A novel method is developed by utilizing the fractional frequency based multi-range rulers to precisely position the passive intermodulation (PIM) sources within radio frequency (RF) cables. The proposed method employs a set of fractional frequencies to create multiple measuring rulers with different metric ranges to determine the values of the tens, ones, tenths, and hundredths digits of the distance. Among these rulers, the one with the lowest frequency determines the maximum metric range, while the one with the highest frequency decides the highest achievable accuracy of the position system. For all rulers, the metric accuracy is uniquely determined by the phase accuracy of the detected PIM signals. With the all-phase Fourier transform method, the phases of the PIM signals at all fractional frequencies maintain almost the same accuracy, approximately 1°(about 1/360 wavelength in the positioning accuracy) at the signal-to-noise ratio (SNR) of 10 dB. Numerical simulations verify the effectiveness of the proposed method, improving the positioning accuracy of the cable PIM up to a millimeter level with the highest fractional frequency operating at 200 MHz.
As an important branch of federated learning, vertical federated learning (VFL) enables multiple institutions to train on the same user samples, bringing considerable industry benefits. However, VFL needs to exchange user features among multiple institutions, which raises concerns about privacy leakage. Moreover, existing multi-party VFL privacy-preserving schemes suffer from issues such as poor reliability and high communication overhead. To address these issues, we propose a privacy protection scheme for four institutional VFLs, named FVFL. A hierarchical framework is first introduced to support federated training among four institutions. We also design a verifiable replicated secret sharing (RSS) protocol 3 2 -sharing and combine it with homomorphic encryption to ensure the reliability of FVFL while ensuring the privacy of features and intermediate results of the four institutions. Our theoretical analysis proves the reliability and security of the proposed FVFL. Extended experiments verify that the proposed scheme achieves excellent performance with a low communication overhead.
To improve the performance of video compression for machine vision analysis tasks, a video coding for machines (VCM) standard working group was established to promote standardization procedures. In this paper, recent advances in video coding for machine standards are presented and comprehensive introductions to the use cases, requirements, evaluation frameworks and corresponding metrics of the VCM standard are given. Then the existing methods are presented, introducing the existing proposals by category and the research progress of the latest VCM conference. Finally, we give conclusions.
In distributed machine learning (DML) based on the parameter server (PS) architecture, unbalanced communication load distribution of PSs will lead to a significant slowdown of model synchronization in heterogeneous networks due to low utilization of bandwidth. To address this problem, a network-aware adaptive PS load distribution scheme is proposed, which accelerates model synchronization by proactively adjusting the communication load on PSs according to network states. We evaluate the proposed scheme on MXNet, known as a real-world distributed training platform, and results show that our scheme achieves up to 2.68 times speed-up of model training in the dynamic and heterogeneous network environment.
Federated learning (FL) is a distributed machine learning approach that could provide secure 6G communications to preserve user privacy. In 6G communications, unmanned aerial vehicles (UAVs) are widely used as FL parameter servers to collect and broadcast related parameters due to the advantages of easy deployment and high flexibility. However, the challenge of limited energy restricts the popularization of UAV-enabled FL applications. An air-ground integrated low-energy federated learning framework is proposed, which minimizes the overall energy consumption of application communication while maintaining the quality of the FL model. Specifically, a hierarchical FL framework is proposed, where base stations (BSs) aggregate model parameters updated from their surrounding users separately and send the aggregated model parameters to the server, thereby reducing the energy consumption of communication. In addition, we optimize the deployment of UAVs through a deep Q-network approach to minimize their energy consumption for transmission as well as movement, thus improving the energy efficiency of the air-ground integrated system. The evaluation results show that our proposed method can reduce the system energy consumption while maintaining the accuracy of the FL model.
Microservices have become popular in enterprises because of their excellent scalability and timely update capabilities. However, while fine-grained modularity and service-orientation decrease the complexity of system development, the complexity of system operation and maintenance has been greatly increased, on the contrary. Multiple types of system failures occur frequently, and it is hard to detect and diagnose failures in time. Furthermore, microservices are updated frequently. Existing anomaly detection models depend on offline training and cannot adapt to the frequent updates of microservices. This paper proposes an anomaly detection approach for microservice systems with multi-source data streams. This approach realizes online model construction and online anomaly detection, and is capable of self-updating and self-adapting. Experimental results show that this approach can correctly identify 78.85% of faults of different types.
Transfer learning aims to transfer source models to a target domain. Leveraging the feature matching can alleviate the domain shift effectively, but this process ignores the relationship of the marginal distribution matching and the conditional distribution matching. Simultaneously, the discriminative information of both domains is also neglected, which is important for improving the performance on the target domain. In this paper, we propose a novel method called Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation (BDTFL). The proposed method can adaptively balance the relationship of both distribution matchings and capture the category discriminative information of both domains. Therefore, balanced feature matching can achieve more accurate feature matching and adaptively adjust itself to different scenes. At the same time, discriminative information is exploited to alleviate category confusion during feature matching. And with assistance of the category discriminative information captured from both domains, the source classifier can be transferred to the target domain more accurately and boost the performance of target classification. Extensive experiments show the superiority of BDTFL on popular visual cross-domain benchmarks.
