International Journal of Intelligent Systems最新文献

Traffic accident prediction serves as a cornerstone of intelligent transportation systems, enabling proactive city-wide control strategies and public safety interventions. Effective models must capture the evolving spatiotemporal propagation of risk while addressing heterogeneous data distributions across urban regions. Current approaches face significant limitations: fixed graph topologies fail to represent nonstationary accident patterns, while uniform task weighting leads to optimization bias toward data-rich areas, ultimately constraining adaptability in adjacency construction and multihop spatial reasoning. To address these challenges, we propose a dynamic multidiffusion graph network with multitask learning (DiffG-MTL) for city-scale accident prediction. Specifically, a dynamic diffusion adjacency generation (DDAG) module constructs time-varying, diffusion-based adjacency matrices through multiple propagation pathways. A multiscale graph structure learning (MGSL) module captures multihop spatial relationships and temporal cues, while effectively highlighting anomalous traffic behaviors. To alleviate regional data imbalance, we introduce a dynamic multitask learning objective that adaptively redistributes learning focus using recall-aware weighting and task-level normalization. Comprehensive evaluations on six widely used datasets demonstrate that DiffG-MTL consistently outperforms state-of-the-art baselines across multiple evaluation metrics. Additional experiments validate its robustness and effectiveness in modeling complex spatiotemporal accident patterns.

Cerebral herniation is a life-threatening neurological emergency, where timely and accurate prediction is crucial for improving patient prognosis. Due to its rapid imaging advantages, CT becomes the preferred choice for cerebral herniation screening. With the continuous development of artificial intelligence technology in the field of neurological diseases, CT-based models provide significant support for computer-aided clinical diagnosis. However, current research on cerebral herniation diagnosis remains limited. Existing methods rely on traditional machine learning or focus solely on midline shift detection, which not only exhibits strong subjectivity but also neglects key structures such as the brainstem and the rich information from sagittal CT images. To address these limitations, this study focuses on mid-sagittal CT images including the brainstem and combines clinical data to construct a multimodal deep learning framework for cerebral herniation prediction. The model integrates mature and advanced deep learning architectures to extract and fuse features from CT images and clinical text data, employing multiscale convolution and attention mechanisms for diagnostic classification. The model is evaluated on datasets from two centers. Results show that on the internal test set, the model achieves accuracy, sensitivity, specificity, and AUC of 89%, 92%, 88%, and 0.94, respectively; on the external test set, it attains accuracy, sensitivity, specificity, and AUC of 81%, 82%, 80%, and 0.89, respectively, outperforming baseline methods and existing state-of-the-art approaches. Additionally, when compared with radiologists on the internal test set, the model’s performance matches or exceeds the consensus of physicians. We also reveal the model’s focus region through visual analysis, which further deepens the understanding of the model’s prediction process and enhances its interpretability. Experiments demonstrate that the proposed method holds significant potential in assisting cerebral herniation diagnosis.

This PRISMA 2020–compliant systematic review examines how intelligent agents, large language models (LLMs), and recurrent neural networks (RNNs) can be combined for industrial maintenance, with a sector-specific focus on mining. Scopus and Web of Science (2018–2025) were searched using replicable queries, and a dual text-representation pipeline (TF–IDF with bi/trigrams and sentence-transformer embeddings) was applied. Model selection scanned k over a predefined grid with internal indices (Silhouette, Davies–Bouldin, and Calinski–Harabasz), and robustness was assessed through multiseed stability, bootstrap consensus, representation-sensitivity checks, and a control run with HDBSCAN. Study quality and risk of bias were appraised with an AI-and-control–oriented matrix (ACE-QA). Two macroclusters emerged. The first centers on distributed control, consensus and formation, fault tolerance, observers, and learning-based designs (fuzzy/neural/RL), including finite/predefined-time and event/dynamic event–triggered mechanisms. The second addresses secure and resilient cooperation under cyber threats (DoS, deception, and FDIA), integrating observer-based estimation and communication-efficient protocols. Cross-cutting findings indicate that event-triggered updates reduce bandwidth and compute requirements, while robust estimation and fault-tolerant control improve availability under harsh conditions and intermittent networks—typical in mining. A maturity map suggests high technical readiness and growing adoption for RNN-based sensing analytics, advancing readiness but emerging adoption for multiagent coordination, and early adoption of LLMs for text-grounded maintenance intelligence. Evidence gaps persist in replicability, cross-site transfer, uncertainty reporting, and mining-grade validation at the edge. A design agenda is outlined that prioritizes digital-twin stress testing, edge-first evaluation of agent coordination, secure-by-design pipelines (authenticated/encrypted messaging and adversarial testing), and shift-aware validation. In sum, a hybrid stack—RNNs for perception, LLMs for knowledge grounding, and agents for coordinated action—offers a practical route to reliable, secure, and communication-efficient predictive maintenance in Mining 4.0.

Prediction of student performance is crucial for enhancing the quality of higher education worldwide by enabling timely interventions and personalized support. The blended learning environment, which integrates online and offline instruction, has become a predominant paradigm, yet it also brings significant challenges for the prediction of student performance due to the inherent complexity and heterogeneity of multimodal data generated across both environments. Specifically, existing approaches often fail to effectively leverage the synergistic potential of numerical behavioral traces and unstructured textual feedback from instructors. To address this problem, this study proposes a unified deep learning framework that integrates convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM) to capture both temporal dynamics and spatial correlations among features in blended learning environment. Unlike previous studies, we incorporate teacher comments on student assignments as textual inputs alongside traditional numerical features. Extensive experiments based on a real-world dataset of approximately 14,878 student records from Shandong University of Finance and Economics (SDUFE) demonstrate that the proposed hybrid model outperforms existing approaches in predictive performance. The results also highlight the significant value of leveraging teacher feedback for improving prediction accuracy, offering practical insights for enhancing educational management and supporting student success in blended learning contexts in higher education.

Heterogeneous multicore processor systems are commonly used for scheduling tasks of DAG applications. Deep reinforcement learning, with its superior ability to perceive decisions directly and handle high-dimensional state actions, has become a prevalent solution for scheduling these systems. However, the incomplete environment models and large action spaces of deep reinforcement learning present significant challenges to scheduling. This paper investigates a scheduling problem in a heterogeneous multicore processor environment. Initially, system environment information is extracted and encoded using a graph convolutional neural network based on integrating adapter and AdapterFusion into the transformer architecture. Then, by separating task selection and processor allocation, the decision space is reduced: the former uses a deep neural network to learn to select nodes, and the latter allocates processors using a heuristic scheduling algorithm combining earliest completion time-based node replication and rolling technology. The entire scheduling process is a Markov decision problem. Therefore, the PPO algorithm with dynamic adjustment of the clipping factor, combined with an advantage actor-critic network, is employed for training, optimizing, and evaluating the algorithm to find the optimal scheduling strategy. The training process adopts a reward function for the time and power consumption required for completed task scheduling to ensure that multiple DAG application task scheduling can achieve optimal performance. Experiments conducted in various environments with different parameters show that, compared to other algorithms, this algorithm reduces the overall execution time and power consumption cost of heterogeneous multicore processor tasks by 11.09%.

The dynamic visual servoing problem studied in this paper differs from existing approaches in two key aspects: the dynamics of the aerial mobile robot are underactuated, and the onboard camera is adaptively calibrated. To address the first challenge, a novel cascade visual servoing framework is developed, consisting of three control loops: the image loop, the attitude loop, and the angular velocity loop. Based on this framework, an extended eye-in-hand vision system is constructed, in which the perspective projection of feature points onto the image plane is decoupled from the rigid body’s attitude. This design allows the proposed visual controller to effectively compensate for image dynamics. Furthermore, unknown intrinsic and extrinsic camera parameters make compensation for image dynamics more difficult. To overcome this issue, a depth-independent composite matrix is introduced, enabling the unknown visual dynamics to be linearly parameterized and integrated with an adaptive control technique. A novel online algorithm is developed to estimate the unknown camera parameters in real time, and an additional adaptation mechanism is incorporated to estimate the rotational inertia of the rigid body. Using Lyapunov theory and Barbalat’s lemma, it is proven that the image tracking error asymptotically converges to zero while all physical variables remain locally bounded. Experimental results confirm that the image tracking error converges to zero over time, with a maximum deviation of no more than two pixels, thereby validating the effectiveness of the proposed visual controller.

With the increasing importance of privacy and data security in network communications, network intrusion detection systems (NIDSs) play a vital role in safeguarding against unauthorized access and data breaches. NIDSs utilize machine learning or deep learning models to distinguish between normal and malicious traffic, taking preventive actions when suspicious activities are identified. However, the vulnerability of these models to adversarial attacks poses a significant threat to data privacy and security. Attackers can exploit adversarial attacks to evade NIDS detection, potentially leading to the compromise of sensitive information. Existing research on adversarial attacks primarily focuses on white-box scenarios, which assume attackers have complete knowledge of the target model. This assumption is unrealistic in real-world scenarios. Moreover, adversarial examples generated through random perturbations or unconstrained methods are often easily detectable by classifiers, and they may not retain the full attack capabilities. To address these issues, this article explores a black-box adversarial attack approach, using alternative model algorithms to obtain the output of the target model without requiring detailed model information and utilizing adversarial sample generation method (A-M) with realistic constraints for adversarial attacks, which is more aligned with real-world data privacy and security issues. When evaluating the method proposed in this article, deep neural network (DNN) was used as the basic model and compared with various models in experiments. Comparing the generated adversarial examples with the original NSL-KDD dataset and KDD-CUP 99 dataset, the accuracy decreased to around 50% in binary and multiclassification scenarios, demonstrating the effectiveness of this method.

Recently, deep reinforcement learning (DRL) has been employed for intelligent traffic-light control and demonstrated promising results. However, state-of-the-art DRL-based systems still rely on discrete decision-making, which can lead to unsafe driving practices. Additionally, existing feature representations of the environment often fail to capture the complex dynamics of traffic flows, resulting in imprecise predictions of traffic conditions. To address these issues, we propose a novel DRL framework based on the multiagent deep deterministic policy gradient algorithm. Our method offers several key innovations: it suggests employing a transitional phase before changing the current phase for safer traffic management, integrates local road network topology into feature representation to enhance the accuracy of traffic flow predictions, and uses two-layer regional features to improve coordination among agents within the region. Our extensive evaluations using simulation of urban mobility, a widely used multimodal traffic simulation package, demonstrated that the proposed method outperformed previous methods and reduced the number of emergency stops, queue lengths, and waiting times.

Dragonfly visual systems intrinsically incorporate a variety of motion-sensitive neurons able to be well contributed to probe into bio-inspired computational models. However, it remains unclear how their visual response mechanisms can be borrowed to construct neurocomputational models for solving optimization problems. Hereby, a feedforward dragonfly visual attention–merged neural network (DVAMNN) with presynaptic and postsynaptic subnetworks is developed to output two types of online activities named learning rates in terms of the dragonfly visual information-processing and attention mechanisms. Integrated such learning rates into a new-type and metaheuristics-inspired state transition strategy, a dragonfly visual attention–merged evolutionary neural network (DVAMENN) with the unique parameter of input resolution is developed to solve ultrahigh dimensional global optimization (UHDGO) problems. The theoretical analysis implicates that the DVAMENN’s complexity is mainly decided by the optimization problem itself. Experimental results have confirmed that DVAMENN can successfully optimize the structures of two sixth-order active filters and discover the global or approximate solutions of the CEC’ 2010 and CEC’ 2013 benchmark suites with dimension 20,000 per example. Nevertheless, the compared metaheuristics encounter unprecedented troubles in the case of UHDGO.

Graph neural networks have emerged as powerful tools for analyzing graph-structured data, particularly in semisupervised node classification tasks. However, the conventional softmax classifier, widely used in such tasks, fails to leverage the spatial information inherent in graph structures. To address this limitation, we propose a graph similarity regularized softmax for graph neural networks, which incorporates nonlocal total variation regularization into the softmax function to explicitly capture graph structural information. The weights in the nonlocal gradient and divergence operators are determined based on the graph’s adjacency matrix. We implement this regularized softmax in two popular graph neural network architectures, GCN and GraphSAGE, and evaluate its performance on citation (assortative) and webpage linking (disassortative) datasets. Experimental results demonstrate that our method significantly improves node classification accuracy and generalization compared to baseline models. These findings highlight the effectiveness of the proposed regularized softmax in handling both assortative and disassortative graphs, offering a principled way to encode graph spatial information into graph neural network classifiers.