Random Walk Strategy Research Articles

Synchronization of multiple mobile reservoir computing oscillators in complex networks

We investigate collective behavior of multiply moving reservoir computing oscillators. Each moving oscillator is fitted to a same dynamical system and then wanders a network navigating by random walk strategy. Interestingly, we find that the moving oscillators gradually present a coherent rhythmic behavior when their number is large enough. In this situation, temporal and spatial characteristics of each moving oscillator are in excellent agreement with that of their learned dynamical system under consideration. Remarkably, we show that these reservoir computing oscillators can exhibit significantly distinct collective behaviors that resemble bifurcation phenomenon when changing a critical reservoir parameter. Furthermore, we find that when studying a continuous chaotic system, intermittent synchronization emerges among these reservoir computing oscillators. But there is no evidence of enhanced correlation in the associated laminar length sequence. Our work provides a feasible framework for studying synchronization phenomena of mobile agents in nature when merely observed information is available.

Single and multi-objectives based on an improved golden jackal optimization algorithm for simultaneous integration of multiple capacitors and multi-type DGs in distribution systems

This paper proposes a novel placement technique based on the improved golden jackal optimization (IGJO) algorithm for multiple capacitor banks (CBs) and multi-type DGs in a distribution network considering single and multi-objective problems. The proposed algorithm incorporates memory-based equations and random walk strategy to enhance the performance of the recent golden jackal optimization in terms of accuracy and convergence speed. The optimization problem is formulated as a weighted multi-objective that seeks to enhance the voltage profiles, boost stability, and minimize the total active power loss. An index named reactive loss sensitivity (QLSI) is also employed with the developed IGJO to identify the candidate nodes for the DGs and CBs installation to reduce the search space of the optimization algorithm. The robustness of the developed IGJO algorithm is evaluated through the CEC 2020 benchmark functions, and a comparison study is conducted with the original GJO and the other nine fresh competitors using various statistical tests to confirm its dominance and superiority. Then, the proposed IGJO is implemented in single and multi-objectives for the optimal deployment of multiple CBs individually and simultaneously with multiple DGs with different operating modes to enhance the performance of the IEEE 69-bus radial distribution system (RDS). The fetched outcomes are compared with the original GJO, weevil optimizer algorithm (WeevilOA), skill optimization algorithm (SOA), and Tasmanian devil optimization (TDO) to further measure its efficacy using different statistical tests. The IGJO algorithm is also applied to deploy multiple DGs for the IEEE 118-bus RDS with the aim of minimizing active loss. The simulation findings affirmed that the proposed IGJO technique beats the other rivals in all investigated situations, qualifying for the optimal inclusion of DGs in the presence of generation and demand uncertainties. Specifically, the integration of three units of CBs synchronously with three DGs Type-I and DG Type-III reduces the active power loss to 4.2664 kW and 3.4178 kW, respectively. The lowest power loss, approximately 2.7989 kW, is achieved with the simultaneous integration of three DG Type-I and DG Type-III using the developed IGJO algorithm.

An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems.

Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.

Model optimization of a high-power commercial PEMFC system via an improved grey wolf optimization method

Proton exchange membrane fuel cell (PEMFC) models are conventionally established with a set of parameters identified under steady-state operating conditions. However, such an approach is insufficient to accurately capture the dynamic characteristics of multi-parameter changes in real-world scenarios. This paper develops a semi-empirical model for a 110-kW commercial PEMFC system based on its dynamic operation data to remedy the defects. To improve the fitting accuracy of the semi-empirical PEMFC model, an improved grey wolf optimization (IGWO) algorithm is proposed for model parameter identification. The IGWO algorithm adopts chaotic mapping to optimize the initial population distribution, and a random walk strategy is incorporated to boost the local search ability of the traditional grey wolf optimization (GWO) algorithm. The effectiveness of this IGWO algorithm in optimizing the semi-empirical model is experimentally verified on the 110-kW PEMFC system under highly dynamic operating conditions. Results show that the proposed IGWO algorithm can effectively identify the semi-empirical model’s parameters, establishing a stable and robust model that outperforms those based on traditional metaheuristic algorithms such as GWO, particle swarm optimization, and genetic algorithm. The demonstrated improvement renders it as better suited for optimizing PEMFC semi-empirical models under real-world operating conditions.

Ensuring security in edge computing through effective blockchain node detection

The rapid development of blockchain technology has garnered increasing attention, particularly in the field of edge computing. It has become a significant subject of research in this area due to its ability to protect the privacy of data. Despite the advantages that blockchain technology offers, there are also security threats that must be addressed. Attackers may manipulate certain nodes in the blockchain network, which can result in tampering with transaction records or other malicious activities. Moreover, the creation of a large number of false nodes can be utilized to gain control and manipulate transaction records of the blockchain network, which can compromise the reliability and security of edge computing. This paper proposes a blockchain node detection method named T^2A2vec that provides a more secure, credible, and reliable solution to address these challenges. In order to achieve T^2A2vec, a transaction dataset that is evenly distributed in both space and time was collected. The transaction dataset is constructed as a transaction graph, where nodes represent accounts and edges describe transactions. BP neural network is used to extract account features, and a random walk strategy based on transaction time, type, and amount is used to extract transaction features. The obtained account features and transaction features are fused to obtain account representation. Finally, the obtained node representation is fed into different classifiers to identify malicious nodes.

Study on Multi-UAV Cooperative Path Planning for Complex Patrol Tasks in Large Cities

Unmanned Aerial Vehicles (UAVs) are increasingly utilized for urban patrol and defense owing to their low cost, high mobility, and rapid deployment. This paper proposes a multi-UAV mission planning model that takes into account mission execution rates, flight energy consumption costs, and impact costs. A kinematics and dynamics model of a quadcopter UAV is established, and the UAV’s flight state is analyzed. Due to the difficulties in addressing 3D UAV kinematic constraints and poor uniformity using traditional optimization algorithms, a lightning search algorithm (LSA) based on multi-layer nesting and random walk strategies (MNRW-LSA) is proposed. The convergence performance of the MNRW-LSA algorithm is demonstrated by comparing it with several other algorithms, such as the Golden Jackal Optimization (GJO), Hunter–Prey Optimization (HPO), Pelican Optimization Algorithm (POA), Reptile Search Algorithm (RSA), and the Golden Eagle Optimization (GEO) using optimization test functions, Friedman and Nemenyi tests. Additionally, a greedy strategy is added to the Rapidly-Exploring Random Tree (RRT) algorithm to initialize the trajectories for simulation experiments using a 3D city model. The results indicate that the proposed algorithm can enhance global convergence and robustness, shorten convergence time, improve UAV execution coverage, and reduce energy consumption. Compared with other algorithms, such as Particle Swarm Optimization (PSO), Simulated Annealing (SA), and LSA, the proposed method has greater advantages in addressing multi-UAV trajectory planning problems.

Ethereum phishing detection based on graph neural networks

AbstractWith the development of blockchain, cryptocurrencies are also showing a boom. However, due to the decentralized and anonymous nature of blockchain, cryptocurrencies have inevitably become a hotbed for fraudulent crimes. For example, phishing scams are frequent, which not only jeopardize the financial security of blockchain, but also hinder the promotion of blockchain technology. To solve this problem, this paper proposes a graph neural network‐based phishing detection method for Ethereum, and validates it using Ethereum datasets. Specifically, this paper proposes a feature learning algorithm named TransWalk, which consists of a random walk strategy for transaction networks and a multi‐scale feature extraction method for Ethereum. Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum phishing detection.

A heterogeneous E-commerce user alignment model based on data enhancement and data representation

Identifying users’ accounts on different platforms is important for the management and marketing of e-commerce platforms. To address the problem of sparse consumer behavior data on e-commerce platforms, this paper designs Double Generative Adversarial Network (Double-GAN) to compensate the data. This method uses not only the data of the one platform , but also of heterogeneous e-commerce platforms for alternate iteration compensation. For the complexity of “user-behavior-commodity” data feature space of e-commerce bookstore platform. Considering Consider the advantages of model JUST in capturing structural and semantic information of multiple types of nodes. This paper proposes a new method UBC2vec to integrate user’s interest in commodities and change the random walk strategy to represent the overall information of data feature space of heterogeneous e-commerce platform. Finally, for the high computational complexity of the user alignment algorithm, this paper constructs a “user-commodity” bipartite graph to delineate the roles of users and reduce the complexity. Experiments show that the model can effectively alleviate the data sparsity problem and reduce the computational complexity of the algorithm. Above the real data set, it can effectively match users’ accounts in different bookstore platforms.

A Multi-Objective Crow Search Algorithm for Influence Maximization in Social Networks

Influence maximization is a key topic of study in social network analysis. It refers to selecting a set of seed users from a social network and maximizing the number of users expected to be affected. Many related research works on the classical influence maximization problem have concentrated on increasing the influence spread, omitting the cost of seed nodes in the diffusion process. In this work, a multi-objective crow search algorithm (MOCSA) is proposed to optimize the problem with maximum influence spread and minimum cost based on a redefined discrete evolutionary scheme. Specifically, the parameter setting based on the dynamic control strategy and the random walk strategy based on black holes are adopted to improve the convergence efficiency of MOCSA. Six real social networks were selected for experiments and analyzed in comparison with other advanced algorithms. The results of experiments indicate that our proposed MOCSA algorithm performs better than the benchmark algorithm in most cases and improves the total objective function value by more than 20%. In addition, the running time of the MOCSA has also been effectively shortened.

Research on the Cuckoo Algorithm for Flexible Workshop Scheduling Problems

As a typical combinatorial optimization problem, the essence of the solution to the scheduling problem is to formulate a reasonable scheduling scheme to arrange and allocate production resources, thereby obtaining the optimal scheduling result. The Cuckoo Search Algorithm (CS), a revolutionary meta-heuristic, is based on the cuckoo's breeding behavior and combines Lévy flight and random walk strategies to more efficiently attain the search goal. CS algorithm has been extensively employed in a variety of intricate combinatorial optimization issues, with its few parameters, precise resolution, random search path optimization, robust search aptitude, and uncomplicated implementation leading to satisfactory outcomes. After in-depth research, we found that the cuckoo search algorithm excels in dealing with flexible workshop scheduling problems. We conduct a series of comparative experiments to further confirm the efficacy of this algorithm. The results show that the cuckoo algorithm performs well in global search and can be used to solve complex flexible workshop scheduling models.

Random walk numerical scheme for the steady-state of stochastic differential equations

The continuous-time random walk (CTRW) scheme is a time-continuous and space-discretization method to obtain the numerical solution of stochastic differential equations (SDEs). Compared with the traditional time-discretization scheme, it has the advantages of numerical stability and can alleviate the curse of dimensionality. This paper proposes an improved version of the CTRW scheme for the numerical solution of SDEs. By compensating the artificial diffusion caused by the Poisson approximation of the drift term of the SDE, the improved CTRW scheme has significantly better performance in the weak noise case, especially in approximating the invariant probability measure. Numerical studies show that the improved CTRW scheme has more accuracy than the existing one but takes less computation time. In addition, it has better accuracy of the mean holding time. We also modify the hybrid Fokker–Planck solver proposed for the CTRW scheme to compute the invariant probability measure.

Meta-path based graph contrastive learning for micro-video recommendation

Nowadays, micro-video sharing platforms have become popular tools for people creating and viewing micro-videos in daily life. The micro-video recommendation task has attracted significant attention from researchers, recently. The key to a high-quality micro-video recommendation system is learning meaningful user and micro-video representations. Recently, many graph neural networks (GNNs) are proposed to learn node representations in graphs, which could be useful for recommendation tasks. However, we argue that directly utilizing existing GNNs in micro-video recommendations is ill-posed. The reasons are: (1) most previous GNNs fail to capture the heterogeneity of heterogeneous graphs since they are designed for homogeneous graphs; (2) they overemphasize node proximity and may hurt the robustness of node embeddings. In contrast to previous work, we propose a meta-path-based graph contrastive learning network (MPGCL) that learns more meaningful user and video embeddings for recommendation. Specifically, we yield homogeneous graphs for user type and video type to better capture heterogeneity based on a well-designed meta-path-based random walk strategy. Furthermore, to learn more robust node embeddings that are less sensitive to noise, we propose a graph contrastive learning network on different types of homogeneous graphs, which maximizes the consistency between graph representations with different views. We do extensive experiments on three real-world datasets and the results show that our model can learn more meaningful embeddings for users and micro-videos and outperforms the strong baselines.

Multiple moving agents on complex networks: From intermittent synchronization to complete synchronization

We investigate multiple moving agents on complex networks. Each of them takes a random walk strategy and carries a chaotic oscillator. Remarkably, we find that with increasing the number of agents, a significant transition occurs from intermittent synchronization to complete synchronization. In particular, we observe that the distribution of laminar length presents a clearly power-law behavior in the intermittent synchronization stage. While reaching a complete synchronization state, correlation dimension and recurrence time statistics of synchronous orbits are in excellent agreement with that of their carrying chaotic system under consideration. Our work reveals that the number of moving agents has a profound effect on shaping synchronization behaviors.

Detecting collusive spammers with heterogeneous graph attention network

Detecting collusive spammers who collaboratively post fake reviews is extremely important to guarantee the reliability of review information on e-commerce platforms. In this research, we formulate the collusive spammer detection as an anomaly detection problem and propose a novel detection approach based on heterogeneous graph attention network. First, we analyze the review dataset from different perspectives and use the statistical distribution to model each user's review behavior. By introducing the Bhattacharyya distance, we calculate the user-user and product-product correlation degrees to construct a multi-relation heterogeneous graph. Second, we combine the biased random walk strategy and multi-head self-attention mechanism to propose a model of heterogeneous graph attention network to learn the node embeddings from the multi-relation heterogeneous graph. Finally, we propose an improved community detection algorithm to acquire candidate spamming groups and employ an anomaly detection model based on the autoencoder to identify collusive spammers. Experiments show that the average improvements of precision@k and recall@k of the proposed approach over the best baseline method on the Amazon, Yelp_Miami, Yelp_New York, Yelp_San Francisco, and YelpChi datasets are [13%, 3%], [32%, 12%], [37%, 7%], [42%, 10%], and [18%, 1%], respectively.

Application of Sine Cosine Egret Swarm Optimization Algorithm in Gas Turbine Cooling System

Gas turbine cooling system is a typical multivariable, strongly coupled, nonlinear, and uncertain MIMO system. In order to solve the control problem of pressure, flow, and temperature of the system, an intelligent approach is necessary and more appropriate. The current system control mainly depends on the experience of the staff, which exists problems such as high labor intensity, low work efficiency and low control accuracy. Lack of accurate models make parameters tune difficultly, and ordinary control methods are difficult to control complex gas turbine cooling system. In this paper, the system transfer function model is built based on the field data obtained under different working conditions and system identification method. The diagonal matrix decoupling method is used to weaken the correlation between variables and achieve independent control among variables. When optimizing the parameters of the controller, Sine Cosine Egret Swarm Optimization Algorithm is proposed. Egret Swarm Optimization Algorithm is composed of Sit-And-Wait strategy, random walk, and encirclement strategy. The sit-and-wait strategy is prone to premature convergence, which makes the optimized parameters unsuitable for gas turbine cooling system. Sine Cosine Algorithm is introduced to randomly use the sine-cosine function for the pseudo-gradient of the weights of the observation equation, thus expanding the search range of the population. Friedman tests prove that the deviation of SE-ESOA is within the allowable range. The results show that the result of Sine Cosine Egret Swarm Optimization Algorithm is more stable and accurate, and it is more suitable for gas turbine cooling system, which solve the pressure, flow, and temperature control problems of complex systems.

Relatively important nodes mining algorithm based on community detection and biased random walk with restart

As modern network communication technology rapidly develops in recent years, complex networks have become a hot multidisciplinary research field. In this field, relatively important nodes mining is an emerging research topic with theoretical significance and application value. However, most researchers in the field of complex networks focus on sorting the global information in the network. Existing relatively important nodes mining algorithms commonly focus on the structural characteristics of the network and do not take into account the influence of community information on relatively important nodes mining. This paper addresses these problems by proposing a relatively important nodes mining algorithm based on community detection and biased random walk with restart (CDBRWR). This approach integrates the community information of the network into the mining of relatively important nodes for the first time and recommends a new biased random walk strategy with restart to realize the accurate and efficient mining of relatively important nodes in various networks. The performance of the proposed algorithm is examined through experimental verification and analysis of real network datasets. Results show that the CDBRWR algorithm outperforms other comparative algorithms in precision, recall, and AUC (area under the curve).

Improving Network Representation Learning via Dynamic Random Walk, Self-Attention and Vertex Attributes-Driven Laplacian Space Optimization.

Network data analysis is a crucial method for mining complicated object interactions. In recent years, random walk and neural-language-model-based network representation learning (NRL) approaches have been widely used for network data analysis. However, these NRL approaches suffer from the following deficiencies: firstly, because the random walk procedure is based on symmetric node similarity and fixed probability distribution, the sampled vertices’ sequences may lose local community structure information; secondly, because the feature extraction capacity of the shallow neural language model is limited, they can only extract the local structural features of networks; and thirdly, these approaches require specially designed mechanisms for different downstream tasks to integrate vertex attributes of various types. We conducted an in-depth investigation to address the aforementioned issues and propose a novel general NRL framework called dynamic structure and vertex attribute fusion network embedding, which firstly defines an asymmetric similarity and h-hop dynamic random walk strategy to guide the random walk process to preserve the network’s local community structure in walked vertex sequences. Next, we train a self-attention-based sequence prediction model on the walked vertex sequences to simultaneously learn the vertices’ local and global structural features. Finally, we introduce an attributes-driven Laplacian space optimization to converge the process of structural feature extraction and attribute feature extraction. The proposed approach is exhaustively evaluated by means of node visualization and classification on multiple benchmark datasets, and achieves superior results compared to baseline approaches.

Improved butterfly optimization algorithm applied to prediction of combined cycle power plant

The electricity output is worth monitoring because of the rising electricity demand. Ambient temperature, air pressure, relative humidity, and exhaust pressure all impact the production output of a combined cycle power plant. This study proposes the BOAPPE algorithm, which combines the butterfly optimization algorithm (BOA) with the phasmatodea population evolution algorithm (PPE) to estimate power output better and reduce excessive cost waste. When used in conjunction with a support vector regression (SVR) model, such as BOAPPE-SVR, for estimating the power output of a power plant under basic load, it not only enhances the model’s prediction accuracy but also successfully avoids the problem of the model entering local optimization too soon. The parallel strategy of the BOAPPE algorithm in this research improves convergence speed, while the random walk strategy prevents the model from sliding into local optimization. The results reveal that the model paired with the BOAPPE algorithm is more accurate and better than the other models in this research when comparing the performance of the parameters such as mean square error, relative error, and correlation coefficient. As a result, the BOAPPE-SVR model is a viable model for power load forecasting.

Detecting Starch-Head and Mildewed Fruit in Dried Hami Jujubes Using Visible/Near-Infrared Spectroscopy Combined with MRSA-SVM and Oversampling.

Dried Hami jujube has great commercial and nutritional value. Starch-head and mildewed fruit are defective jujubes that pose a threat to consumer health. A novel method for detecting starch-head and mildewed fruit in dried Hami jujubes with visible/near-infrared spectroscopy was proposed. For this, the diffuse reflectance spectra in the range of 400–1100 nm of dried Hami jujubes were obtained. Borderline synthetic minority oversampling technology (BL-SMOTE) was applied to solve the problem of imbalanced sample distribution, and its effectiveness was demonstrated compared to other methods. Then, the feature variables selected by competitive adaptive reweighted sampling (CARS) were used as the input to establish the support vector machine (SVM) classification model. The parameters of SVM were optimized by the modified reptile search algorithm (MRSA). In MRSA, Tent chaotic mapping and the Gaussian random walk strategy were used to improve the optimization ability of the original reptile search algorithm (RSA). The final results showed that the MRSA-SVM method combined with BL-SMOTE had the best classification performance, and the detection accuracy reached 97.22%. In addition, the recall, precision, F1 and kappa coefficient outperform other models. Furthermore, this study provided a valuable reference for the detection of defective fruit in other fruits.

Semantic-aware network embedding via optimized random walk and paragaraph2vec

The Deepwalk-based network embedding algorithm, which was inspired by the word2vec model, can quickly and efficiently learn a low-dimensional vector representation for each node in a complex network. However, the success of word2vec in natural language environments relies heavily on ubiquitous contextual semantics, and the Deepwalk model is less accurate than other deep models due to ignoring contextual semantics in complex networks. To solve this challenge, a semantic-aware network embedding algorithm is proposed in this paper, simply called SANE, via optimized random walk and paragaraph2vec. In the SANE, a semantic-aware random walk strategy is designed to unsupervised generate many semantic-bearing node sequences from a complex network as a training set. Then, based on the training set, the paragraph2vec model is optimized by considering both global semantics and local semantics for learning more accurate low-dimensional node feature representations. Experiments on multiple tasks and multiple networks show the advantages of our SANE algorithm.