Underwater Acoustic Communication Receiver Using Deep Belief Network

Lee-Leon, Abigail; Yuen, Chau; Herremans, Dorien

doi:10.1109/tcomm.2021.3063353

Cited by 25 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep belief network (DBN) based UAC receiver was presented in Lee‐Leon et al 32 In order to solve the problem of the Doppler effect due to the signal distortion and multi‐path propagation, the machine learning‐based DBN model has been developed for a receiver system. Received signal classification and DBN‐based de‐noising has been covered in the receiver system.…”

Section: Related Workmentioning

confidence: 99%

An improved underwater wireless sensor network communication using Internet of Things and signal to noise ratio analysis

Kapileswar

Polasi

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Underwater acoustic (UWA) channels are widely regarded as one of the most challenging communication mediums. Low frequencies are best for acoustic propagation, and the bandwidth available for communication is extremely small. The worst channel situation often limits the efficiency of UWA communication systems due to the difficulty and time‐varying nature of the UWA channel. To solve the existing limitations related with underwater signal transmission and communication, an improved underwater communication system incorporated with Internet of Things (IoT) is proposed in this work. The proposed system utilizes the orthogonal signal division multiplexing modulation technique. Here the signal transmission process is achieved with the help of an IoT network system. An improved AdaBoost channel estimation algorithm is used to obtain the channel information. This work utilizes an improved stochastic gradient descent optimization method for selecting the suitable mode of signal transmission based on the estimated channel. Further, an adaptive recursive least square channel equalization algorithm is used for channel compensation. The simulation results are obtained with the help of the MATLAB platform. The performance is analyzed in terms of parameters such as signal to noise ratio, bit error rate, and mean square error. A comparison of the proposed method is also made with the existing methods. The evaluation results show that the proposed method performs better than the existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

An improved underwater wireless sensor network communication using Internet of Things and signal to noise ratio analysis

Kapileswar

Polasi

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…In [14], the authors also proposed a joint UWA-OFDM demodulation, channel-estimation, and balanced-neural-network structure, to realize the integration of the receiving device. The authors in [15] proposed a UWA receiving system based on a Deep Belief Network (DBN), which effectively alleviated the performance decline caused by the Doppler effect and multiple-path transmission in communication. The simulation and offshore test results verified the effectiveness of this method.…”

Section: Introductionmentioning

confidence: 99%

Underwater-Acoustic-OFDM Channel Estimation Based on Deep Learning and Data Augmentation

Guo,

et al. 2024

Electronics

View full text Add to dashboard Cite

In UnderWater-Acoustic-Orthogonal-Frequency-Division-Multiplexing-(UWA-OFDM) communication, the traditional interpolated channel estimation method produces error codes, due to the small number of user pilots, uneven distribution, and complex channel characteristics. In this paper, we propose a novel UWA-channel-estimation method based on Deep Learning (DL). First, based on a small number of channel samples, we used the CWGAN-GP model to generate enhanced classified underwater-acoustic channel samples to have semantic similarity to the real samples and also to present the diversity of the samples. After obtaining the channel sample, the pilot estimation matrix was processed in a similar image way. Here, we extracted the channel features by constructing a convolutional network structure similar to U-Net, weakening the impact of feature information loss. A Channel-Attention-Denoising-(CAD) module was also designed, to further optimize the reconstructed channel information. The simulation results verified the superiority of the proposed algorithm, in terms of Mean Square Error (MSE) and Bit-Error Rate (BER) compared to the existing Least-Squares-(LS), Deep-Neural-Network-(DNN), and ChannelNet algorithms.

show abstract

“…As an emerging field of study, UWA communications and networking has placed a strong emphasis on multiuser communication 1 . Underwater communications (UWC) are necessary for a variety of uses, including remote control in the early warning, national security, off‐shore oil industry, new resource discovery, speech transmission between divers, scientific data collection from ocean‐bottom stations, and mapping the ocean floor for the detection of objects and the discovery of new resources 2,3 . Through the use of acoustic wave transmission, it is possible to have reliable UWC.…”

Section: Introductionmentioning

confidence: 99%

A new optimized least‐square sparse channel estimation scheme for underwater acoustic communication

Kumar

2023

Int J Communication

View full text Add to dashboard Cite

Summary In underwater acoustic (UWA) communication, orthogonal frequency division multiplexing (OFDM) is a promising technology that is highly essential to get channel state information meant for channel estimation (CE). Nevertheless, higher complexity, slower convergence, and poor performance, which degrade the performance estimation, are the limitations of the traditional CE methodologies. Thus, by amalgamating the least square (LS)‐CE algorithm along with polynomial interpolated black widow optimization (PI‐BWO) model, an optimized least square sparse (OLSS) CE algorithm has been proposed to intend for a UWA‐OFDM communication system. Formerly, by utilizing the 2's complement shift left turbo encoding (2CSL‐TE) methodology, the input signal is encoded. After that, the modulated encoded signal is provided for inverse fast Fourier transform (IFFT) operations; subsequently, they are transferred over the UWA channel toward the receiver OFDM. By employing the OLSS methodology, the received OFDM signal's interference‐free region is utilized for sparse CE at the receiver. Regarding symbol error rate (SER), bit error rate (BER), mean square error (MSE), and peak signal‐to‐noise ratio (PSNR), the proposed model's experiential outcome is evaluated and analogized with the other prevailing methodologies. When analogized with the conventional models, the proposed estimation methodologies achieved better performance.

show abstract

Underwater Acoustic Communication Receiver Using Deep Belief Network

Cited by 25 publications

References 35 publications

An improved underwater wireless sensor network communication using Internet of Things and signal to noise ratio analysis

An improved underwater wireless sensor network communication using Internet of Things and signal to noise ratio analysis

Underwater-Acoustic-OFDM Channel Estimation Based on Deep Learning and Data Augmentation

A new optimized least‐square sparse channel estimation scheme for underwater acoustic communication

Contact Info

Product

Resources

About