Graph Construction Method Research Articles

A Study on a Knowledge Graph Construction Method of Safety Reports for Process Industries

There are some representative reports in industrial safety engineering, such as the Hazard and Operability Analysis and Pre-Hazard Analysis; however, a large amount of industrial safety knowledge in the report has not been fully explored. In order to reuse and release the value of industrial safety knowledge, this paper constructs a new industrial safety knowledge extraction framework. The framework combines the asset management shell to summarize the knowledge concept entities of machine description language and model description language. According to the safety report template, the framework also constructs a new industrial safety knowledge-mapping standard structure. Specifically, firstly, considering that the knowledge structure of safety reports is different in different processes of the process industry, this paper innovatively proposes a general industrial safety knowledge-mapping standard structure, which provides a practical solution for the integration of industrial knowledge representation problems in different processes. Secondly, based on the research progress of named entities, this paper presents an industrial named entity extraction method (INERM) for the process industry. This method designs an entity weight model to calculate the entity weight of each sentence, and adds part-of-speech weight to improve the entity extraction algorithm, which alleviates the problem that the existing entity extraction methods cannot reasonably use the semantic information and context of word. Finally, we construct a triple of industrial safety knowledge based on the rules and store it in Neo4j. In this paper, four semantic-type templates and five semantic relation templates are constructed based on the new industrial safety knowledge map standardization construction process of the process industry. The comparative experiments show that the accuracy of the INERM on the test set is improved by 17 percentage points on average compared with other key entity extraction algorithms. A total of 1329 entities are constructed in the directional application example of the fluid transportation process, which provides a large number of references for the safety of the fluid transportation process and is more conducive to improving the safety guarantee of the fluid transport process.

Graph Construction Method for GNN-Based Multivariate Time-Series Forecasting

Multivariate time-series forecasting (MTSF) plays an important role in diverse real-world applications. To achieve better accuracy in MTSF, time-series patterns in each variable and interrelationship patterns between variables should be considered together. Recently, graph neural networks (GNNs) has gained much attention as they can learn both patterns using a graph. For accurate forecasting through GNN, a well-defined graph is required. However, existing GNNs have limitations in reflecting the spectral similarity and time delay between nodes, and consider all nodes with the same weight when constructing graph. In this paper, we propose a novel graph construction method that solves aforementioned limitations. We first calculate the Fourier transform-based spectral similarity and then update this similarity to reflect the time delay. Then, we weight each node according to the number of edge connections to get the final graph and utilize it to train the GNN model. Through experiments on various datasets, we demonstrated that the proposed method enhanced the performance of GNN-based MTSF models, and the proposed forecasting model achieve of up to 18.1% predictive performance improvement over the state-of-the-art model.

A Classification Method for English Texts Based on Hybrid Recurrent Neural Network and Graph Construction in Social Recommendation Systems

Text classification (TC) methods are widely used in the field of recommendation systems. Text data has the characteristics of short length, large capacity, and variable data distribution, resulting in sparsity and concept drift issues, which pose challenges to text classification methods. In view of this, a recursive neural network and graph construction method has been proposed for classifying English texts in social recommendation systems. First, the English text document serves as the original dataset. Then, the data is preprocessed through tokenization, removal of stop words, stemming, and min-max normalization. Meanwhile, the principal component analysis is used to extract text features from English texts. Finally, feature selection is performed using information gain technology to improve text classification performance. The simulation results show that compared with the comparison method, the proposed algorithm has ideal results in accuracy, precision, recall, F1-score, true positive rate, and false positive rate. Meanwhile, based on experimental data, it was found that the proposed method outperforms state-of-the-art methods in text analysis of English text works.

DSR-GCN: Differentiated-Scale Restricted Graph Convolutional Network for Few-Shot Hyperspectral Image Classification

Graph convolution networks (GCNs) have shown great potentials for few-shot hyperspectral image (HSI) classification. Mainstream GCNs construct graph according to single scale segmentation, which usually ignores subtle adjacency relation between small regions, leading to unreliable initial local graph. To overcome the above issue, we propose a differentiated-scale restricted GCN (DSR-GCN) for HSI classification. Firstly, we propose a differentiated-scale graph construction method considering both the subtle and relative wider range spectral-spatial relation. Secondly, restricted fusion loss is designed to restrict the fusion of features extracted with differentiated-scale GCN branches. Finally, we design a lightweight spatial-spectral siamese network to remedy local pixel-level features. The proposed DSR-GCN can better model spatial structure with a reliable and refined graph, and it can capture more discriminate features in few-shot learning (FSL) scenario. Extensive experiments conducted on four benchmark data sets demonstrate that DSR-GCN outperforms the other deep learning methods in terms of classification accuracy and generalization performance, with the improvements in terms of OA around 6.20%~23.41% (Indian Pines), 4.45%~ 16.48% (University of Pavia), 4.25%~11.85% (Salinas), and 2.0%~17.23% (University of Houston) under 5 labeled samples per class.

Picture-in-Picture Strategy-Based Complex Graph Neural Network for Remaining Useful Life Prediction of Rotating Machinery

Graph neural networks are increasingly explored in the field of Prognostics and Health Management (PHM) due to their excellent performance when dealing with non-Euclidean data. However, current graph neural networks are mostly based on real domain modeling. In addition, existing graph construction methods rely on the prior positional relationship of multiple sensors. In view of the above, this paper proposes complex graph neural network based on the picture-in-picture strategy (CGNN-PIP) to realize the remaining useful life (RUL) prediction of rotating machinery under multi-channel signals. Specifically, the classical graph convolution operation is upgraded to generalized complex graph convolution, and complex graph neural network is further constructed to extract deep degenerate feature representations. Meanwhile, the picture-in-picture strategy is designed to guide graph construction, which takes the single-path graph as a node of the new graph to build a deeper-level graph. We verified the effectiveness and superiority of the proposed method through two case studies on different run-to-failure datasets. The results show that the proposed CGCN-PIP can reasonably construct the topology map of the complex domain data, and extract the temporal and structural information reflecting the equipment degradation. The comparison with state-of-the-art methods also proves that CGCN-PIP has advantages in terms of prediction accuracy and training consumption.

Oversmoothing Relief Graph Convolutional Network-Based Fault Diagnosis Method With Application to the Rectifier of High-Speed Trains

In the conventional graph convolutional network (GCN)-based fault diagnosis method, multilayer GCN model is often used for feature extraction. However, the application of multilayer GCN will encounter oversmoothing problem, and thus reduce the diagnostic performance. Therefore, the oversmoothing relief GCN (OsR-GCN) method is proposed. Specifically, two association graph construction methods, namely the Euclidean distance (ED)-based method and the structure analysis (SA)-based method, are first introduced. Then, the constructed graph and measurements are input to the OsR-GCN model, in which a weight coefficient is proposed to relieve the oversmoothing problem. Next, an improved particle swarm optimization algorithm is introduced to find the optimal weight coefficient. Finally, the proposed method is applied to diagnose the pulse rectifier faults in a hardware-in-the-loop simulated traction control system of high-speed trains. The achieved results show that the proposed method outperforms the existing fault diagnosis methods.

Dynamic knowledge modeling and fusion method for custom apparel production process based on knowledge graph

Compared with ordinary mass-produced apparel products, custom apparel products will generate more data at each stage of their life cycle. Such data is in a highly dynamic state, while the relationship between the data is more complex. However, the current use of traditional relational data to store the whole life cycle data of custom apparel products has several problems of high redundancy, weak correlation, discrete distribution, and certain limitation of storage capacity. Therefore, based on knowledge graph, a dynamic knowledge modeling and fusion method is proposed for the production process of custom apparel. Firstly, an ontology-based knowledge modeling method is designed for custom apparel, which defined three types of ontology modeling methods for the process, resources, and features. On this basis, a knowledge graph construction method based on bi-directional fusion for the custom apparel production system is proposed. With one order as a unit, a knowledge graph facet (KGF) model, as well as the derived knowledge representation, generation and fusion method, is established to realize dynamic knowledge fusion of the custom apparel production process. Finally, taking the suit production process of a custom apparel factory as an example, the corresponding knowledge graph is constructed based on the ontology knowledge model, and the effectiveness of the proposed knowledge fusion method is verified.

Generation of Configuration Space Trajectories Over Semi-Constrained Cartesian Paths for Robotic Manipulators

Serial-link manipulators are required to execute trajectories that enable a robot end-effector or a tool to track a Cartesian path. Practical applications may not require constraining all six degrees of freedom (position and orientation) of the tool resulting in semi-constrained paths. Semi-constrained paths allow improved success rates and better quality trajectories as the robot has more freedom to meet the kinematic and dynamic constraints. Additionally, robotic applications will need to use multiple tool center points (TCPs) on the tool to generate feasible paths for the robot. We present an iterative graph construction method to find trajectories for semi-constrained Cartesian paths that also use multiple TCPs. Our graph-based method finds multiple inverse kinematic solutions for possible Cartesian poses that the robot can take and connects them to build a graph. The algorithm uses cues from the Cartesian space to prioritize poses that produce a better quality solution. A biasing scheme is also developed to selectively sample the starting Cartesian poses from available choices. Our method finds near-optimal solutions with significantly fewer nodes and edges in the graph. The algorithm’s performance results on complex industrial test cases are provided. Note to Practitioners—Industrial applications permit the relaxation of one or more degrees of freedom of the tool while following the Cartesian paths. The relaxation of constraints is introduced by defining tolerances between the tool and the workpiece. Multiple TCPs have to be employed for many tasks to use different surfaces of the tool. In this paper, we present a planning algorithm for semi-constrained Cartesian paths that can incorporate the use of multiple TCPs. The user can define discrete TCPs over the tool contact points or surfaces. The tolerances can be easily defined as angular limits on tool orientation along the Cartesian path. Our planning algorithm can work with others via point constraints in Cartesian space or joint space of the robot. Practitioners from the industry can use the method presented in this paper to develop automated robotic cells that do cutting, sanding, polishing, welding, painting, composite layup, additive manufacturing, and several other common applications.

Hyperspectral Band Selection With Iterative Graph Autoencoder

Hyperspectral band selection (BS) is an important task for hyperspectral image (HSI) processing, which aims to select a discriminative and low-redundant band subset. As a significant cue for BS, structure information describes the cross-band correlation which brings the redundancy of HSI. Existing methods model structure information via manual rule-based graph construction. However, such a graph construction method fails to model complex and diverse structural relationships of HSI data. To address this problem, we propose a data-driven method, named iterative graph auto-encoder for band selection (IGAEBS). It adaptively captures structure information by a data-specific automatic construction process, rather than by a fixed empirical design. Specifically, we propose a new unsupervised pretext task to train graph convolution neural network to extract HSI features. These features are used to construct a graph to represent the structural relationships among bands. To enhance the reliability of the graph, we further design an iterative graph improvement mechanism to progressively refine the structure representation. Using the derived graph, we partition the bands into several clusters and select a representative band from each cluster. During the selection process, both intra- and inter-cluster information are considered to improve the discriminativeness of band subset. Extensive experiments are conducted on three public data sets to validate the superiority of the proposed method compared to other state-of-the-art methods.

Constructing Product Usage Context Knowledge Graph Using User-Generated Content for User-Driven Customization

Abstract User-driven customization is a particular design paradigm where customers act as co-designers to configure products based on their needs. However, due to insufficient product usage experience, customers may design a product incompatible with their environment and needs. Such incompatibility can negatively affect the performance of some customized features or even cause product failure. As a result, customers may hesitate to customize products because additional complexities and uncertainties are perceived. Product usage context (PUC), as all the environment and application factors that affect customer needs and product performance, can be used to facilitate customer co-design in user-driven customization. Identifying individual customer’s PUC can help customers foresee potential design failures, make more holistic design decisions, and be confident with their designs. Against the background, this paper proposes a PUC knowledge graph (PUCKG) construction method using user-generated content (UGC). The proposed method can convert crowdsourced corner cases into structured PUCKG to support personal PUC prediction, summarization, and reasoning. A case study of robot vacuum cleaners is conducted to validate the efficacy of the proposed method.

Heterogeneous graph construction and node representation learning method of Treatise on Febrile Diseases based on graph convolutional network

ObjectiveTo construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) dataset and explore an optimal learning method represented with node attributes based on graph convolutional network (GCN). MethodsClauses that contain symptoms, formulas, and herbs were abstracted from Treatise on Febrile Diseases to construct symptom-formula-herb heterogeneous graphs, which were used to propose a node representation learning method based on GCN − the Traditional Chinese Medicine Graph Convolution Network (TCM-GCN). The symptom-formula, symptom-herb, and formula-herb heterogeneous graphs were processed with the TCM-GCN to realize high-order propagating message passing and neighbor aggregation to obtain new node representation attributes, and thus acquiring the nodes’ sum-aggregations of symptoms, formulas, and herbs to lay a foundation for the downstream tasks of the prediction models. ResultsComparisons among the node representations with multi-hot encoding, non-fusion encoding, and fusion encoding showed that the Precision@10, Recall@10, and F1-score@10 of the fusion encoding were 9.77%, 6.65%, and 8.30%, respectively, higher than those of the non-fusion encoding in the prediction studies of the model. ConclusionNode representations by fusion encoding achieved comparatively ideal results, indicating the TCM-GCN is effective in realizing node-level representations of heterogeneous graph structured Treatise on Febrile Diseases dataset and is able to elevate the performance of the downstream tasks of the diagnosis model.

Missing-edge aware knowledge graph inductive inference through dual graph learning and traversing

Knowledge graph (KG) is a kind of structured human knowledge of modeling the relations between real-world entities. This paper studies the KG inductive inference problem, i.e., predicting the relations for out-of-KG entities. However, due to the incomplete nature of the KGs, the connections of some relations are missing. This makes existing differentiable rule learning methods unable to represent some possible rule candidates, which will further affect the inductive inference result. To solve this challenge, our research hypothesis is that the semantics of relation’s argument can be well used to reflect the possible connections between relations. We propose a KG inductive inference model, RuleNet, which consists of two parts. Firstly, a query-dependent dual graph construction method is proposed, which is able to learn the relation connections using the information of the relation’s argument. Secondly, a dual graph traversing method is proposed, which is able to traverse all possible rule candidates even if some rules cannot be formed due to the missing edges. Performance of the proposed methods is evaluated using the FB15K237 (10%–20%), WN18RR (10%–20%) and YAGO3-10 (10%–20%) benchmarks. Experimental results show that RuleNet achieves a superior performance compared with many strong baselines. Ablation studies have verified the effectiveness of the proposed network components. Qualitative analysis shows that RuleNet can learn meaningful dual graph and logic rules.

Relational Graph Construction Method and Information Management System Based on the Relational Graph Convolutional Network

The Internet is like a huge neural network that is thought to be built, linking all the information in the human brain, and the communication between people is a part of the communication in the whole society. Social products are the medium of communication between people, so the efficiency of social products directly affects the efficiency of people and even the whole society. This paper mainly focuses on social applications as the object to carry out research. This paper is dedicated to optimizing the user experience and social experience of mobile social products, optimizing the design strategies of each process of social products, and exploring the possibility and development direction of social products in the future. Firstly, it conducts in-depth research on the related theories of human social behavior based on the social relationship graph and summarizes the factors that affect the intimacy between nodes in the social relationship graph. Then, it discusses the role of these factors in designing social products and studies how to apply these factors to all aspects of product development. Then, this design method using intimacy factor is abstracted and summarized into a design model, which is convenient for product developers to understand and use. Finally, the practice shows that the mobile social design method based on the social relationship graph can effectively guide the design of mobile social products and provide users with an intimate and efficient social experience that can meet the social needs of users. The accuracy rate is effectively improved by 21%, which proves the value and prospect of the research, design, and development of this topic in the field of mobile social products.

Zero-shot surface defect recognition with class knowledge graph

Convolutional neural networks (CNNs)-based methods achieve excellent performance on surface defects that belong to the same base classes from a training set, which plays an essential role in ensuring product quality in manufacturing systems. However, in the real world, novel classes of defects always exit due to the complexity and changes of the manufacturing environment. These novel classes are never seen during the training stage but are required to be correctly classified. This paper proposes a class knowledge graph (ZS-CKG) method to address the zero-shot problem in real-world surface defect recognition. In the proposed ZS-CKG method, the class knowledge graph construction method (CKGC) is proposed to construct a class knowledge graph to establish the relationship between base and novel defect classes. Then learns class features by using a graph convolutional neural network. The ZS-CKG utilizes the transformer encoder with capturing long-range dependencies to extract features of defect samples to obtain discriminative defect image features, due to the fact that industrial defects have different shapes and sizes. The experimental results on the public NEU-CLS dataset and real engineering dataset printed circuit boards (PCB) surface defects collected from an actual manufacturing factory demonstrate that the proposed method can effectively address zero-shot surface defect recognition. The ZS-CKG achieve an accuracy of 60.91% and 50.53% on the NEU-CLS and PCB datasets, respectively, which increase by 33.82% and 2.36% compared to the best competing method.

Graph method for driving behavior optimization based on “SAF-ECO” description of behavior characteristics

Considering the fact that driving behavior data possesses characteristics of strong real-time, poor stability, and continuous change, this study proposes the Individual Driving Behavior Graph Construction Method (DBGCM), which visually presents the time trajectory of driving behavior to explore safety-ecological (SAF-ECO) characteristics of individual drivers. The results can be applied in the analysis of driving safety ecology and as a reference for driving behavior optimization. This study is based on the micro-driving behavior data collected by the on-board diagnostic devices (OBD), which can create a graph on individual driver behavior characteristics via nodes and time axis as its elements. Additionally, the method of Longest Common Subsequence (LCSS) is proposed to identify the similarity among different driving behavior graphs. The data results of taxi drivers under different SAF-ECO levels lead to the conclusion that the driving behavior characteristics graph analysis is consistent with the SAF-ECO classification. The similarity of graphs among “safe and non-eco” drivers is higher than that within other categories. Finally, the research discusses in detail the data requirements, method verification, and future applications. The reasonable coupling characteristic description of “SAF-ECO” driving behavior is conducive to the enhancement of drivers’ self-management ability, driving education, and customization for drivers.

Combining knowledge graph into metro passenger flow prediction: A split-attention relational graph convolutional network

With the rapid development of intelligent operation and management in metro systems, accurate network-scale passenger flow prediction has become an essential component in real-time metro management. Although numerous novel methods have been applied in this field, critical barriers still exist in integrating travel behaviors and comprehensive spatiotemporal dependencies into prediction. This study constructs the metro system as a knowledge graph and proposes a split-attention relational graph convolutional network (SARGCN) to address these challenges. Breaking the limitations of physical metro networks, we develop a metro topological graph construction method based on the historical origin–destination (OD) matrix to involve travel behaviors. Then, we design a metro knowledge graph construction method to incorporate land-use features. To adapt prior knowledge of metro systems, we subsequently propose the SARGCN model for network-scale metro passenger flow prediction. This model integrates the relational graph convolutional network (R-GCN), split-attention mechanism, and long short-term memory (LSTM) to explore the spatiotemporal correlations and dependence between passenger inflow and outflow. According to the model validation conducted on the metro systems in Shenzhen and Hangzhou, China, the SARGCN model outperforms the advanced baselines. Furthermore, quantitative experiments also reveal the effectiveness of its component and the constructed metro knowledge graph.

Novel Projection Schemes for Graph-Based Light Field Coding.

In light field compression, graph-based coding is powerful to exploit signal redundancy along irregular shapes and obtains good energy compaction. However, apart from high time complexity to process high dimensional graphs, their graph construction method is highly sensitive to the accuracy of disparity information between viewpoints. In real-world light field or synthetic light field generated by computer software, the use of disparity information for super-rays projection might suffer from inaccuracy due to vignetting effect and large disparity between views in the two types of light fields, respectively. This paper introduces two novel projection schemes resulting in less error in disparity information, in which one projection scheme can also significantly reduce computation time for both encoder and decoder. Experimental results show projection quality of super-pixels across views can be considerably enhanced using the proposals, along with rate-distortion performance when compared against original projection scheme and HEVC-based or JPEG Pleno-based coding approaches.

Dynamic graph convolutional networks based on spatiotemporal data embedding for traffic flow forecasting

Traffic flow forecasting has always been a challenge owing to its complicated spatiotemporal dependencies. Few of previous works can exploit the implicit interactions among traffic flows, leading to the superficial extraction of spatiotemporal features. Though graph convolutional networks have showed exciting performance in traffic flow forecasting, existing works either ignore the dynamic characteristics of the correlations among sensors or fail to extract the hidden fine-grained correlations among sensors, which makes it difficult to model the spatial dependency deeply. Therefore, a new deep learning model is proposed in this study to overcome these drawbacks and to achieve accurate traffic flow forecasting. First, a new spatiotemporal data embedding method is proposed to convert the original traffic flows into traffic flow vectors, so that the implicit correlations among traffic flows can be quantified and measured. Then, to sufficiently extract the non-linear global temporal features, a new temporal vector convolutional neural network is proposed to deal with the traffic flow vectors. Finally, a new dynamic correlation graph construction method is proposed to exploit the dynamic characteristics of correlations among sensors and explore the hidden fine-grained correlations among sensors, which is conducive to learning deep non-Euclidean spatial features. Experiments on five traffic datasets demonstrate that the proposed model is superior to state-of-the-art baseline models.

A Deep Domain-Adversarial Transfer Fault Diagnosis Method for Rolling Bearing Based on Ensemble Empirical Mode Decomposition

In recent years, the deep learning-based fault diagnosis methods for rotating mechanical equipment have attracted great concern. However, because the data feature distributions present differences in applications with varying working conditions, the deep learning models cannot provide satisfactory performance of fault prediction in such scenarios. To address this problem, this paper proposes a domain adversarial-based rolling bearing fault transfer diagnosis model EMBRNDNMD. First of all, an EEMD-based time-frequency feature graph (EEMD-TFFG) construction method is proposed, and the time-frequency information of nonlinear nonstationary vibration signal is extracted; secondly, a multi-branch ResNet (MBRN) structure is designed, which is used to extract deep features representing the bearing state from EEMD-TFFG; finally, to solve the model domain adaptation transfer problem under varying working conditions, the adversarial network module and MK-MMD distribution difference evaluation method are introduced to optimize MBRN, so as to reduce the probability distribution difference between the deep features of source domain and target domain, and to improve the accuracy of EMBRNDNMD in state diagnosis of target domain. The results of experiments carried out on two bearing fault test platforms prove that EMBRNDNMD can maintain an average accuracy above 97% in fault transfer diagnosis tasks, and this method also has high stability and strong ability of scene adaptation.

Pruning graph convolutional network-based feature learning for fault diagnosis of industrial processes

In recent years, deep learning has been widely applied in process fault diagnosis due to its powerful feature extraction ability. A predominant property of these fault diagnosis models is to extract effective features from process signal. However, it is still difficult for them to construct the feature association relationship between input data. To solve these problems, this paper proposes a new graph neural network (GNN), pruning graph Convolutional network (PGCN), to perform feature learning based on the graph data. One dimensional process data are transformed into graph data by a graph construction method. A graph Convolutional network (GCN) is used to extract the features of process data. A pruning method of graph structure is proposed to effectively extract important information from process fault data. The feasibility and effectiveness of PGCN are verified on two benchmark processes, i.e., continuous stirred-tank reactor (CSTR) and fed-batch fermentation penicillin process (FBFP). The experimental results show that the performance of PGCN in feature extraction and process fault diagnosis is better than that of other typical methods, which provides a good possibility for the application of GCN in industrial process fault diagnosis.