Time series prediction is essential in many real-world applications, including power monitoring, traffic forecasting, and early warning of extreme weather events. While deep learning-based models have demonstrated strong performance in this domain, most existing approaches treat the input sequence holistically, failing to account for the distinct characteristics of its underlying components. This often hinders the extraction of deep, meaningful features. To address this issue, we propose a novel model, termed Seasonal-Trend decomposition based on Loess with Multi-Graph Attention Interaction (STL-MGAI), which integrates time series decomposition with component-specific graph modeling to improve both pattern learning and feature fusion. Specifically, STL decomposition is employed to extract three orthogonal components—trend, seasonal, and residual—which are then processed individually using adaptive graph convolution, a periodic-constrained graph attention network, and dynamic graph convolution, respectively. A feature fusion module, along with orthogonality constraints, ensures effective integration of these component-wise features while preserving their independence. Additionally, embedding this architecture within an Informer-based encoder-decoder framework enhances its capacity for long-range sequence modeling. Extensive experiments on both univariate and multivariate benchmarks demonstrate that STL-MGAI achieves superior accuracy and efficiency in long-term forecasting tasks. Notably, it improves prediction accuracy by 16.38% in energy consumption forecasting and by 19.52% in weather prediction. The model’s modular design and adaptive graph convolution also contribute to enhanced generalization and interpretability.

Advanced Persistent Threats (APTs) pose severe challenges to Next-Generation Communication Networks (NGCNs) due to their stealthiness and NGCNs’ dynamic topology, while conventional GNN-based intrusion detection systems suffer from static aggregation and poor adaptability to unseen nodes. To address these issues, this paper proposes DAA-FPN-SAGE, a lightweight graph-based detection framework integrating Dynamic Adaptive Aggregation (DAA) and Multi-Scale Feature Pyramid Network (MSFPM). Leveraging GraphSAGE’s inductive learning capability, the framework effectively models unseen nodes or subgraphs and adapts to NGCN’s dynamic changes (e.g., elastic network slicing, online AI model updates)—a key advantage for handling NGCN’s real-time topological variations. The DAA module employs multi-hop attention to dynamically assign weights to neighbors at different hop distances, enhancing capture of hierarchical dependencies in multi-stage APT attack chains. The MSFPM module fuses local-global structural information via a gated feature selection mechanism, resolving dimensional inconsistency and enriching attack behavior representation. Extensive experiments on StreamSpot, Unicorn, and DARPA TC#3 datasets demonstrate superior performance, meeting detection requirements of large-scale NGCNs.

This study tackles computational bottlenecks, training instability, and insufficient cross-modal semantic alignment in high-resolution multimodal image processing. We propose TriVLLo, an innovative multi-scale vision-language modeling framework. Our main contributions are: First, we introduce factorized 2D positional encoding and a dynamically configurable modular architecture. This approach decouples height and width position information. It improves spatial localization reliability for images with extreme aspect ratios. It also reduces computational parameters and alleviates training instability. Second, we design a unified multi-scale feature extraction and modality interaction mechanism. This uses adaptive image processing and multi-perspective feature pyramids. It enhances robustness to inputs of any resolution. It also achieves fine-grained alignment of vision-language features through a shared embedding space. Third, we build a high-quality dataset with 11K samples for fine-grained reasoning. This dataset supports improvements in visual ranking, semantic alignment, and narrative reasoning. Experiments show that TriVLLo achieves 87.4% of GPT-4V's performance on the MM-Vet benchmark. It demonstrates a 93.0 percentage-point improvement over Emu2 in spatial cognition tasks. It attains 89.2% accuracy on knowledge generation tasks. These results significantly outperform state-of-the-art methods.

The detection of abnormal electricity load data using big data analysis technology has garnered considerable attention from the academic community. However, traditional methods often require ample labeled data to train the model which increases the cost. This article tackles the issues of high model training costs and poor transferability associated with traditional supervised learning methods. We propose a contrastive learning network-based abnormal electricity load detection method (ED-CLN). First, our model enhances training samples through data augmentation and learns the similarities and differences between samples from temporal and contextual perspectives of the sample sequence. This approach enables the acquisition of common feature representations for model training tasks. Then, the weight data of the model trained using unlabeled data is migrated to the supervised training model. Finally, the trained source model is fine-tuned for abnormal electricity load data detection tasks to improve the overall learning effectiveness of the model. The results demonstrate that ED-CLN outperforms both supervised learning methods and various classic contrastive learning methods in anomaly detection, which can effectively identify the abnormal electricity load data.

Thanks to the development of the Internet of Things, a large number of sensors have been deployed, resulting in the collection of abundant time series data. These data series contain potential space-time connection and noise at the same time. Prediction and health management (PHM) aim to provide decision support based on the health state of an entire engineering system. Additionally, the predicting future values also contribute to decision making and fall under the category of time series forecasting. While the existing methods focus on capturing the correlation between the data and reducing the impact of noise, they often fail to fully utilize the noise present in the time series data. In this article, we propose a framework for multivariate time series forecasting called GAGNN. This framework integrates the idea of a generative adversarial network and a graph neural network organically. It adopts the graph neural network as the generator and a multilayer perceptron as the discriminator. Finally, the prediction module is used to obtain the prediction results. The generator, discriminator, and prediction module are trained jointly. Our experimental results demonstrate that our model outperforms the original model on most benchmark data sets and achieves the best results on three out of six benchmark data sets.

Extending the length of time series forecasting has a long-term impact on smart grid energy consumption planning, residential electricity monitoring, extreme weather warning, and other real applications. This article studies the reliable long-term load trend forecasting approaches in smart grid environment. In recent years, the improved neural networks models based on self-attention mechanism show good performances in many sequence tasks, but most studies focus on reducing the complexity of networks layer, and can not restrain the increase of calculation error in longer distance forecasting scenarios. Also, most models lack the ability to mine potential high-dimensional features of time series. Based on these problems, we design a reliable hierarchical self-attention model named as long-term stability network (LTSNet), which adopts a tree-shaped decomposition neural network architecture based on hierarchical residual self-attention blocks, to top-down incrementally mine high-dimensional features of temporal components. At the same time, the attention matrix is used for feature interaction at each layer, to reduce the distribution gap between time series fragments in different domains. Compared with existing study models, LTSNet maintains stable forecasting performance and speed in long-term forecasting services, achieved the most reliable multivariate and univariate forecasting results in multiple domain scenarios. Compared with the latest models, the forecasting accuracy of the proposed model is improved by 22.8% and 13.8%, respectively, covering three applications: energy consumption, residential electricity consumption, and weather forecasting. At the same time, our experiments verify that the hierarchical decomposition networks can be used as a backbone architecture to effectively extended to longer dimensional load trend forecasting scenarios.

In recent years, unmanned aerial vehicles (UAV) or drones have become ubiquitous in our daily lives, bringing great convenience to our lives and playing a pivotal role in future wireless networks and the Internet of things. One of the major problems associated with the UAV is the heterogeneous nature of such deployments; this heterogeneity poses many challenges, particularly in the areas of security and privacy. The key to solving these problems is to accurately identify and authenticate drones. In this article, a reliable UAV identify framework based on radio frequency fingerprint is proposed. First, we established a wireless signal label architecture and systematically collected, analyzed, and recorded the radio frequency signals of different UAVs in different flight modes and different distances in the telemetry link, and established UAV signal datasets. Then, the intelligent algorithm and anti-UAV system are designed by using the collected dataset, and the feasibility of the developed dataset for detecting and identifying UAVs is verified by using machine learning and deep learning. The simulation results show that under the condition of Gaussian white noise, the method based on deep learning achieves high reliability, and when the SNR is not less than 5dB, the model achieves more than 95% of the monitoring and recognition accuracy. Finally, we discussed the possible applications of the dataset in the future.

In recent years, with the continuous development of artificial intelligence algorithms, their applications in network intrusion detection have become more and more widespread. However, as the network speed continues to increase, network traffic increases dramatically, and the drawbacks of traditional machine learning methods such as high false alarm rate and long training time are gradually revealed. CNN(Convolutional Neural Networks) can only extract spatial features of data, which is obviously insufficient for network intrusion detection. In this paper, we propose an intrusion detection model that combines CNN and BiSRU (Bi-directional Simple Recurrent Unit) to achieve the goal of intrusion detection by processing network traffic logs. First, we extract the spatial features of the original data using CNN, after that we use them as input, further extract the temporal features using BiSRU, and finally output the classification results by softmax to achieve the purpose of intrusion detection.

Since its introduction, IoT (Internet of Things) has enjoyed vigorous support from governments and research institutions around the world, and remarkable achievements have been obtained. The perception layer of IoT plays an important role as a link between the IoT and the real world; the security has become a bottleneck restricting the further development of IoT. The perception layer is a self-organizing network system consisting of various resource-constrained sensor nodes through wireless communication. Accordingly, the costly encryption mechanism cannot be applied to the perception layer. In this paper, a novel lightweight data integrity protection scheme based on fragile watermark is proposed to solve the contradiction between the security and restricted resource of perception layer. To improve the security, we design a position random watermark (PRW) strategy to calculate the embedding position by temporal dynamics of sensing data. The digital watermark is generated by one-way hash function SHA-1 before embedding to the dynamic computed position. In this way, the security vulnerabilities introduced by fixed embedding position can not only be solved effectively, but also achieve zero disturbance to the data. The security analysis and simulation results show that the proposed scheme can effectively ensure the integrity of the data at low cost.