Guangdong University of Technology

Dingfei Ma

Yi Fang

Liang Lv

Pingping Chen

Bo Nie

Yurong Wang

Xiaomin Li

A coding method based on multiple-mode orthogonal frequency division multiplexing with index modulation (MM-OFDM-IM) is provided. A coded bit sequence is divided into an index-layer sequence and a symbol-layer sequence. According to the index-layer sequence and the symbol-layer sequence, a plurality of constellation modes respectively corresponding to the plurality of subcarriers and which one of a plurality of constellation symbols respectively corresponding to the plurality of constellation modes is carried by each of the plurality of subcarriers are determined. A constellation mode permutation corresponding to each of the plurality of subcarriers is in a symmetrical distribution. The coded bit sequence is converted into the plurality of constellation symbols. The plurality of constellation symbols are respectively loaded to the plurality of subcarriers. A coding device based on MM-OFDM-IM is also provided.

Coding method and device based on multiple-mode orthogonal frequency division multiplexing with index modulation (MM-OFDM-IM)

A training method based on an improved protograph neural decoder includes the following steps: a to-be-trained decoding network is constructed based on an initial variable sub-network layer, an initial check sub-network layer and a preset shuffled belief-propagation (BP) sub-network layer; the initial variable sub-network layer, the initial check sub-network layer and the preset shuffled BP sub-network layer are updated and trained by calculating log-likelihood ratio (LLR) based on a preset mean square error loss function and a preset decoder objective function to obtain a target protograph neural decoder; and the preset mean square error loss function is configured to calculate a loss value between output information of the check sub-network layer and the preset shuffled BP sub-network layer. The target protograph neural decoder includes an optimized variable sub-network layer, an optimized check sub-network layer and an optimized shuffled BP sub-network layer. A training device is also provided.

Training method and device based on improved protograph neural decoder

Growing community of inventors

Guangzhou, China

Dingfei Ma