Dongqiu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Dongqiu Zhang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Dandan Huang
Nanjing Normal Univ, Educ Sci Dept, Nanjing 210000, Peoples R China
1 shared publicationDongqiu Zhang
Nanjing Normal Univ, Educ Sci Dept, Nanjing 210000, Peoples R China
1 shared publicationGuangzhi Zhang
Suihua Univ, Informat Engn Dept, Suihua 152000, Peoples R China
1 shared publication- Guangzhi Zhang
Harbin Engineering University
1 shared publication Wenkui Li
Information Engineering Department of Suihua University, Suihua 152000, China
1 shared publication- Wenkui Li
Department of Information Engineering, Suihua University, Suihua, China
1 shared publication
Latest Publications
- 8 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 18 (2) , 872-880
A Network Coding Scheme Transmitting Specific Data and Universal Data Based on Deep Learning
For a wireless sensor network (WSN), we proposed a network coding scheme that adopts a neural network (NN) instead of methods based on Shannon theory, and this scheme can transmit specific data such as images of specific data sets. In further, it also can transmit universal data with the channel code. In the source, the specific data or the code word is sent out to a network performing network coding, where the universal data are encoded into the code word with Reed Solomon code and Polar code. In the intermediate nodes, the network coding based on Shannon theory is replaced with a multilayer perceptron, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In the sink, we trained a NN with the received massage as the input and the original data as the label. The trained NN includes the sublayers, which are the subneural networks in every node. We test the new transmission scheme for some datasets and channel code such as Reed Solomon code in a WSN environment, and it is proven to be effective.
- 8 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 18 (2) , 872-880
A Network Coding Scheme Transmitting Specific Data and Universal Data Based on Deep Learning
For a wireless sensor network (WSN), we proposed a network coding scheme that adopts a neural network (NN) instead of methods based on Shannon theory, and this scheme can transmit specific data such as images of specific data sets. In further, it also can transmit universal data with the channel code. In the source, the specific data or the code word is sent out to a network performing network coding, where the universal data are encoded into the code word with Reed Solomon code and Polar code. In the intermediate nodes, the network coding based on Shannon theory is replaced with a multilayer perceptron, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In the sink, we trained a NN with the received massage as the input and the original data as the label. The trained NN includes the sublayers, which are the subneural networks in every node. We test the new transmission scheme for some datasets and channel code such as Reed Solomon code in a WSN environment, and it is proven to be effective.
- Open Access
- 14 July 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-9
An Improved Math Word Problem (MWP) Model Using Unified Pretrained Language Model (UniLM) for Pretraining
Natural Language Understanding (NLU) and Natural Language Generation (NLG) are the general methods that support machine understanding of text content. They play a very important role in the text information processing system including recommendation and question and answer systems. There are many researches in the field of NLU such as Bag of words, N-Gram, and neural network language model. These models have achieved a good performance in NLU and NLG tasks. However, since they require lots of training data, it is difficult to obtain rich data in practical applications. Thus, pretraining becomes important. This paper proposes a semisupervised way to deal with math word problem (MWP) tasks using unsupervised pretraining and supervised tuning methods, which are based on the Unified pretrained Language Model (UniLM). The proposed model requires fewer training data than traditional models since it uses model parameters of tasks that have been learned before to initialize the model parameters of new tasks. In this way, old knowledge helps new models successfully perform new tasks from old experiences instead of from scratch. Moreover, in order to help the decoder make accurate predictions, we combine the advantages of AR and AE language models to support one-way, sequence-to-sequence, and two-way predictions. Experiments, carried out on MWP tasks with 20,000+ mathematical questions, show that the improved model outperforms the traditional models with a maximum accuracy of 79.57%. The impact of different experiment parameters is also studied in the paper and we found that a wrong arithmetic order leads to incorrect solution expression generation.
- 14 July 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-9
Open AccessAn Improved Math Word Problem (MWP) Model Using Unified Pretrained Language Model (UniLM) for Pretraining
Natural Language Understanding (NLU) and Natural Language Generation (NLG) are the general methods that support machine understanding of text content. They play a very important role in the text information processing system including recommendation and question and answer systems. There are many researches in the field of NLU such as Bag of words, N-Gram, and neural network language model. These models have achieved a good performance in NLU and NLG tasks. However, since they require lots of training data, it is difficult to obtain rich data in practical applications. Thus, pretraining becomes important. This paper proposes a semisupervised way to deal with math word problem (MWP) tasks using unsupervised pretraining and supervised tuning methods, which are based on the Unified pretrained Language Model (UniLM). The proposed model requires fewer training data than traditional models since it uses model parameters of tasks that have been learned before to initialize the model parameters of new tasks. In this way, old knowledge helps new models successfully perform new tasks from old experiences instead of from scratch. Moreover, in order to help the decoder make accurate predictions, we combine the advantages of AR and AE language models to support one-way, sequence-to-sequence, and two-way predictions. Experiments, carried out on MWP tasks with 20,000+ mathematical questions, show that the improved model outperforms the traditional models with a maximum accuracy of 79.57%. The impact of different experiment parameters is also studied in the paper and we found that a wrong arithmetic order leads to incorrect solution expression generation.
- Open Access
- 5 June 2020
- Published by Springer Nature in EURASIP Journal on Wireless Communications and Networking
- Vol. 2020 (1)
Research on correction algorithm of propagation error in wireless sensor network coding
It is very difficult to deal with the problem of error correction in random network coding, especially when the number of errors is more than the min-cut of the network. We combine a small field with rank-metric codes to solve this problem in this paper. With a small finite field, original errors are compressed to propagated errors, and their number is smaller than the min-cut. Rank-metric codes are introduced to correct the propagated errors, while the minimum rank distance of the rank-metric code is hardly influenced by the small field. It is the first time to correct errors more than the min-cut in network coding with our method using a small field. This new error-correcting algorithm is very useful for the environment such as a wireless sensor network where network coding can be applied.
- 5 June 2020
- Published by Springer Nature in EURASIP Journal on Wireless Communications and Networking
- Vol. 2020 (1)
Open AccessResearch on correction algorithm of propagation error in wireless sensor network coding
It is very difficult to deal with the problem of error correction in random network coding, especially when the number of errors is more than the min-cut of the network. We combine a small field with rank-metric codes to solve this problem in this paper. With a small finite field, original errors are compressed to propagated errors, and their number is smaller than the min-cut. Rank-metric codes are introduced to correct the propagated errors, while the minimum rank distance of the rank-metric code is hardly influenced by the small field. It is the first time to correct errors more than the min-cut in network coding with our method using a small field. This new error-correcting algorithm is very useful for the environment such as a wireless sensor network where network coding can be applied.