A5066779249- Underwater Vehicles and Communication Systems
- Wireless Signal Modulation Classification
- Blind Source Separation Techniques
- Speech and Audio Processing
- Advanced Adaptive Filtering Techniques
- Optical Wireless Communication Technologies
- PAPR reduction in OFDM
- Underwater Acoustics Research
- Radar Systems and Signal Processing
- Advanced Wireless Communication Technologies
- Image Processing Techniques and Applications
- Marine animal studies overview
- Energy Efficient Wireless Sensor Networks
- Energy Harvesting in Wireless Networks
- Maritime Navigation and Safety
- Advanced Image Processing Techniques
- Digital Holography and Microscopy
- Fractal and DNA sequence analysis
- Marine and Coastal Research
- Machine Fault Diagnosis Techniques
- Direction-of-Arrival Estimation Techniques
- Advanced biosensing and bioanalysis techniques
- Advanced Wireless Communication Techniques
Jiangsu University of Science and Technology
2021-2024
Institute of Acoustics
2024
Chinese Academy of Sciences
2024
Underwater acoustic target recognition (UATR) is an important supporting technology for underwater information acquisition and countermeasure. Usually, ship radiated noise covered by the background previous deep learning methods this task rely on clear effective features. We propose a novel network called AMNet to alleviate problem in letter. It consists of multibranch backbone coupled with convolutional attention network. The proposed able obtain internal features from time-frequency map...
This paper provides a review of the NTIRE 2021 challenge targeting defocus deblurring using dual-pixel (DP) data. The goal this single-track was to reduce spatially varying blur present in images captured with shallow depth field. used were obtained DP sensor that provided pair views per image. Submitted solutions evaluated conventional signal processing metrics, namely peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). Out 185 registered participants, nine...
Low energy consumption has always been one of the core issues in routing design underwater sensor networks. Due to high cost and difficulty deployment replacement current nodes, many applications require protocol consider network lifetime extension problem. Based on this, we designed a new that takes into account both low balanced consumption, achieves effective lifetime, called adaptive power-controlled depth-based for wireless networks (APCDBRP). The consists two phases: (1) route...
This letter presents the power of deep learning for signal detection in orthogonal frequency division multiplexing with index modulation (OFDM-IM) systems. In this letter, we propose Y-shaped net-based scheme fully connected layers (Y-FC) and bidirectional long short-term memory units (Y-BLSTM) to further optimize data reception. scheme, active indices constellation demapping are learned by two parallel sub-neural networks respectively, output features then concatenated flattened obtain...
To address the problems of high complexity and poor bit error rate (BER) performance traditional communication systems in underwater acoustic environments, this paper incorporates theory deep learning into a conventional system proposes data-driven filter bank multicarrier (FBMC) communications based on convolutional autoencoder networks. The proposed is globally optimized by two one-dimensional (Conv1D) modules at transmitter receiver, it realizes signal reconstruction through end-to-end...
The orthogonal time frequency space (OTFS) modulation technique can provide reliable communication in time-varying channels. Due to the dispersive characteristics of underwater acoustic channels, this paper proposes an OTFS-IM system based on Hamming distance optimization reduce impact dispersion communication. Firstly, is introduced, which introduces index into Delay–Doppler (DD) domain make OTFS have stronger anti-Delay–Doppler capability. In contrast, since there sequence redundancy a...
Ship radiated noise is an important information source of underwater acoustic targets, and it great significance to the identification classification ship targets. However, there are a lot interference noises in water, which leads reduction model recognition rate. Therefore, results targets severely affected. This paper proposes machine learning Dempster–Shafer (ML‐DS) decision fusion method. The algorithm combines deep learning. It uses evidence‐based decision‐making theory realize feature...
Abstract In recent years, research on modulated signal recognition using deep learning (DL) has achieved remarkable success, allowing automatic modulation (AMR) to play a crucial role in modern communication systems. The emergence of the attention mechanism then rapidly led wide range applications image classification and speech recognition, which proves effectiveness mechanism. this paper, authors propose network model feed‐forward Attention with Residuals networks Long Short‐Term Memory...
By contraposing the signal detection for filter bank multicarrier (FBMC) communications with underwater acoustic (UWA) channel, this paper analyzes traditional imaginary interference problem and proposes a deep learning-based method. The neural network feature extraction automatic learning ability is employed to replace demodulation modules recover transmitted signals without explicit channel estimation equalization. Sufficient data sets are generated according measured conditions in...
Abstract For the channel estimation problem under α -stable distributed impulse interference, traditional fixed-step adaptive filtering cannot satisfy fast convergence speed and low steady-state error at same time, whereas variable-step method is able to effectively solve this contradiction. This paper proposes an improved variable step-size least mean p -power algorithm that offers good robustness against impulsive noise. The proposed takes into account linkage between errors uses...
Underwater acoustic channels often have to face the interference of impulsive noise, which is usually modeled by α-stable distribution in simulation experiments. To solve problem underwater channel estimation under this paper proposes a convex combination–variable-step-size least mean p-norm algorithm. The algorithm incorporates combination into variable-step-size and uses different convergence domains provided changing parameters Gaussian function further improve effect after convergence....
The conventional adaptive filtering algorithm in signal processing with fixed step size will lead to its stability and convergence unable be combined at the moment. To deal this problem, least mean p-power (LMP) is improved, a variable based on an improved softsign function proposed. uses construct function, while moving weighted average method applied update keep efficiency of stable. Simulation experiments indicate that LMP further reduces steady-state error maintaining original speed,...
Recently, the orthogonal time-frequency space (OTFS) modulation technique has been proposed to provide reliable communication over time-varying channels, combined with double dispersion characteristics of underwater acoustic channels improve BER performance and spectral efficiency communication. In this paper, we propose an system combining index OTFS. This uses indexed bits control activation grid in delay-Doppler domain, allowing flexible adjustment number silent activated grids, resulting...