This letter proposes a distributed path selection algorithm based on the meta multi-agent proximal policy optimization (Meta-MAPPO). The algorithm leverages transferable knowledge to achieve faster and more stable policy optimization in dynamic satellite networks. We integrate meta-learning into the MAPPO framework, equipping agents with rapid adaptation capabilities and enhancing convergence efficiency through experience sharing. Simulation results on a 96-satellite Walker–Delta constellation demonstrate that the proposed framework achieves at least a 5% reduction in average end-to-end delay, maintains zero packet loss, and converges faster, demonstrating its efficiency and robustness in dynamic satellite network environments.

Epidemic forecasting is vital for public health, yet privacy concerns impede inter-institutional data sharing and limit model performance. Federated learning has emerged as a promising approach, but previous research has been limited to specific datasets and temporal prediction. In this paper, we present a privacy-preserving framework, federated framework for epidemic on networks (FFEN), for node-level epidemic prediction on networks that leverages federated learning (FL) to model the spatio-temporal propagation of epidemic severity across data-isolated subnetworks. A Spatio-Temporal Graph Attention Network (STGAT) is proposed to enhance federated epidemic prediction by effectively capturing spatio-temporal dependencies. Extensive simulations on various epidemic processes within a real-world airline network comprehensively evaluate FL’s efficacy under diverse scenarios. To further assess robustness, we introduce the efficacy energy metric, systematically analyzing key factors affecting FL performance. Numerical results validate the effectiveness of FFEN in complex epidemic prediction and demonstrate that STGAT outperforms traditional temporal approaches in capturing dynamic epidemic propagation.

With the global promotion of fifth-generation (5G) communications, researches for sixth generation (6G) communications are being globally launched from various perspectives. Industrial Internet of Things (IIoT), which is the most representative application that reflects the ubiquitous connectivity characteristics of 6G, has attracted much attention. To explore for a feasible perspective in promoting ubiquitous connectivity and improving IIoT abilities, in this article, we seek solutions to incorporate two promising techniques, i.e., nonorthogonal multiple access (NOMA) and statistical signal transmission (SST). To accomplish such a motivation, we conceive the feasible transceiver architecture for the union of NOMA-SST technique, and elaborate workflow and detection procedures for both uplink and downlink modes. A dedicated resilient window strategy is designed thereafter, which largely strengthen weaker NOMA users’ SST performance without depressing stronger users. The proposed technique is finally testified through both simulation experiments and practical applications. Numerical results verify that NOMA-SST technique has satisfactory detection performance in common IIoT environments. It is also manifested that the proposed technique can refine various aspects, including recall rate and sensing accuracy of monitoring services, successful handling rate of emergency situations, etc., for practical IIoT applications. Such advantages are promising for practice.

Relation extraction is an important task in the field of natural language processing. Previous works mainly focus on adopting pipeline methods or joint methods to model relation extraction in general scenarios. However, these existing methods face challenges when adapting to complex relation extraction scenarios, such as handling overlapped triplets, multiple triplets, and cross-sentence triplets. In this paper, we revisit the advantages and disadvantages of the aforementioned methods in complex relation extraction. Based on the in-depth analysis, we propose a novel two-stage bidirectional extract-then-evaluate framework namedBeeRe. In the extraction stage, we first obtain the subject set, relation set, and object set. Then, we design subject- and object-oriented triplet extractors to iteratively recurrent obtain candidate triplets, ensuring high recall. In the evaluation stage, we adopt a relation-oriented triplet filter to determine subject-object pairs based on relations in triplets obtained in the first stage, ensuring high precision. We conduct extensive experiments on three public datasets to show thatBeeReachieves state-of-the-art performance in both complex and general relation extraction scenarios. Even when compared to large language models like closed-source/open-source LLMs,BeeRestill has significant performance gains.

Adversarial examples (AEs) make Internet-of-Things (IoT) systems to face a great challenge. The tiny fluctuations in AEs mislead the learning model, let the model accept, and make wrong decisions. So, accurately identifying AEs is significant for improving the robustness in IoT systems. In this article, a method to identify AEs for time-series data is proposed. We analyze the characteristics of adversarial time-series examples and normal time-series samples and propose a time-series representation method. The tiny fluctuations in AEs are easily discovered by this representation. A metric is also designed to support this representation method to identify AEs with supervised learning and unsupervised learning methods. Our representation method and the metric is applied with supervised learning and unsupervised learning methods to identify time series in real data set and data sets in the official UCR repository. The experimental results show that our method has a great ability to identify AEs, compared to previous approaches.

Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which lead to severe damages to both patients and hospital services. One of such errors is the mismatch between diagnose and prescription, which we address as “medication anomaly” in the paper, and clinicians used to manually identify and correct them. With the development of machine learning techniques, researchers are able to train specific model for the task, but the process still requires expert knowledge to construct proper features, and few semantic relations are considered. In this paper, we propose a simple, yet effective detection method that tackles the problem by detecting the semantic inconsistency between diagnoses and prescriptions. Unlike traditional outlier or anomaly detection, the scheme uses continuous bag of words to construct the semantic connection between specific central words and their surrounding context. The detection of medication anomaly is transformed into identifying the least possible central word based on given context. To help distinguish the anomaly from normal context, we also incorporate a ranking accumulation strategy. The experiments were conducted on two real hospital electronic medical records, and the topN accuracy of the proposed method increased by 3.91 to 10.91% and 0.68 to 2.13% on the datasets, respectively, which is highly competitive to other traditional machine learning-based approaches.

A well-designed fitness function is essential to the effectiveness and efficiency of evolutionary testing. Fitness function design has been researched extensively. For fitness calculation, so far the switchcase construct has been regarded as a nested if-else structure with respect to the control flow. Given a target embraced in a case branch, test data taking different case branches receive different approximation levels. Since the approximation levels received by test data do not evaluate their suitability accurately, the guidance provided by the existing approach to evolutionary search is misleading or lost. Despite the switch-case construct.s wide use in industrial applications, no previous work has addressed this problem.

Evolutionary Testing has been shown a promising technology for the automatic test data generation. It reformulates test data generation as a metaheuristic search. A well- designed fitness function is essential to the efficiency of evolutionary search. Many efforts have been directed at the design and implementation of fitness function in recent years. However, previous work has just focused on the control dependency of the target on the branches in the same function. When function calls exist in the desired execution trace to the target, the evaluation of the test data on the coverage of these function calls, which should be provided to the evolutionary search, is not captured by the existing fitness function. In this case, the existing fitness function can not fairly evaluate the test data. And the evolutionary search will be hampered or even fail in severe cases. In this paper, a new term is first proposed to incorporate into the existing fitness function. It is applied to evaluate the test data's coverage of function calls along the desired path to the target. The new fitness function can evaluate the test data more fairly, resulting in a better guidance to the evolutionary search. This can be seen by the experiments carried out on two cases.

This letter analyzes the mean-square convergence of a deficient-length least mean-square adaptive filter whose length is less than that of the unknown system and proves that filter length and the envelope of impulse response are the important factors in convergence rate control. For the impulse response with an exponential decay envelope, which covers a large set of physical systems, e.g., acoustic echo path, an optimal filter length sequence is figured out to achieve the fastest convergence. The simulations of an exact exponential decay envelope and of a real-life echo path in a car environment are performed via computer, and the results validate our analysis well.