Node Weight Research Articles

Three-Way Selection Random Forest Optimization Model for Anomaly Traffic Detection

With the application and development of Internet technology, network traffic is growing rapidly, and the situation of network security is becoming more and more serious. As an important way to protect network security, abnormal traffic detection has been paid more and more attention. In this paper, the uncertainty of the samples in the abnormal traffic detection dataset is studied. Combining the three-way decision idea with the random forest algorithm, a three-way selection random forest optimization model for abnormal traffic detection is proposed. Firstly, the three-way decision idea is integrated into the random selection process of feature attributes, and the attribute importance based on decision boundary entropy is calculated. The feature attributes are divided into the normal domain, abnormal domain, and uncertain domain, and the three-way attribute random selection rules are designed to randomly select the feature attributes that conform to the rules from different domains. Secondly, the classifier evaluation function is constructed by combining pure accuracy and diversity, and the anomaly traffic detection base classifier with a high evaluation value is selected for integration to eliminate the unstable factors caused by randomness in the process of base classifier generation. Thirdly, the optimal node weight combination of the base classifier is obtained by iterative calculation of the gray wolf optimization algorithm to further improve the prediction effect and robustness of the model. Finally, the model is applied to the abnormal traffic detection dataset. The experimental results show that the prediction accuracy of the three-way selection random forest optimization model on CIC-IDS2017, KDDCUP99, and NSLKDD datasets is 96.1%, 95.2%, and 95.3%, respectively, which has a better detection effect than other machine learning algorithms.

Relation-Aware Weighted Embedding for Heterogeneous Graphs

Heterogeneous graph embedding, aiming to learn the low-dimensional representations of nodes, is effective in many tasks, such as link prediction, node classification, and community detection. Most existing graph embedding methods conducted on heterogeneous graphs treat the heterogeneous neighbours equally. Although it is possible to get node weights through attention mechanisms mainly developed using expensive recursive message-passing, they are difficult to deal with large-scale networks. In this paper, we propose R-WHGE, a relation-aware weighted embedding model for heterogeneous graphs, to resolve this issue. R-WHGE comprehensively considers structural information, semantic information, meta-paths of nodes and meta-path-based node weights to learn effective node embeddings. More specifically, we first extract the feature importance of each node and then take the nodes’ importance as node weights. A weighted random walks-based embedding learning model is proposed to generate the initial weighted node embeddings according to each meta-path. Finally, we feed these embeddings to a relation-aware heterogeneous graph neural network to generate compact embeddings of nodes, which captures relation-aware characteristics. Extensive experiments on real-world datasets demonstrate that our model is competitive against various state-of-the-art methods.

Diverse phase transitions in optimized directed network models with distinct inward and outward node weights.

We consider growing directed network models that aim at minimizing the weighted connection expenses while at the same time favoring other important network properties such as weighted local node degrees. We employed statistical mechanics methods to study the growth of directed networks under the principle of optimizing some objective function. By mapping the system to an Ising spin model, analytic results are derived for two such models, exhibiting diverse and interesting phase transition behaviors for general edge weight, inward and outward node weight distributions. In addition, the unexplored cases of negative node weights are also investigated. Analytic results for the phase diagrams are derived showing even richer phase transition behavior, such as first-order transition due to symmetry, second-order transitions with possible reentrance, and hybrid phase transitions. We further extend previously developed zero-temperature simulation algorithm for undirected networks to the present directed case and for negative node weights, and we can obtain the minimal cost connection configuration efficiently. All the theoretical results are explicitly verified by simulations. Possible applications and implications are also discussed.

Design of a Learning Path Recommendation System Based on a Knowledge Graph

Current learning platforms generally have problems such as fragmented knowledge, redundant information, and chaotic learning routes, which cannot meet learners' autonomous learning requirements. This paper designs a learning path recommendation system based on knowledge graphs by using the characteristics of knowledge graphs to structurally represent subject knowledge. The system uses the node centrality and node weight to expand the knowledge graph system, which can better express the structural relationship among knowledge. It applies the particle swarm fusion algorithm of multiple rounds of iterative simulated annealing to achieve the recommendation of learning paths. Furthermore, the system feeds back the students' learning situation to the teachers. Teachers check and fill in the gaps according to the performance of the learners in the teaching activities. Aiming at the weak links of students' knowledge points, the particle swarm intelligence algorithm is used to recommend learning paths and learning resources to fill in the gaps in a targeted manner.

Attack-model-independent stabilization of networked control systems under a jump-like TOD scheduling protocol

This paper is concerned with the stabilization of networked control systems (NCSs) under multi-packet transmission and denial of service (DoS) attacks. To deal with node congestions and DoS attacks, a jump-like try-once-discard (TOD) protocol is first proposed to orchestrate the priority of normal nodes and the attacked nodes over the network. Compared with the existing TOD scheduling, the proposed scheduling scheme has the advantage of jumping out the attacked nodes by designing node weighting matrices. To reduce the effects of DoS attacks, an attack-model-independent impulsive closed-loop model is well established, which couples the effects of the proposed protocol and DoS attacks in a unified framework. Then, a sufficient attack-model-independent stabilization criterion is derived. Compared with the existing attack-model-dependent methods, the desired dynamic output feedback performance is well guaranteed under multi-channel time-varying DoS attacks. Finally, an illustrative example is used to verify the effectiveness of proposed method.

MHTAN-DTI: Metapath-based hierarchical transformer and attention network for drug-target interaction prediction.

Drug-target interaction (DTI) prediction can identify novel ligands for specific protein targets, and facilitate the rapid screening of effective new drug candidates to speed up the drug discovery process. However, the current methods are not sensitive enough to complex topological structures, and complicated relations between multiple node types are not fully captured yet. To address the above challenges, we construct a metapath-based heterogeneous bioinformatics network, and then propose a DTI prediction method with metapath-based hierarchical transformer and attention network for drug-target interaction prediction (MHTAN-DTI), applying metapath instance-level transformer, single-semantic attention and multi-semantic attention to generate low-dimensional vector representations of drugs and proteins. Metapath instance-level transformer performs internal aggregation on the metapath instances, and models global context information to capture long-range dependencies. Single-semantic attention learns the semantics of a certain metapath type, introduces the central node weight and assigns different weights to different metapath instances to obtain the semantic-specific node embedding. Multi-semantic attention captures the importance of different metapath types and performs weighted fusion to attain the final node embedding. The hierarchical transformer and attention network weakens the influence of noise data on the DTI prediction results, and enhances the robustness and generalization ability of MHTAN-DTI. Compared with the state-of-the-art DTI prediction methods, MHTAN-DTI achieves significant performance improvements. In addition, we also conduct sufficient ablation studies and visualize the experimental results. All the results demonstrate that MHTAN-DTI can offer a powerful and interpretable tool for integrating heterogeneous information to predict DTIs and provide new insights into drug discovery.

Signal-Power-Based Combination Weight Rule for Distributed Blind Equalization in WSN Model

In this paper, we consider how to improve the performance of distributed estimation over a diffusion network in order to estimate the unknown parameter of interest from noisy measurements. Specifically, the distributed blind equalization based on the single-input multiple-output channel model over a wireless sensor network (WSN) is discussed in this paper. We propose a new combination weight rule that the weight of each sensor node is assigned by the signal power of the sensor (received) signal instead of only the degree of each sensor node. We assume that each channel from the common transmitter to the sensor nodes in the WSN is common and that noises, the variances of which are different, are included at each channel. The average mean square error and symbol error rate performance characteristics of the distributed blind equalization are investigated. Simulations show that a significant performance improvement is obtained by employing the proposed combination weight rule compared with using conventional combination weight rules.

Optimized DPoS consensus strategy: Credit-weighted comprehensive election

Consensus algorithm, which allows distrust nodes to reach a consensus in the overall state of the blockchain, is one of the basic characteristics of the blockchain network. Since the delegate nodes elected in the DPoS consensus algorithm are always nodes with a large amount of currency, it usually leads to low voting activity of other nodes. To solve this problem, we propose a credit-weighted comprehensive election, codenamed as CW-DPoS. We propose that the voting weight of nodes is positively correlated with the credit value. First calculate the activity of the node based on k-shell,second calculate the weighted voting value of the node. Finally, the delegator is selected through the comprehensive method of node activity and weighted votes. The performance of the proposed method is compared with the existing consensus mechanism of DPoS, and the experimental result shows that the activity of the nodes has been improved to about 84 % and selects honest nodes more fairly.

Balanced neighbor exploration for semi-supervised node classification on imbalanced graph data

Graph neural networks (GNNs) are powerful models for node classification tasks. When the nodes exhibit a skew distribution, the imbalanced graph data and the message-passing way of GNNs may significantly influence the decision boundary. Existing methods, generating additional nodes and edges or assigning weights of nodes to balance the training scenario, generally have a complicated implementation and a high time complexity. To this end, we propose Balanced Neighbor Exploration (BNE), an algorithm to improve training efficiency and classification performance in a fundamentally different way without generating nodes and computing weights. Intuitively, nodes highly influenced by nodes in one class should have a higher probability of belonging to the class. Inspired by this intuition, BNE incorporates more nodes highly influenced by minority nodes into the minority set to provide a balanced training scenario. The neighbor exploration involves sum and sort operations whose time complexities are O(N) and O(Nlog⁡N), respectively, with a fast operation process. Moreover, BNE conducts the message-passing and neighbor exploration processes simultaneously, with a straightforward implementation. Experiments on real-world imbalanced graph data demonstrate that BNE vastly outperforms the state-of-the-art methods for semi-supervised node classification on imbalanced graph data.

Active tension control of the conical winding system based on the neural network control algorithm of radial-basis functions

A conical winding formation and tension control system was proposed in the doubling operation based on the yarn guide mode of a single spindle in this study. Conical winding formation realized the radial unwinding of wound package. An overfeed mechanism was introduced to achieve closed-loop control of yarn tension. The overfeed wheel was driven by a brushless Direct Current motor. The tension control system combined a Proportion Integration Differentiation controller with a radial-basis-function neural network, whose purpose was to meet the control requirements of the brushless DC motor. This system consisted of three main steps: Firstly, the radial-basis-function neural network was used to identify the system online. Secondly, the gradient descent method was used to adjust the node weight, center vector, and baseband width. Finally, incremental PID parameters online were adjusted according to the identified Jacobian information. A mathematical model of a control system was established in Matrix Laboratory. An experimental platform was designed for doubling winder to compare the control effects of Radial-basis-function-PID with traditional PID. The simulation results showed that the RBF-PID had a smaller overshoot of yarn tension, shorter adjustment time, and smaller steady-state error compared with the traditional PID controller in doubling operation by simulating the mathematical model. Experimental results showed the RBF-PID controller had good performance and stability and could be applied to yarns with different average linear velocity, yarn counts and strands . The yarn tension fluctuation will not exceed ±3% of the target value when the experimental materials and the cone angles are unchanged.

Effects of Ouabain in Ehrlich Tumor Development in vitro and in vivo

Ouabain (OUA) is a cardiotonic steroid with an immunomodulatory and anti-inflammatory role in different experimental models. Currently, the potential antineoplastic effect of OUA has been studied, however, research is needed to better understand OUA role during tumor development. Therefore, our aim was to investigate the OUA effects on Ehrlich tumor (ET) development in vitro and in vivo. To evaluate the cytotoxic effects of OUA on ET in vitro the cells were incubated with different concentrations of OUA during 24h and 48h and our results showed that only the [1000 ?M] decreased the number and viability of ET cells in the two analyzed times. To study the OUA effects on ET in vivo, Swiss mice were pretreated with 0.56 mg/kg of OUA intraperitoneally (i.p.) for three consecutive days. To develop ET in the solid form, one hour after the last day of pretreatment, ET cells were inoculated subcutaneously into the footpad and the animals were monitored for 13 days. To develop the ascitic form, ET cells were inoculated (i.p.) and the animals were monitored for 3 days. OUA was able to reduce the thickness and weight of the tumor paw, in addition to reduce the weight of the popliteal lymph node. In the ascitic tumor, OUA reduced the number of neutrophils and macrophages and increased the lymphocytes in the peritoneum. Thus, we demonstrated that OUA affects ET development both in vitro and in vivo. Our results suggest a new perspective in the anti-inflammatory, immunomodulatory and a possible anti-cancer role of ouabain and brings new concepts about the pathophysiological role of this substance.

Study on Denoising Method of Photoionization Detector Based on Wavelet Packet Transform

Aiming at the task of noise suppression caused by the photoionization detector (PID) monitoring signal of volatile organic compounds (VOCs) due to local non-uniformity of the photocathode surface of PID in the ionization chamber, this paper proposes an analytical method of a PID signal with the adaptive weight of the small wave package decomposition node. The PID signal is transmitted to the upper machine software through the single-chip microcontroller. The appropriate wavelet packet decomposition level is determined according to the time frequency characteristics of the original signal of the PID, and the optimal wavelet packet base is selected through the polynomial fitting of the signal quality evaluation index. By comparing the quality of signals processed by the traditional wavelet packet denoising method and the denoising method presented in this paper, the superiority of the proposed method in the denoising signals of PID was verified. This method can eliminate the noise generated by local non-uniformity on the photocathode surface of the PID ionization chamber in a high humidity environment, which lays a foundation for the accurate monitoring of VOCs in a high humidity environment.

Auxiliary graph-based energy-efficient routing resource allocation algorithm in space division multiplexing elastic optical networks

Space division multiplexing elastic optical networks (SDM-EONs) are considered as a efficient solution for increasing the link’s capacity. However, the SDM-EONs brought challenges to be explored, notably the routing, core and spectrum assignment (RCSA) problem. For the real network, another important issue should be considered is the problem of energy consumption. The auxiliary graph (AG) can abstract node devices into elements in it and support various routing policies for different purposes by adjusting the weights of AG edges. Therefore, this paper proposes an auxiliary graph-based energy efficient routing resource allocation algorithm (AG-EERRA) to jointly optimize the energy consumption and RCSA. Each node of the auxiliary graph is abstracted from the devices of physical node. The intra edge weights of nodes set the function associated with the energy consumption model. The inter edge weights of node are composed link length, free frequency slots, modulation efficiency and the value of core crosstalk innovatively. Meanwhile, the impact of inter-core crosstalk on request is reduced by crosstalk avoidance strategy and crosstalk aware strategy. In the proposed auxiliary graph, the shortest weight path is selected to transmit requests that can reduce network energy consumption and blocking probability. Under the high-load network, request splitting is performed for the requests that cannot successfully find a route to improve energy efficiency. Simulation results show that the proposed algorithm can improve the network energy efficiency while reducing request blocking probability compared to comparison algorithms.

Central node selection algorithm of minimizing maximum weighted response time based on dynamic programming

In order to minimize the maximum weighted response time for any node in the network to reach the central control node, a central control node election algorithm based on dynamic programming is proposed. Firstly, the response times of nodes and links in the wireless network are modeled as the node weights and edge weights in the network topology, and then the central control node election problem that minimizes the maximum weighted response time for any node in the network to reach the central control node is modeled as the central problem, where represents the number of central control nodes. Then, by using the interpolation method based on dynamic programming, the weighted response time between the two points can be obtained, and the K-central problem modeled is transformed into several R-control set problems. Then, several control R-set problems are transformed into several 0-1 integer programming problems, and each integer programming problem can be solved one by one by using the branch and bound method. Finally, a simplified implementation method based on the above algorithm is given when K=1, the optimality of the proposed algorithm is proved and the complexity of the algorithm is analyzed. Simulation results show that the proposed central control algorithm can minimize the maximum weighted response time of the network.

Exploring Multi-Dimension User-Item Interactions With Attentional Knowledge Graph Neural Networks for Recommendation

It is commonly agreed that a recommender system should use not only explicit information (i.e., historical user-item interactions) but also implicit information (i.e., incidental information) to deal with the problem of data sparsity and cold start. The knowledge graph (KG), due to its expressive structural and semantic representation capabilities, has been increasingly used for capturing auxiliary information for recommender systems, such as the recent development of graph neural network (GNN) based models for KG-aware recommendation. Nevertheless, these models have the shortcoming of insufficient node interactions or improper node weights during information propagation, which limits the performance of recommender systems. To address this issue, we propose a Multi-dimension Interaction based attentional Knowledge Graph Neural Network (MI-KGNN) for enhanced KG-aware recommendation. MI-KGNN characterizes similarities between users and items through information propagation and aggregation in knowledge graphs. As such, it can optimize the updating direction of node representation by fully exploring multi-dimension interactions among nodes during information propagation. In addition, MI-KGNN introduces a dual attention mechanism, which allows users and items to jointly determine the weight of neighbor nodes. As a result, MI-KGNN can effectively capture and represent both structural (i.e., the topology of interactions) and semantic information (i.e., the weight of interactions) in the knowledge graph. Experimental results show that the proposed model significantly outperforms baseline methods for top-K recommendation. Specifically, the recall rate is increased by 5.78%, 6.66%, and 3.22% on three public datasets, compared with the best performance of existing methods.

Problems of Automatic Processing of Scientific Texts based on Extraction of Information from Encyclopedias of Relevant Domain Areas

The article discusses the problems arising in the automatic processing of scientific texts and presents the results of work on creating a combined method for aspect-oriented analysis of scientific texts in the field of fundamental disciplines, taking into account both knowledge of the subject area and statistical methods of text processing. Thematic encyclopedias, which are not only a source of professional scientific terminology, but are considered to be an information resource for extracting knowledge about the subject area, are proposed to be used as training data. The work offers the structure of templates designed to extract information from the partially structured text of the encyclopedia, considers the structure of extracted sets of professional terms, offers the algorithm of formation of semantic relationships between special terms. The process of knowledge extraction in this paper is demonstrated on the example of processing four encyclopedias: mathematical, physical, chemical, medical. The general principles of the formation of domain scientific terminology are highlighted, and statistical data on the terminological composition in each of the examined areas is given. Within the framework of the conducted research on the basis of the texts of encyclopedias the basic semantic graphs of the corresponding scientific fields with the relations between the professional terms introduced on them are constructed. Basic graphs accumulate knowledge about the scientific field and are intended for the subsequent thematic analysis of unstructured texts of scientific articles. The Implemented algorithm of extraction of semantics of the given scientific text is based both on amplification of weights of nodes — terms of the applied domain, and on the correction of semantic relations between the nodes of the graph according to the processed text. The results of experiments on automatic construction of the list of keywords of the article are given. The results were compared with the list of keywords specified by the author of the article. It should be noted that the relevance of correctly extracted terms is mainly determined by semantic links in the basic domain graph, and depends significantly less on the number of keywords in the original article, which demonstrates the advantage of the proposed combined method compared with a simple frequency analysis. The sample analysis of the texts of the articles on mathematics showed good accuracy in the extraction of key terms compared to the list of keywords specified by the author of the article.

Exploring the metro construction accidents and causations for improving safety management based on data mining and network theory

PurposeThe purpose of this study is to identify the causative factors of metro construction safety accidents, analyze the correlation between accidents and causative factors and assist in developing safety management strategies for improving safety performance in the context of the Chinese construction industry.Design/methodology/approachTo achieve these objectives, 13 types and 48 causations were determined based on 274 construction safety accidents in China. Then, 204 cause-and-effect relationships among accidents and causations were identified based on data mining. Next, network theory was employed to develop and analyze the metro construction accident causation network (MCACN).FindingsThe topological characteristics of MCACN were obtained, it is both a small-world network and a scale-free network. Controlling critical causative factors can effectively control the occurrence of metro construction accidents. Degree centrality strategy is better than closeness centrality strategy and betweenness centrality strategy.Research limitations/implicationsIn practice, it is very difficult to quantitatively identify and determine the importance of different accidents and causative factors. The weights of nodes and edges are failed to be assigned when constructing MCACN.Practical implicationsThis study provides a theoretical basis and feasible management reference for construction enterprises in China to control construction risks and reduce safety accidents. More safety resources should be allocated to control critical risks. It is recommended that safety managers implement degree centrality strategy when making safety-related decisions.Originality/valueThis paper establishes the MCACN model based on data mining and network theory, identifies the properties and clarifies the mechanism of metro construction accidents and causations.

Network intrusion detection via tri-broad learning system based on spatial-temporal granularity

Network intrusion detection system plays a crucial role in protecting the integrity and availability of sensitive assets, where the detected traffic data contain a large amount of time, space, and statistical information. However, existing research lacks the utilization of spatial-temporal multi-granularity data features and the mutual support among different data features, thus making it difficult to specifically and accurately identify anomalies. Considering the distinctions among different granularities, we propose a framework called tri-broad learning system (TBLS), which can learn and integrate the three granular features. To explore the spatial-temporal connotation of the traffic information accurately, a feature dataset containing three granularities is constructed according to the characteristics of time, space, and data content. In this way, we use broad learning basic units to extract abstract features of different granularities and then express these features in different feature spaces to enhance them separately. We use a normal distribution initialization method in BLS to optimize the weights of feature nodes and enhancement nodes for better detection accuracy. The merits of our proposed model are exhibited on the UNSW-NB15, CIC-IDS-2017, CIC-DDoS-2019, and mixed traffic datasets. Experimental results show that TBLS outperforms the typical BLS in terms of various evaluation metrics and time consumption. Compared with other machine learning methods, TBLS achieves better performance metrics.

ОПРЕДЕЛЕНИЕ НАДЕЖНОСТИ ЭЛЕМЕНТОВ ГАЗОПОРШНЕВЫХ АГРЕГАТОВ С СИНХРОННЫМИ ГЕНЕРАТОРАМИ МЕТОДОМ АНАЛИЗА ИЕРАРХИЙ

Relevance In the process of extracting hydrocarbon raw materials, associated petroleum gas (APG) is released, which in itself is a valuable fuel. Previously, associated gas released during extraction was simply burned, which was irrational and harmful to the environment. However, in modern conditions, oil companies tend to use associated gas. One of the best available technologies for the utilization of associated petroleum gas and the generation of electric energy is the use of gas piston units (GPU) at oil and gas producing enterprises, which are widely used at the present time. Progress in design methods and production technology of electric machines is expressed, among other things, in increasing their reliability, however, it is obvious that it will not be possible to completely avoid failures. The problem of solving issues of assessing and ensuring the reliability of GPU used for the utilization of associated petroleum gas at oil-producing enterprises is becoming more and more urgent every year, since serious losses of an economic and environmental nature are associated with insufficient reliability: emergency stops of GPU lead to the shutdown of funds of oil-producing wells and forced burning of APG on an open-type candle with the release of a large amount of the amount of greenhouse gases. Aim of research To study the reliability of gas piston units based on the weight indicators of their elements (functional units). Research methods The research uses the hierarchy analysis method (Saaty method) and the «weakest link» method. Results The article uses a methodology for evaluating equipment reliability indicators based on the weight indicators of functional units, taking into account the importance of reliability criteria. The node weight is calculated using the hierarchy analysis method (Saaty method). In accordance with the proposed methodology, the probability of trouble-free operation of the considered machines for the period of normal operation is calculated. Conclusions are drawn about the prioritization of technical impact on functional elements.

Evaluation of Green Spaces in Hilla City According to Green Network Concept

The study focuses on the feasibility of connecting urban green spaces at an urban scale through a network because of the population growth and land use changes at the expense of green areas, which has led to the fragmentation and destabilization of the ecosystem in the Hilla city center in Babylon province /Iraq. The methodology will be according to two stages: first, the current state assessment was used to determine the encroachment of the areas. Secondly, it uses the gravity model and the least-cost path model in GIS to determine the level of interaction between nodes. Therefore, the research hypothesis was that connecting strong nodes to a comprehensive and integrated network increases the strength of the interaction. According to the results, there is no clear hierarchy in the distribution of urban green spaces within Hilla city, with only two levels: locality and urban on the urban level, there is no possibility of establishing a network between green spaces because of three factors: encroached uses mainly the residential, distance between patches and the node weight.