Channel Noise Optimization of Polar Codes Decoding Based on a Convolutional Neural Network

Yan, Ming; Lou, Xingrui; Wang, Yan

doi:10.1155/2021/1434347

Cited by 11 publications

(5 citation statements)

References 33 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the attention problem, the GCT is introduced in the GRSU-L module to obtain the most attentional part of the image before performing feature extraction. It is set before each convolutional layer of GRSU-L so that the module can extract more attentional features 33 . The regions with higher attention weights are often the main part of the image, and the use of gated attention enables the model to segment the main part better.…”

Section: Proposed Methodsmentioning

confidence: 99%

SU2GE-Net: a saliency-based approach for non-specific class foreground segmentation

Liu

Cai

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Salient object detection is vital for non-specific class subject segmentation in computer vision applications. However, accurately segmenting foreground subjects with complex backgrounds and intricate boundaries remains a challenge for existing methods. To address these limitations, our study proposes SU2GE-Net, which introduces several novel improvements. We replace the traditional CNN-based backbone with the transformer-based Swin-TransformerV2, known for its effectiveness in capturing long-range dependencies and rich contextual information. To tackle under and over-attention phenomena, we introduce Gated Channel Transformation (GCT). Furthermore, we adopted an edge-based loss (Edge Loss) for network training to capture spatial-wise structural details. Additionally, we propose Training-only Augmentation Loss (TTA Loss) to enhance spatial stability using augmented data. Our method is evaluated using six common datasets, achieving an impressive $$F_{\beta }$$ F β score of 0.883 on DUTS-TE. Compared with other models, SU2GE-Net demonstrates excellent performance in various segmentation scenarios.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

SU2GE-Net: a saliency-based approach for non-specific class foreground segmentation

Liu

Cai

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…As mentioned in the introduction, most deep learning methods are based on the sEMG signals. The mainstream methods can be classified into three categories: CNN models [ 11 , 12 , 13 , 14 , 15 , 16 , 17 ], RNN models [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ], and ANN models [ 25 , 26 , 27 , 28 ]. The single-layer CNN proposed by Zia ur Rehman M accomplished the classification task of 7 gestures [ 12 ], which pioneered the application of CNN models to gesture recognition.…”

Section: Related Workmentioning

confidence: 99%

“…Many studies have proposed machine learning or deep learning algorithms to implement Myo-based gesture recognition tasks. Among them, support vector machine (SVM) [ 1 , 2 , 3 , 4 ], k-nearest neighbor (KNN) [ 5 , 6 , 7 , 8 , 9 ], decision tree (DT) [ 10 ], convolutional neural network (CNN) [ 11 , 12 , 13 , 14 , 15 , 16 , 17 ], recurrent neural network (RNN) [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ], and artificial neural networks (ANN) [ 25 , 26 , 27 , 28 , 29 , 30 ] are the most popular algorithms with good recognition accuracy; however, there are still some challenges in this field of research. First, most studies build their datasets for specific application scenarios; these datasets involve mostly less than 10 gesture actions, and there is a lack of publicly available datasets for more classification tasks.…”

Section: Introductionmentioning

confidence: 99%

Multi-Category Gesture Recognition Modeling Based on sEMG and IMU Signals

Jiang

Song

Zhang

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Gesture recognition based on wearable devices is one of the vital components of human–computer interaction systems. Compared with skeleton-based recognition in computer vision, gesture recognition using wearable sensors has attracted wide attention for its robustness and convenience. Recently, many studies have proposed deep learning methods based on surface electromyography (sEMG) signals for gesture classification; however, most of the existing datasets are built for surface EMG signals, and there is a lack of datasets for multi-category gestures. Due to model limitations and inadequate classification data, the recognition accuracy of these methods cannot satisfy multi-gesture interaction scenarios. In this paper, a multi-category dataset containing 20 gestures is recorded with the help of a wearable device that can acquire surface electromyographic and inertial (IMU) signals. Various two-stream deep learning models are established and improved further. The basic convolutional neural network (CNN), recurrent neural network (RNN), and Transformer models are experimented on with our dataset as the classifier. The CNN and the RNN models’ test accuracy is over 95%; however, the Transformer model has a lower test accuracy of 71.68%. After further improvements, the CNN model is introduced into the residual network and augmented to the CNN-Res model, achieving 98.24% accuracy; moreover, it has the shortest training and testing time. Then, after combining the RNN model and the CNN-Res model, the long short term memory (LSTM)-Res model and gate recurrent unit (GRU)-Res model achieve the highest classification accuracy of 99.67% and 99.49%, respectively. Finally, the fusion of the Transformer model and the CNN model enables the Transformer-CNN model to be constructed. Such improvement dramatically boosts the performance of the Transformer module, increasing the recognition accuracy from 71.86% to 98.96%.

show abstract

“…On the other hand, some studies have introduced the idea of lowdensity parity-check (LDPC) codes for reference and used the belief propagation (BP) algorithm to enhance the performance of polar codes [6,7]. In addition, the latest popular technologies, such as deep learning, are also used in polar codes [8,9]. However, deep learning technology is often combined with BP decoding algorithm, so this paper will not introduce deep learning technology in detail.…”

Section: Introductionmentioning

confidence: 99%

A latency‐reduced SC flip decoding algorithm for polar codes

2022

View full text Add to dashboard Cite

The successive cancellation flip (SC Flip) decoding algorithm was recently suggested for decoding polar codes, which could improve the performance of the frame error rate (FER). The performance of the SC Flip (SCF) decoding algorithm is strong, and its computational complexity tends to be the same as that of the SC decoder at medium to high signal-tonoise ratios (SNRs). However, the decoding latency of the SCF decoding algorithm is large. In this paper, a new method for detecting whether or not the flipped bit is correct is proposed. The proposed method makes a decision according to the changing log likelihood ratio (LLR) value caused by the flipped bit to ensure that the decoding process can be terminated in advance and the decoding latency is reduced. The simulation results show that the proposed Latency-Reduced SCF decoding algorithm can decrease computational complexity and decoding latency, while also achieving similar decoding performance compared to its counterpart.

show abstract

Channel Noise Optimization of Polar Codes Decoding Based on a Convolutional Neural Network

Cited by 11 publications

References 33 publications

SU2GE-Net: a saliency-based approach for non-specific class foreground segmentation

SU2GE-Net: a saliency-based approach for non-specific class foreground segmentation

Multi-Category Gesture Recognition Modeling Based on sEMG and IMU Signals

A latency‐reduced SC flip decoding algorithm for polar codes

Contact Info

Product

Resources

About