A5072257665- Underwater Vehicles and Communication Systems
- Indoor and Outdoor Localization Technologies
- Underwater Acoustics Research
- Advanced Adaptive Filtering Techniques
- Oral and Maxillofacial Pathology
- Advanced Algorithms and Applications
- Dental Implant Techniques and Outcomes
- Energy Efficient Wireless Sensor Networks
- Dental Radiography and Imaging
- Blind Source Separation Techniques
- Water Quality Monitoring Technologies
- Speech and Audio Processing
Wuhan University
2022-2024
Institute of Art
2023
Systems Engineering Society of China
2013
The proportionate recursive least squares (PRLS) algorithm has shown faster convergence and better performance than both updating (PU) mechanism based mean (LMS) algorithms RLS with a sparse regularization term. In this paper, we propose variable forgetting factor (VFF) PRLS penalty, e.g., l <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</inf> -norm, for identification. To reduce the computation complexity of proposed algorithm, fast...
The underwater sensor network localization algorithm is one of the very important steps in initialization process. Due to deployment environmental constraints, node can only be indirectly localized by calculation. Based on traditional Ad Hoc algorithm, this paper discusses an improved suitable for environment.
Abstract A virtual space-time diversity soft direct-adaptation turbo euqalization (SDATEQ) is proposed for single-input-single-output (SISO) underwater acoustic (UWA) communications based on fractionally-spaced decision-feedback equalizer (SFSDFE) and time-reversal mirror (VTRM). The SFSDFE combined with recursive least-squares (RLS) algorithm employed to achieve space increases the mutual information (MI) of iterations faster convergence. Bidirectional structure VTRM exploited mitigate...
The diversity combining technique performs well in the inhibition of multipath, it has been widely used underwater acoustic (UWA) array signal processing. However, noise can seriously affect processing results diversity. conventional filtering algorithms cannot deal with nonlinear components radiation and have a poor effect on complex signals. This study proposes novel angle method based two-stage model to overcome problem. A noise-reduction deep convolutional neural network (DCNN) as...
Space–time diversity (STD) has been widely applied in underwater acoustic (UWA) communication due to its exceptional anti-multipath performance. However, noise can seriously affect the processing results of STD. The conventional filtering algorithms cannot deal with nonlinear components and may not work well for complex-type signals. This study proposes an improved STD method a joint noise-reduction learning model above issues. We construct dedicated UWA signals first stage. Complex-type...
Radiolucent jaw lesions (RJLs) classification on cone beam computed tomography (CBCT) images is a very important issue in computer-aided diagnosis for medical applications. In the CBCT image, lesion region occupies small part but contains discriminative features, and background area also includes some other useful features besides lot of irrelevant bone structure thus how to comprehensively learning valuable from challenge. Furthermore, RJLs exhibit similar hypodensity their borders have...
The oceanic positioning, navigation and timing (PNT) network requires high-quality underwater acoustic message transmission. Turbo equalization technology has exhibited superior performance for (UWA) communications compared with conventional channel equalizers. To overcome the reduction caused by severe doubly selective UWA channels, virtual space-time diversity soft direct-adaptation turbo is proposed communications. scheme improves ability of typical equalizer to deal both Doppler...