the prediction layers. However, these methods do not attempt to identify the significance of data segments and therefore are susceptible to poor imputation values or model degradation from high missing value rates. This paper develops Cyclic Gate enhanced recurrent neural networks with learnt waveform parameters to automatically identify important data segments within a time series and neglect unimportant segments. By using the proposed networks, the negative impact of missing data on model performance is mitigated through the addition of customised cyclic opening and closing gate operations. Cyclic Gate Recurrent Neural Networks are tested on several sequential time series datasets for classification performance. For long sequence datasets with high rates of missing values, Cyclic Gate enhanced RNN models achieve higher performance metrics than standard gated recurrent neural network models, conventional non-neural network machine learning algorithms and current state of the art RNN cell variants.

Evaluation of thermodynamic consistency of kinetic parameters in cyclic enzyme-catalyzed reaction networks

It is shown by analysis of a cyclic enzymatic network that the presence of zero net flux/current cycles impose strong thermodynamic constraints on the values of the kinetic parameters. Thermodynamic analysis is carried out for the four-node pyramidal reaction network involving the conversion of 7,8-­dihydrofolate (H2F) and NADPH in the presence of H+ to 5,6,7,8-­tetrahydrofolate (H4F) and NADP+ catalyzed by the universal enzyme dihydrofolate reductase (DHFR). The complete set of empty reaction routes in the DHFR pathway is identified, equations for the thermodynamic constraints imposed on the rate constants of the various elementary steps are written down, and the thermodynamic consistency of the experimentally determined rate constants is evaluated. The visual approach based on the theory of graphs can be employed to test the thermodynamic consistency of kinetic parameters of general cyclic enzyme-catalyzed reaction networks.

Image Super-Resolution Method Based on Dual Learning

Existing super-resolution methods convert high-resolution images into low-resolution images, and use the synthesized images as input to train the model. However, it is difficult for synthetic low-resolution images to reflect the characteristics of real low-resolution images, resulting in poor model performance in practical applications. To address this problem, we propose a recurrent super-resolution framework, which consists of a degradation model and a reconstruction model. The degradation model degenerates the real high-resolution image into a more real low-resolution image, which is used as the input of the super-resolution reconstruction network, and then uses the reconstruction model to reconstruct the low-resolution image, and calculates the error with the original image. The generated high-resolution image is input into the degradation model again for degradation processing, forming a symmetrical and cyclic network structure, so that the super-resolution model has a better effect when reconstructing the real low-scoring image. In addition, the spatial attention mechanism is introduced into the generator network, which expands the receptive field of the convolution kernel, better extracts long-distance image features and improves the texture details of super-resolution images, which is consistent with the global.

Cyclic Global Guiding Network for Point Cloud Completion

The application of 3D scenes has gradually expanded in recent years. A 3D point cloud is unreliable when it is acquired because of the performance of the sensor. Therefore, it causes difficulties in utilization. Point cloud completion can reconstruct and restore sparse and incomplete point clouds to a more realistic shape. We propose a cyclic global guiding network structure and apply it to point cloud completion tasks. While learning the local details of the whole cloud, our network structure can play a guiding role and will not ignore the overall characteristics of the whole cloud. Based on global guidance, we propose a variety of fitting planes and layered folding attention modules to strengthen the local effect. We use the relationship between the point and the plane to increase the compatibility between the network learning and the original sparse point cloud. We use the attention mechanism of the layer overlay to strengthen the local effect between the encode and decode. Therefore, point clouds are more accurate. Our experiments indicate the effectiveness of our method on the ShapeNet, KITTI, and MVP datasets and are superior to other networks.

Analysis of English Translation Model Based on Artificial Intelligence Attention Mechanism

The particularity and quantity of English translation terms have a great impact on the quality and effect of machine translation and can not meet the requirements of English translation of terms. At the same time, technical exchange and communication in different fields need the expression of professional terms. In addition, although the neural machine translation model has good translation performance, it is not ideal for target languages with small translation needs and limited corpus resources. In order to solve the problems existing in the English translation model, this paper constructs the transformer model by replacing the cyclic neural network variables and introducing the attention mechanism. The term information is integrated into two pretraining models to improve the learning ability of model language sentence relationship. Maintain the integrity of terminology information by fully completing the training. The experimental results show that, compared with the other three term translation models, the translation model in this paper has the advantage of term information. At the same time, the deep neural network English term translation model can obtain more fine-grained word relevance. In different corpora, the Bleu score of the model is good, showing obvious translation performance advantages. This study provides a good professional reference value for the translation of English terms.

Hexagonal cyclical network structure and operating mechanism of the social-ecological system

Research on the social-ecological system unifies society, the economy, resources and the environment and provides an integrated and systematic research framework through which to study complex earth system problems, such as climate change, globalization, land use/cover change and population growth. This research aims to provide support for the excavation of the deep-seated coupling mechanism of the social-ecological system by revealing the basic structure of this system to answer the following three questions. What are the elements of the social-ecological system? What are the correlations between elements? How does the system work? The results are as follows. (1) The social-ecological system consists of six basic elements—population, capital, facility, management, resource, and environment—the first four of which constitute the social subsystem, and the last two of which constitute the ecological subsystem. (2) The basic material circulation and social production chains formed by the six basic elements through specific material and information flow are interrelated; they are fed to each other to form a unit social-ecological system, and a hexagonal network structure is formed through the networking of flow elements. (3) The essential feature of the operation of the hexagonal network structure is circulation. The basic social production chain is nested in the basic material circulation chain; that is, the ecological subsystem provides raw materials and services for social production, then starts the next cycle after absorbing the waste generated by the social subsystem during the production and consumption process. This research reveals that the social-ecological system structure is not only a static geometric network with stability and elasticity formed layer by layer due to multiple factors but also a dynamic circular network based on the circular movement of factors, which can distinguish flow and stock.

GSCINet: Gradual Shrinkage and Cyclic Interaction Network for Salient Object Detection

Feature Pyramid Network (FPN) has been widely applied in the task of salient object detection (SOD), which has achieved great performance. However, most existing FPN-based SOD methods still have some limitations, such as insufficient guidance due to gradual dilution of semantic information, excessive computation leading to slow inference speed, and low efficiency of training models. In this paper, we design a novel Gradual Shrinkage and Cyclic Interaction Network (GSCINet) for efficient and accurate SOD, consisting of a Multi-Scale Contextual Attention Module (MSCAM) and an Adjacent Feature Shrinkage and Interaction Module (AFSIM). Specifically, the MSCAM aims at efficiently capturing multi-scale and multi-receptive-field contextual attention information through a series of well-designed convolutions and attention weight matrices of different scales to enhance the performance of initial input features. Subsequently, in AFSIM, we propose a gradual shrinkage structure and introduce a circular interaction mechanism to optimize the compressed features with less calculation cost, thereby enabling fast and accurate inference of salient objects. Extensive experimental results demonstrate the high efficiency and superiority of GSCINet against 17 state-of-the-art (SOTA) saliency detection methods under multiple evaluation metrics.

Application of efficient recognition algorithm based on deep neural network in English teaching scene

The recognition of English texts in teaching scenes is a practical research direction. English text recognition can be widely used in English teaching scenes, such as assisting teachers to recognise students’ English homework, text positioning before text translation, developing outdoor classrooms, assisting junior students in scene understanding and so on. To identify English information in different scenes as accurately as possible, identifying the corresponding text content is the key. Based on a deep neural network, this paper proposes GCN-Attention English recognition algorithm. The experiment adopts the deep learning framework Tensorflow, which combines 104 × 104 size GCN with an attention mechanism for training. The output of GCN is used to train the cyclic neural network to continuously predict the next most likely letter in the sequence. The goal of training is to match the output words with the expected words as much as possible. The test results show that the model can have a good recognition accuracy for the scene image data set used in teaching.

A Semantic Model of Internet of Things for Intelligent Translation and Learning

There were a lot of multisource data and heterogeneous devices in the intelligent system of the Internet of things, and the existing methods were difficult to meet the service needs of users for intelligent entities. Therefore, this paper proposed a semantic model construction method of the Internet of things based on intelligent translation and learning. Firstly, on the basis of summarizing the relevant theories of semantic Internet of things, this paper analyzed the semantic data and its characteristics, and expounded the common ontology matching methods. Secondly, according to the characteristics of service ontology and user ontology in intelligent Internet of things system, a method of matching two different ontologies based on string and semantic relationship was proposed, and the cyclic neural network method was used to organically integrate the semantic data of ontology. Finally, in order to realize the perception and representation of the context information of the Internet of things, a semantic model of the Internet of things based on intelligent translation and learning was constructed. Through experimental comparative analysis, the results showed that compared with the traditional methods based on semantic similarity and semantic distance, the semantic model of the Internet of things proposed in this paper had better performance in accuracy and recall, and can achieve better application effect of the Internet of things system. The model proposed in this paper will provide a theoretical reference for further exploring the sharing and service of heterogeneous devices and data in the intelligent Internet of things system.

Application of Attention Mechanism with Prior Information in Natural Language Processing

When using deep learning methods to model natural language, a recurrent neural network that can map input sequences to output sequences is usually used. Considering that natural language contains more complicated syntactic structures, and the performance of cyclic neural networks in long sentence processing will decrease, scholars have introduced an attention mechanism into the model, which has improved the above problems to a certain extent. The existing attention mechanism still has some shortcomings, such as the inability to explicitly obtain the known syntactic structure information in the sentence, and the poor interpretability of the output probability. In response to the above problems, this article will improve the attention mechanism in the recurrent neural network model. Firstly, the prior information in the natural language sequence is constructed as a graph model through syntactic analysis and other means, and then the graph structure regularization term is introduced into the sparse mapping. A new function netmax is constructed to replace the softmax function in the traditional attention mechanism, thereby improving the performance of the model and making the degree of association. The input values corresponding to larger input samples are closer, making the output of the attention mechanism easier to understand. The innovation of this paper mainly lies in that the weight calculation method which can be widely used in the attention mechanism is proposed by combining the deep learning model with statistical knowledge, which opens a channel to introduce the prior information for the deep learning model in natural language processing tasks.

Research on throughput prediction of 5G network based on LSTM

This paper proposes a wireless network traffic prediction model based on long-term and short-term memory cyclic neural networks. Through simulation experiments, the throughput prediction of 5G wireless networks using different scheduling algorithms for many different types of services is studied. The results verify that the long short-term memory prediction model has acceptable prediction accuracy and algorithm training speed, meets the needs of wireless network traffic prediction, and has a good application prospect.

Research on Discourse Transfer Analysis Based on Deep Learning of Cross-language Transfer

With the current exchange and communication between different countries becoming more and more frequent, the language conversion of different countries has become a difficult problem. The analysis of a series of problems in cross-language discourse conversion, the study of the discourse conversion path, and innovation motivation based on the deep learning theory of cross-language transfer, it has theoretical and practical significance. This paper aims at the technical difficulties in speech conversion methods to effectively utilize the local mode information of signal time spectrum and the long-term correlation of speech signal. A discourse conversion method based on convolutional recurrent neural network model is proposed. In the model, the extended convolutional neural network is used to model the long-term correlation of speech signals. In the part of speech fundamental frequency estimation, the prosodic information generated by the decomposition of the fundamental frequency by continuous wavelet transform is used as the training target of the fundamental frequency estimation model. The experimental results show that the speech transformation method based on the convolutional cyclic network model proposed in this paper has better quality and intelligibility than the speech transformed by the contrast method.

An Improved Four-Rotor UAV Autonomous Navigation Multisensor Fusion Depth Learning

Whether it is for military or civilian use, quadrotor UAV has always been one of research central issues. Most of the current quadrotor drones are manually operated and use GPS signals for navigation, which not only limits the operating range of the drone but also consumes a lot of manpower and material resources. This research mainly studies the method of realizing autonomous flight and conflict avoidance of quadrotor UAV by using multisensor system and deep learning method in extreme flight conditions through track prediction. The convolutional neural network method is used to extract the image information collected by the UAV sensor system. And it uses the cyclic neural network to extract the time feature of the information collected by the UAV sensor. The research results show that the track prediction method based on the deep learning method has higher flight accuracy for quadrotor UAVs. The yaw error of the spatial position is only 2.82%, and the maximum error of the time characteristic error tolerance is only 0.77%.

Design and Analysis of English Intelligent Translation System Based on Internet of Things and Big Data Model.

Today, we have entered an era of big data. Under the background of global economization, communication in all walks of life is becoming more and more frequent and cross-language communication is inevitable. Cross-language communication is difficult for many people. The online translation system can greatly reduce the communication barriers between people of different languages. As an efficient tool, the translation system can realize the translation of different languages under the conditions of retaining the original semantics equivalent conversion. The article adopts the Internet of Things technology and big data model to build an English intelligent translation system, which can realize intelligent translation between multiple languages and English. The research results of the article show the following: (1) For samples with high semantic feature values, the correlation coefficient and similarity coefficient will be higher. Therefore, it can be concluded that for different semantics, the similarity is generally positively correlated with its feature value and correlation coefficient. The translation speed of the system proposed in the article is the fastest among the three translation systems. When the number of sentences is 10,000, the translation speed of the translation system proposed in the article is 5.89 seconds, the translation speed of the network multilingual translation system is 6.74 seconds, and the translation speed of the traditional translation system is 10.53 seconds. (2) The translation accuracy of the big data intelligent translation model proposed in the article is the highest among the three models. The translation accuracy of simple sentences can reach 99%. The translation accuracy of general sentences is 98%, and the translation accuracy of complex sentences is 95%. The BLEU value of the method in this paper is basically the same as that of the RNN cyclic neural network translation model. When translating general sentences, the BLEU value of the method in this paper is slightly higher than that of the RNN cyclic neural network translation model; especially when translating complex sentences by machine, the BLEU value of the method in this paper is far higher than that of the RNN translation model. (3) The average response time will increase with the increase in the number of tests, and the success rate generally remains above 98%, close to 100%, indicating that the response time of the system operation is normal. The number of designed test cases for the data processing module is 90, the number of executed test cases is 90, and the execution rate can reach 100%. Normal operation means that in the process of operation, no fault occurs. In the system load test, the load of serial number 1 is normal, the average delay is 38 seconds, the average delay of serial number 2 is 48 seconds, the average delay of serial number 3 is 59 seconds, the average delay of serial number 4 is 62 seconds, and the average delay of serial number 5 is 47 seconds. The delay of data packets under all kinds of loads can meet the standard requirements.

Using Bidirectional Long-Term Memory Neural Network for Trajectory Prediction of Large Inner Wheel Routes

When a large car turns at an intersection, it often leads to tragedy because the driver does not pay attention to the incoming car or the dead corner of the line of sight of the car body. On the market, the wheel difference warning system used in large cars generally adds sensors or lenses to confirm whether there are incoming vehicles in the dead corner of the line of sight. However, the accident rate of large vehicles has not been reduced due to the installation of a vision subsidy system. The main reason is that motorcycle and bicycle drivers often neglect to pay attention to the inner wheel difference formed when large vehicles turn, resulting in accidents with large vehicles at intersections. This paper proposes a bidirectional long-term memory neural network for the prediction of the inner wheel path trajectory of large cars, mainly from the perspective of motorcycle riders, through the combination of YOLOv4 and the stacked Bi-LSTM model used in this study to analyze the motion of large cars and predict the inner wheel path trajectory. In this study, the turning trajectory of large vehicles at the intersection is predicted by using an object detection algorithm and cyclic neural network model. Finally, the experiment shows that this study uses the stacked Bi-LSTM trajectory prediction model to predict the next second trajectory with one second trajectory data, and the prediction accuracy is 87.77%; it has an accuracy of 75.75% when predicting the trajectory data of two seconds. In terms of prediction error, the system has a better prediction error than LSTM and Bi-LSTM models.

Multistationarity in Cyclic Sequestration-Transmutation Networks.

We consider a natural class of reaction networks which consist of reactions where either two species can inactivate each other (i.e., sequestration), or some species can be transformed into another (i.e., transmutation), in a way that gives rise to a feedback cycle. We completely characterize the capacity of multistationarity of these networks. This is especially interesting because such networks provide simple examples of "atoms of multistationarity", i.e., minimal networks that can give rise to multiple positive steady states.