Continuous Vector Research Articles

A novel graph neural networks approach for 3D product model retrieval

ABSTRACT With the quick development of intelligent manufacturing technology, increasing of 3D product models data resource raises the need for product models retrieval method that can fully exploit model information, whereas the existing methods only concern geometric information with little or no manufacturing information. Model-Based Definition (MBD) 3D engineering has gained wide popularity in recent times which enables smart manufacturing by attaching product manufacturing information. Its tip orientation to the effective reuse of MBD for reducing development time and creating an efficient digital thread. In this paper, we proposed the MBD-based attribute adjacency graph neural networks (MAAGNN) with attention mechanism. Firstly, the MBD-based attribute adjacency graph (MAAG) is established to fully express the product semantic information, which includes geometric and non-geometric information of the MBD model. Then graph neural network (GNN) is employed to embed the MAAG into continuous vector spaces, and attention mechanism is introduced to adaptively recognize more important features information, which can solve the ambiguity problem caused by blend features such as chamfer. Finally, the model is trained to achieve fast and accurate retrieval of the MBD models. Experiments demonstrate its potential advantages to meet the requirements of engineering applications.

An Efficient Sorting Algorithm for Capacitor Voltage Balance of Modular Multilevel Converter With Space Vector Pulsewidth Modulation

Thisarticle presents an efficient analogue sorting algorithm for balancing the submodule (SM) capacitor voltages of modular multilevel converter (MMC). The proposed analogue sorting algorithm offers the advantage of fast convergence rate without any need of recursive loops for the implementation on embedded devices. It can be easily implemented with combinational logic operations on field programmable gate array (FPGA) and provides less hardware and computational overhead. The functionality and performance of the proposed analogue sorting algorithm is evaluated with the simulation model of three phase five-level MMC in MATLAB/Simulink environment. The real time implementation of the proposed sorting algorithm with the SM capacitor voltage balancing strategy is implemented on Altera/Cylone - I (EP1C12Q240C8N) FPGA. A five-level continuous space vector pulsewidth modulation (CSVPWM) is realized on a PIC microcontroller (PIC18F452). A down-scaled model of single-phase five-level MMC is designed and constructed to investigate the reliable and stable operation of MMC with the proposed analogue sorting algorithm and SVPWM method. Simulation and experimental results are presented for validation.

Graph Neural Network Encoding for Community Detection in Attribute Networks.

In this article, we first propose a graph neural network encoding method for the multiobjective evolutionary algorithm (MOEA) to handle the community detection problem in complex attribute networks. In the graph neural network encoding method, each edge in an attribute network is associated with a continuous variable. Through nonlinear transformation, a continuous valued vector (i.e., a concatenation of the continuous variables associated with the edges) is transferred to a discrete valued community grouping solution. Further, two objective functions for the single-attribute and multiattribute network are proposed to evaluate the attribute homogeneity of the nodes in communities, respectively. Based on the new encoding method and the two objectives, a MOEA based upon NSGA-II, called continuous encoding MOEA, is developed for the transformed community detection problem with continuous decision variables. Experimental results on single-attribute and multiattribute networks with different types show that the developed algorithm performs significantly better than some well-known evolutionary- and nonevolutionary-based algorithms. The fitness landscape analysis verifies that the transformed community detection problems have smoother landscapes than those of the original problems, which justifies the effectiveness of the proposed graph neural network encoding method.

The Optimal Classical Continuous Control Quaternary Vector of Quaternary Nonlinear Hyperbolic Boundary Value Problem

This work is concerned with studying the optimal classical continuous control quaternary vector problem. It is consisted of; the quaternary nonlinear hyperbolic boundary value problem and the cost functional. At first, the weak form of the quaternary nonlinear hyperbolic boundary value problem is obtained. Then under suitable hypotheses, the existence theorem of a unique state quaternary vector solution for the weak form where the classical continuous control quaternary vector is considered known is stated and demonstrated by employing the method of Galerkin and the compactness theorem. In addition, the continuity operator between the state quaternary vector solution of the weak form and the corresponding classical continuous control quaternary vector is demonstrated in three different infinite dimensional spaces (Hilbert spaces). Furthermore, with suitable hypotheses, the existence theorem of an optimal classical continuous control quaternary vector dominated by the weak form of the quaternary nonlinear hyperbolic boundary value problem is stated and demonstrated.

The Classical Continuous Optimal Control for Quaternary Nonlinear Parabolic Boundary Value Problems with State Vector Constraints

This paper aims to study the quaternary classical continuous optimal control problem consisting of the quaternary nonlinear parabolic boundary value problem, the cost function, and the equality and inequality constraints on the state and the control. Under appropriate hypotheses, it is demonstrated that the quaternary classical continuous optimal control ruling by the quaternary nonlinear parabolic boundary value problem has a quaternary classical continuous optimal control vector that satisfies the equality constraint and inequality state and control constraint. Moreover, mathematical formulation of the quaternary adjoint equations related to the quaternary state equations is discovered, and then the weak form of the quaternary adjoint equations is obtained. Lastly, both the necessary conditions for optimality and sufficient conditions for optimality of the proposed problem are stated and proved. The derivation for the Fréchet derivative of the Hamiltonian is attained.

Innovation and Integration Development of the Cultural Industry Based on Mapping Knowledge Domains.

In view of the less current user data of the cultural industry, its classification and presentation form are complex. This paper constructs the MKD of the cultural industry integration through the RDF graph model and realizes the distributed vector representation of cultural project semantic information by using the fine-tuning translation distance model TransH. The semantic information of cultural industry fusion is mapped to a continuous vector space, and the distributed vector representation of cultural projects is realized. The results show that it is helpful to accurately express the correlation between different regions and cultural types and to explore the data association and implicit relationship of innovation and integration development in the cultural industry.

Seroprevalence Rates against West Nile, Usutu, and Tick-Borne Encephalitis Viruses in Blood-Donors from North-Western Romania.

Introduction: West Nile virus (WNV), Usutu virus (USUV), and the tick-borne encephalitis virus (TBEV) are all arboviruses belonging to Flaviviridae family. All are characterized by vectorial transmission and sometimes associated with neuroinvasive infections. The circulation of these viruses is considered endemic in parts of Europe, with human cases reported in many countries. Among hosts, the viruses are vectored by hematophagous arthropods, such as mosquitoes (WNV, USUV) and ticks (TBEV). Considering the currently outdated knowledge regarding the epidemiology of these viruses in Romania, the aim of our study was to assess the seroprevalence rates of WNV, USUV, and TBEV among healthy blood donors in north-western Romania. Methods: Human blood samples from healthy donors were collected between November 2019 and February 2020 in six counties from the north-western region of Romania. The samples were serologically tested by ELISA and serum neutralization test. Results: Overall, we obtained a seroprevalence of 3.17% for WNV, 0.08% for TBEV, and 0% for USUV. Conclusion: Despite the low seroprevalence of WNV, USUV, and TBEV in our study, we highlight the need for continuous nationwide vector and disease surveillance and implementation of control measures. Further research is required for an optimal overview of the epidemiological status of the Romanian population regarding these flaviviruses together with countrywide awareness campaigns.

Contact-centric deformation learning

We propose a novel method to machine-learn highly detailed, nonlinear contact deformations for real-time dynamic simulation. We depart from previous deformation-learning strategies, and model contact deformations in a contact-centric manner. This strategy shows excellent generalization with respect to the object's configuration space, and it allows for simple and accurate learning. We complement the contact-centric learning strategy with two additional key ingredients: learning a continuous vector field of contact deformations, instead of a discrete approximation; and sparsifying the mapping between the contact configuration and contact deformations. These two ingredients further contribute to the accuracy, efficiency, and generalization of the method. We integrate our learning-based contact deformation model with subspace dynamics, showing real-time dynamic simulations with fine contact deformation detail.

Proper Noun Embedding Model for the Korean Dependency Parsing

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

Noninvasive Lung Cancer Early Detection via Deep Methylation Representation Learning

Early detection of lung cancer is crucial for five-year survival of patients. Compared with the pathological analysis and CT scans, the circulating tumor DNA (ctDNA) methylation based approach is noninvasive and cost-effective, and thus is one of the most promising methods for early detection of lung cancer. Existing studies on ctDNA methylation data measure the methylation level of each region with a predefined metric, ignoring the positions of methylated CpG sites and methylation patterns, thus are not able to capture the early cancer signals. In this paper, we propose a blood-based lung cancer detection method, and present the first ever study to represent methylation regions by continuous vectors. Specifically, we propose DeepMeth to regard each region as a one-channel image and develop an auto-encoder model to learn its representation. For each ctDNA methylation sample, DeepMeth achieves its representation via concatenating the region vectors. We evaluate DeepMeth on a multicenter clinical dataset collected from 14 hospitals. The experiments show that DeepMeth achieves about 5%-8% improvements compared with the baselines in terms of Area Under the Curve (AUC). Moreover, the experiments also demonstrate that DeepMeth can be combined with traditional scalar metrics to enhance the diagnostic power of ctDNA methylation classifiers. DeepMeth has been clinically deployed and applied to 450 patients from 94 hospitals nationally since April 2020.

Resulting Voltage Vector Moduli of Discrete States and Their Relationship with the Line-to-line Voltages of a Seven-phase Symmetrical Winding

A seven-phase valve converter connected to a symmetrical seven-phase winding has 126 logical states and can produce 126 discrete resulting voltage vectors. The converter state digital codes have the form (0000001-1111110), and the moduli of these vectors have eight values. The aim of the study is to define a numerical relationship between the resulting voltage vector moduli of discrete states and the line-to-line voltage ratios of a seven-phase symmetrical winding. The resulting voltage vector moduli of discrete states correspond to the moduli of the continuous rotation vectors obtained by expanding the corresponding phase voltage functions in the Fourier series. In carrying out the study, the vector analysis methods were used. The obtained results can be useful in designing an electric drive based on a seven-phase motor with vector control.

A multi-dimensional city data embedding model for improving predictive analytics and urban operations

PurposeA smart city is a potential solution to the problems caused by the unprecedented speed of urbanization. However, the increasing availability of big data is a challenge for transforming a city into a smart one. Conventional statistics and econometric methods may not work well with big data. One promising direction is to leverage advanced machine learning tools in analyzing big data about cities. In this paper, the authors propose a model to learn region embedding. The learned embedding can be used for more accurate prediction by representing discrete variables as continuous vectors that encode the meaning of a region.Design/methodology/approachThe authors use the random walk and skip-gram methods to learn embedding and update the preliminary embedding generated by graph convolutional network (GCN). The authors apply this model to a real-world dataset from Manhattan, New York, and use the learned embedding for crime event prediction.FindingsThis study’s results show that the proposed model can learn multi-dimensional city data more accurately. Thus, it facilitates cities to transform themselves into smarter ones that are more sustainable and efficient.Originality/valueThe authors propose an embedding model that can learn multi-dimensional city data for improving predictive analytics and urban operations. This model can learn more dimensions of city data, reduce the amount of computation and leverage distributed computing for smart city development and transformation.

There Exist Transitive Piecewise Smooth Vector Fields on $$\mathbb {S}^2$$ but Not Robustly Transitive

It is well known that smooth (or continuous) vector fields cannot be topologically transitive on the sphere $\S^2$. Piecewise-smooth vector fields, on the other hand, may present non-trivial recurrence even on $\S^2$. Accordingly, in this paper the existence of topologically transitive piecewise-smooth vector fields on $\S^2$ is proved, see Theorem \ref{teorema-principal}. We also prove that transitivity occurs alongside the presence of some particular portions of the phase portrait known as {\it sliding region} and {\it escaping region}. More precisely, Theorem \ref{main:transitivity} states that, under the presence of transitivity, trajectories must interchange between sliding and escaping regions through tangency points. In addition, we prove that every transitive piecewise-smooth vector field is neither robustly transitive nor structural stable on $\S^2$, see Theorem \ref{main:no-transitive}. We finish the paper proving Theorem \ref{main:general} addressing non-robustness on general compact two-dimensional manifolds.

A probabilistic ensemble approach for knowledge graph embedding

Knowledge graph embedding (KGE) is a technique for embedding entities and relations of knowledge graphs (KGs) into continuous vector spaces while maintaining the inherent structure of KGs, in this way link prediction can be facilitated by scoring candidate triples. Existing KGE models only capture specific features of a KG, however, link prediction capacity heavily relies on comprehensive features of a KG. In this work, we propose an ensemble approach for KGE by incorporating the features captured by different KGE models. As a key step, we propose a probabilistic scoring index for characterizing the link prediction performance of a given KGE model. Based on this we established a theoretical framework to calculate the optimal parameters for the ensemble model and predict its corresponding link prediction rate. In particular, we proved that our ensemble approach can always improve link prediction performance under some assumptions. The Upper Confidence Bound Algorithm is then used to adjust the parameters. Experimental results on two widely used KGs show that the proposed ensemble approach achieves the state-of-the-art link prediction rate.

Link Prediction in Knowledge Graphs: A Hierarchy-Constrained Approach

Link prediction over a knowledge graph aims to predict the missing head entities <inline-formula><tex-math notation="LaTeX">$h$</tex-math></inline-formula> or tail entities <inline-formula><tex-math notation="LaTeX">$t$</tex-math></inline-formula> and missing relations <inline-formula><tex-math notation="LaTeX">$r$</tex-math></inline-formula> for a triple <inline-formula><tex-math notation="LaTeX">$(h,r,t)$</tex-math></inline-formula> . Recent years have witnessed great advance of knowledge graph embedding based link prediction methods, which represent entities and relations as elements of a continuous vector space. Most methods learn the embedding vectors by optimizing a margin-based loss function, where the margin is used to separate negative and positive triples in the loss function. The loss function utilizes the general structures of knowledge graphs, e.g., the vector of <inline-formula><tex-math notation="LaTeX">$r$</tex-math></inline-formula> is the translation of the vector of <inline-formula><tex-math notation="LaTeX">$h$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$t$</tex-math></inline-formula> , and the vector of <inline-formula><tex-math notation="LaTeX">$t$</tex-math></inline-formula> should be the nearest neighbor of the vector of <inline-formula><tex-math notation="LaTeX">$h+r$</tex-math></inline-formula> . However, there are many particular structures, and can be employed to promote the performance of link prediction. One typical structure in knowledge graphs is hierarchical structure, which existing methods have much unexplored. We argue that the hierarchical structures also contain rich inference patterns, and can further enhance the link prediction performance. In this paper, we propose a hierarchy-constrained link prediction method, called hTransM, on the basis of the translation-based knowledge graph embedding methods. It can adaptively determine the optimal margin by detecting the single-step and multi-step hierarchical structures. Moreover, we prove the effectiveness of hTransM theoretically, and experiments over three benchmark datasets and two sub-tasks of link prediction demonstrate the superiority of hTransM.

The Optimal Control Problem for Triple Nonlinear Parabolic Boundary Value Problem with State Vector Constraints

In this paper, the classical continuous triple optimal control problem (CCTOCP) for the triple nonlinear parabolic boundary value problem (TNLPBVP) with state vector constraints (SVCs) is studied. The solvability theorem for the classical continuous triple optimal control vector CCTOCV with the SVCs is stated and proved. This is done under suitable conditions. The mathematical formulation of the adjoint triple boundary value problem (ATHBVP) associated with TNLPBVP is discovered. The Fréchet derivative of the Hamiltonian" is derived. Under suitable conditions, theorems of necessary and sufficient conditions for the optimality of the TNLPBVP with the SVCs are stated and proved.

Resource-aware synchronized path following of multiple unmanned surface vehicles with experiments: A cooperative vector field approach

This paper presents a cooperative vector field approach for synchronized path following of multiple autonomous surface vehicles (USVs) with limited communication resources. First, a cooperative vector field is proposed by introducing a path coordination design into a three-dimensional vector field. Based on the cooperative vector field, concise guidance laws of surge speed and angular rate are derived for synchronized path following. In order to reduce communication times among USVs, an event-triggered cooperative vector field is next proposed. Specifically, a predictor is devised to predict the current path variables by using the last transmitting ones, and an event-triggered mechanism is developed based on the predicted path variables. Then, a self-triggered cooperative vector field is developed to avoid continuous listening. A self-triggered mechanism is designed such that each USV predicts its next triggering time and broadcasts it to its neighbors at the current triggering time. The stability of the three cooperative vector fields is analyzed, and Zeno behavior is excluded. Finally, both simulation and experiment results are provided to illustrate the efficacy of the proposed continuous, event-triggered, and self-triggered cooperative vector fields for resource-aware synchronized path following.

Learning structured embeddings of knowledge graphs with generative adversarial framework

Many large knowledge graphs are now available and ready to provide semantically structured information that is regarded as an important resource for question answering and decision support tasks. However, they are built on rigid symbolic frameworks which makes them hard to be used in other intelligent systems. Knowledge graph embedding approaches are gaining increasing attention, which embeds symbolic entities and relations into continuous vector spaces. Such graph embeddings are often learned by training a model to distinguish true triples from negative ones. Unfortunately, the negative triples created by replacing their heads or tails with randomly selected entities are easily identified by the model, which makes them insufficient to train useful models. To this end, we propose a method under a generative adversarial architecture to learn graph embeddings, in which a generative network is trained to provide continually improved “plausible” triples whereas a discriminative network learns to distinguish truth triples from the others by competing with the generator in a two-player minimax game. When arriving at a convergence, the generative network recovers the training data and can be used for knowledge graph completion, while the discriminative network is trained to be a good triple classifier. Extensive experiments demonstrate our method can improve multiple graph embedding models with a significant margin on both link prediction and triple classification tasks.

Lie brackets of nonsmooth vector fields and commutation of their flows

It is well-known that the flows generated by two smooth vector fields commute, if the Lie bracket of these vector fields vanishes. This assertion is known to extend to Lipschitz continuous vector fields, up to interpreting the vanishing of their Lie bracket in the sense of almost everywhere equality. We show that this cannot be extended to general a.e. differentiable vector fields admitting a.e. unique flows. We show, however, that the extension holds when one field is Lipschitz continuous and the other one is merely Sobolev regular (but admitting a regular Lagrangian flow).

TissueSpace: a web tool for rank-based transcriptome representation and its applications in molecular medicine.

Cross-platform or cross-experiment transcriptome data is hard to compare as the original gene expression values from different platforms cannot be compared directly. The inherent gene expression ranking information is rarely utilized. Use of reduced vector to represent transcriptome data independent of platforms. Thus, we turned the expression profile into a rank vector, where a higher expression has a higher rank value, then applied Latent semantic analysis (LSA) to get compact and continuous 100-dimensional vector representations for samples. Results showed that the reconstructed vector has a precision of 96.7% in recovering tissue labels from an independent dataset. A user-friendly tool TissueSpace was developed, which provides users the following functionalities: (1) convert different gene ID types to Ensembl gene IDs; (2) project any human transcriptome profile to get vector representation for downstream analysis; (3) functional enrichment for each of the 100-dimensional vector features. Case studies for its applications in human common diseases indicate its usefulness. TissueSpace could be used to generate testable hypotheses for translational medicine. The TissueSpace tool is available at http://bioinformatics.fafu.edu.cn/tissuespace/ .