International Journal of Intelligent Systems最新文献

The global economy and society are seriously threatened by the pervasive spread of counterfeit goods. Their high level of simulation makes real and fake goods extremely similar in appearance and difficult to distinguish. The existing identification techniques mostly use CNNs and transformer architectures. However, CNNs have limitations in modeling long-range dependencies, leading to their limited classification performance, while vision transformers (ViTs), although excellent in modeling long-range dependencies, the quadratic computational complexity of their self-attention mechanism makes it difficult to be widely used in real-world scenarios with limited computational resources. According to recent research, long-range relationships can be accurately modeled using the state space model (SSM), which is represented by Mamba, while preserving linear computational complexity. Motivated by this, we proposed CGMamba, a SSM-based intelligent recognition model for counterfeit goods. Specifically, we constructed a novel hybrid basic block called global-local feature aggregation (GLFA). This block greatly enhances the feature extraction capability for counterfeit goods by deeply integrating the local feature extraction capability of the CNN and the global modeling capability of SSM. It is composed of three components: a local feature extractor, a global feature extractor, and an adaptive feature aggregation module (AFAM). In addition, to address the problem of lack of counterfeit goods image data, we constructed a large counterfeit goods dataset containing 101,480 images covering 104 categories for model training and evaluation. The experimental results showed that CGMamba achieved 90.99% Top 1 accuracy on the self-constructed dataset and 79.5% on the public dataset CNFOOD-241, which significantly outperforms the existing methods. The source code is available at https://github.com/wth1998/CGMamba.git.

As an essential component of the internet of things, the internet of vehicles (IoV) holds broad application prospects in areas such as safe driving, intelligent transportation, and service reservations. Due to the security and privacy requirements, anonymous authentication schemes are widely used in IoV. However, traditional certificate-based anonymous authentication schemes suffer from several drawbacks such as poor scalability and high management costs of certificates. Furthermore, centralized authentication architectures are susceptible to a single point of failure. To this end, we propose a blockchain-based certificateless anonymous cross-domain authentication (BCACA) scheme for IoV. In this scheme, we adapt a network model with multiple domain managers (DMs) based on blockchain, in which DMs establish distributed trust within the network and act as miners to upload vehicle registration and authentication transactions to the blockchain, assisting in cross-domain authentication. Based on this framework, a certificateless signature scheme is designed, which supports authentication across different domains without the need for complex certificate exchange mechanisms. In addition, this scheme provides an identity revocation mechanism encompassing both intradomain and cross-domain scenarios to ensure the security and reliability of the IoV. Security proofs demonstrate that the scheme is provably secure under the random oracle model and exhibits strong resistance against known attacks. Performance analysis indicates that the proposed scheme has lower computational overhead and transmission delay compared to other relevant schemes.

In mixed-flow assembly lines, conflicts exist between the diverse production modes and the dynamic maintenance demand. There is an urgent demand to shift the adaptive manufacturing from passive scheduling to proactive scheduling. The uncertain evolution of the scheduling performance and the equipment state causes difficulty in balancing the production load and the predicted maintenance under the degradation effect. This paper aims at the production scheduling and mixed-flow assembly line maintenance and proposes an improved hybrid Tabu Search and Genetic Algorithm (hybrid TSGA)–based proactive scheduling method for production prediction. Initially, the method constructs a real-time state model for the equipment state, workshop manufacturing efficiency, manufacturing resource state, and manufacturing execution system feedback information. The production process status information is used as input to a mathematical modeling method, which is used to obtain the production trend of mixed flow assembly line in the workshop. Afterward, the hybrid TSGA is deployed and its sequential decision-making capability is used to generate a proactive scheduling scheme based on the production trend prediction. The proposed methodology was implemented in a robotic flexible welding automobile production line for production scheduling, with its efficacy empirically validated. Simulation results demonstrated a 6% reduction in total completion time for multimachine, multiprocess scheduling scenarios, demonstrating superior performance.

Accurate traffic speed prediction holds immense significance in mitigating traffic congestion and enhancing traffic safety. However, traffic data exhibit distinct patterns across different cycles (such as weekdays, weekends, and holidays), making it challenging for traditional models to effectively capture this multiperiod heterogeneity in traffic data. Furthermore, most existing research on traffic speed prediction struggles to efficiently capture the spatiotemporal characteristics of dynamic traffic data simultaneously. To tackle these challenges, this paper first introduces spatiotemporal-aware position encoding (STAPE) technology, which addresses the multiperiod heterogeneity in traffic data by integrating temporal cycle information with spatial position information. Second, a multilevel spatiotemporal feature extraction architecture is designed, leveraging graph convolutional network (GCN) to capture the topological structure and spatial features of the traffic road network. By applying gated recurrent unit (GRU) to capture the temporal dependencies of traffic data, and combining GCN and GRU in multiple stages, this architecture deeply explores the spatiotemporal features of traffic data. Additionally, this paper integrates a multihead attention mechanism, which, in conjunction with the parallelized attention channel adaptive mechanism and the multilevel spatiotemporal feature extraction architecture, enhances the model’s ability to adaptively model different spatiotemporal patterns dynamically, thereby efficiently capturing the dynamically changing spatiotemporal features. Extensive performance evaluation experiments conducted on the METR-LA and PEMS-BAY datasets demonstrate that the predictive performance of the proposed model surpasses that of nine other baseline methods.

Identity management (IDM) systems in cloud computing struggle to securely manage user identities and access privileges in distributed environments. However, centralized IDM solutions come with high trust costs, single points of failure, and a need for appropriate security response. This paper proposes a novel decentralized IDM framework utilizing blockchain technology and automatic provisioning (AP) techniques to improve cloud computing’s security, scalability, and operational efficiency. The framework employs Ethereum smart contracts and role-based access control (RBAC) to ensure secure, transparent, and automated management of user identities. Key features include support for single sign-on (SSO), multifactor authentication (MFA), and delegated proof-of-stake (DPoS) consensus for secure transaction validation. Our proposed scheme utilizes the Ethereum blockchain and smart contracts for managing user access, ensuring transparent and immutable record-keeping. The scheme introduces RBAC mechanisms to ensure precise privilege allocation and dynamic updates. The scheme also supports key IDM processes, including SSO, MFA, and lifecycle management of identities. The framework incorporates DPoS consensus to enhance security for efficient transaction validation and the prevention of fraud. To address fraudulent activities, the scheme uses machine learning to detect blockchain fraud with 99.1% accuracy, demonstrating robustness and efficiency for large-scale cloud infrastructures.

Handling class imbalance is a fundamental challenge in supervised learning, particularly in real-world scenarios where minority classes are critical yet underrepresented. This paper presents a novel dynamic-balancing pipeline that enhances automated machine learning (AutoML) performance on imbalanced tabular datasets. The proposed approach integrates both traditional and generative resampling techniques with adaptive, class-specific thresholds, enabling automated and dataset-sensitive balancing strategies. To assess its generalizability, the pipeline is applied uniformly across binary, multiclass, and multilabel classification tasks. Each configuration is evaluated within an AutoML framework using performance and efficiency metrics, with outcomes validated through statistical testing and effect size analysis. The study also incorporates dataset complexity measures—including feature-label dependency and class overlap—to investigate how structural characteristics affect balancing efficacy. By combining principled resampling, exhaustive grid search, and rigorous evaluation, the pipeline enables more robust and efficient AutoML workflows. This work contributes a flexible and reproducible framework for addressing class imbalance, particularly in multilabel contexts, and establishes a foundation for scalable, complexity-aware resampling in automated model development.

The rapid growth of e-commerce has amplified the need for efficient logistics and delivery route planning. The Traveling Salesman Problem (TSP) provides a mathematical framework to address this challenge by finding optimal delivery routes. In this study, we propose a novel algorithm, DPSO-Q, which synergizes the adaptability of reinforcement learning from Ant-Q with the computational efficiency of Discrete Particle Swarm Optimization (DPSO). By leveraging swarm intelligence and adaptive learning mechanisms, DPSO-Q achieves a balance between computational efficiency and high-quality solutions. Experimental evaluations demonstrate its potential for large-scale logistics optimization, making it a promising tool for addressing the complexities of modern supply chain systems. DPSO-Q reduces tour lengths by up to 7.5% compared to DPSO and achieves execution times over 90% faster than ACO and Ant-Q on standard datasets such as ch130 and zi929.

Bipolar neutrosophic soft sets are powerful tools for modeling data under conditions of uncertainty and imprecision due to their rich parametric structure and the useful mathematical properties of the operations defined on them. In this paper, motivated by the limitations of existing decision-making algorithms, we introduce a new numerical characteristic, the energy of a bipolar neutrosophic soft set defined using singular values, analogous to the graph energy and nuclear norm. Our goal is to develop an efficient decision-making algorithm that successfully identifies the optimal alternative even in cases where other algorithms provide inaccurate or inconsistent results. Our research is motivated by the need for more reliable decision-making methods in complex soft environments and the potential of the energy-based approach to overcome the weaknesses of existing methods, which we demonstrate through a comparative analysis using concrete examples.

The winch’s performance under complex sea conditions is significantly influenced by its collecting and releasing processes. To enhance its performance and reliability, an optimization approach considering wave disturbances and control laws is proposed to balance time efficiency and tension stability. Within a multiobjective optimization framework, the method designs constant tension control and robust adaptive speed control and introduces sinusoidal acceleration trajectories to minimize tension surges and reduce system impacts caused by rapid starts/stops. The constant tension controller reduces wave disturbances, while the speed controller manages the working process. These controllers are designed with unknown reference signals determined during the optimization process. Additionally, the objective functions in the optimization phase aim to reduce working time and tension fluctuations, with constraints ensuring system safety and mission requirements. Furthermore, an experimental platform constructed on a ship validates the accuracy of the winch model. The optimized process not only shortens operational time, as collecting same length only consumption 127.44 s compared 143.14 s without optimization, but also reduces tension and acceleration. More importantly, transitions between states become more gradual. This indicates that the proposed method is both time-efficient and effective in dampening tension fluctuations and mitigating the effects of abrupt changes during the working process.

Cleaning and inspection of pipelines and gun barrels are crucial for ensuring safety and integrity to extend their lifespan. Existing automatic inspection approaches lack high robustness, as well as portability, and have movement restrictions and complexity. This study presents the design and development of a scalable, comprehensive automated inspection, cleaning, and evaluation mechanism (CAICEM) for large-sized pipelines and barrels with diameters in the range of 105 mm–210 mm. The proposed system is divided into electrical and mechanical assemblies that are independently designed, tested, fabricated, integrated, and controlled with industrial grid controllers and processors. These actuators are suitably programmed to provide the desired actions through toggle switches on a simple housing subassembly. The stress analysis and material specifications are obtained using ANSYS to ensure robustness and practicability. Later, on-ground testing and optimization are performed before industrial prototyping. The inspection system of the proposed mechanism includes barrel-mounted and brush-mounted cameras with sensors utilized to keep track of the pipeline deposits and monitor user activity. The experimental results demonstrate that the proposed mechanism is cost-effective and achieves the desired objectives with minimum human efforts in the least possible time for both smooth and rifled large-diameter pipes and barrels.