Complex & Intelligent Systems最新文献

Transfer learning, as a machine learning approach to enhance model generalization, has found widespread applications across various domains. However, the risk of privacy leakage during the transfer process remains a crucial consideration. Differential privacy, with its rigorous mathematical foundations, has been proven to offer consistent and robust privacy protection. This study delves into the problem of linear regression transfer learning under differential privacy and, on this basis, proposes a novel strategy incorporating prior information as a constraint to further enhance model performance and stability. In scenarios where the transferable source is known, a two-step transfer learning algorithm incorporating prior information is proposed. This approach leverages prior knowledge to effectively constrain the model parameters, ensuring that the solution space remains reasonable throughout the transfer process. For cases where transferable sources are unknown, a non-algorithmic, cross-validation-based method for transferable source detection is introduced to mitigate adverse impacts stemming from non-informative sources. The effectiveness of the proposed algorithms is validated through simulations and real-world data experiments.

In the realm of daily human interactions, a rich tapestry of behaviors and actions is observed, encompassing a wealth of informative cues. In the era of burgeoning big data, extensive repositories of images and videos have risen to prominence as the primary conduits for disseminating information. Grasping the intricacies of human behaviors depicted within these multimedia contexts has evolved into a pivotal quandary within the domain of computer vision. The technology of behavior recognition finds its practical application across domains such as human-computer interaction, intelligent surveillance, and anomaly detection, exhibiting a robust blend of pragmatic utility and scholarly significance. The present study introduces an innovative human body behavior recognition framework anchored in skeleton sequences and multi-stream fused spatiotemporal graph convolutional networks. Developed upon the foundation of graph convolutional networks, this method encompasses three pivotal refinements tailored to ameliorate extant challenges. First and foremost, in response to the complex task of capturing distant interdependencies among nodes within graph convolutional networks, we incorporate a spatial attention module. This module adeptly encapsulates long-term node interdependencies via precision-laden positional information, thus engendering interconnections that span diverse temporal and spatial contexts. Subsequently, to elevate the discernment of channel information within the network and to optimize the allocation of attention across distinct channels, we introduce a channel attention mechanism. This augmentation fortifies the discernment of motion-related features. Lastly, confronting the lacuna of information gaps prevalent within single-stream data, we deploy a multi-stream fusion methodology to fortify model outputs, ultimately fostering more precise prognostications concerning action classifications. Empirical results bear testament to the efficacy of the proposed multi-stream fused spatiotemporal graph convolutional network paradigm for skeleton-centric behavior recognition, evincing a pinnacle recognition accuracy of 96.0% on the expansive NTU-RGB+D skeleton dataset, alongside a zenithal accuracy of 37.3% on the Kinetics-Skeleton dataset—emanating from RGB data and furthered through pose estimation.

Sequential recommendation systems capture the dynamic interests of users and predict their future preferences. A noteworthy problem in sequential recommendation is coping with the intrinsic changes of user interests. The sequence of user interactions is generated by more than a single and stable global preference, users may have interest drift that occur in a short period of time. We call this short-term interest drift as the local preference of users, which is often a key factor affecting the final choice of users. However, existing methods have limitations in observing local preferences, which leads to an incomplete consideration of the local preferences. Moreover, using a single model to represent global–local preferences obscure the distinct features of each, limiting the potential synergistic benefits. To alleviate the above limitations, we propose a novel model with a dual-channel structure to monitor both global and local preferences and ensure they complement each other. The model extracts the global preferences of users with a bidirectional Transformer using random masking and a sliding window, and extracts the local preferences with a patch-based stacked bottleneck residual convolution. To enable the model to consider both the global and local preferences of users, we design an adaptive orthogonal fusion module, which effectively fuses the two preferences and enables the two feature types to complement and enhance each other. We integrate the fused user preferences with a knowledge distillation method that further improves the model’s expressive ability. We conduct extensive experiments on three widely used datasets, and the results show that our model outperforms current state-of-the-art models.

The metaphor is a pervasive linguistic device that has become an active research topic in the computer field because of its essential role in language's cognitive and communicative processes. Currently, the rapid expansion of social media encourages the development of multimodal. As the most popular communication method in social media, memes have attracted the attention of many linguists, who believe that metaphors contain rich metaphorical information. However, multimodal metaphor detection suffers from insufficient information due to the short text of memes and lacks effective multimodal fusion methods. To address these problems, we utilize a single-pass non-autoregressive text generation method to convert images into text to provide additional textual information for the model. In addition, the information of different modes is fused by a multi-layer fusion module consisting of a prefix guide module and a similarity-aware aggregator. The module can reduce the heterogeneity between modes, learn fine-grained information, and better integrate the characteristic information of different modes. We conducted many experiments on the Met-Meme dataset. Compared with the strong baseline model in the experiment, the weighted F1 of our model on three data types of the MET-Meme dataset improved by 1.95%, 1.55%, and 1.72%, respectively. To further demonstrate the effectiveness of the proposed method, we also conducted experiments on a multimodal sarcasm dataset and obtained competitive results.

Collective motions are prevalent in various natural groups, such as ant colonies, bird flocks, fish schools and mammal herds. Physical or mathematical models have been developed to formalize and/or regularize these collective behaviors. However, these models usually follow pairwise topology and seldom maintain better responsiveness and persistence simultaneously, particularly in the face of sudden predator-like invasion. In this paper, we propose a specified higher-order topology, rather than the pairwise individual-to-individual pattern, to enable optimal responsiveness-persistence trade-off in collective motion. Then, interactions in hypergraph are designed between both individuals and sub-groups. It not only enhances connectivity of the interaction network but also mitigates its localized feature. Simulation results validate the effectiveness of the proposed approach in achieving a subtle balance between responsiveness and persistence even under external disturbances.

As the Internet of Things (IoT) technology becomes extensively deployed, IoT security issues are increasingly prominent. The traffic patterns of IoT are complex and high-dimensional, which makes it difficult to distinguish the tiny differences between normal and malicious samples. To tackle the above problems, we propose an IoT intrusion detection architecture based on Gramian angular difference fields (GADF) imaging technology and improved Transformer, named ImagTIDS. Firstly, we encode the network traffic data of IoT into images using GADF to preserve more robust temporal and global features, and then we propose a model named ImagTrans for extracting local and global features from network traffic images. ImagTIDS utilizes the self-attention mechanism to dynamically adjust the attention weights and adaptively focus on the important features, effectively suppressing the adverse effects of redundant features. Furthermore, due to the serious class imbalance problem in IoT intrusion detection, we utilize Focal Loss to dynamically scale the model gradient and adaptively reduce the weights of simple samples to focus on hard-to-classify classes. Finally, we validate the effectiveness of the proposed method on the publicly available IoT intrusion detection datasets ToN_IoT and DS2OS, and the experimental results show that the proposed method achieves superior detection performance and higher robustness on class imbalance datasets compared to other remarkable methods.

The modern decision-making environment is complex and dynamic. Global supply chain networks are increasingly exposed to unsystematic risks. Therefore, decision-makers need greater flexibility and precision to better manage uncertain market changes and complex international environments. To construct an accurate multi-criteria group decision-making (MCGDM) model, it is necessary to select appropriate evaluation criteria and identify alternative ranking methods based on specific decision problems. To develop a suitable MCGDM model for dynamic environments, this paper develops a new MCGDM model based on probabilistic interval-valued intuitionistic hesitant fuzzy sets (PIVIHFSs), regret theory, and the extended ELimination Et Choice Translating Reality (ELECTRE) III method. Firstly, this paper proposes two new aggregation operators, including the generalized probabilistic interval-valued intuitionistic hesitant fuzzy weighted averaging (GPIVIHFWA) operator and the generalized probabilistic interval-valued intuitionistic hesitant fuzzy weighted geometric (GPIVIHFWG) operator. To incorporate the decision-maker (DM)'s regret aversion, a bidirectional projection measure is proposed to calculate the advantages and disadvantages between two probabilistic interval-valued intuitionistic hesitant fuzzy elements (PIVIHFEs). The regret values of PIVIHFEs are determined using the bidirectional projection measure instead of utility values in the regret-rejoice function. Then, this paper constructs an extended ELECTRE III method and establishes a decision-making model based on the Borda rule for ranking and selecting the best alternatives. Finally, the effectiveness and robustness of the proposed model are verified through a numerical example, and the results are discussed through sensitivity analysis and comparative analysis.

Vehicle connectivity technologies has propelled integrated optimization of vehicle’s motion and power splitting becoming a hotspot in eco-driving control research. However, the security issues and power sources life loss of fuel cell-battery hybrid electric vehicle (FCHEV) are still challenging due to disturbances and power sources degradation. To address these problems, in this paper, control barrier function (CBF) based multi-objective energy management strategy (EMS) for FCHEV in car-following process is proposed. Firstly, the state of health models of fuel cell and battery are established to reflect the relationship between power sources degradation and energy consumption. Secondly, multi-objective model predictive control (MPC) based EMS framework is developed by comprehensive considering tracking performance, comfort, fuel consumption and power sources life loss. Thirdly, to robustly cope with disturbances and uncertainties, discrete-time CBFs are designed to enforce safety-critical constraints related to safety issues of both vehicle dynamics and powertrain operation in MPC. Finally, comprehensive simulations in extreme and long driving cycle testing scenarios show the proposed strategy can prevent vehicles from entering unsafe states, while improving fuel economy by 9.95%, reducing power sources life loss by 6.53%.

As one of the fundamental tasks in computer graphics and image processing, image stitching aims to combine multiple images with overlapping regions to generate a high-quality naturalness panorama. Most deep learning based image stitching methods suffer from unsatisfactory performance, because they neglect the cooperation relationship and complementary information between reference image and target image. To address these issues, we propose a progressive alignment and interwoven composition network (PAIC-Net) to produce satisfactory panorama images, which learns the cooperation relationship by a progressive homography alignment module and captures the complementary information by an interwoven image composition module. Specifically, a progressive homography alignment module is presented to align the input images, which progressively warps the reference and target images by focusing more on the combination of self-features and cooperation features. Then, an interwoven image composition module is presented to seamlessly fuse aligned image pairs, where the complementary information of one-view is captured to guide another-view in an interweaved way. Finally, an alignment loss and a composition loss are introduced to reduce alignment distortions and enhance seam consistency of the final image stitching results. Experimental results on benchmark datasets demonstrate that PAIC-Net outperforms state-of-the-art image stitching methods both quantitatively and qualitatively.

Many of the phenomena around us are a combination of directed and undirected relationships between different subjects, which will be more complex despite the existence of multiple relationships between objects. For example, in business relations between countries and social networks, communication is sometimes one-way or two-way. Checking and processing such information is managed in mixed graphs. Previous research has been based on the assumption that there is a general relationship between all vertices in a mixed graph. In this article, a new framework for fuzzy information management is introduced by combining fuzzy mixed graph and graph structure along with mentioning its properties. The concept of connectedness has been considered as one of the topics in this study. In this regard, some of their properties were examined by introducing some basic concepts such as paths, cycles, bridges, and cut vertices. Also, some attributes such as degree, neighborhood, order and size are defined. The results showed that although there existed a close relationship between the fuzzy mixed graph structure and the graph structure, the existence of multiple and distinct relationships between the vertices has created new definitions of concepts. This change can be seen especially in the degree of nodes and neighborhoods. Finally, its application in the field of trade relations between countries is presented.