Internet of Vehicles (IoV) communication serves as a critical enabler for intelligent transportation systems, where the reliability of data sharing fundamentally determines overall system performance. Data reliability not only dictates the quality of IoV services but also constitutes a core factor in ensuring traffic safety and improving road operational efficiency. At present, IoV data sharing confronts several key challenges: (i) degradation of message credibility due to malicious attackers; (ii) ineffectiveness of conventional reputation mechanisms under high vehicular mobility; and (iii) channel congestion and information loss caused by redundant data transmissions. To address these issues, this paper proposes a Hybrid Hash Chord Protocol, which integrates Geohash geocoding with the Chord distributed lookup algorithm to establish a location-aware peer-to-peer data forwarding mechanism. This approach enables efficient data transmission with reduced hop count. In addition, a recursive traffic data filtering method is introduced to effectively suppress duplicate data reporting. Moreover, a Bayesian Dynamic Fading Reputation Model is developed, incorporating time decay factors and historical behavior weighting to mitigate intelligent attacks and node inertia, thereby enhancing road safety and traffic efficiency. Experimental results indicate that, within an IoV data-sharing context, the proposed model improves traffic efficiency by approximately 4% and reduces overall communication overhead by 36% compared to existing schemes. When the reputation threshold is set to 0.35, the model achieves a 100% malicious vehicle detection rate, whereas benchmark methods remain below 80% under the same threshold. In summary, the proposed framework achieves a notable balance among enhancing data trustworthiness, optimizing traffic performance, and minimizing communication costs, offering a practicable solution for building efficient and reliable IoV data-sharing systems.

Recently, blockchain has been widely used in important scenarios (e.g., finance and auditing). To fully meet the needs of various business scenarios and reduce deployment costs, cloud blockchain services (CBS) are now being offered by cloud computing providers. However, in high-frequency and large-scale transaction scenarios, blockchain performance faces serious challenges, limiting its further application. Therefore, blockchain performance optimization (BPO) has become a key field. Recent BPO methods that adjust blockchain configuration parameters like block size, offer benefits such as low cost and easy deployment. However, these methods face challenges including unsuitability for dynamic environments, high optimization overhead, and failure to consider marginal utility (MU) in BPO. MU describes the decreasing effectiveness of BPO as transaction arrival rates increases, eventually leading to limited BPO benefits. This paper proposes a data-driven BPO framework (BPO-CBS) for CBS. First, a blockchain performance prediction model is trained using ensemble learning. Second, a performance scoring and adjustment mechanism is designed to identify optimal configuration parameters and adjust them to enhance BPO. Finally, extensive quantitative and qualitative comparisons with related works show that BPO-CBS achieves more effective BPO with low optimization overhead.

Service workflows are fundamental in software ser-vice systems where standardized processes are implemented as workflow models to achieve automated service execution. Despite the obvious benefits of model-driven architecture, its mainstream adoption is hampered by the need for extensive knowledge and sophisticated modeling abilities to create such models. Recently, multi-agent frameworks have thrived in handling complex tasks by harnessing collective intelligence to tackle intricate problems. MASFlow, a progressive multi-agent collaboration framework for automated service workflow model generation, is presented in this paper. Through the use of specialized agents that represent various team responsibilities, MASFlow replicates real-world design cooperation by breaking down the modeling process into three coordinated phases: Structuring, Orchestration, and Re-view. Experimental results demonstrate that MASFlow effectively mitigates the hallucination generation phenomenon commonly observed in large language models (LLMs) when handling complex service workflows through a phased task decomposition strategy. With an accuracy rate of 92.83%, the generated service workflow model demonstrated notable advantages above existing mainstream neural network architecture techniques and solutions that directly use LLMs.

In the domain of target tracking, leveraging auxiliary modalities such as depth, thermal, and event data to enhance tracking robustness has garnered substantial attention. Due to the scarcity of visual multimodal datasets, state-of-the-art approaches primarily rely on parameter-efficient fine-tuning to adapt models. However, existing studies often neglect the adaptation of fine-tuning to specific datasets, frequently focusing only on non-RGB modalities or employing them as prompts. Additionally, current methods overly emphasize modal balance while disregarding modality adaptation to environmental conditions. To address these limitations, we propose a unified visual multimodal detection framework named IMTrack. This model incorporates LoRA (Low-Rank Adaptation) and Adapter for fine-tuning RGB and auxiliary modalities, respectively, and employs confidence-based cross-attention to strengthen feature interaction and adaptability. Furthermore, we introduce a complementary masking multi-scene optimization strategy to enhance robustness in complex environments. Extensive experiments on five datasets validate the efficacy of our model. The results demonstrate that IMTrack surpasses existing methods in many indicators, achieving state-of-the-art performance. Notably, the robustness of our model to auxiliary modes is improved by more than 2%. Our source code is available at: https://github.com/cxy-lzk/IMTrack.

In recent years, the accelerated advancement of Internet of Vehicles (IoV) technology has significantly enhanced user experiences by providing intelligent services, such as multimedia entertainment and autonomous driving in vehicles. However, the enforcement of regulations concerning vehicle violations in IoV environments predominantly relies on manual methods, which are both expensive and challenging. Moreover, the inherent constraints in existing surveillance systems result in regulatory blind spots. Consequently, it is imperative to develop intelligent IoV-based surveillance mechanisms to improve the efficiency of detecting and rectifying violations. In this article, we propose a blockchain-based self-supervision model for vehicle violations that utilizes intervehicle reporting and voting mechanisms to enhance the detection rate of violations and reduce regulatory pressure. A forensic blockchain is introduced in the model to enable a review of the reporting results, which improves the security and reliability of the system. Additionally, more vehicles are incentivized to participate in the system through reputation-based rewards, punishments, and incentives. The system was deployed on the Hyperledger Fabric platform. Simulation experiments were conducted using Veins, SUMO, and OMNeT++. The experimental results verify the effectiveness of the model. The reporting and voting mechanism significantly inhibit violations, and the reward and reputation mechanism effectively promote the participation of vehicles.

Difficulty in parking leads to many issues, such as traffic congestion, and hinders the development of intelligent transportation systems. One significant reason is that the cruise parking does not fully utilize real-time information about the parking lot (e.g., availability status of the parking spaces), resulting in low parking efficiency and high parking costs. Even though reservation parking improves parking efficiency, its reservation service is coarse (e.g., could not reserve a specific parking space). Therefore, to achieve more efficient parking and optimize existing reservation services, we propose a real-time parking space view (PSV) framework (called PRPSV). PSV can reflect the position distribution and availability status of each parking space in a parking lot, which enables drivers to quickly and efficiently obtain real-time parking information and complete parking decisions. However, there have been fewer studies on PSV in recent years, and these methods are high-cost, limited scalability, and do not use PSV to optimize parking efficiency and services. Therefore, we propose a method to construct and update PSV accurately. Further, we model cruise and reservation modes in non-PSV and PSV-based scenarios to compare and analyze the impact of PSV on parking efficiency. Finally, the comprehensive qualitative comparison with related work demonstrates the innovativeness of PRPSV and the sufficient experimental results and a case study in an actual parking lot show that PRPSV can efficiently and accurately construct and update PSV, and the introduction of PSV can effectively improve parking efficiency and optimize reservation services.

Software defect prediction technology can discover potential errors or hidden defects by establishing prediction models before the use of products in the field of software engineering, so as to reduce subsequent problems and improve software quality and security. However, building predictive models requires enough software defect dataset support, especially defect samples. Due to the involvement of confidential information from various organizations or enterprises, software defect data cannot be shared and effectively utilized. Therefore, to achieve collaborative training of multiparty shared software defect prediction models while keeping the data local to various organizations, we made the federated learning framework for the issue of software defect prediction. Meanwhile, the nondefect and defect instances in software defect datasets are usually imbalanced, which can seriously affect the software defect prediction performance of the model. Therefore, this study designs a novel federated oversampling learning framework Fed-OLF. First, the TabDiT method based on deep generative model is proposed in Fed-OLF to expand and rebalance the local imbalanced software defect dataset of each client with a certain degree of privacy protection. Second, a parameter aggregation strategy based on local information entropy is proposed in Fed-OLF to further optimize the parameter aggregation effect of the global shared model, thereby achieving better model performance. We conduct extensive experiments on the PROMISE dataset and the NASA Promise repository, and experimental results on the PROMISE dataset and the NASA Promise repository show that, the proposed Fed-OLF exhibits better predictive performance under the F1-score, G-mean, and AUC metrics when compared with the advanced baseline methods. In addition, we verify that both the TabDiT method and the parameter aggregation strategy based on local information entropy in Fed-OLF are useful, and the combination of them can more effectively improve model performance.

The increasing production of service description documents by enterprises and service providers has prompted the need for automated service workflow generation. This paper explores a method that combines large language models (LLMs) and graph neural network (GNNs) to address this challenge. Automatically extracting service workflows from documents also provides a convenient and efficient solution for situations where process mining algorithms cannot be utilized due to the absence of logs. The proposed method begins by employing LLMs to extract activity nodes and conditional nodes from service workflow description documents. These nodes are then organized into an initial graph using chain connections and auxiliary connections provided by the LLMs. Subsequently, an inductive GNN is utilized to analyze node embeddings within the service workflow, enabling the learning of semantic representations and connection rules. This facilitates the discovery of potential connections among nodes, leading to the generation of efficient service workflows. The experimental results demonstrate that the proposed method achieves an F1-Score of 0.818 in predicting node relationships. Furthermore, ablation experiments have been conducted to validate the effectiveness of incorporating both LLMs and GNNs.

Summary Robotic process automation (RPA), a tool driven by business processes as the kernel, continues to heat up in the business community. However, process‐centric RPA modeling lacks an effective means. To address this problem, we propose a method for automatic process acquisition using RPA process descriptions as input. Existing deep learning process generation methods cannot be applied at the phrase level and have low accuracy at the sentence level. The proposed neural network method is based on an attention mechanism for automatic business process model generation from RPA process descriptions (A‐PGRD). The approach analyzes easily accessible and unstructured natural language text documents, constructs a non‐autoregressive neural network with an attention mechanism to retrieve the business process hierarchy, and generates a tree‐like business process graph using unsupervised automation. Through K‐fold cross‐validation, the method achieves an accuracy of 41.7% on the manually collected open‐source RPA business process dataset. Compared with the previous method, the method improves the learning efficiency by 23%–27%. The obtained results can be applied to the RPA tool to better optimize the business process and thus help organizations gain an edge over their competition.

Recent years, the successful application of blockchain in cryptocurrency has attracted a lot of attention, but it has also led to a rapid growth of illegal and criminal activities. Phishing scams have become the most serious type of crime in Ethereum. Some existing methods for phishing scams detection have limitations, such as high complexity, poor scalability, and high latency. In this article, we propose a novel framework named phishing detection on Ethereum via augmentation ego-graph based on graph neural network (PEAE-GNN). First, we obtain account labels and transaction records from authoritative websites and extract ego-graphs centered on labeled accounts. Then we propose a feature augmentation strategy based on structure features, transaction features and interaction intensity to augment the node features, so that these features of each ego-graph can be learned. Finally, we present a new graph-level representation, sorting the updated node features in descending order and then taking the mean value of the top n to obtain the graph representation, which can retain key information and reduce the introduction of noise. Extensive experimental results show that PEAE-GNN achieves the best performance on phishing detection tasks. At the same time, our framework has the advantages of lower complexity, better scalability, and higher efficiency, which detects phishing accounts at early stage.

Blockchain is a trans-generational technology that is gradually introduced and applied in many fields because of its characteristics such as tamper-proof, traceability, and decentralization. However, the performance bottlenecks of blockchain have been one factor that hinders its practical application. This paper proposes a blockchain performance optimization framework (called LearningChain). We use a temporal convolution network to predict the transaction arrival rate of the blockchain and propose an ensemble learning-based method and a meta-learning-based method to train a blockchain performance prediction model, respectively. We design a performance scoring mechanism to dynamically tune the configuration parameters of the blockchain to optimize the blockchain performance. In addition, we collect and contribute a blockchain performance dataset (called HFBTP) for other researchers to research. The sufficient experimental results and analysis show that LearningChain can effectively optimize blockchain performance. The quantitative and qualitative comparisons with related work demonstrate the superiority and innovation of our work, LearningChain reaches state-of-the-art, is highly applicable, scalable, and can be applied to many practical blockchain-based application scenarios and different blockchain platforms. LearningChain can be complemented with other existing blockchain performance optimization tools and methods to further enhance the effectiveness of blockchain performance optimization.

The process model repository has demonstrated unprecedented success in a variety of industrial and process as a service scenarios. With the rapid increase of massive business process-related data under Industry 4.0, effectively retrieval of process models from large process model repositories becomes a critical challenge for process mining, process deployment and process model acquisition. To accelerate the retrieval of process models from a large process repository, existing retrieval methods rely solely on building single dimension process model indices. In this article we show that this single dimension indexing approach is not only inefficient but also cumbersome for supporting high performance retrieval services over large process model repositories. We propose a new business process model indexing and retrieval with structure and behavior fusion. In the indexing stage, we propose a process model index generation paradigm method with two novel features. First, our index algorithm can transform thetrace equivalent process model(TEPM) with complex structures into a process tree, which can better capture process sequence semantics than the existing approach based on block structured process model. Second, we improve the method for computing the process tree edit distance for measuring process model similarity by introducing the process tree similarity method, which can distinguish leaf nodes and non-leaf nodes and improve the limitations of the traditional edit distance algorithm. Extensive experiments using real world process repositories demonstrate that the proposed methods are under polynomial time in both the model index generation and model querying stages, and offer superior retrieval performance compared to existing process model retrieval methods in terms of efficiency, search capability and scope.

Intelligent transportation system (ITS) is an important application area of software engineering. Traffic forecasting plays a pivotal role in ITS. Because of the natural graph properties of traffic road networks, graph convolutional network (GCN) is currently the mainstream method for modeling the spatial correlation of road networks. However, most GCN-based models use graph adjacency matrices that are either pre-defined based on Euclidean distances or learned through node embedding matrices. This results in the inability to model time-varying spatial relationship owing to various unexpected external factors. Moreover, traditional graph structures may not be able to fully encode complex spatial relationship. In this study, we first propose three aspects to be considered to model the spatial correlation of road networks: geospatial, functional spatial, and time-varying spatial correlations. We capture geospatial and functional spatial correlations from a global perspective and time-varying spatial correlation from a local perspective through a Time-varying graph structure generator (TVGSG). The time-varying spatial correlation of local perspectives is constructed by a hypergraph capable of capturing complex higher-order correlation. Then, we propose a framework named Adaptive Spatio-Temporal Hypergraph Convolutional Network (ASTHGCN), which combines graph diffusion convolution (GDC) and gated temporal convolutional network (Gated TCN) into a module capable of modeling spatio-temporal features simultaneously. By stacking multiple modules mentioned above, ASTHGCN is able to extract rich spatio-temporal information for advance prediction. Experiments on METR-LA and PEMS-BAY demonstrated that ASTHGCN achieved the best performance compared to the baseline methods for both short-term prediction (15 min ahead) and medium and long-term prediction (30 and 60 min ahead).

Unified modeling language (UML) activity diagrams depict the internal behavior of different program operations with the help of nodes and edges, describing the business logic in user requirements. Traditionally, requirements engineers and practitioners refer to business process documents and analyze them to build UML activity diagrams manually, which makes labor and time consuming. Recently, deep learning technology has been utilized in various fields and has achieved excellent results. We propose a novel pipeline, named TAG, for automatically generating UML activity diagrams based on deep learning. The inspiration for TAG is as follows: (1) Semantic roles1, such as signal and condition entities in texts, can be obtained via sequence labeling; (2) A business process document corresponds to a semantic role sequence. According to the predefined rules, the semantic role sequence is used to construct the graph neural network, and the temporal activity relationship in a business process document is predicted via multi-layer semantic fusion; (3) Use temporal activity relationships to generate UML activity diagrams automatically. The entire process was automatically completed. SAP is the largest non-American software company by revenue. We obtained the original data from the SAP website and sorted them as business process documents. After preliminary experiments, a temporal activity relationship prediction accuracy rate of 79.87% was achieved. Simultaneously, some business process documents are available from https://github.com/lwx142857/bussiness-process.

Large pre-trained language models have shown strong capabilities in the field of natural language processing, and in recent years research demonstrated that they can also produce surprising results from natural language descriptions in automatic code-generation applications. Although such models have performed well in a variety of domains, there is evidence that they can be affected by adversarial attacks, Consequently, it has become important to measure the robustness of models by producing adversarial examples. In this study, we proposed an attack method called the Modifier for Code Generation Attack (M-CGA), which is the first time a white box adversarial attack has been applied to the field of code generation. The M-CGA method measures the robustness of a model by producing adversarial examples that can cause the model to produce code that is incorrect or does not meet the criteria for use. Preliminary experimental results showed the M-CGA method to be an effective attack method, providing a new research direction in automatic code synthesis.

The parking lot is one of the important components of the intelligent transportation system (ITS). The current parking lots mainly use instant parking, which has low parking efficiency, during peak hours, which leads to traffic congestion. To guarantee the stable operation of parking lots, we propose a blockchain-enabled parking reservation framework, called BPR. Traditional parking reservation systems may exist the condition of malicious reservations, and resulting in wasted parking spaces. Therefore, we design a reputation mechanism to manage the parking reservation behavior of vehicles and reduce the number of malicious nodes. In addition, to balance the performance of the blockchain at different times (especially during peak hours), we use deep learning (DL) to dynamically adjust the block size to make the blockchain run more efficiently and stably. We deploy the system in Hyperledger Fabric and conduct effectiveness experiments. The comprehensive evaluation results and analysis show that the proposed reputation mechanism can effectively curb malicious nodes from reserving parking spaces and reduce the waste of parking resources. And the block size will be dynamically adjusted to balance the performance of the blockchain at different periods, this method is also applicable to other blockchain performance-sensitive scenes. Finally, this paper is compared with related work to demonstrate the innovation and feasibility of this work from various aspects.