The widespread application of Distributed Acoustic Sensing (DAS) in security monitoring has increased the demand for advanced intrusion recognition algorithms. Conventional approaches often divide the process into two stages: signal processing and recognition modeling. However, this separation introduces two key challenges: (1) signal processing quality is typically assessed only through the final recognition outcome, lacking a unified optimization mechanism, which limits efficiency and generalization. (2) The two-stage framework is unsuitable for tasks requiring high real-time performance. Therefore, we propose the Frequency-Time Integrated Transformer (FTIformer) to address these challenges. FTIformer integrates the Multi-head Time-Frequency Perception (MTFP) module and the Self-Attention Module (SAM), achieving unified optimization of time-frequency signal extraction and pattern recognition through loss function backpropagation. Furthermore, in complex environments, multiple events of interest may occur within the same detection cycle, causing feature overlap and potential confusion of model outputs. To mitigate this, we decompose the multi-event recognition task into multiple single-event recognition tasks. Building on this approach, class-specific loss is proposed for the first time, which guides the model in learning unique representations for each event. We conducted experiments using a private dataset and a public dataset. Experimental results indicate that FTIformer achieves an accuracy, precision, and recall of 0.946, 0.976, and 0.979, respectively, on the private dataset, and 0.897, 0.956, and 0.966 on the public dataset. The detailed implementation of the proposed model is available at https://github.com/linjie1888/FTIformer-notebook.

Output uncertainty indicates whether the probabilistic properties of the overall distribution reflect objective characteristics of the model output. Unlike most loss functions and metrics in machine learning, uncertainty pertains to individual samples, but validating it on individual samples is unfeasible. When validated collectively, it cannot fully represent individual sample properties, posing a challenge in assessing and calibrating model confidence in a limited data set. Hence, it is crucial to consider confidence calibration characteristics. To counter the adverse effects of the gradual amplification of the classifier output amplitude in supervised learning, we introduce a post-processing parametric calibration method, ρ-Norm Scaling, which expands the calibrator expression and mitigates overconfidence due to excessive amplitude while preserving accuracy. Moreover, calibrator optimization based bin-level calibration error often results in the loss of significant instance-level information. Therefore, we include probability distribution regularization, which incorporates a priori information that the instance-level uncertainty distribution after calibration should resemble the distribution before calibration. Experimental results demonstrate the substantial enhancement in the post-processing calibrator for uncertainty calibration with our proposed method.

This paper addresses a data-driven sliding mode bipartite consensus issue for nonlinear discrete-time multi-agent systems with antagonistic interactions and limited communication resources. Initially, the signed graph theory is employed, and a combined measurement error function is formulated, transforming the bipartite consensus issue into a traditional consensus issue. An enhanced compact form dynamic linearization model is then established based on the input/output data and the formulated combined measurement error function. Moreover, a dynamic event-triggered function and a sliding-mode surface are designed, leading to the development of a fully distributed dynamic event-triggered sliding-mode bipartite consensus (DET-SMBC) approach. The proposed DET-SMBC approach is subsequently extended to a fully distributed dynamic event-triggered robust sliding-mode bipartite consensus (DET-RSMBC) scheme to improve robustness. The convergences of the tracking errors of both methods are rigorously deduced. Finally, simulation studies and hardware experiments are conducted to demonstrate the effectiveness of the proposed methods. Note to Practitioners—In multi-agent systems, the applicability of existing methods can be reduced by some issues, such as uncertain dynamics models, unknown disturbances, and the limitation of communication bandwidth. These issues can influence existing methods’ usefulness and cause instability, so DET-SMBC and DET-RSMBC methods are proposed in this paper. Compared with existing results, identifying a precise dynamics model for each controlled plant is unnecessary, the necessity of high-performance hardware for data transmission is relieved, and the effects of unknown disturbances are reduced. Moreover, the proposed methods are applied to realistic servo motor systems to conduct speed bipartite consensus tasks well. It is noted that most complicated mechanisms are controlled by servo motors, so the proposed methods can be applied to more practical engineering systems.

Modern deep learning models often exhibit overconfident predictions, inadequately capturing uncertainty. During model optimization, the expected calibration error tends to overfit earlier than classification accuracy, indicating distinct optimization objectives for classification error and calibration error. To ensure consistent optimization of both model accuracy and model calibration, we propose a novel method incorporating a probability-dependent gradient decay coefficient into loss function. This coefficient exhibits a strong correlation with the overall confidence level. To maintain model calibration during optimization, we utilize a proportional-integral-derivative (PID) controller to dynamically adjust this gradient decay rate, where the adjustment relies on the proposed relative calibration error feedback in each epoch, thereby preventing the model from exhibiting over-confidence or under-confidence. Within the PID control system framework, the proposed relative calibration error serves as the control system output, providing an indication of the overall confidence level, while the gradient decay rate functions as the controlled variable. Moreover, recognizing the impact of gradient amplitude of adaptive decay rates, we implement an adaptive learning rate mechanism for gradient compensation to prevent inadequate learning of over-small or over-large gradient. Empirical experiments validate the efficacy of our PID-based adaptive gradient decay rate approach, ensuring consistent optimization of model calibration and model accuracy.

Due to inappropriate sample selection and limited training data, a distribution shift often exists between the training and test sets. This shift can adversely affect the test performance of graph neural networks (GNNs). Existing approaches mitigate this issue by either enhancing the robustness of GNNs to distribution shift or reducing the shift itself. However, both approaches necessitate retraining the model, which becomes unfeasible when the model structure and parameters are inaccessible. To address this challenge, we propose FR-GNN, a general framework for GNNs to conduct feature reconstruction. FR-GNN constructs a mapping relationship between the output and input of a well-trained GNN to obtain class representative embeddings and then uses these embeddings to reconstruct the features of labeled nodes. These reconstructed features are then incorporated into the message passing mechanism of GNNs to influence the predictions of unlabeled nodes at test time. Notably, the reconstructed node features can be directly utilized for testing the well-trained model, effectively reducing the distribution shift and leading to improved test performance. This remarkable achievement is attained without any modifications to the model structure or parameters. We provide theoretical guarantees for the effectiveness of our framework. Furthermore, we conduct comprehensive experiments on various public data sets. The experimental results demonstrate the superior performance of FR-GNN in comparison to multiple categories of baseline methods.

Graph adversarial attacks can be classified as either white-box or black-box attacks. White-box attackers typically exhibit better performance because they can exploit the known structure of victim models. However, in practical settings, most attackers generate perturbations under black-box conditions, where the victim model is unknown. A fundamental question is how to leverage a white-box attacker to attack a black-box model. Some current black-box attack approaches employ white-box techniques to attack a surrogate model, resulting in satisfactory outcomes. Nonetheless, such white-box attackers must be meticulously designed and lack theoretical assurances for attack effectiveness. In this paper, we propose a novel framework that utilizes simple white-box techniques to conduct black-box attacks and provides the lower bound for attack performance. Specifically, we first employ a more comprehensive GCN technique named BiasGCN to approximate the victim model, and subsequently, use a simple white-box approach to attack the approximate model. We provide a generalization guarantee for our BiasGCN and employ it to obtain the lower bound on attack performance. Our method is evaluated on various datasets, and the experimental results indicate that our approach surpasses recently proposed baselines.

In wireless power transfer (WPT) systems, inverters are used to achieve high‐frequency conversion of DC/AC, and their conversion efficiency and working frequency are key factors affecting the system’s power transfer efficiency. In practical applications, many hardware issues, such as power transistor shutdown and loss, are the main reasons that affect the inverter conversion efficiency. On the other hand, the working frequency of WPT systems ranges from hundreds of kHz to a few MHz, and traditional voltage and current phasor estimation requires a very high sampling rate which is difficult to achieve. To overcome these limitations, this paper introduces a phase‐shifting full bridge inverter using a zero‐voltage switching (ZVS) soft switching technology to optimize the conversion efficiency of the inverter. Meanwhile, apparent power is introduced to detect the operating frequency and phase angle. Combined with an FPGA soft switching control strategy, this approach allows for the quick adjustment of the driving pulse of MOS transistors, as well as the voltage and current at the transmitting end, to a completely symmetrical state in real‐time, effectively suppressing frequency offset and achieving efficient frequency tracking control and maximum efficiency tracking (MET) control of the WPT system. Through simulation and experiments, the ZVS soft switching technology has been achieved with the inverter control strategy, leading to improved conversion efficiency. The frequency offset that can be corrected can reach 0.1 Hz using the apparent power detection method, and the maximum transfer efficiency of the WPT system can reach 91%.

Incremental Extreme Learning Machine is one of the constructive neural networks and provides a fast architecture building mechanism by adding the hidden layer neurons incrementally. There are two phases in constructing the newly added nodes. One is to assign the weights of the hidden nodes quickly with different methods, and the other is to compute the output weights by the least squares methods after obtaining the parameters in the previous phase. Nevertheless, it has a basic deficiency in the aforementioned construction scheme that there is no guarantee on the simultaneous optimization of the weights in the hidden and output layers, respectively, which may produce a lot of redundant nodes in the final models. In this paper, a new integrated optimization method is proposed to construct the simultaneously optimized weights in the first and second phases, and the corresponding integrated optimization incremental-ELM (termed as IOI-ELM) is established. Furthermore, a novel convergence analysis method is developed to provide an upper constraint bound for the selection of the parameters. The simulation results demonstrate and verify that the performance of our approach is much better than other constructive learner models.