Abstract Existing fault diagnosis problems in discrete event systems are typically modeled using (variants of) Petri nets, where faults are detected based on modified state class graph (MSCG). However, these methods overlook data flow in systems, leading to models that cannot accurately describe system operational behavior. Additionally, existing fault detection methods often fail to identify faults related to data flow due to the lack of data flow descriptions in MSCG, resulting in misjudgments. To address these issues, data flow needs to be considered when modeling the system. Specifically, we extended the labeled time Petri net by adding corresponding data element operations and database table operations on transitions. This extension enables the simulation of data flow and reflects interactions between data elements, resulting in a new model called the labeled time Petri net with table. Additionally, we refined the MSCG by incorporating data element information and the values of data items in the database table, generating a new graph called MSCG$^{*}$. MSCG$^{*}$ effectively shows the data flow changes in the system. Based on the MSCG$^{*}$, we identify transition sequences that are logically consistent with the observable label sequences. Linear inequalities are then constructed from these transition sequences to find effective transition sequences that satisfy the time constraints. The faults in the system caused by data flow require further detection and verification. We define the system’s data constraints as follows: if the states in MSCG$^{*}$ satisfy the data constraints, the system has no faults; otherwise, the system has faults. This diagnostic method detects faults in the system from the perspectives of time and data constraints, thus accurately judging the system’s fault states. Finally, we verified the feasibility and effectiveness of the proposed method through case analysis.

In safety-critical reinforcement learning tasks such as robot navigation, autonomous driving, and industrial control, real-time monitoring of agent behavior is paramount to prevent unsafe actions from compromising system reliability. We introduce Safe Fuzzy Control Barrier Functions (Safe Fuzzy-CBF), a monitoring framework that continuously evaluates agent risk using a smooth control barrier function learned from data via Takagi-Sugeno fuzzy rules, rather than relying on a predefined model-based barrier. In the offline phase, we extract fuzzy rules from trajectory data and construct a continuously differentiable barrier that unifies state, action, and cost into a single risk metric. During online execution, we estimate the barrier’s time derivative using finite differences, apply Lipschitz-based corrections, and when the barrier condition is violated, we solve a small quadratic program in the normalized control space to compute a safe corrective action. Evaluated on three Safety-Gymnasium navigation tasks and the MetaDrive autonomous driving environment, our framework detects emerging safety violations in real time and enforces runtime safety without degrading the underlying RL policy’s performance, achieving up to an 86.8% reduction in accumulated cost.

Query-based trip recommendation is an important task in location-based services (LBS), which aims to provide users with a sequence of points of interest (POIs) based on their queries. In trip recommendation, the effect of the visited POIs on the following decisions of users, called a forward effect, is mined by the existing studies. However, the effect of the following POIs on the previously visited ones, called a reverse effect, receives no attention. Therefore, this work proposes a graph-based double-layer bidirectional model for trip recommendation (GDB-TR), which is designed to mine both forward and reverse effects through bidirectional computation. Forward computation explores the influence of user’s history preferences on the next choice; reverse computation explores the influence of future goals on the current decision. Specifically, the model uses a heterogeneous graph to model users’ check-in trajectories with spatial and temporal information. Subgraphs are extracted from the heterogeneous graph, and an adjacency matrix is built for each subgraph. Vector representations of POIs and POI categories are obtained by fusing matrices based on a neural network. The double-layer bidirectional neural network is used to recommend a trip based on the user query, with one layer mining users’ preferences for POIs and the other layer mining the preferences for POI categories. Bidirectional computation is performed between the initial and destination nodes in each layer, capturing both forward and reverse effects. Specifically, a forward computation mines the influence of preceding POIs or POI categories on following ones, while a reverse computation does that reversely. Finally, experiments are conducted on five popular real data sets. The results show that GDB-TR outperforms all baseline models onF1and pairs-F1values, which validates the effectiveness of the proposed approach.

Despite significant advances in machine learning for financial forecasting, prevailing approaches face a fundamental modeling challenge in simultaneously capturing long-term stability and short-term agility in stock return prediction. Current methodologies tend to treat these temporal characteristics as mutually exclusive, where models demonstrate strong performance in identifying persistent patterns, they often suppress short-term fluctuations as noise, thus lacking sensitivity to short-term market fluctuations. Conversely, models that overemphasize short-term fluctuations risk overfitting to transient market noise, thereby undermining long-term robustness. To resolve this trade-off, we propose the temporal stability-flexibility network (TSF-Net), which addresses the limitations of existing architectures that rely onsingle-module processing or fixed-weight fusionof mixed-frequency features. Unlike these approaches, which inevitably sacrifice either trend stability or noise sensitivity, TSF-Net introduces anadaptive weight allocation strategythat dynamically reconciles long-term trends with short-term fluctuations based on real-time volatility regimes. The framework first decouples temporal regimes via wavelet decomposition, then processes purified components through parallel, noninterfering pathways (stability-oriented transformer for low-frequency fundamentals; agility-oriented TCN with cross-stock attention), and finally integrates them through learnable gating mechanisms that optimally balance persistent patterns against transient shocks. On 1043 Chinese A-share stocks (2013–2022), TSF-Net achieves Sharpe ratios of 0.75–1.69, outperforming state-of-the-art baselines by 44%–163% with 20%–88% lower maximum drawdown. Ablation studies confirm 213% volatility increase without frequency separation and 62.5% return degradation without real-time dynamics capture.

The Longest Common Subsequence (LCS) problem is fundamental in bioinformatics and file difference comparison algorithms, yet its conventional dynamic programming (DP) approach has a time complexity of$\mathcal{O}(m n)$, making it computationally expensive for large-scale inputs. Parallelization offers a promising solution to accelerate the LCS computation. Existing methods parallelize its computation along the antidiagonal direction of the DP matrix but suffer from poor cache utilization and high communication overhead. In this paper, we propose a novel parallel LCS algorithm that combines antidiagonal tiling with lightweight semaphore-based synchronization to enhance cache locality and reduce inter-thread communication costs. Our approach partitions the DP matrix into localized tiles along anti-diagonals and employs lightweight semaphores to guarantee dependency constraints, significantly improving the computation efficiency. Experimental results on sequences of length$\mathbf{1 0 k}$demonstrate that our algorithm achieves a$6.9 \times$speedup ratio over the serial version, outperforming both well-known anti-diagonal parallelization method and task-queue-based method.

The performance of models trained by Multi-Agent Reinforcement Learning (MARL) is sensitive to perturbations in observations, lowering their trustworthiness in complex environments. Adversarial training is a valuable approach to enhance their performance robustness. However, existing methods often overfit to adversarial perturbations of observations and fail to incorporate prior information about the policy adopted by their protagonist agent, i.e., the primary one being trained. To address this important issue, this paper introduces Adversarial Training with Stochastic Adversary (ATSA), where the proposed adversary is trained online alongside the protagonist agent. The former consists of Stochastic Director (SDor) and SDor-guided generaTor (STor). SDor performs policy perturbations by minimizing the expected team reward of protagonists and maximizing the entropy of its policy, while STor generates adversarial perturbations of observations by following SDor's guidance. We prove that SDor's soft policy converges to a global optimum according to factorized maximum-entropy MARL and leads to the optimal adversary. This paper also introduces an SDor-STor loss function to quantify the difference between a) perturbations in the agent's policy and b) those advised by SDor. We evaluate our ATSA on StarCraft II tasks and autonomous driving scenarios, demonstrating that a) it is robust against diverse perturbations of observations while maintaining outstanding performance in perturbation-free environments, and b) it outperforms the state-of-the-art methods.

Reinforcement Learning (RL) is widely used in tasks where agents interact with an environment to maximize rewards. Building on this foundation, Safe Reinforcement Learning (Safe RL) incorporates a cost metric alongside the reward metric, ensuring that agents adhere to safety constraints during decision-making. In this paper, we identify that Safe RL is vulnerable to backdoor attacks, which can manipulate agents into performing unsafe actions. First, we introduce the relevant concepts and evaluation metrics for backdoor attacks in Safe RL. It is the first attack framework in the Safe RL field that involves both Positive and Negative Action sample (PNAct) is to implant backdoors, where positive action samples provide reference actions and negative action samples indicate actions to be avoided. We theoretically point out the properties of PNAct and design an attack algorithm. Finally, we conduct experiments to evaluate the effectiveness of our proposed backdoor attack framework, evaluating it with the established metrics. This paper highlights the potential risks associated with Safe RL and underscores the feasibility of such attacks. Our code and supplementary material are available at https://github.com/azure-123/PNAct.

Abstract Self-supervised learning (SSL) has become a promising and popular learning paradigm for graph data, offering the advantage of capturing informative knowledge without reliance on manual labels. As a representative class of generative graph SSL models, existing graph autoencoders (GAE) excel in link prediction tasks and are steadily improving in node classification tasks. However, GAE is essentially based on the Information Maximization (InfoMax) principle, always captures much redundant information. In this paper, we propose an Alternating-update-strategy based Graph Autoencoder, including alternating update module (AUM) and GAE. For AUM, we design an Alternating-update-strategy to generate a new graph with reduced redundancy, in order to reduce the amount of redundant information that the encoder may capture. For GAE, we feed it the new graph and employ a re-mask decoding strategy to generate node representations. Our model is evaluated on five common real-world datasets for the node classification task, and the experimental results demonstrate its superiority. Meanwhile, our model has also achieved excellent results in specific e-commerce warehousing application scenarios.

Many operations in workflow systems are dependent on database tables. The classical workflow nets and their extensions (e.g., workflow nets with data) cannot model these operations, so that they cannot find some related errors. Recently, workflow nets with tables (WFT-nets) were proposed to remedy such a flaw. However, existing methods for constructing the reachability graph of the WFT-nets can generate pseudo states because they do not take into account the guards that constrain the enabling and firing of transitions. Additionally, only the soundness property of WFT-nets is considered that represents a single design requirement, while many other requirements, especially those related to tables, cannot be analyzed. In this article, we re-define the formalism of WFT-nets by augmenting the constraints of guards to them and re-name them as workflow nets with tables and constraints (WFTC-nets). We propose a new method to generate the state reachability graph (SRG) of WFTC-nets such that the SRG can avoid pseudo states by considering the guard constraints. To represent design requirements related to database operations, we define database-oriented computation tree logic (DCTL). We design the model checking algorithms of DCTL based on the SRG of WFTC-nets and develop a tool. Experiments on several public benchmarks show the usefulness of our methods.

Information leakage easily occurs in large-scale information interactions and brings harm to individuals, enterprises, and society. As a well-known security policy, Chinese Wall (CW) provides a security guideline, which combines mandatory and discretionary access control to avoid information leakage. Colored Petri nets (CPNs) are a widely used formal method, well suited for verification of CW policy due to the capability of characterizing the concurrency. However, CPN easily suffers from the problem of state space explosion due to the interleaving semantics. The unfolding techniques can effectively alleviate this problem. In this article, we apply simplified CPN and their unfolding techniques to detect information leakage against CW policy. Specifically, we define a CPN-based CW model, propose an algorithm to generate the merged process of CPN, and detect the potential information leakage by analyzing the structural behaviors of its unfoldings. Furthermore, we conduct a case study and several experiments to show the advantages of our method. The results exhibit that our method can effectively detect information leakage against CW policy and alleviate the state space explosion.

Graph neural networks (GNNs) are capable of modeling graph data using various types of nodes and edges, and thus can be widely used in the fields of recommender systems and bioinformatics. However, most existing graph neural network models do not alleviate the problem of incomplete raw graph data and the need for extensive labels. This leads to increased labor costs and produces suboptimal or even incorrect results. In this article, we propose an end-to-end method for fusing learnable node-level and edge-level augmentation in automatic graph-level contrastive learning (NEAGCL), consisting of a graph preprocessing module and tailored graph-level contrastive learning. In the graph preprocessing module, we propose a parallel view generator method, which solves the problem of data incompleteness by simultaneously performing adaptive structure enhancement and learnable node information optimization. In tailored graph-level contrastive learning, we employ contrast learning in self-supervised learning and classification loss to jointly train graph classifiers, thus solving the problem of relying on the original labels. Besides, our model employs differentiable contrastive learning and is an end-to-end self-supervised model. Comparative tests of semisupervised learning and unsupervised learning on seven benchmark datasets for graph-level tasks demonstrate the superiority of our model. We demonstrate that effective graph contrastive learning requires learning better joint representations of graph structures and node attributes to improve the performance of graph-level tasks.

Industry 5.0 enhances manufacturing ability through efficient human-machine interaction, combining human resources and robots to complete tasks more accurately and effectively. Artificial intelligence (AI) plays an essential role in Industry 5.0. As a branch in AI, multiagent deep reinforcement learning (MADRL) attracts vast attention in both academia and industry. However, there is a gap between virtual and physical environments in terms of howcleanan observed state is. In addition, state adversarial attacks can seriously impact the performance of MADRL. Hence, how to improve the robustness of MADRL algorithms is an important research topic. In this article, we propose an optimal policy-based state adversary attack method that would make the MADRL algorithm more robust when it is applied in the training process of agents. Two case studies related to Industry 5.0 and a general case study are presented in which robustness training against the optimal adversarial attack is tested. The MADRL algorithms involved in the experiments include centralized training and decentralized execution (CTDE) framework and shared experience actor-critic (SEAC) to demonstrate the universality of our method.

Formal verification becomes increasingly critical to ensure system functionality, reliability and safety as they grow in complexity. Existing methods tend to focus on a single dimension of system aspects—such as control flow, data flow or timing constraints—or, at most, consider two of these perspectives without integrating all three. In addition, data flow models generally represent high-level data abstraction without including operational details within underlying contexts. The inability of these models to capture system behavior undermines their reliability, ultimately increasing the likelihood of the corresponding systems malfunctioning. To address these issues, we propose a formal verification method based on a timed Petri net with database tables (TPDT-net). First, we model the system using TPDT-net and generate its state reachability graph (SRG). Next, we extend timed computation tree logic (TCTL) by introducing database-related data element operators, thus proposing a database-oriented TCTL (DTCTL) model checking method. In addition, we formalize the system correctness problem as corresponding DTCTL formulas, which are analyzed based on the SRG. This approach transforms correctness verification into a satisfiability problem of DTCTL formulas within the SRG. Finally, we validate the practicality and effectiveness of the proposed method through case studies and experiments.

This paper introduces an innovative method for converting Rust source code to Petri nets while checking deadlock detection caused by synchronization primitives such as Mutex, RwLock, and CandVar in concurrent Rust programs. We establish conversion rules and develop tools to facilitate this process. During the scanning process, this method can exclude functions unrelated to locks, thus reducing the size of the Petri net. The experiment proves that our method is superior to the most advanced one.

The Petri-net-based information flow analysis offers an effective approach for detecting information leakage by the concept of non-interference. Although the related studies propose efficient solutions, they lack quantitative evaluation on information leakage. In this paper, we propose a novel method for quantitative evaluation of information security based on stochastic labeled Petri nets (SLPNs) and information flow analysis. Specifically, we introduce four different levels of security metrics, and provide a methodology for evaluating the information security. Furthermore, a case study is presented to show the feasibility of our method.

Credit card fraud detection (CCFD) is an important issue concerned by financial institutions. Existing methods generally employ aggregated or raw features as their representations to train their detection models. Yet such features tend to fall short of effectively exposing the characteristics of various frauds. In this work, we propose a spatial-temporal gated network (STGN) to automatically learn new informative transactional representations containing users’ transactional behavioral information for CCFD. A gated recurrent neural net unit is specifically constructed with a time-aware gate and location-aware gate to extract users’ spatial and temporal transactional behaviors. A spatial-temporal attention module is designed to expose the transaction motive of users in their historical transactional behaviors, which allows the proposed model to better extract the fraudulent characteristics from successive transactions with time and location information. A representation interaction module is offered to make rational decisions and learn compositive transactional representations. A real-world transaction dataset is used in experiments to verify the efficacy of the learned new representations. The results demonstrate that our proposed model outperforms the state-of-the-art ones, thus greatly advancing the field of CCFD.Note to Practitioners—The features of transaction records reflect the characteristics of users’ transactional behaviors. Therefore, effective features are critical for accurate CCFD. However, fraudsters often pretend to be legitimate users during transactions to deceive the CCFD system. As a result, fraudulent behaviors become concealed within legitimate ones, signifying that original features are inadequate for accurate CCFD. Thus, it is imperative for researchers and practitioners to extract new features that can well expose fraud characteristics. While existing methods employing some transaction aggregation strategies can spot certain fraudulent behaviors, they fail to clearly cluster all the anomalous behaviors and distinguish them from legitimate behaviors. Therefore, this work is driven by the urgent demand to extract new informative features for CCFD. Its primary focus is to unveil the aggregation of fraudulent transactional behaviors from both temporal and spatial perspectives, enabling more accurate CCFD. Specifically, this work introduces a new STGN model that automatically learns new transactional representations incorporating users’ transactional behavioral information for CCFD. By comprehensively considering the time interval and location interval of consecutive user transactions, we thoroughly reveal the temporal and spatial aggregation of fraudulent behavior, which provides valuable insights for CCFD practitioners: 1) employing features that integrate the behavioral characteristics of fraudsters instead of the original features can enhance the model’s capability to identify frauds, and 2) taking into account the time and location intervals of users’ consecutive historical transactions can better uncover the behavioral characteristics of fraudsters.

Heterogeneous information network (HIN) has been applied in a wide variety of graph analysis tasks. At present, it is a trend of heterogeneous graph neural networks (HGNNs) to cast the meta-paths aside, since it solves the problem of structural information loss caused by artificially designed meta-paths. However, existing meta-path-free HGNNs fail to take into account that most node types in many HINs have no attributes, and they cannot make full use of sparse node attributes when applied to HINs with missing attributes. Furthermore, their computation of attention coefficients explores the correlations of node attributes while almost ignoring structural ones, which may limit the expression ability of the model and cause overfitting in model training. To alleviate these issues, we propose an HGNN with attribute enhancement and structure-aware attention (HGNN-AESA). First, we design an attribute enhancement module (AEM) to connect more useful attributed nodes to the target nodes. Specifically, AEM introduces a random walk with restart (RWR) strategy to obtain structural relevance scores of each node within its specific subgraph. The structural relevance scores are used to capture potentially influential attributed nodes in high-order neighborhood for each target node. Second, we propose heterogeneous structure-aware attention layers (HSALs) to learn node representations. HSALs follow a hierarchical attention framework, including node-level and type-level attention. The node-level attention aggregates feature (attribute) embeddings of same-type neighbors, and the relevant attention coefficients depend on the combination of node attributes and heterogeneous structural interventions. The type-level attention fuses all type-specific vector representations and generates the ultimate node embedding. Finally, extensive experiments on three different real-world HIN datasets demonstrate that our model outperforms state-of-the-art methods.

The innovations in technologies have led to the emergence of digital finance such as online payment, online insurance, online lending, and supply chain finance. Digital finance has greatly facilitated people’s lives, accelerated the circulation of capital in various fields, and enhanced the vitality of financial markets. However, it exposes many increasing risks and hidden dangers such as stock volatility, trading fraud, credit card fraud, and privacy leakage[1],[2],[3],[4],[5],[6],[7]. How to effectively calculate, control, manage, and utilize financial big data and make full use of artificial intelligence technology to ensure financial security is an important research question. Solving it faces many challenges. These challenges not only include the complexity of data and computation but also the effectiveness of intelligent optimization algorithms and ways to deal with human behaviors and social environments[8],[9].

Many machine learning methods have been proposed to achieve accurate transaction fraud detection, which is essential to the financial security of individuals and banks. However, most existing methods either leverage original features only or require manual feature engineering so that they show a weak ability to learn discriminative representations from transaction data. Moreover, criminals often commit fraud by imitating cardholders’; behaviors, which causes the poor performance of existing detection models. In this article, we propose an adaptive sampling and aggregation-based graph neural network (ASA-GNN) that learns discriminative representations to improve the performance of transaction fraud detection. A neighbor sampling strategy is performed to filter noisy nodes and supplement information for fraudulent nodes. Specifically, we use cosine similarity and edge weights to adaptively select neighbors with similar behavior patterns for target nodes and then find multihop neighbors for fraudulent nodes. A neighbor diversity metric is designed by calculating the entropy of neighbors to tackle the camouflage issue of fraudsters and explicitly alleviate the oversmoothing phenomena. Extensive experiments on three real financial datasets demonstrate that ASA-GNN outperforms state-of-the-art ones.

With the rapid development of Internet industry, the learning methods based on data stream have attracted more and more attention owing to their great application value in many industries such as banking, insurance, and telecom industry. In the process of learning from stream data, one of the most significant challenges is how to adapt to the so-called concept drift which means that the data stream distribution changes over time in unpredictable ways. To deal with the problem, some methods have been put forward. However, most of them pay more attention to the whole entity of a given model and overlook the impact of local data on the model. In this article, we propose a novel ensemble algorithm to overcome the problem of ignoring local samples in previous methods, namely, the fit prediction algorithm based on local optimum (FPLO) which uses the information of local data to fit (predict) a concept drift. Furthermore, an adaptive method based on the so-called concept changing rate is proposed to choose those classifiers of suitable sizes to overcome the problem of selecting too much or too little historical drift information in previous methods and to make the prediction more accurate. The experimental results on nine synthetic stream datasets and eight real-world stream datasets which all have the concept drift problem show that our FPLO is able to tackle the problem more effectively in comparison to other state-of-the-art methods.

Since minority samples are substantially less common than majority samples, many industrial applications, such as credit card fraud detection (CCFD) and defective part identification, call for imbalanced classification. The performance of a classifier tends to suffer from the noisy samples in majority or minority classes. This work proposes a new undersampling scheme, called a clustering-based noisy-sample-removed undersampling scheme (NUS) for imbalanced classification. The majority class samples are first clustered. The distance of the majority class sample from the cluster center that is furthest away is used as the radius to build a hypersphere, with each cluster’s center assumed to be a spherical center. We determine the Euclidean distance between the center of a cluster and each minority sample to find whether they are in the hypersphere or not. Afterward, we exclude noisy samples from the minority class. The noisy samples of majority classes are removed by using the same procedure. Second, we propose an NUS, which combines noisy sample removal with undersampling techniques. Finally, to prove the effectiveness of NUS, we integrate NUS with the basic classifiers random forest (RF), decision tree (DT), and logistics regression (LR). We conduct their comparison with seven undersampling, oversampling, and noisy-sample-removed methods. This work performs experiments on 13 public and three real transaction datasets related to e-commerce. The results show that NUS plays a positive role in promoting existing classifiers’ performance.

How to obtain informative representations of transactions and then perform the identification of fraudulent transactions is a crucial part of ensuring financial security. Recent studies apply graph neural networks (GNNs) to the transaction fraud detection problem. Nevertheless, they encounter challenges in effectively learning spatial-temporal information due to structural limitations. Moreover, few prior GNN-based detectors have recognized the significance of incorporating global information which encompasses similar behavioral patterns and offers valuable insights for discriminative representation learning. Therefore, we propose a novel heterogeneous GNN called Spatial-Temporal-Aware Graph Transformer (STA-GT) for transaction fraud detection problems. Specifically, we design a temporal encoding strategy to capture temporal dependencies and incorporate it into the GNN framework, enriching spatial-temporal information and improving expressive ability. Furthermore, we introduce a transformer module to learn local and global information. Pairwise node–node interactions overcome the limitation of the GNN structure and build up the interactions between a target node and many long-distance ones. Experimental results on two financial datasets demonstrate that our STA-GT is more effective on the transaction fraud detection task compared to general GNN models and GNN-based fraud detectors.

Credit card fraud detection is a challenging task since fraudulent actions are hidden in massive legitimate behaviors. This work aims to learn a new representation for each transaction record based on the historical transactions of users in order to capture fraudulent patterns accurately and, thus, automatically detect a fraudulent transaction. We propose a novel model by improving long short-term memory with a time-aware gate that can capture the behavioral changes caused by consecutive transactions of users. A current-historical attention module is designed to build up connections between current and historical transactional behaviors, which enables the model to capture behavioral periodicity. An interaction module is designed to learn comprehensive and rational behavioral representations. To validate the effectiveness of the learned behavioral representations, experiments are conducted on a large real-world transaction dataset provided to us by a financial company in China, as well as a public dataset. Experimental results and the visualization of the learned representations illustrate that our method delivers a clear distinction between legitimate behaviors and fraudulent ones, and achieves better fraud detection performance compared with the state-of-the-art methods.

Multiagent deep reinforcement learning (DRL) makes optimal decisions dependent on system states observed by agents, but any uncertainty on the observations may mislead agents to take wrong actions. The mean-field actor-critic (MFAC) reinforcement learning is well-known in the multiagent field since it can effectively handle a scalability problem. However, it is sensitive to state perturbations that can significantly degrade the team rewards. This work proposes a Robust MFAC (RoMFAC) reinforcement learning that has two innovations: 1) a new objective function of training actors, composed of a policy gradient function that is related to the expected cumulative discount reward on sampled clean states and an action loss function that represents the difference between actions taken on clean and adversarial states and 2) a repetitive regularization of the action loss, ensuring the trained actors to obtain excellent performance. Furthermore, this work proposes a game model named a state-adversarial stochastic game (SASG). Despite the Nash equilibrium of SASG may not exist, adversarial perturbations to states in the RoMFAC are proven to be defensible based on SASG. Experimental results show that RoMFAC is robust against adversarial perturbations while maintaining its competitive performance in environments without perturbations.

Multiagent deep reinforcement learning (MADRL) has been recently applied in many fields, including industry 5.0, but it is sensitive to adversarial attacks. Although adversarial attacks can be detrimental, they are crucial for testing and assisting in enhancing the robustness of models. Existing attacks on MADRL-based models are not sufficient since these attacks involve fixed perturbed agents, without taking into account cases where perturbed agents change. In this article, we present a novel adversarial attack framework. In this framework, we define critical agents that change over time, i.e., when they are perturbed a little, the whole multiagent system is perturbed greatly. Then, we identify critical agents through their worst-case joint actions. In this identifying process, we use gradient information, differential evolution, and SARSA to deal with the challenge caused by changes in the perturbed agents and to compute the worst-case joint actions. After identifying them, we use the target attack method to perturb them. We apply our method to attack the models trained by two state-of-the-art MADRL algorithms under three environments, including two industry-related ones. The experimental results demonstrate our method has a stronger perturbing ability than the existing methods.

Multi-agent reinforcement learning (MARL) has been widely applied in many fields, such as smart traffic and unmanned aerial vehicles. However, most MARL algorithms are vulnerable to adversarial perturbations on agent states. Robustness testing for a trained model is an essential step for confirming the trustworthiness of the model against unexpected perturbations. This work proposes a novel Robustness Testing framework for MARL that attacks states of Critical Agents (RTCA). The RTCA has two innovations: 1) a differential evolution (DE) based method to select critical agents as victims and to advise the worst-case joint actions on them, and 2) a team cooperation policy evaluation method employed as the objective function for the optimization of DE. Then, adversarial state perturbations of the critical agents are generated based on the worst-case joint actions. This is the first robustness testing framework with varying victim agents. RTCA demonstrates outstanding performance in terms of the number of victim agents and destroying cooperation policies.

Computation tree logic of knowledge (CTLK) can be used to specify many properties related to privacy of multiagent systems (MASs). Our previous work defined knowledge-oriented Petri nets (KPNs) to formally describe both the interacting/collaborating process of multiagents and their epistemic evolutions. Our KPN-based verification of CTLK required to obtain all reachable states, the transition relation of all states, and the equivalence relations of all states with respect to knowledge, which resulted in a serious state explosion problem and thus only fit some small-scale systems. This article adopts reduced ordered binary decision diagram (ROBDD) to deal with this problem. Especially, the ROBDD technique is used to encode and store all reachable states but not to encode and store any transition relation or equivalence relation. However, when verifying a CTLK formula, the transition relation and equivalence relation of some states must be known. To solve this problem, we design the related algorithms to compute only those required relations and prove their correctness. We design the related model checking algorithms and develop a tool. A number of experiments are done by using a famous benchmark about the privacy problem of MAS: the dining cryptographers protocol (DCP), and the results illustrate the advantages of our methods. For example, our tool running with a general PC spends less than 14 h to verify the DCP with 1200 cryptographers, which involves about 101080 states and two CTLK formulas with more than 6000 atomic propositions and more than 3600 operators. This represents a significant advance in the field of model checking.

With the popularity of credit cards worldwide, timely and accurate fraud detection has become critically important to ensure the safety of their user accounts. Existing models generally utilize original features or manually aggregated features as their transactional representations, while they fail to reveal the hidden fraudulent behaviors. In this work, we propose a novel model to extract transactional behaviors of users and learn new transactional behavioral representations for credit card fraud detection. Considering the characteristics of transactional behaviors, two time-aware gates are designed in a recurrent neural net unit to learn long- and short-term transactional habits of users, respectively, and to capture behavioral changes of users caused by different time intervals between their consecutive transactions. A time-aware-attention module is proposed and employed to extract the behavioral information from their consecutive historical transactions with time intervals, which enables the proposed model to capture behavioral motive and periodicity inside their historical transactional behaviors. An interaction module is designed to learn more comprehensive and rational representations. To prove the effectiveness of the learned transactional behavioral representations, experiments are conducted on a large real-world transaction dataset and a public one. The results show that the learned representation can well distinguish fraudulent behaviors from legitimate ones, and the proposed method can improve the performance of credit card fraud detection in terms of various evaluation criteria over the state-of-the-art methods.

With the applications of deep learning in safety-critical domains such as autonomous driving systems gaining ground, it demands rigorous verification to guarantee the safety and reliability of corresponding systems. As the intelligent component in such systems, neural networks (NNs) must be robust in that their outputs are not affected by minor perturbation to inputs. Many research studies have shown that formal methods are effective ways to the robustness verification of NNs. However, most of the existing approaches are focused on NNs that contain monotonic activation functions, such as ReLU, Tanh, and Sigmoid. In this work, we propose an approach to verify the robustness of NNs with the nonmonotonic activation function called Swish. Such networks have been proved to have a better performance on image classification than other NNs. In our approach, we turn the robustness verification problem into a constraint-solving problem using the linear approximation technique. We first model the affine function of an NN into a linear constraint model. Then, for nonlinear activation functions, we leverage an efficient approximation strategy to linearly approximate them. Finally, we utilize the constraint solver gurobi to solve the model, which reveals that the model satisfies the robustness property. We develop a prototype tool and evaluate it with open-sourced NNs. Experimental results showed the effectiveness and efficiency of our approach.

When a group of real-time tasks with dependent relations are performed in parallel in a multiprocessor interruptible environment, time-related requirements are easily destroyed so that the correct design of such a system is complex and difficult. Therefore, it is necessary for designers to use some precise methods to verify their correctness, while model checking based on time Petri nets and timed computation tree logic (TCTL) is such an effective method. However, the existing models and tools only focus on those multiprocessor real-time systems where the number of processors of the same type is just one, and thus, they cannot work for the case that the number of processors of the same type is greater than one. Hence, this article proposes prioritized time-point-interval Petri nets (PToPN) to deal with it and defines their firing rules and state graphs to represent their behaviors. A PToPN can explicitly model the preemptive scheduling of such a real-time system, and TCTL formulas specifying design requirements of the system can be verified based on its state graph. Besides, we propose TCTL with unknown time bounds, denoted as TCTL$_{x}$, to compute the minimum or maximum time bound ensuring a related formula holds. Such a quantitative analysis is very necessary in the real applications because they can be used to compute some performances of a system such as the worst-case execution time of tasks and the idle time of processors. We design the related algorithms and develop a tool. We use a real example from HUAWEI Company to show the usefulness of our method, and do some experiments to show the advantages of our method compared with another state-of-the-art one.

Missing-data errors easily occur in cyber-physical systems (CPSs). Although many business process modeling notation (BPMN)-based methods are proposed to model CPSs and detect errors, it is hard to automatically verify their correctness, especially in the data flows, due to their lack of formal specifications. By comparison, Petri nets, as a formal method, are widely used to detect data-flow errors. However, these methods easily suffer from the state-space explosion problem. This is mainly because their reachability graphs or state transition graphs are based on the interleaving semantics. As an unfolding technique of Petri net, a merged process can characterize concurrency relations and alleviate this problem. Thus, we utilize the merged process of Petri net with data (PD-net) to check the missing-data errors of the CPS. We first transform a BPMN of the CPS into a PD-net and generate its merged process. Meanwhile, we analyze its structural behaviors and data-adjacent events. Furthermore, we propose an algorithm for checking missing-data errors. In addition, a case study and some experiments are done to show the practicality and effectiveness of our method.

Lightweight convolutional neural networks (CNNs) rely heavily on the design of lightweight convolutional modules (LCMs). For an LCM, lightweight design based on repetitive feature maps (LoR) is currently one of the most effective approaches. An LoR mainly involves an extraction of feature maps from convolutional layers (CE) and feature map regeneration through cheap operations (RO). However, existing LoR approaches carry out lightweight improvements only from the aspect of RO but ignore the problems of poor generalization, low stability, and high computation workload incurred in the CE part. To alleviate these problems, this article introduces the concept of key features from a CNN model interpretation perspective. Subsequently, it presents a novel LCM, namely CEModule, focusing on the CE part. CEModule increases the number of key features to maintain a high level of accuracy in classification. In the meantime, CEModule employs a group convolution strategy to reduce floating-point operations (FLOPs) incurred in the training process. Finally, this article brings forth a dynamic adaptation algorithm ( α -DAM) to enhance the generalization of CEModule-enabled lightweight CNN models, including the developed CENet in dealing with datasets of different scales. Compared with the state-of-the-art results, CEModule reduces FLOPs by up to 54% on CIFAR-10 while maintaining a similar level of accuracy in classification. On ImageNet, CENet increases accuracy by 1.2% following the same FLOPs and training strategies.

With the development of IoT, virtual reality, cloud computing, and digital twin technologies, the advent of metaverse has attracted increasing world attention. Metaverse integrates and applies multiple emerging technologies to cloud education, smart health, digital government, and emergency evacuation. Evacuation systems are of great importance to ensure life safety. Due to panic, people in a building may not be able to make the right judgment to choose an optimal path to leave the building in case of an emergency event such as a fire. As a branch of machine learning, deep reinforcement learning (DRL) can model an evacuation scene, collect real-time information, such as crowd distribution and disaster location, find the optimal escape path with a path-planning algorithm, induce the movement state of the crowd through dynamic guidance signs, and improve the evacuation efficiency. In this article, we apply DRL technology to solve the efficient emergency evacuation problem with the help of metaverse and show a training system built upon metaverse that would enable evacuees to choose the most efficient route and leave the building in the least amount of time. The information collected by various sensors, such as video cameras and smoke detectors, can give a whole picture of the status of the building in a real-time manner. The collected data are processed by cloud servers in which a DRL model is trained to dynamically guide evacuees. Experiments in different simulation scenes demonstrate that the proposed method is superior to the traditional static guidance method in saving evacuation time. It can effectively avoid major crowding along the evacuation route and improve evacuation efficiency.

Metaverse is an artificial virtual world mapped from and interacting with the real world. In metaverse, digital entities coexist with their physical counterparts. Powered by deep learning, metaverse is inevitably becoming more intelligent in the interactions between reality and virtuality. However, it is confronted with a nontrivial problem known as sim2real transfer when deep learning techniques try to bridge the reality gap between the physical world and simulations. In this article, we use multiagent deep reinforcement learning (MARL) to implement collective intelligence for digital entities as well as their physical counterparts. To model the immersive environments in metaverse, we define a nonstationary variant of Markov games and propose a recurrent MARL solution to it. Based on the solution, MARL sim2real transfer that bridges real and virtual multiple unmanned aerial vehicle (multi-UAV) systems is successfully conducted by employing recurrent multiagent deep deterministic policy gradient (R-MADDPG) with the domain randomization technique. Additionally, we use perception-control modularization to improve the generalization performance of MARL policies and make training more efficient.

How to guarantee the consistency between different systems has become a bone of contention in model-driven software development. Behavioral relations are a prominent technique/method to analyze the consistency degree of two workflow systems. There are four kinds of behavioral relations, i.e., strict order relation, exclusiveness relation, interleaving order relation, and inverse order relation. An activity in a module may be in different behavioral relations with activities in another module. We call the latter module aspecial modulein this article. However, the existing measuring methods for behavioral consistency do not consider special modules at all. Thus, if we conduct a consistency analysis of different systems by these methods, we may get an inaccurate consistency degree, or obtain no results. In order to solve this problem, we use workflow nets (WF-nets) to model workflow systems and re-explore their behavioral relations. Then, their behavioral relation matrices (BRMs) are constructed. Based on BRMs, some new measurement methods are proposed to calculate the behavioral consistency degree of two WF-net systems. Finally, a group of experiments is done to show the effectiveness of our methods.

With the development of smart devices and mobile communication technologies, e‐commerce has spread over all aspects of life. Abnormal transaction detection is important in e‐commerce since abnormal transactions can result in large losses. Additionally, integrating data flow and control flow is important in the research of process modeling and data analysis since it plays an important role in the correctness and security of business processes. This paper proposes a novel method of detecting abnormal transactions via an integration model of data and control flows. Our model, called Extended Data Petri net (DPNE), integrates the data interaction and behavior of the whole process from the user logging into the e‐commerce platform to the end of the payment, which also covers the mobile transaction process. We analyse the structure of the model, design the anomaly detection algorithm of relevant data, and illustrate the rationality and effectiveness of the whole system model. Through a case study, it is proved that each part of the system can respond well, and the system can judge each activity of every mobile transaction. Finally, the anomaly detection results are obtained by some comprehensive analysis.

This paper proposes a new heuristic method to quickly construct OBDD variable order for Petri net based CTL model checking. Consequently, OBDDs using these orders have a good compressing effect for modular and loosely-coupled Petri nets. For further enhancing the performance of our model checking, we apply a model checking strategy: when producing the reachability graph of a Petri net, we only store its states encoded by an OBDD but not any state transition since the number of state transitions is generally much greater than the number of states themselves; while computing the set of satisfiable states of a CTL formula, we utilize these states and the structure of the Petri net to do so. Consequently, this strategy can generally improve space and time efficiency of model checking. A number of experiments show the effectiveness of our method. For example, our method can verify deadlocks of Dining Philosophers Problem for the case of 5000 philosophers in 12 hours, which has about 103300states.

Fraud detection has attracted significant attention in financial institutions, especially utilizing some artificial intelligent methods to automatically detect fraudulent transactions. With the study and application of intelligent fraud detection technology, scholars found that the representation learning method can reveal more information about fraud patterns, which is also crucial for detection task. Therefore, in this work, we present a novel method for detecting fraud transactions by combining two modules learning hidden information at different levels of data in a unified framework. To address and explore the deep representation of features of transaction behaviors, we propose a two-level attention model to capture them by integrating two data embeddings at the data sample level and the feature level. In particular, the sample-level attention model captures the detailed information more centrally that is difficult to determine; the feature-level attention model extends the information of feature dependences. We further combine them to train a final fraud detection model. Extensive experiments are conducted using a data set provided by a financial company in China and several public financial data sets. The results confirm the effectiveness of our proposed method in detecting fraudulent transactions compared with other state-of-the-art methods.

The correctness of workflow systems is dependent on not only their control-flows but also their data-flows.WFD-nets(Workflow net with data) can model both control-flow and data-flow of workflow systems, and are used to analyze/verify their correctness. The existing methods of analyzing/verifying WFD-nets are based on their reachability graphs. However, the reachability-graph-based methods have two flaws: state space explosion and pseudo states, since the guard functions are not handled perfectly. Note that every transition of a WFD-net is labeled by a guard function, which is a Boolean expressionw.r.t.data and can determine the progress of control-flow. In order to solve these problems, we propose aguard-driven reachability graphthat can both alleviate the state space explosion problem and avoid pseudo states. We describe the related algorithms and develop a tool. A group of experiments illustrate the advantage and effectiveness of our approach, and an example of property loan shows its usefulness.

Epistemic logic can specify many design requirements of privacy and security of multi-agent systems (MAS). The existing model checkers of epistemic logic use some programming languages to describe MAS, induce Kripke models as the behavioral representation of MAS, apply Ordered Binary Decision Diagrams (OBDD) to encode Kripke models to solve their state explosion problem and verify epistemic logic based on the encoded Kripke models. However, these programming languages are usually non-intuitive. More seriously, their OBDD-based model checking processes are often time-consuming due to their dynamic variable ordering for OBDD. Therefore, we define Knowledge-oriented Petri Nets (KPN) to intuitively describe MAS, induce similar reachability graphs as the behavioral representation of KPN, apply OBDD to encode all reachable states, and finally verify epistemic logic. Although we also use OBDD, we adopt a heuristic method for the computation of a static variable order instead of dynamic variable ordering. More importantly, while verifying an epistemic formula, we dynamically generate its needed similar relations, which makes our model checking process much more efficient. In this paper, we introduce our work.

Deep learning methods have shown great potentiality in the credit card fraud detection field. Unfortunately, they cannot explain their predictions, while a financial company expects to know the reason that a transaction is decided to be fraud. There have been some studies of the interpretability of deep learning methods in other fields, but we find that their effects are not very good when we directly use them to the credit card fraud detection problem, because they ignore the behavior patterns of the cardholder, and cannot deal with the nonlinear local boundary. In this paper, we propose a new method, MANE (Model-Agnostic Non-linear Explanations) for deep learning models, that can provide a set of interpretable features for each transaction. First, we use a cardholder's historical transactions to extract a set of behavior patterns for the cardholder via an aggregation strategy. Next, we use nonlinear model GBDT (Gradient Boosting Decision Tree) to mine cross features based on these behavior patterns, so that our explanation model can approximate the local boundary of a complex deep learning model. Finally, for every to-be-explained sample, we obtain its neighbors by using a random perturb method, then we train an interpretable linear regression model for the sample based on its neighbors, the behavior patterns of this cardholder and the related cross features. Our experiments on a real dataset demonstrate that our method achieves better effects.

Credit card fraud detection is an important study in the current era of mobile payment. Improving the performance of a fraud detection model and keeping its stability are very challenging because users' payment behaviors and criminals' fraud behaviors are often changing. In this article, we focus on obtaining deep feature representations of legal and fraud transactions from the aspect of the loss function of a deep neural network. Our purpose is to obtain better separability and discrimination of features so that it can improve the performance of our fraud detection model and keep its stability. We propose a new kind of loss function, full center loss (FCL), which considers both distances and angles among features and, thus, can comprehensively supervise the deep representation learning. We conduct lots of experiments on two big data sets of credit card transactions, one is private and another is public, to demonstrate the detection performance of our model by comparing FCL with other state-of-the-art loss functions. The results illustrate that FCL outperforms others. We also conduct experiments to show that FCL can ensure a more stable model than others.

AdaBoost is a boosting-based machine learning method under the assumption that the data in training and testing sets have the same distribution and input feature space. It increases the weights of those instances that are wrongly classified in a training process. However, the assumption does not hold in many real-world data sets. Therefore, AdaBoost is extended to transfer AdaBoost (TrAdaBoost) that can effectively transfer knowledge from one domain to another. TrAdaBoost decreases the weights of those instances that belong to the source domain but are wrongly classified in a training process. It is more suitable for the case that data are of different distribution. Can it be improved for some special transfer scenarios, e.g., the data distribution changes slightly over time? We find that the distribution of credit card transaction data can change with the changes in the transaction behaviors of users, but the changes are slow most of the time. These changes are yet important for detecting transaction fraud since they result in a so-called concept drift problem. In order to make TrAdaBoost more suitable for the abovementioned case, we, thus, propose an improved TrAdaBoost (ITrAdaBoost) in this article. It updates (i.e., increases or decreases) the weight of a wrongly classified instance in a source domain according to the distribution distance from the instance to a target domain, and the calculation of distance is based on the theory of reproducing kernel Hilbert space. We do a series of experiments over five data sets, and the results illustrate the advantage of ITrAdaBoost.

Convolutional neural networks (CNNs) have demonstrated great competence in feature representation, and then, achieved a good performance to many classification tasks. Cross-entropy loss, together with softmax, is arguably one of the most commonly used loss functions in CNNs (that is generally called softmax loss). However, the softmax loss can result in a weakly discriminative feature representation since it focuses on the interclass separability rather than the intraclass compactness. This article proposes a pairwise Gaussian loss (PGL) for CNNs that can well address the intraclass compactness through significantly penalizing those similar sample pairs with a relatively large distance. At the same time, PGL can still ensure a good interclass separability. Experiments show that PGL can guarantee that CNNs obtain a better classification performance compared to not only the softmax loss but also others often used in CNNs. Our experiments also show that PGL has a stable convergence for the stochastic gradient descent optimization method in CNNs and a good generalization ability for different structures of CNNs.

Workflow nets and their extensions with data flows, e.g., workflow nets with data and colored workflow nets, can well model the business processes of workflow systems, and their soundness guarantees that systems have neither deadlock nor livelock. However, some design requirements related to the changes of data values within multiple business cases are not reflected by these models, and thus, some errors of the modeled systems cannot be detected by them. In this article, we propose workflow nets with tables (WFT-nets) to model workflow systems that are closely related to the database (i.e., different users, records, and attributes). We define the firing rule of WFT-nets via data refinements in order to avoid infinite states caused by unbounded data. We use first-order linear temporal logic to represent the design requirements of records and attributes' values and then define the soundness of WFT-nets. We construct an algorithm to verify soundness. A tool is developed, and a group of experiments are done to illustrate the effectiveness of our methods.

This paper focuses on the behavior similarity of workflow nets (WF-nets). The similarity of two WF-nets reflects their consistent degree in behaviors. It explores the behavioral relations of subsets of transitions based on the interleaving semantics, and more accurate relations are defined than the existing work. Therefore, a more accurate similarity of two WF-nets (in their behaviors) can be obtained than that in the existing work that usually do not consider the loop and complex correspondence. By refining the interleaving relation in a behavioral profile into six types, this paper proposes the notion of a relation profile based on behavioral profile. Based on the relation profile of a WF-net, behavioral relation matrix can be constructed. Additionally, we refine the complex correspondence and generate a group of behavioral relation submatrices from the behavioral relation matrix. By using them we present a new formula to measure the behavior similarity of two WF-nets. Finally, examples illustrate that our method can measure the similarity degree more accurately.

The class imbalance problem exists in many real-world applications such as fraud detection, medical diagnosis and spam filtering, and seriously influences the performance of learning algorithms. Randomly undersampling is a famous method to solve the problem. However, it cannot well extract the samples nearby the cross-edge of majority and minority classes due to its randomness, while these samples are very important for a classifier since they influence the classification performance. In this paper, we propose a novel Gaussian Mixture Undersampling (GMUS for short). GMUS mainly contains three steps. Firstly, a Gaussian Mixture Model (GMM) is applied to fit the majority samples. Secondly, considering the probability density function (PDF) of predicted minority samples on the well-fitted GMM, the maximum of PDF is selected as the cross-edge of two classes. Finally, we undersample the majority samples near the cross-edge. We do experiments on 16 public datasets and the results demonstrate that GMUS can sample more informative instances and thus improve the performance of classifiers compared with the state-of-the-art undersampling methods. We also apply GMUS to the credit card fraud detection and obtain a good performance.

Location recommendation method is an important application in a location-based social network. At present, it is a trend to integrate different recommendation methods since they have their own advantages in capturing different preferences of users and an integrated method can generally provide a better performance than every individual. However, the existing integration policies do not learn user preferences in their integration processes so that they cannot make full use of the advantage of each method. Therefore, we propose a novel integration method: learning-to-rank-based integration. In our method, a confidence coefficient is applied for each user in the integration process, and these coefficients can well optimize recommendation performance. A learning-to-rank-based algorithm is designed to train the confidence coefficients. A group of experiments are done on a real large-scale check-in data set, and the results demonstrate that our method outperforms the state-of-the-art ones.

Credit card is now popular in daily life. Meanwhile, credit card fraud events occur more frequently, which result in massive financial losses. There are a number of fraud detection methods, but they do not deeply mine features of customer's transaction behavior so that their detection effectiveness is not too desirable. This paper focuses on two aspects of feature mining. Firstly, the features of credit card transactions are expanded in time dimension to characterize the distinct payment habits of legal users and criminals. Secondly, Capsule Network (CapsNet) is adopted to further dig some deep features on the base of the expanded features, and then a fraud detection model is trained to identify if a transaction is legal or fraud. Through experiments on a real transaction dataset, we demonstrate that the time dimension extension can improve the performance of fraud detection, and then CapsNet is further illustrated to be more advantageous in fraud detection compared with other models.

Petri nets are used to detect the errors of data inconsistency in concurrent systems. The detection methods usually apply a breadth-first or depth-first search to the reachability graphs of Petri nets. However, they spend too much space and time due to the blind search strategy. In this paper, we propose a heuristic method that can save lots of space and time. First we define structural data inconsistency of Petri nets which is more likely to cause the errors of data inconsistency. Then, in order to detect the errors as fast as possible, a heuristic function is proposed to guide the construction of a reachability graph. Furthermore, we propose a detection algorithm and develop a tool. Our experiments illustrate the advantage and effectiveness of our method.

With the rapid development of electronic commerce, the number of transactions by credit cards are increasing rapidly. As online shopping becomes the most popular transaction mode, cases of transaction fraud are also increasing. In this paper, we propose a novel fraud detection method that composes of four stages. To enrich a cardholder's behavioral patterns, we first utilize the cardholders' historical transaction data to divide all cardholders into different groups such that the transaction behaviors of the members in the same group are similar. We thus propose a window-sliding strategy to aggregate the transactions in each group. Next, we extract a collection of specific behavioral patterns for each cardholder based on the aggregated transactions and the cardholder's historical transactions. Then we train a set of classifiers for each group on the base of all behavioral patterns. Finally, we use the classifier set to detect fraud online and if a new transaction is fraudulent, a feedback mechanism is taken in the detection process in order to solve the problem of concept drift. The results of our experiments show that our approach is better than others.

The correctness of a time-critical system is closely related to the time of responding and performing every event. Our motivation example, alternating bit protocol , and application example, multi-track level crossing with sensors , both demonstrate that some nondeterministic behaviours can take place if the time associated with events is configured inappropriately or some concurrent events are controlled imperfectly in an overlapping period. These nondeterministic behaviours decrease the reliability and/or safety of a time-critical system. Therefore, it is valuable to formalise and check (non)determinacy. Time Petri Nets (TPN) in which the firing of every event is limited to a fix time interval are used to model time-critical systems in this article. We proposes a novel notion for TPN named time-soundness . It guarantees that the system always owns deterministic behaviours after any event is performed no matter when the event is performed. We utilise the notion of bisimulation to prove that the time-soundness can guarantee the behavioural determinacy. We propose an algorithm to check time-soundness, develop the related tool, and do experiments to show the usefulness and effectiveness of our notion and method.

With the popularization of online shopping, transaction fraud is growing seriously. Therefore, the study on fraud detection is interesting and significant. An important way of detecting fraud is to extract the behavior profiles (BPs) of users based on their historical transaction records, and then to verify if an incoming transaction is a fraud or not in view of their BPs. Markov chain models are popular to represent BPs of users, which is effective for those users whose transaction behaviors are stable relatively. However, with the development and popularization of online shopping, it is more convenient for users to consume via the Internet, which diversifies the transaction behaviors of users. Therefore, Markov chain models are unsuitable for the representation of these behaviors. In this paper, we propose logical graph of BP (LGBP) which is a total order-based model to represent the logical relation of attributes of transaction records. Based on LGBP and users' transaction records, we can compute a path-based transition probability from an attribute to another one. At the same time, we define an information entropy-based diversity coefficient in order to characterize the diversity of transaction behaviors of a user. In addition, we define a state transition probability matrix to capture temporal features of transactions of a user. Consequently, we can construct a BP for each user and then use it to verify if an incoming transaction is a fraud or not. Our experiments over a real data set illustrate that our method is better than three state-of-the-art oneoness.

Personalized trip recommendation has drawn much attention recently with the development of location-based services. How to utilize the data in the location-based social network to recommend a single Point of Interest (POI) or a sequence of POIs for users is an important question to answer. Recommending the latter is called trip recommendation that is a challenging study because of the diversity of trips and complexity of involved computation. This work proposes a maximal-marginal-relevance-based personalized trip recommendation method that considers both relevance and diversity of trips in trip planning. An ant-colony-optimization-based trip planning algorithm is developed to efficiently plan a trip. Finally, case studies and experiments illustrate the effectiveness of our method.

Petri nets are widely used to model and analyse concurrent systems. There exist two distinct classes of Petri nets that focus on different features of concurrent systems. The first one features multiple parallel processes sharing a group of common resources but not interacting/collaborating with each other. The second one allows multiple parallel processes to interact/collaborate with each other via message exchange but does not share any common resources. However, in many distributed environments, multiple processes both interact/collaborate with each other and share some common resources. To model and analyse such systems, this article defines a new class of Petri nets called Parallel Process Nets (P 2 Ns) that may be viewed as a generalization of the two mentioned above. We propose collaborativeness and close collaborativeness for P 2 Ns. The former guarantees that a modelled system is both deadlock-free and livelock-free, and the latter guarantees that it is deadlock-free, livelock-free, and starvation-free. These concepts and ideas are illustrated through some classical examples such as Producer-Consumer Problem and Dinning Philosophers Problem. Algorithms are developed to decide them. At last, P 2 Ns are applied to the modelling and analysis of two real systems: hospital information system and elevator scheduling system.

The errors of data inconsistency occur in a concurrent system when some concurrent operations are conducted improperly. The model-checking technique is widely used to detect them based on the state transition graph. However, the state space explosion problem is the biggest obstacle for this technique, since the state transition graph is based on the interleaving semantics that can result in a rapid increase of the graph scale. In addition, data inconsistency is closely related with concurrent operations, but the state transition graph hardly characterizes concurrency due to its interleaving semantics. The unfolding technique of Petri nets can both alleviate the state explosion and characterize concurrency because it is based on the concurrent semantics. In this paper, we define Petri net with data to model concurrent systems with three kinds of data operations: read , write, and delete, and then formalize data inconsistency. We propose an unfolding method to produce a finite complete prefix (FCP) for each PD-net. Then, a matrix that represents all concurrency relations of transitions is constructed in view of FCP. Furthermore, the error of data inconsistency can be detected via this matrix. The related algorithms and the developed tool are introduced, and experiments illustrate their effectiveness and advantages. An example of industrial information system shows the usefulness of our study.

Effectiveness is the most important factor considered in the ranking models yielded by algorithms of learning to rank (LTR). Most of the related ranking models only focus on improving the average effectiveness but ignore robustness. When a ranking model ignores robustness, the effectiveness for many queries is possibly very poor although the average effectiveness for all queries is relatively high. Therefore, Wang et al. first consider robustness in their ranking models. However, the robustness formula defined by Wang et al. cannot characterize those queries whose effectiveness are hurt seriously in comparison with the baseline model. In order to overcome this shortcoming, we propose a novel formula of characterizing robustness based on portfolio theory, and construct a multiobjective optimization model of the robust LTR in which the formula is used. Based on this model, we propose an approach of risk-sensitive and robust LTR, named as R2Rank, which is based on the framework of archived multiobjective simulated annealing algorithm and the idea of preference ranking organization method for enrichment evaluation. The experimental results show that the ranking models produced by our proposed R2Rank approach are better in both effectiveness and robustness than those produced by three state-of-the-art LTR approaches.

It is a valuable study for Location-based Social Network (LBSN) make a more accurate Points-of-Interest (POI) recommendation since that can improve users' experiences. There have been many methods of POIs recommendation that consider context, personal preference pattern, and/or matrix factorization. However, the continuous contexts have not been thoroughly considered in these methods. This paper first proposes a locations splitting method which can handle both continuous and discrete contexts. Moreover, we present a Context-aware Probabilistic Matrix Factorization method (CPMF) that factorizes a frequency matrix of contexts and locations to obtain the user-location checkin probabilities. We design a Personal Preference Confidence (PPC) to extract a set of reliable POIs with confidence values for every user. Finally, we propose a hybrid recommender which fuses CPMF with PPC to recommend top-n POIs. Experiments on a large-scale real-world checkins dataset demonstrate that our recommendation method obtains a well performance and effect.

The general Petri nets are not suitable to model the data operations of concurrent read and coverable write. Therefore, Petri net with data operations (PN-DO) is defined, which extends contextual nets with write arcs and some other components. Its execution semantics are defined, and a new method is proposed to construct its reachability graph that is of a smaller scale than traditional reachability graph. Based on this kind of reachability graph, we propose a method to check the errors of inconsistent data and missing data. Meanwhile, case studies are given to illustrate the effectiveness of our methods.

The number of web services has grown drastically. Then how to manage them efficiently in a service repository is an important issue to address. Given a special field, there often exists an efficient data structure for a class of objects, e.g., the Google' Bigtable is very suitable for webpages' storage and management. Based on the theory of the equivalence relations and quotient sets, this work proposes a multilevel index model for large-scale service repositories, which can be used to reduce the execution time of service discovery and composition. Its novel use of keys as inspired by the key in relational database can effectively remove the redundancy of the commonly-used inverted index. Its four function-based operations are for the first time proposed to manage and maintain services in a repository. The experiments validate that the proposed model is more efficient than the existing structures, i.e., sequential and inverted index ones.

This correspondence paper focuses on classification and recognition of different objects in a satellite image. First, for every object we need to compute its fingerprint as its unique recognition. We improve the traditional elastic grid technique. Every object is partitioned into a set of grids. For each grid, we use its texture feature, a five-tuple features generated by gray level co-occurrence matrix, rather than its center value, an average value of grays, to characterize it. We utilize the feature-standardizing method to handle this five-tuple features and then generate the fingerprint of each grid. An ordered sequence of fingerprints of all grids of an object is viewed as the fingerprint of this object. Furthermore, on the basis of the fingerprints of objects, we use the Lebesgue measure to compute their dissimilarities, and thus these objects are classified. In this paper, we develop the related algorithms. The experimental results show that classification and recognition generated by our method is more accurate than others, which implies that the method of computing dissimilarity is better.

In this paper, we propose a Markov chain-based testability growth model (TGM) for the just in-time fix program. This model can help the system designers to manage the testability growth process during system maturation. We also derive a cost-benefit model for allocating test resources to optimize a specified testability metric subject to a constraint on cumulative test cost. Bayesian inference, coupled with a hybrid genetic and particle swarm optimization method, is used to estimate the parameters of the TGM from evolving data, and the resulting model is utilized to track and project the testability metric. A near-optimal Lagrangian relaxation-based algorithm is applied to solve the test resource allocation problem. The testability growth and resource allocation models are validated via simulation examples. Results show that the model and algorithms presented in this paper have the potential to efficiently manage the testability growth problem.

van der Aalst et al. proved that the soundness problem is solvable in polynomial time for free-choice workflow nets (FCWF-nets). However, FCWF-nets cannot model most web services composition and interorganizational business processes because the interaction among processes does not usually satisfy the free-choice requirement. Asymmetricchoice workflow nets (ACWF-nets) as a larger class than FCWF-nets can model lots of such cases. Our previous work showed that the (weak) soundness problem is co-NP-hard for three-bounded ACWF-nets. Later, Tiplea et al. proved that for three-bounded acyclic ACWF-nets, the weak soundness problem is co-NP-complete. We sharp these results in this paper. First, we prove that for ACWF-nets, whether they are one-bounded or k-bounded (k > 1), the soundness problem is co-NP-hard. Second, it is proven that the soundness is equivalent to the weak soundness for any acyclic ACWF-nets, i.e., an acyclic ACWF-net is sound if and only if it is weakly sound.

Workflow nets (WF-nets) are widely used to model and verify the business process management systems and composite web services. The (weak) soundness of WF-nets is an important criterion for the correctness of these systems. This paper focuses on the complexity of solving the (weak) soundness problem. Aalst et al. have proven that the (weak) soundness problem is decidable. Our previous work has proven that the soundness problem for bounded WF-nets is PSPACE-complete. This paper shows that the weak soundness problem for bounded WF-nets is also PSPACE-complete. Aalst et al. has proven that the soundness problem is polynomially solvable for free-choice WF-nets (FCWF-nets). This paper discovers that the weak soundness problem is equivalent to the soundness problem for FCWF-nets. Therefore, the weak soundness problem for FCWF-nets is also polynomially solvable. Unfortunately, many composite web services are not modeled by FCWF-nets. Lots of them can be modeled by asymmetric-choice WF-nets (ACWF-nets). This paper proves that the soundness problem is co-NP-hard for ACWF-nets even when they are three-bounded. Additionally, this paper proves that the k-soundness problem is equivalent to the weak soundness problem for WF-nets, which implies that the k-soundness problem for bounded WF-nets is also PSPACE-complete.

Owing to their rapid development, services are increasing rapidly in quantity. The consequence is that there are so many services that share the same or similar functions. Therefore, it is important to select a credible and optimal service. Reputation as one of the important parameters of services plays a significant role in the decision support for service selection. This paper proposes a novel two-phase method to calculate service reputation. The first phase uses a dynamic weight formula to calculate reputation such that it can reflect the latest tendency of a service. The second one uses an olfactory response formula to mitigate the negative effect of unfair ratings. Some experiments are conducted and the results validate the effectiveness of the proposed method.

Such concurrent systems as Web services and workflow systems can be viewed as a composition of a set of subsystems. Subsystems interact with each other through a set of message channels in order to perform a task. This work defines a class of Petri nets called interactive Petri nets (IPNs) to model these systems. IPNs can be used to analyze their behavior, find potential problems, and then improve their designs. Compatibility is an important concept for a composed system and reflects the possibility of correct/proper interaction among its subsystems. In order to characterize different cooperative abilities in practice, compatibility and weak compatibility are defined for IPNs. Some relationships among (weak) compatibility, liveness, reversibility, and boundedness are revealed. Based on them, this work proves that the (weak) compatibility problem is co-NP-hard. A taxonomy is also presented for IPNs in order to explore whether some subclasses can be analyzed efficiently. Based on it, we can identify several IPN subclasses, some of which can be analyzed in polynomial time.

This paper presents a class of Petri nets, process nets with channels (PNCs) that can model some types of concurrent systems in two aspects: process and interaction. Its significance lies in offering efficient analysis and verification methods for these systems. PNCs belong to the class of extended free choice nets. This paper establishes the conditions to examine their liveness, reversibility, and reachability based on their structural characteristics. Siphons, traps, and a state equation are used to describe these conditions such that analysis techniques based on reachability graphs and siphon enumeration are avoided. A polynomial-time algorithm is presented for the liveness analysis, and an effective method is also given to decide the reachability. A real-world example is used to illustrate the application of PNCs.

This paper gives a necessary and sufficient condition for the liveness of normal nets, i.e. a normal net with a given initial marking is live if and only if it is structurally repetitive and each minimal siphon is marked in any reachable marking. Furthermore, it is proved that a normal net is structurally live if and only if it is structurally repetitive. Finally, we prove that a weakly persistent net, which is a special normal net, is live for a given initial marking if and only if it is structurally repetitive and each minimal siphon is marked in the initial marking. That is to say, the liveness of weakly persistent nets can be decided by the net structure and the initial marking only.

This paper proposes the concept of Key-resource/operation-place Pairs (KP) of S3PR (systems of simple sequential processes with resources). Based on KP, two policies are presented to prevent deadlocks in flexible manufacturing systems (FMS) that can be modeled by S3PR. The idea is to control some key resource places only to guarantee that all strict minimal siphons (SMS) never become empty, thereby making the controlled system live. It enables one to design two easy-to-implement control policies. The first one can guarantee that the controlled system is live, and the second one can also make the controlled system live if there is no SMS containing any control place in the controlled system. At last, a well-known FMS example is used to illustrate the proposed concept and policies.