Traffic prediction plays an essential role in many real-world applications ranging from route planning to vehicular communications. The goal of making accurate prediction is challenging due to the dynamic and various spatial-temporal correlations in traffic network. Numerous methods have been proposed to capture the spatial-temporal correlations, however, there are two major challenges: i ) The task of synchronously capturing dynamic and various spatial-temporal correlations has not been fully explored yet. ii ) Lack of an adaptive mechanism to model different influences caused by different external factors. To overcome these challenges, we propose a unified spatial-temporal attention network entitled USTAN. First, it constructs the spatial neighbor graph and the temporal neighbor array to describe the spatial and temporal correlations respectively. By expanding the spatial neighbors in temporal perspective according to the temporal neighbor array, all the spatial-temporal neighbors can be gathered together. Second, a single unified attention component is performed on all the spatial-temporal neighbors for capturing the spatial-temporal correlations all at once. In addition, a gated fusion module is designed to fuse the external factors adaptively to reduce predicting error. Extensive experiments on real-world traffic prediction tasks demonstrate the superiority of our proposed framework.

It is difficult for existing Internet of Things (IOT) intrusion detection systems to simultaneously identify and classify network anomalies, especially when the classification of unknown attacks is required, which brings great risks to the use of IOT devices. This paper applies transformers to decouple false associations by causal reasoning to obtain an intelligent interpretable IOT detection system that can classify known attacks and identify unknown attacks. To achieve these goals, a causal transformer-based intelligent detection system for IOT devices is proposed. The system is divided into three main modules. First, training is conducted based on known traffic types with prior knowledge, and then the detection samples containing unknown attack types are classified into known traffic types. Second, the causal feature distribution of known traffic types is learned based on causal attention, and the causal feature distribution differences between normal and abnormal traffic samples are amplified with the minimax strategy to distinguish their types. Then, all traffic samples different from the known types are integrated into unknown types for causal transformer classification until there is only one type. Validation is performed on three broad and representative IOT datasets, and the results show that the causal transformer detection system can not only correctly classify known attacks but also achieve a 100% success rate in identifying cyberattacks on IOT datasets. In addition, more than 99% of unknown attack types can be effectively identified and classified, providing timely and effective guidance for cybersecurity defense.

Stay time is important for understanding people’s travel behavior and mobility motivation. In this paper, by leveraging private car trajectory data, we propose a novel systematic approach for implementing stay behavior detection and stay time prediction. Specifically, we first propose a fuzzy logic-based stay detection method for detecting stay behavior in a large-scale private car trajectory dataset. Then, we design a spatiotemporal feature extraction method called clustering and kernel (CaK) by considering the spatial similarity, temporal periodicity and spatiotemporal correlation of stay behavior data. Furthermore, we propose a stay time predictor (STP) based on gradient-boosting regression trees and a long short-term memory network that can estimate the future durations of private car users’ stays in various scenarios. We perform extensive experiments based on two real-life trajectory datasets. The experimental results demonstrate that the STP achieves a predictive accuracy (specifically, the root-mean-square error) of 123.94 and R ² of 0.893 for stay time prediction of individual stays. This study provides a new perspective for understanding people’s stay behavior.

The proliferation of internet-connected devices and the complexity of modern network environments have led to the collection of massive and high-dimensional datasets, resulting in substantial information redundancy and sample imbalance issues. These challenges not only hinder the computational efficiency and generalizability of anomaly detection systems but also compromise their ability to detect rare attack types, posing significant security threats. To address these pressing issues, we propose a novel causal genetic network-based anomaly detection method, the CNSGA, which integrates causal inference and the nondominated sorting genetic algorithm-III (NSGA-III). The CNSGA leverages causal reasoning to exclude irrelevant information, focusing solely on the features that are causally related to the outcome labels. Simultaneously, NSGA-III iteratively eliminates redundant information and prioritizes minority samples, thereby enhancing detection performance. To quantitatively assess the improvements achieved, we introduce two indices: a detection balance index and an optimal feature subset index. These indices, along with the causal effect weights, serve as fitness metrics for iterative optimization. The optimized individuals are then selected for subsequent population generation on the basis of nondominated reference point ordering. The experimental results obtained with four real-world network attack datasets demonstrate that the CNSGA significantly outperforms existing methods in terms of overall precision, the imbalance index, and the optimal feature subset index, with maximum increases exceeding 10%, 0.5, and 50%, respectively. Notably, for the CICDDoS2019 dataset, the CNSGA requires only 16-dimensional features to effectively detect more than 70% of all sample types, including 6 more network attack sample types than the other methods detect. The significance and impact of this work encompass the ability to eliminate redundant information, increase detection rates, balance attack detection systems, and ensure stability and generalizability. The proposed CNSGA framework represents a significant step forward in developing efficient and accurate anomaly detection systems capable of defending against a wide range of cyber threats in complex network environments.

Predicting the future parking locations and durations of private vehicles using vehicular edge devices is critical for real-time intelligent transportation services, ranging from instant point-of-interest recommendations to dynamic route planning. Advanced deep neural networks like Transformers demonstrate exceptional performance in mobility prediction; however, their heavy reliance on dense matrix multiplication makes them unsuitable for real-time applications on vehicular edge devices. Spiking neural networks offer a potential solution due to their asynchronous event-driven characteristics and low power consumption. However, existing spiking neural networks face three fundamental challenges: (1) handling heterogeneous inter-event intervals; (2) mitigating quantization errors in regression tasks under limited simulation steps; and (3) efficiently regulating information flow based on external contexts. To address these challenges, we propose an event-driven spiking neural network for private vehicle parking prediction called Spark. First, we design a Time-Adaptive Leaky Integrate-and-Fire neuron with a lookup table-based decay mechanism to efficiently model variable inter-event intervals. Second, an accumulate-based readout strategy is introduced to mitigate quantization errors by integrating discrete spike trains into continuous output values for high-precision regression. Third, a Spiking Contextual Gating module is proposed to selectively regulate spiking information flow across channels based on environmental context. These components are integrated into a unified architecture that maintains high prediction accuracy while remaining computationally efficient. Extensive experiments on real-world datasets demonstrate that Spark achieves an effective balance between prediction accuracy and computational efficiency compared to baselines.

Urban parking spaces are key city resources that directly affect how easily people get around and the quality of their daily travel. Accurately predicting future parking space availability can improve the efficiency of using parking spaces. For instance, it can enhance smart parking applications like shared parking and EV charging scheduling. However, because parking behavior is dynamic and constantly changing, it is challenging to predict parking space availability over the medium-to-long term. This paper proposes a Scale-Fusion Transformer model (SFFormer) to address dynamic changes in parking spaces availability caused by complex parking behaviors, as well as challenges in medium-to-long-term prediction modeling. The three key innovations are as follows: (1) a scale-fusion module integrating short-term and long-term parking trends, (2) an adaptive data compression mechanism for multi-scale prediction tasks, and (3) a Transformer-encoder-based time pattern capturing architecture, which is adaptable to diverse parking lots and long-term prediction scenarios. Experiments on real parking datasets demonstrate that the SFFormer model significantly outperforms state-of-the-art models such as iTransformer, PatchTST, DLinear, and Autoformer.