[go: up one dir, main page]

CN110826703A - A Signal Sequence Detection Method of Communication System Based on Cooperative Time-varying Bidirectional Recurrent Neural Network - Google Patents

A Signal Sequence Detection Method of Communication System Based on Cooperative Time-varying Bidirectional Recurrent Neural Network Download PDF

Info

Publication number
CN110826703A
CN110826703A CN201911265807.7A CN201911265807A CN110826703A CN 110826703 A CN110826703 A CN 110826703A CN 201911265807 A CN201911265807 A CN 201911265807A CN 110826703 A CN110826703 A CN 110826703A
Authority
CN
China
Prior art keywords
neural network
time
layer
sequence
network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201911265807.7A
Other languages
Chinese (zh)
Other versions
CN110826703B (en
Inventor
孙黎
王宇威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Publication of CN110826703A publication Critical patent/CN110826703A/en
Application granted granted Critical
Publication of CN110826703B publication Critical patent/CN110826703B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00—Arrangements affording multiple use of the transmission path
    • H04L5/003—Arrangements for allocating sub-channels of the transmission path

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses a communication system signal sequence detection method based on a cooperative time-varying bidirectional recurrent neural network, which comprises the following steps: preprocessing a signal sequence received by a receiving end of a communication system, inputting the preprocessed data sequence into a cooperative time-varying bidirectional cyclic neural network, and performing soft decision through network output. The preceding and following layers of the hidden layer of the cooperative time-varying bidirectional cyclic neural network are in a cooperative structure, and time-varying weights are used for combination when the preceding and following networks of the last layer of the neural network are combined to obtain the final output of the neural network.

Description

一种基于协作式时变双向循环神经网络的通信系统信号序列 检测方法A Signal Sequence of Communication System Based on Cooperative Time-varying Bidirectional Recurrent Neural Network Detection method

技术领域technical field

本发明涉及通信系统信号检测技术领域，特别涉及一种基于协作式时变双向循环神经网络的通信系统信号序列检测方法。The invention relates to the technical field of communication system signal detection, in particular to a communication system signal sequence detection method based on a cooperative time-varying bidirectional cyclic neural network.

背景技术Background technique

在现代的数字通信系统中，信号检测是一个重要的组成部分。信号在发送端经过编码，调制之后发送出去，经过信道之后来到接收端，这时候接收端收到的信号是经过噪声干扰或者码间串扰的信号，所以就需要使用信号检测来对接收到的信号进行判决。在传统的无线通信中，利用的是电磁波来传输信息，传播机理可以由麦克斯韦方程组进行描述，所以可以使用数学公式建立信道的概率统计模型，进而可以依据信道的概率统计模型来设计信号检测算法。但是在一些新型的通信系统，例如水声通信、分子通信等，或者在信道状况比较复杂的传统系统中，就难以通过建立有效的描述信号传播的模型。所以在这些情况下，使用一种不依赖于信道的概率统计模型的方法来设计信号检测方法就具有重要的实际意义。In modern digital communication systems, signal detection is an important part. The signal is encoded and modulated at the transmitting end and sent out. After passing through the channel, it arrives at the receiving end. At this time, the signal received by the receiving end is a signal that has undergone noise interference or inter-symbol crosstalk, so it is necessary to use signal detection to detect the received signal. signal for decision. In traditional wireless communication, electromagnetic waves are used to transmit information, and the propagation mechanism can be described by Maxwell's equations, so mathematical formulas can be used to establish the probability and statistics model of the channel, and then the signal detection algorithm can be designed according to the probability and statistics model of the channel. . However, in some new communication systems, such as underwater acoustic communication, molecular communication, etc., or in traditional systems with complex channel conditions, it is difficult to establish an effective model to describe signal propagation. So in these cases, it is of great practical significance to use a method that does not depend on the probability and statistical model of the channel to design the signal detection method.

机器学习当中的深度学习比较适用于在难以进行信道建模的通信系统中的信号检测问题。深度学习的优势在于其隐藏层可以在一定的误差范围内拟合任何的函数，具有巨大的灵活性。而现有的神经网络结构并不完全适用通信系统信号检测问题，所以提出一种基于协作式时变双向循环神经网络的通信系统信号检测检测方法就具有重要意义。Deep learning in machine learning is more suitable for signal detection problems in communication systems where channel modeling is difficult. The advantage of deep learning is that its hidden layer can fit any function within a certain error range, which has great flexibility. However, the existing neural network structure is not completely suitable for the problem of signal detection in communication systems, so it is of great significance to propose a method for signal detection and detection in communication systems based on cooperative time-varying bidirectional recurrent neural network.

发明内容SUMMARY OF THE INVENTION

为了克服上述现有技术的不足，本发明的目的在于提供一种基于协作式时变双向循环神经网络的通信系统信号序列检测方法，该方法可以提高信号检测的正确率。In order to overcome the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a signal sequence detection method of a communication system based on a cooperative time-varying bidirectional cyclic neural network, which can improve the accuracy of signal detection.

为了实现上述目的，本发明采用的技术方案是：In order to achieve the above object, the technical scheme adopted in the present invention is:

一种基于协作式时变双向循环神经网络的通信系统信号序列检测方法，该通信系统的发送信号的有限集合为Γ＝{s1,s2,...,sm}，有s1,s2,...,sm共m种符号，通信系统发送端在k时刻的发送符号为xk，定义在该时刻的发送信号为pk＝[1(xk＝s1),1(xk＝s2),...,1(xk＝sm)]，其中1(·)代表指示函数，在pk向量中，只有一个元素为1，其余的元素都为零，发送序列的长度为K，则发送序列为PK＝[p1,p2,...,pK]T，通信系统的接收端在k时刻接收到的接收信号为yk＝[uk1,uk2,...,ukl]，该信号为一个长度为l的向量，则信号序列为YK＝[y1,y2,...,yK]T，其特征在于，该信号序列检测方法包括以下步骤：A method for detecting signal sequence of communication system based on cooperative time-varying bidirectional cyclic neural network, the limited set of transmitted signals of the communication system is Γ={s 1 , s 2 ,...,s m }, with s 1 , s 2 , . _ _ (x k =s 2 ),...,1(x k =s m )], where 1(·) represents the indicator function, in the p k vector, only one element is 1, and the rest are zero, The length of the transmission sequence is K, then the transmission sequence is P K =[p 1 ,p 2 ,...,p K ] T , and the received signal received by the receiving end of the communication system at time k is y k =[u k1 ,u k2 ,...,u kl ], the signal is a vector of length l, then the signal sequence is Y K =[y 1 ,y 2 ,...,y K ] T , characterized in that the The signal sequence detection method includes the following steps:

1)对接收端接收到的序列进行去均值的预处理，首先计算出信号序列的平均值：1) Preprocess the sequence received by the receiver to remove the mean value, and first calculate the average value of the signal sequence:

然后让接收序列中的每一个数据都减去该平均值得到数据序列IK：Then subtract this average from each data in the received sequence to get the data sequence I K :

Figure BDA0002312804800000022
Figure BDA0002312804800000022

其中IK＝[i1,i2,...,iK]T，

Figure BDA0002312804800000023
where I K =[i 1 ,i 2 ,...,i K ] T ,
Figure BDA0002312804800000023

2)把数据序列IK输入一个N层的使用协作式时变双向循环神经网络结构的神经网络中，该网络的输出层的神经元个数为m，网络中的神经元是RNN，GRU，LSTM或者其余循环神经网络神经元其中的一种，神经网络在k时刻的输出为ok＝[zk1,zk2,...,zkm]，其中zki代表的是在第k时刻的发送信号为si的概率，则神经网络输出的序列为OK＝[o1,o2,...,oK]T；2) Input the data sequence I K into an N-layer neural network using a cooperative time-varying bidirectional cyclic neural network structure, the number of neurons in the output layer of the network is m, and the neurons in the network are RNN, GRU, LSTM or one of the other recurrent neural network neurons, the output of the neural network at time k is ok = [z k1 , z k2 ,..., z km ], where z ki represents the time at the kth time. The probability that the transmitted signal is s i , then the sequence output by the neural network is OK = [o 1 , o 2 ,..., o K ] T ;

3)把神经网络的输出序列OK进行软判决，即对于k时刻输出ok＝[zk1,zk2,...,zkm]来说，先找出

Figure BDA0002312804800000031
则发送信号判定为
Figure BDA0002312804800000032
则发送信号序列的判定为
Figure BDA0002312804800000033
完成序列检测。3) Soft decision is made on the output sequence OK of the neural network, that is, for the output at time k = [z k1 , z k2 ,..., z km ], first find out
Figure BDA0002312804800000031
Then the sent signal is determined as
Figure BDA0002312804800000032
Then the determination of the transmitted signal sequence is
Figure BDA0002312804800000033
Complete sequence detection.

所述的步骤2)中所述的协作式时变双向循环神经网络结构包括以下部分：The cooperative time-varying bidirectional recurrent neural network structure described in the step 2) includes the following parts:

1)该神经网络的输入序列为IK＝[i1,i2,...,iK]T，其中对于k时刻，神经网络的输入为则神经网络的输入层的神经元个数为l；1) The input sequence of the neural network is I K =[i 1 , i 2 ,...,i K ] T , where for k time, the input of the neural network is Then the number of neurons in the input layer of the neural network is l;

2)神经网络的隐含层为N，在神经网络隐含层前后层之间为协作式结构，在第k时刻，网络的第n层向n+1层传播的方式为：2) The hidden layer of the neural network is N, and there is a cooperative structure between the hidden layers before and after the neural network. At the kth moment, the nth layer of the network propagates to the n+1 layer in the following way:

Figure BDA0002312804800000035
Figure BDA0002312804800000035

Figure BDA0002312804800000036
Figure BDA0002312804800000036

其中

Figure BDA0002312804800000037
为在第k时刻第n+1层的前向网络的输入，
Figure BDA0002312804800000038
为在第k时刻第n+1层的后向网络的输入，
Figure BDA0002312804800000039
为第k时刻第n层的前向网络的输出，
Figure BDA00023128048000000310
为第k时刻第n层的后向网络的输出，
Figure BDA00023128048000000311
为把第n层的输出组合起来的权值，m为协作长度，代表的是在第n层向n+1层传播的时候使用了第n层的当前时刻以及前m-1个时刻的输出进行协作；in
Figure BDA0002312804800000037
is the input of the forward network of the n+1th layer at the kth time,
Figure BDA0002312804800000038
is the input of the backward network of the n+1th layer at the kth time,
Figure BDA0002312804800000039
is the output of the forward network of the nth layer at the kth time,
Figure BDA00023128048000000310
is the output of the backward network of the nth layer at the kth time,
Figure BDA00023128048000000311
For the weight of combining the outputs of the nth layer, m is the cooperation length, which means that the current moment of the nth layer and the output of the previous m-1 moments are used when the nth layer is propagated to the n+1 layer. to collaborate;

3)在神经网络的最后一层的前后向网络进行合并的时候使用时变的权值来合并，得到神经网络最后的输出，在第k时刻神经网络的输出ok为：3) When the forward and backward networks of the last layer of the neural network are merged, the time-varying weights are used to merge to obtain the final output of the neural network. The output o k of the neural network at the kth moment is:

Figure BDA00023128048000000312
Figure BDA00023128048000000312

其中

Figure BDA00023128048000000313
表示最后一层的前向网络的输出，
Figure BDA00023128048000000314
表示最后一层的后向网络的输出，[·,·]表示把两个输出拼接在一起，W(k)表示时变的权值；in
Figure BDA00023128048000000313
represents the output of the forward network of the last layer,
Figure BDA00023128048000000314
Represents the output of the backward network of the last layer, [·,·] indicates that the two outputs are spliced together, and W(k) indicates the time-varying weight;

所述的时变权值的获取方法为，构建一个全连接神经网络，把时间k作为输入，输出时变权值W(k)：The method for obtaining the time-varying weights is to construct a fully connected neural network, take time k as the input, and output the time-varying weights W(k):

W(k)＝NNfully(k) (4)W(k)=NN fully (k) (4)

其中NNfully(·)为全连接神经网络代表的函数。where NN fully ( ) is the function represented by the fully connected neural network.

本发明的有益效果：Beneficial effects of the present invention:

本发明所述的一种基于协作式时变双向循环神经网络的通信系统信号序列检测方法，在对接收信号进行了预处理之后输入协作式时变双向循环神经网络，在神经网络前后层之间为协作式结构，令前后向网络在往后层传播的过程中互相协作，以及在神经网络的最后一层的前后向网络进行合并的时候考虑到了前后向网络判决可信度的时变性，使用时变的权值来合并，提高了信号检测的准确性。The method for detecting a signal sequence of a communication system based on a cooperative time-varying two-way cyclic neural network according to the present invention, after preprocessing the received signal, the cooperative time-varying two-way cyclic neural network is input, and between the front and rear layers of the neural network It is a cooperative structure, so that the forward and backward networks cooperate with each other in the process of propagation to the back layer, and when the forward and backward networks of the last layer of the neural network are merged, the time-varying decision reliability of the forward and backward networks is taken into account. The time-varying weights are combined to improve the accuracy of signal detection.

附图说明Description of drawings

图1为协作式时变双向循环神经网络结构示意图。Figure 1 is a schematic diagram of the structure of a cooperative time-varying bidirectional recurrent neural network.

具体实施方式Detailed ways

下面结合附图对本发明作进一步详细说明。The present invention will be further described in detail below in conjunction with the accompanying drawings.

本发明所述一种基于协作式时变双向循环神经网络的通信系统信号序列检测方法，该通信系统的发送信号的有限集合为Γ＝{s1,s2,...,sm}，通信系统发送端在k时刻的发送信号为pk＝[1(xk＝s1),1(xk＝s2),...,1(xk＝sm)]，其中1(·)代表指示函数，在pk向量中，只有一个元素为1，其余的元素都为零，发送序列的长度为K，则发送序列为PK＝[p1,p2,...,pK]T。通信系统的接收端在k时刻接收到的接收信号为yk＝[uk1,uk2,...,ukl]，则信号序列为YK＝[y1,y2,...,yK]T，其特征在于，该信号序列检测方法包括以下步骤：A method for detecting a signal sequence of a communication system based on a cooperative time-varying bidirectional cyclic neural network according to the present invention, the limited set of the transmitted signals of the communication system is Γ={s 1 , s 2 ,...,s m }, The transmission signal of the transmitting end of the communication system at time k is p k =[1(x k =s 1 ),1(x k =s 2 ),...,1(x k =s m )], where 1( ) represents the indicator function. In the p k vector, only one element is 1, and the rest of the elements are zero. The length of the transmission sequence is K, then the transmission sequence is P K =[p 1 ,p 2 ,..., p K ] T . The received signal received by the receiving end of the communication system at time k is y k =[u k1 ,u k2 ,...,u kl ], then the signal sequence is Y K =[y 1 ,y 2 ,..., y K ] T , it is characterised in that the signal sequence detection method comprises the following steps:

1)对接收端接收到的序列进行去均值的预处理，首先计算出信号序列的平均值：1) Preprocess the sequence received by the receiver to remove the mean value, and first calculate the average value of the signal sequence:

Figure BDA0002312804800000051
Figure BDA0002312804800000051

然后让接收序列中的每一个数据都减去该平均值得到数据序列IK：Then subtract this average from each data in the received sequence to get the data sequence I K :

Figure BDA0002312804800000052
Figure BDA0002312804800000052

其中IK＝[i1,i2,...,iK]T，

Figure BDA0002312804800000053
where I K =[i 1 ,i 2 ,...,i K ] T ,
Figure BDA0002312804800000053

2)把数据序列IK输入一个N层的使用协作式时变双向循环神经网络结构的神经网络中，其中网络中的神经元可以是RNN，GRU，LSTM或者其余循环神经网络神经元。神经网络在k时刻的输出为ok＝[zk1,zk2,...,zkm]，其中zki代表的是在第k时刻的发送信号为si的概率，则神经网络输出的序列为OK＝[o1,o2,...,oK]T。2) Input the data sequence I K into an N-layer neural network using a cooperative time-varying bidirectional recurrent neural network structure, where the neurons in the network can be RNN, GRU, LSTM or other recurrent neural network neurons. The output of the neural network at time k is ok =[z k1 ,z k2 ,...,z km ], where z ki represents the probability that the transmitted signal at time k is si , then the output of the neural network is The sequence is O K =[o 1 ,o 2 ,...,o K ] T .

3)把神经网络的输出序列OK进行软判决，即对于k时刻输出ok＝[zk1,zk2,...,zkm]来说，先找出则发送信号判定为

Figure BDA0002312804800000055
则发送信号序列的判定为
Figure BDA0002312804800000056
完成序列检测。3) Soft decision is made on the output sequence OK of the neural network, that is, for the output at time k = [z k1 , z k2 ,..., z km ], first find out Then the sent signal is determined as
Figure BDA0002312804800000055
Then the determination of the transmitted signal sequence is
Figure BDA0002312804800000056
Complete sequence detection.

上述步骤2)中所述的协作式时变双向循环神经网络结构包括以下部分：The cooperative time-varying bidirectional recurrent neural network structure described in the above step 2) includes the following parts:

1)该神经网络的输入序列为IK＝[i1,i2,...,iK]T，其中对于k时刻，神经网络的输入为

Figure BDA0002312804800000057
则神经网络的输入层的神经元个数为l；1) The input sequence of the neural network is I K =[i 1 , i 2 ,...,i K ] T , where for k time, the input of the neural network is
Figure BDA0002312804800000057
Then the number of neurons in the input layer of the neural network is l;

2)神经网络的隐含层为N，在神经网络隐含层前后层之间为协作式结构，在第k时刻，网络的第n层向n+1层传播的方式为：2) The hidden layer of the neural network is N, and there is a cooperative structure between the hidden layers before and after the neural network. At the kth moment, the nth layer of the network propagates to the n+1 layer in the following way:

Figure BDA0002312804800000058
Figure BDA0002312804800000058

Figure BDA0002312804800000059
Figure BDA0002312804800000059

其中

Figure BDA00023128048000000510
为在第k时刻第n+1层的前向网络的输入，
Figure BDA00023128048000000511
为在第k时刻第n+1层的后向网络的输入，
Figure BDA00023128048000000512
为第k时刻第n层的前向网络的输出，
Figure BDA00023128048000000513
为第k时刻第n层的后向网络的输出，
Figure BDA00023128048000000514
为把第n层的输出组合起来的权值，m为协作长度，代表的是在第n层向n+1层传播的时候使用了第n层的当前时刻以及前m-1个时刻的输出进行协作；in
Figure BDA00023128048000000510
is the input of the forward network of the n+1th layer at the kth time,
Figure BDA00023128048000000511
is the input of the backward network of the n+1th layer at the kth time,
Figure BDA00023128048000000512
is the output of the forward network of the nth layer at the kth time,
Figure BDA00023128048000000513
is the output of the backward network of the nth layer at the kth time,
Figure BDA00023128048000000514
For the weight of combining the outputs of the nth layer, m is the cooperation length, which means that the current moment of the nth layer and the output of the previous m-1 moments are used when the nth layer is propagated to the n+1 layer. to collaborate;

3)在神经网络的最后一层的前后向网络进行合并的时候使用时变的权值来合并，得到神经网络最后的输出，在第k时刻神经网络的输出ok为：3) When the forward and backward networks of the last layer of the neural network are merged, the time-varying weights are used to merge to obtain the final output of the neural network. The output o k of the neural network at the kth moment is:

Figure BDA0002312804800000061
Figure BDA0002312804800000061

其中

Figure BDA0002312804800000062
表示最后一层的前向网络的输出，
Figure BDA0002312804800000063
表示最后一层的后向网络的输出，[·,·]表示把两个输出拼接在一起，W(k)表示时变的权值；in
Figure BDA0002312804800000062
represents the output of the forward network of the last layer,
Figure BDA0002312804800000063
Represents the output of the backward network of the last layer, [·,·] indicates that the two outputs are spliced together, and W(k) indicates the time-varying weight;

时变权值的获取方法为，构建一个全连接神经网络，把时间k作为输入，输出时变权值W(k)：The time-varying weight is obtained by constructing a fully connected neural network, taking time k as the input, and outputting the time-varying weight W(k):

W(k)＝NNfully(k) (4)W(k)=NN fully (k) (4)

其中NNfully(·)为全连接神经网络代表的函数。where NN fully ( ) is the function represented by the fully connected neural network.

Claims (3)

1. A communication system signal sequence detection method based on a cooperative time-varying bidirectional cyclic neural network is characterized in that a finite set of transmission signals of the communication system is gamma { s ═ s1,s2,...,smIs of s1,s2,...,smM symbols are total, and the transmitting symbol of a transmitting end of the communication system at the time k is xkDefining the transmitted signal at that time as pk＝[1(xk＝s1),1(xk＝s2),...,1(xk＝sm)]Where 1 (-) represents the indicator function, at pkIn a vector, there is only one elementThe element is 1, the rest elements are zero, the length of the transmission sequence is K, and the transmission sequence is PK＝[p1,p2,...,pK]TThe receiving end of the communication system receives the received signal at the time k as yk＝[uk1,uk2,...,ukl]The signal is a vector of length l, and the signal sequence is YK＝[y1,y2,...,yK]TThe signal sequence detection method is characterized by comprising the following steps:
1) preprocessing the mean value of the sequence received by a receiving end, firstly calculating the mean value of the signal sequence:
then, the average value is subtracted from each data in the received sequence to obtain the data sequence IK：
Figure FDA0002312804790000012
Wherein IK＝[i1,i2,...,iK]T，
Figure FDA0002312804790000013
2) Data sequence IKInputting into a N-layer neural network using cooperative time-varying bidirectional recurrent neural network structure, the number of neurons in the output layer of the network is m, the neuron in the network is one of RNN, GRU, LSTM or other recurrent neural network neurons, and the output of the neural network at time k is ok＝[zk1,zk2,...,zkm]Wherein z iskiTypically, the transmitted signal at time k is siThe probability of (c) is then the sequence of the neural network output is OK＝[o1,o2,...,oK]T；
3) Output sequence O of neural networkKMaking soft decisions, i.e. outputting o for time kk＝[zk1,zk2,...,zkm]To say, first, find out
Figure FDA0002312804790000014
The transmission signal is determined as
Figure FDA0002312804790000015
The decision to transmit a signal sequence
Figure FDA0002312804790000021
And completing sequence detection.
2. The method for detecting the signal sequence of the communication system based on the cooperative time-varying bidirectional cyclic neural network as claimed in claim 1, wherein the cooperative time-varying bidirectional cyclic neural network structure in step 2) comprises the following parts:
1) the input sequence of the neural network is IK＝[i1,i2,...,iK]TWherein for time k, the input to the neural network isThe number of the neurons of the input layer of the neural network is l;
2) the hidden layer of the neural network is N, a cooperative structure is formed between the front layer and the rear layer of the hidden layer of the neural network, and at the kth moment, the mode of the propagation from the nth layer of the network to the N +1 layer is as follows:
Figure FDA0002312804790000023
Figure FDA0002312804790000024
wherein
Figure FDA0002312804790000025
Is the input to the forward network of layer n +1 at time k,
Figure FDA0002312804790000026
for the input to the backward network of layer n +1 at time k,
Figure FDA0002312804790000027
is the output of the forward network of the nth layer at time k,
Figure FDA0002312804790000028
the output of the backward network of the nth layer at the kth time,in order to combine the outputs of the nth layer, m is the cooperation length, which represents that the outputs of the current time and the previous m-1 times of the nth layer are used for cooperation when the nth layer is propagated to the n +1 layer;
3) merging the backward and forward networks of the last layer of the neural network by using a time-varying weight to obtain the final output of the neural network, and outputting o of the neural network at the kth momentkComprises the following steps:
Figure FDA00023128047900000210
wherein
Figure FDA00023128047900000211
Represents the output of the forward network of the last layer,output of backward network representing the last layer, [, ]]Indicating that the two outputs are spliced together, w (k) represents a time-varying weight.
3. The method for detecting the signal sequence of the communication system based on the cooperative time-varying bidirectional recurrent neural network as claimed in claim 1, wherein the time-varying weight is obtained by constructing a fully-connected neural network, inputting time k, and outputting a time-varying weight w (k):
W(k)＝NNfully(k) (4)
wherein NNfully(. cndot.) is a function represented by a fully-connected neural network.
CN201911265807.7A 2019-06-06 2019-12-11 Communication signal detection method based on cooperative time-varying bidirectional recurrent neural network Active CN110826703B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910492246 2019-06-06
CN2019104922468 2019-06-06

Publications (2)

Publication Number Publication Date
CN110826703A true CN110826703A (en) 2020-02-21
CN110826703B CN110826703B (en) 2022-06-07

Family

ID=69544670

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911265807.7A Active CN110826703B (en) 2019-06-06 2019-12-11 Communication signal detection method based on cooperative time-varying bidirectional recurrent neural network

Country Status (1)

Country Link
CN (1) CN110826703B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111711585A (en) * 2020-06-11 2020-09-25 西安交通大学 A real-time signal sequence detection method based on deep learning
CN113300904A (en) * 2021-04-14 2021-08-24 浙江工业大学 Mobile molecular communication bidirectional network performance analysis method based on amplification forwarding and analog network coding strategies

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106647808A (en) * 2017-01-05 2017-05-10 南宁市健佳网络科技有限公司 Method for searching AUVs and allocating and controlling capturing tasks based on fuzzy control algorithm
CN109525369A (en) * 2018-11-28 2019-03-26 电子科技大学 A kind of channel coding type blind-identification method based on Recognition with Recurrent Neural Network
CN109670580A (en) * 2018-12-21 2019-04-23 浙江工业大学 A kind of data recovery method based on time series
US20190138887A1 (en) * 2017-11-01 2019-05-09 Board Of Trustees Of Michigan State University Systems, methods, and media for gated recurrent neural networks with reduced parameter gating signals and/or memory-cell units

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106647808A (en) * 2017-01-05 2017-05-10 南宁市健佳网络科技有限公司 Method for searching AUVs and allocating and controlling capturing tasks based on fuzzy control algorithm
US20190138887A1 (en) * 2017-11-01 2019-05-09 Board Of Trustees Of Michigan State University Systems, methods, and media for gated recurrent neural networks with reduced parameter gating signals and/or memory-cell units
CN109525369A (en) * 2018-11-28 2019-03-26 电子科技大学 A kind of channel coding type blind-identification method based on Recognition with Recurrent Neural Network
CN109670580A (en) * 2018-12-21 2019-04-23 浙江工业大学 A kind of data recovery method based on time series

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MARK EISEN 等: "Learning Optimal Resource Allocations in Wireless Systems", 《IEEE TRANSACTIONS ON SIGNAL PROCESSING》 *
杨文臣 等: "多智能体强化学习在城市交通网络信号控制方法中的应用综述", 《计算机应用研究》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111711585A (en) * 2020-06-11 2020-09-25 西安交通大学 A real-time signal sequence detection method based on deep learning
CN111711585B (en) * 2020-06-11 2021-06-22 西安交通大学 A real-time signal sequence detection method based on deep learning
CN113300904A (en) * 2021-04-14 2021-08-24 浙江工业大学 Mobile molecular communication bidirectional network performance analysis method based on amplification forwarding and analog network coding strategies

Also Published As

Publication number Publication date
CN110826703B (en) 2022-06-07

Similar Documents

Publication Publication Date Title
CN110289927B (en) Channel Simulation Implementation Method Based on Conditional Generative Adversarial Networks
CN115438708A (en) Classification and identification method based on convolutional neural network and multi-mode fusion
CN112422208B (en) A signal detection method based on adversarial learning under unknown channel model
CN110061946B (en) Depth signal detection method for high-speed rail
CN110826703A (en) A Signal Sequence Detection Method of Communication System Based on Cooperative Time-varying Bidirectional Recurrent Neural Network
CN113822363B (en) Convolutional neural network time delay estimation method based on quadratic rational kernel function
CN114070415A (en) Optical fiber nonlinear equalization method and system
CN112468230B (en) Wireless ultraviolet light scattering channel estimation method based on deep learning
CN113381828A (en) Sparse code multiple access random channel modeling method based on condition generation countermeasure network
CN109618288B (en) Wireless sensor network distance measurement system and method based on deep convolutional neural network
CN110188837A (en) A Method of MVB Network Fault Diagnosis Based on Fuzzy Neural
CN114285715A (en) Nonlinear equalization method based on bidirectional GRU-conditional random field
Zhang et al. Deep learning based underwater acoustic OFDM receiver with joint channel estimation and signal detection
CN115984146A (en) Global consistency-based marine chlorophyll concentration image completion method and network
CN101651643A (en) Blind equalization method for wavelet neural network based on space diversity
CN111711585B (en) A real-time signal sequence detection method based on deep learning
CN115733548A (en) Nonlinear Damage Compensation System and Method Based on Neural Network Equalizer
CN120128277A (en) A joint optimization method of delay and error in underwater acoustic communication with dynamic symbol interval based on reinforcement learning
CN116488970B (en) Balancing method for high-speed optical communication system
CN119561806A (en) Channel compensation method, device, electronic device and storage medium
CN118200103A (en) A method for detecting OFDM signals
CN113608264B (en) Joint pre-stack elastic inversion parameter and depth network target inversion method
CN111683026B (en) CMA-SAE-based underwater acoustic channel signal processing method and system
CN117639838A (en) Spread spectrum underwater sound signal demodulation method based on deep neural network
CN116418633A (en) Depth Expanded Underwater Acoustic Channel Estimation Method Based on Sparse and Low-rank Features

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant