Adaptive federated filter for multi-sensor nonlinear system with cross-correlated noises

Wang, Lijun; Wang, Sisi; Yang, Wenzhi

doi:10.1371/journal.pone.0246680

Cited by 6 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer alignment [18] divided the high-dimensional state vector into two parts Improved covariance [19] derived a real-time estimates of improved covariance SINS/GPS/CNS/Radar integrated system [11] calculated the state parameters with dual-state detection Joint filter to fuse data [20] INS/CNS/DVL combined system Federated unscented Kalman filter [21] with different vehicle motion models to estimate Federated hybrid filter [22] utilizes a minimum variance criterion to fuse An adaptive filter [23] conquer the performance degradation Federated filter with a feedback scheme [24] GNSS/INS/visual odometry combined positioning system Federated Kalman filter for indoor positioning distance is estimated through RSS and improved the calculation speed. Ma et al presented a federated adaptive filter based on improved covariance [19], which derived real-time estimates of improved covariance according to maximum likelihood estimation criteria.…”

Section: Methods Contributionmentioning

confidence: 99%

See 1 more Smart Citation

A SINS/DVL/USBL integrated navigation and positioning IoT system with multiple sources fusion and federated Kalman filter

et al. 2022

View full text Add to dashboard Cite

The navigation and positioning subsystem offers important position information for an autonomous underwater vehicle (AUV) system. It plays a crucial role during the underwater exploration and operations of AUV. Many scholars research underwater navigation and positioning. Various improved methods and systems were presented. However, as the diversity of the ocean environment, the random drift of the gyroscope, error accumulation, the variety of tasks, and other negative factors, the navigation and positioning results are uncertain and incredible. The accuracy, stability, and robustness are not guaranteed, which cannot meet the increasing application requirement. Therefore, we put forward a SINS/DVL/USBL integrated navigation and positioning IoT system with multiple resource fusion and a federated Kalman filter. In this method, we first present an improved SINS/DVL combined subsystem with a filtering gain compensation strategy. So we can enhance the accuracy and stability of the navigation and position system. Secondly, we proposed a USBL positioning subsystem with the Kalman filtering acoustic signals to improve USBL positioning performance. Lastly, we present a federated Kalman filter to fuse the positioning information from the SINS/DVL combined positioning subsystem and the USBL positioning subsystem. Through the three methods, we can enhance the positioning accuracy and robustness. Comprehensive simulation results indicated the feasibility and effectiveness of the proposed SINS/DVL/USBL integrated navigation and positioning system, which provides critical reference for other positioning method, and it also offers crucial position information for AUV to achieve high accuracy and efficiency tasks.

show abstract

Section: Methods Contributionmentioning

confidence: 99%

“…In the filter [22], a minimum variance criterion is utilized to fuse the estimate of each local filter. Wang et al presented a federated filter for a multiple-sensor cross-correlations strategy [23]. An adaptive filter was utilized as a local filter, which can conquer the performance degradation.…”

Section: Methods Contributionmentioning

confidence: 99%

A SINS/DVL/USBL integrated navigation and positioning IoT system with multiple sources fusion and federated Kalman filter

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In the filter, a minimum variance criterion is utilized to fuse the estimate of each local filter. Reference [24] presented a federated filter for multiple-sensor crosscorrelations strategy. An adaptive filter was utilize as a local filter, which can conquer the performance degradation .To enhance the accuracy and robustness, reference [25] proposed a federated filter with a feedback scheme for a GNSS/INS/visual odometry combined positioning system.…”

Section: Related Workmentioning

confidence: 99%

A SINS/DVL/USBL Integrated Navigation and Positioning IoT System with Multiple Sources Fusion and Federated Kalman Filter

Luo

Yan

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

The navigation and positioning subsystem offers important position information for an autonomous underwater vehicle (AUV) system. It plays a crucial role during the underwater exploration and operations of AUV. Many scholars research underwater navigation and positioning. And many promising methods and systems were presented. However, as the diversity of ocean environment, the random drift of the gyroscope, error accumulation, the diversity of tasks, and other negative factors, the navigation and positioning result is uncertain and incredible. The accuracy, stability and robustness are not guaranteed, which can not meet the increasing application requirement. Therefore, we put forward a SINS/DVL/USBL integrated navigation and positioning IoT system with multiple resource fusion and a federated Kalman filter. In this method, we first present an improved SINS/DVL combined subsystem with filtering gain compensation strategy. The accuracy and stability of the navigation and position system can be enhanced. Secondly, We proposed a USBL positioning subsystem with the Kalman filtering acoustic signals to improve USBL positioning performance. Lastly, we present a federated Kalman Filter to fuse the positioning information from the SINS/DVL combined positioning subsystem and the USBL positioning subsystem. Through the above three methods, we can improve the positioning accuracy and robustness. Comprehensive simulation results indicated the feasibility and effectiveness of the proposed SINS/DVL/USBL integrated navigation and positioning system.

show abstract

“…This phenomenon occurs primarily due to three reasons: user reluctance to share data, strict data sharing policies, and high communication costs. In particular, amidst the growing emphasis on data privacy, a solution that complies with the EU’s General Data Protection Regulation and China’s Internet Personal Information Security Protection Guidelines is necessary [ 5 , 6 ]. Moreover, even with the widespread implementation of 5G, coping with the substantial user behavior data generated by the 4.9 billion internet users in 2021 [ 7 ] and an average weekly online time of 28.5 hours [ 8 ] remains a challenge.…”

Section: Introductionmentioning

confidence: 99%

Empowering precise advertising with Fed-GANCC: A novel federated learning approach leveraging Generative Adversarial Networks and group clustering

Su,

Wei,

Lei

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

In the realm of targeted advertising, the demand for precision is paramount, and the traditional centralized machine learning paradigm fails to address this necessity effectively. Two critical challenges persist in the current advertising ecosystem: the data privacy concerns leading to isolated data islands and the complexity in handling non-Independent and Identically Distributed (non-IID) data and concept drift due to the specificity and diversity in user behavior data. Current federated learning frameworks struggle to overcome these hurdles satisfactorily. This paper introduces Fed-GANCC, an innovative federated learning framework that synergizes Generative Adversarial Networks (GANs) and Group Clustering. The framework incorporates a user data augmentation algorithm predicated on adversarial generative networks to enrich user behavior data, curtail the impact of non-uniform data distribution, and enhance the applicability of the global machine learning model. Unlike traditional approaches, our framework offers user data augmentation algorithms based on adversarial generative networks, which not only enriches user behavior data but also reduces the challenges posed by non-uniform data distribution, thereby enhancing the applicability of the global machine learning (ML) model. The effectiveness of Fed-GANCC is distinctly showcased through experimental results, outperforming contemporary methods like FED-AVG and FED-SGD in terms of accuracy, loss value, and receiver operating characteristic (ROC) indicators within the same computing time. Experimental results vindicate the effectiveness of Fed-GANCC, revealing substantial enhancements in accuracy, loss value, and receiver operating characteristic (ROC) metrics compared to FED-AVG and FED-SGD given the same computational time. These outcomes underline Fed-GANCC’s exceptional prowess in mitigating issues such as isolated data islands, non-IID data, and concept drift. With its novel approach to addressing the prevailing challenges in targeted advertising such as isolated data islands, non-IID data, and concept drift, the Fed-GANCC framework stands as a benchmark, paving the way for future advancements in federated learning solutions tailored for the advertising domain. The Fed-GANCC framework promises to offer pivotal insights for the future development of efficient and advanced federated learning solutions for targeted advertising.

show abstract

Adaptive federated filter for multi-sensor nonlinear system with cross-correlated noises

Cited by 6 publications

References 43 publications

A SINS/DVL/USBL integrated navigation and positioning IoT system with multiple sources fusion and federated Kalman filter

A SINS/DVL/USBL integrated navigation and positioning IoT system with multiple sources fusion and federated Kalman filter

A SINS/DVL/USBL Integrated Navigation and Positioning IoT System with Multiple Sources Fusion and Federated Kalman Filter

Empowering precise advertising with Fed-GANCC: A novel federated learning approach leveraging Generative Adversarial Networks and group clustering

Contact Info

Product

Resources

About