CN116707712A - Superimposed channel state information feedback method for differential modulation auxiliary parallel branch fusion - Google Patents
Superimposed channel state information feedback method for differential modulation auxiliary parallel branch fusion Download PDFInfo
- Publication number
- CN116707712A CN116707712A CN202310842826.1A CN202310842826A CN116707712A CN 116707712 A CN116707712 A CN 116707712A CN 202310842826 A CN202310842826 A CN 202310842826A CN 116707712 A CN116707712 A CN 116707712A
- Authority
- CN
- China
- Prior art keywords
- csi
- differential
- modulation
- branch
- channel state
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000004927 fusion Effects 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000013507 mapping Methods 0.000 claims abstract description 18
- 238000011084 recovery Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 10
- 238000013139 quantization Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000021615 conjugation Effects 0.000 claims description 2
- 230000005251 gamma ray Effects 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0023—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the signalling
- H04L1/0028—Formatting
- H04L1/0029—Reduction of the amount of signalling, e.g. retention of useful signalling or differential signalling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/69—Spread spectrum techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0023—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the signalling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/26—Systems using multi-frequency codes
- H04L27/2601—Multicarrier modulation systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Digital Transmission Methods That Use Modulated Carrier Waves (AREA)
Abstract
The invention discloses a superposition channel state information feedback method for differential modulation auxiliary parallel branch fusion, which comprises the following steps: the user terminal: and the user performs superposition, mapping and differential modulation on the downlink CSI vector real-valued and quantized and modulated UL-US to obtain a differential modulated signal, and feeds the differential modulated signal back to the base station. Base station end: the received signals are subjected to parallel processing according to the traditional branch and the learning branch and then are fused; and finally, sending the recovery information of the downlink CSI and the initial characteristic of the CSI into a fusion network Fushion_Net to obtain the enhanced recovery precision downlink CSI fused with the two paths of signal characteristics. The invention avoids the sending guidance of the user terminal, thereby saving bandwidth resources, reducing the energy expenditure of the user terminal, having generalization and improving the reconstruction precision of the downlink CSI.
Description
Technical Field
The invention relates to the technical field of machine learning superimposed channel state information feedback, in particular to a superimposed channel state information (CSI, channel State Information) feedback method for parallel branch fusion assisted by differential modulation.
Background
In order to reduce feedback overhead and thus reduce uplink bandwidth resource occupation and User Equipment (UE) end energy consumption, existing methods mainly focus on compressed feedback of downlink CSI. The CSI feedback method based on compressed sensing (CS, compressed sensing) reduces feedback overhead by developing a signal sparse structure. However, the CS-based CSI feedback is based on a sparse downlink CSI assumption under a certain sparse basis, which sometimes does not coincide with the actual one, resulting in a significant degradation of the downlink CSI sparse reconstruction performance. Deep Learning (DL) is applied to the CSI feedback, so that the CSI feedback overhead is effectively reduced, and the feedback precision of the CSI is improved. The DL-based superposition CSI feedback method superimposes downlink CSI on an uplink user data sequence (UL-US, uplink User Data Sequences) and feeds back the downlink CSI to a Base Station (BS) end, thereby avoiding occupation of additional uplink bandwidth resources due to feedback of the downlink CSI and improving spectrum efficiency. Furthermore, in order for the BS to demodulate UL-US, the UE typically needs to send a pilot for uplink channel estimation to the BS, inevitably taking up uplink bandwidth resources and consuming UE energy. Fortunately, the superposition channel state information feedback method of the differential modulation auxiliary parallel branch fusion avoids feedback overhead and guide overhead for uplink channel estimation by a differential mode and a superposition technology, thereby reducing uplink bandwidth resource occupation and saving energy consumption of a UE end. However, differential detection brings about degradation in detection performance, and superimposed signal processing brings about superimposed interference. In order to solve the problem, the invention adopts a traditional parallel architecture of a processing branch and a learning processing branch (based on a DL mode), reduces superposition interference and compensates performance loss caused by differential detection. Unlike the DL processing mode alone, the present invention uses the parallel architecture to alleviate the problem of generalization difficulty in DL processing by using the traditional processing branches; meanwhile, the learning processing branch is used for back feeding, so that the defects of the traditional processing branch in inhibiting superposition interference and compensating for differential detection are overcome. Therefore, the method of the invention combines the traditional processing branch and the learning processing branch (based on DL mode), thereby improving the reconstruction precision of the downlink CSI, improving the UL-US detection performance and simultaneously having DL generalization.
Disclosure of Invention
The invention aims to provide a superposition channel state information feedback method for fusing differential modulation auxiliary parallel branches, which saves uplink bandwidth resources, reduces energy consumption of a user end and improves reconstruction accuracy of downlink CSI (channel state information) compared with the prior CSI feedback for uplink pilot channel estimation.
The superimposed channel state information feedback method for the differential modulation auxiliary parallel branch circuit fusion comprises the following steps:
and (3) user terminal processing:
s1, the regulated UL-USWith the bit stream form CSI w epsilon {0,1}, after real valued, quantized and spread spectrum P×1 Overlapping and sequentially carrying out mapping treatment and differential modulation to obtain differential modulated signals +.>And fed back to the base station.
The real value is to make the downlink CSI vectorReal-valued Wei real-valued CSI information>
The quantization is toPerforming a-bit quantization to obtain real and imaginary bit stream information m E {0,1} 2aN×1 ;
The spreading refers to spreading matrixObtaining a spread spectrum signal w equal to d by the formula w=qm with m;
the differential modulation is to s= [ s ] 1 ,s 2 ,...,s p ] T According to the rulesDifferential modulation is performed and x is discarded 0 =1, resulting in a differential modulation signal +.>
The mapping process further comprises the sub-steps of:
s11, according to the modulation order gamma adopted by the element digital modulation in UL-USd 1 Obtaining the modulation order gamma of the element mappable symbols in the superimposed signal (d+w) 2 The method comprises the following steps: gamma ray 2 =γ 1 +1;
S12, mapping each element in the superimposed signal (d+w) into gamma 2 Modulation symbols of order, forming digital modulation symbols of order 1 higher than d modulation order
Base station end processing:
the base station end processes the received signals in parallel according to the traditional processing branch and the learning processing branch and then fuses the processed signals;
s2, a traditional processing branch:
s21, the base station end receives the received signalPerforming word-by-word Fu Chafen demodulation and inverse mapping to recover bit stream form CSI->And modulated UL-US->
S22, willPerforming despreading and dequantization to obtain downlink CSI recovery information->
The received signal r is represented by the formula r=x.sup.h UL Obtained by +n, whereinIndicating the equivalent of the uplink channel(s),representing additive noise;
the word-by-word Fu Chafen demodulation is performed by solving forObtaining a differential demodulation signal wherein ,/>Representing an i-th decision value; r is (r) i 、r i-1 Respectively representing the i-th element and the i-1 th element in r; s is(s) t Representing the constellation set of digital modulation symbols at (gamma + 1) order +.>In (a) trial constellation point values, superscript indicates conjugation, and ++>Expressed in the collection->Is selected to maximize { t ,Re[·]Representing the real part;
s3, learning processing branches: inputting the received signal into the learning branchNetwork Info_Net to obtain CSI initial characteristics
Step S3 comprises the following sub-steps:
s31, constructing a data set { r, h } label Training the learning branch network Inform_Net to obtain network parameters of the learning branch network Inform_Net;
s32, training labelThe downlink CSI vector h is obtained by real valued, namely:
h label =[Re(h 1 ),Im(h 1 ),...,Re(h N ),Im(h N )] T
s33, inputting r into a learning branch network Info_Net to obtain CSI initial characteristics during online operationThe specific process can be expressed as follows:
wherein ,fInfe (. Cndot.) represents a network learning operation, Θ Infe Representing the network parameters of Enh-CsiNet.
S4, willAnd->Sending the signals into a fusion network Fushion_Net to obtain the downlink CSI (channel state information) with enhanced recovery accuracy and fused two paths of signal characteristics>
The step S4 of the method for feeding back the superimposed channel state information of the differential modulation auxiliary parallel branch fusion comprises the following substeps:
s41, the despreading process refers to using the same spreading matrix as the user sideThrough->Obtaining despread CSI in the form of a bit stream>
S42, the dequantization processing refers to a pair ofPerforming a-bit dequantization to obtain initial feature +.>
S43, the fusion network Fushion_Net is obtained by constructing a data set { h } T ,h label Training Fushion_Net to obtain network parameters, h T For offline training of Fushion_NetTraining data of (a), and when running online, h T Inputting the fusion network Fushion_Net to obtain final downlink CSI +.>The specific process can be expressed as follows:
wherein ,fFus (. Cndot.) represents a network learning operation, Θ Fus Representing the network parameters of the fushion_net.
The invention utilizes differential modulation and superposition technology to carry out CSI feedback, extracts parallel network Info_Net and fusion network Fushion_Net through light weight characteristics to improve the reconstruction precision of downlink CSI, combines the advantages of quantization coding, digital modulation, mapping phasing and DL technology, feeds back differential modulation signals subjected to differential modulation to a base station through OFDM modulation technology, obtains downlink CSI recovery information by differential demodulation, inverse mapping and digital demodulation and dequantization processing at the base station end, simultaneously utilizes the characteristics to extract parallel network Info_Net to directly extract downlink CSI from a received signal, finally fuses final reconstruction CSI according to the downlink CSI recovery information and the downlink CSI obtained from the characteristics to extract parallel network Info_Net by the fusion network Fushion_Net, and greatly saves uplink bandwidth resources and UE end energy while avoiding transmitting guidance for channel estimation at the UE end and completely avoiding feedback expenditure, and ensures the reconstruction precision of the CSI.
Compared with the existing CSI feedback of the uplink pilot channel estimation, the method and the device have the advantages that uplink bandwidth resources are saved by utilizing the differential coding technology, the energy consumption of a user terminal is reduced, and the reconstruction accuracy of the downlink CSI is improved by utilizing a lightweight neural network.
Drawings
FIG. 1 is a schematic general flow diagram of the present invention;
FIG. 2 is a flow chart of the client according to the present invention;
fig. 3 is a flow diagram of a base station according to the present invention.
Detailed Description
The present invention will be described in detail with reference to the following examples and drawings, but it should be understood that the examples and drawings are only for illustrative purposes and are not intended to limit the scope of the present invention in any way. All reasonable variations and combinations that are included within the scope of the inventive concept fall within the scope of the present invention.
The method for feeding back the superposition channel state information by combining the differential modulation auxiliary parallel branches, as shown in the flow of fig. 1, comprises the following steps:
the client process as shown in fig. 2:
s1, the regulated UL-USWith the bit stream form CSI w epsilon {0,1}, after real valued, quantized and spread spectrum P×1 Overlapping and sequentially carrying out mapping treatment and differential modulation to obtain differential modulated signals +.>And feeding back to the base station;
the base station side processes as shown in fig. 3:
the base station end processes the received signals in parallel according to the traditional processing branch and the learning processing branch and then fuses the processed signals;
s2, a traditional processing branch: base station end receives received signalsPerforming word-by-word Fu Chafen demodulation, inverse mapping, despreading and dequantization processing to recover modulated UL-US +.>Downstream CSI recovery information +.>
S3, learning processing branches: inputting the received signal into learning branch network Info_Net to obtain CSI initial characteristic
S4, willAnd->Together send into fusion network FushionNet to obtain the enhanced recovery accuracy downlink CSI (channel state information) fused with the two paths of signal characteristics>
The specific procedure of this embodiment is as follows:
a1, mapping the superimposed signal (d+w) to a digital modulation symbol of order 1 higher than the d modulation order is as follows: taking QPSK modulation (modulation order 2) for UL-US as an example, assume modulated UL-USLength 8, d is:
quantized spread bit stream form csi= [1,1,1,1,0,0,0,0], then (d+w) is:
mapping (d+w) to 8PSK (modulation order 3) digital modulation symbol by mapping processThe method comprises the following steps:
a2, performing differential modulation on the digital modulation symbol s to obtain a differential modulation signal x, which is as follows: taking QPSK modulation (modulation order γ=2), 4-bit quantization (a=4) as an example, assume that the mapped digital modulation symbol s length p= 8,s is:
according to the rule of differential modulationThe differential modulation signal x can be calculated as:
a3, the base station end performs differential demodulation mode on the received signal r by character to obtain a differential demodulation signalOne specific example of which is as follows:
assume that a signal is receivedDemodulation rule +.>Differential demodulation is performed on the received signal r to obtain a differential demodulated signal +.>To->The first element->For example, the specific solving process is as follows:
constellation setCo-inclusion->Four constellation points, first constellation point +.>Substituted into Re s t ·r i * r i-1 ]The result obtained is 1;
substituting the second constellation points to the fourth constellation points in sequence to obtain the results of 0,0 and-1 respectively;
the maximum result when substituting the first constellation point is obtained
Sequentially solving the residual elements in r according to the same method, and differentially demodulating the signalsThe final representation can be:
it should be noted that the embodiments described herein are for the purpose of aiding the reader in understanding the practice of the invention, and it should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (6)
1. The superimposed channel state information feedback method for the differential modulation auxiliary parallel branch circuit fusion is characterized by comprising the following steps of:
and (3) user terminal processing:
s1, the regulated UL-USWith the bit stream form CSIw epsilon {0,1}, after real valued, quantized and spread P×1 Overlapping and sequentially carrying out mapping treatment and differential modulation to obtain differential modulated signals +.>And feeding back to the base station;
base station end processing:
the base station end processes the received signals in parallel according to the traditional processing branch and the learning processing branch and then fuses the processed signals;
s2, a traditional processing branch:
s3, learning processing branches: inputting the received signal into learning branch network Info_Net to obtain CSI initial characteristic
S4, willAnd->Sending the signals into a fusion network Fushion_Net to obtain the downlink CSI (channel state information) with enhanced recovery accuracy and fused two paths of signal characteristics>
2. The method for feeding back superimposed channel state information by combining differential modulation auxiliary parallel branches according to claim 1, wherein in step S1, said real valued is to feed down CSI vectorsReal valued as real valued CSI information
The quantization is toPerforming a-bit quantization to obtain real and imaginary bit stream information m E {0,1} 2aN×1 ;
The spreading refers to spreading matrixObtaining a spread spectrum signal w equal to d by the formula w=qm with m;
the differential modulation is to s= [ s ] 1 ,s 2 ,...,s p ] T According to the rulesDifferential modulation is performed and x is discarded 0 =1, resulting in a differential modulation signal +.>
3. The method for feeding back superimposed channel state information by combining differential modulation auxiliary parallel branches according to claim 2, wherein the mapping process in step S1 further comprises the sub-steps of:
s11, according to the modulation order gamma adopted by the element digital modulation in UL-USd 1 Obtaining the modulation order gamma of the element mappable symbols in the superimposed signal (d+w) 2 The method comprises the following steps: gamma ray 2 =γ 1 +1;
S12, mapping each element in the superimposed signal (d+w) into gamma 2 Modulation symbols of order, forming digital modulation symbols of order 1 higher than d modulation order
4. A method for feedback of superimposed channel state information for differential modulation assisted parallel branch fusion according to claim 3, wherein S2 comprises the sub-steps of:
s21, a base station end receives a received signalPerforming word-by-word Fu Chafen demodulation and inverse mapping to recover bit stream form CSIAnd modulated UL-US->
S22, willPerforming despreading and dequantization to obtain downlink CSI recovery information->
The word-by-word Fu Chafen demodulation is performed by solving forObtaining differential demodulation signal->
wherein ,representing an i-th decision value; r is (r) i 、r i-1 Respectively representing the i-th element and the i-1 th element in r; s is(s) t Representing the constellation set of digital modulation symbols at (gamma + 1) order +.>In (a) trial constellation point values, superscript indicates conjugation, and ++>Expressed in the collection->Is selected to maximize { t ,Re[·]Representing the real part;
the inverse mapping refers to the inverse process of mapping processingIs restored to-> and />
5. The method for feeding back superimposed channel state information for differential modulation assisted parallel branch fusion according to claim 4, wherein step S3 comprises the sub-steps of:
s31, constructing a data set { r, h } label Training the learning branch network Inform_Net to obtain network parameters of the learning branch network Inform_Net;
s32, training labelThe downlink CSI vector h is obtained by real valued;
s33, inputting r into a learning branch network Info_Net to obtain CSI initial characteristics during online operation
6. The method for feeding back superimposed channel state information for differential modulation assisted parallel branch fusion according to claim 5, wherein step S4 comprises the sub-steps of:
s41, the despreading process refers to using the same spreading matrix as the user sideThrough->Obtaining despread CSI in the form of a bit stream>
S42, the dequantization processing refers to a pair ofPerforming a-bit dequantization to obtain initial characteristics of CSI
S43, the fusion network Fushion_Net is obtained by constructing a data set { h } T ,h label Training Fushion_Net to obtain network parameters, h T For offline training of Fushion_NetIs included in the training data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310842826.1A CN116707712A (en) | 2023-07-10 | 2023-07-10 | Superimposed channel state information feedback method for differential modulation auxiliary parallel branch fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310842826.1A CN116707712A (en) | 2023-07-10 | 2023-07-10 | Superimposed channel state information feedback method for differential modulation auxiliary parallel branch fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116707712A true CN116707712A (en) | 2023-09-05 |
Family
ID=87835853
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310842826.1A Pending CN116707712A (en) | 2023-07-10 | 2023-07-10 | Superimposed channel state information feedback method for differential modulation auxiliary parallel branch fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116707712A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117336125A (en) * | 2023-11-28 | 2024-01-02 | 西华大学 | Decision feedback channel estimation method and device in differential OTFS system |
-
2023
- 2023-07-10 CN CN202310842826.1A patent/CN116707712A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117336125A (en) * | 2023-11-28 | 2024-01-02 | 西华大学 | Decision feedback channel estimation method and device in differential OTFS system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP1699195B1 (en) | Channel estimation method operable to cancel a dominant disturber signal from a received signal | |
CN116707712A (en) | Superimposed channel state information feedback method for differential modulation auxiliary parallel branch fusion | |
US20070201577A1 (en) | Apparatus and method for signal reception in multiple input multiple output (MIMO) communication system | |
CN112564757A (en) | Deep learning 1-bit compression superposition channel state information feedback method | |
CN111368979A (en) | PAPR suppression method for MIMO-OFDM system | |
US20170170991A1 (en) | Communication terminal and method for receiving data | |
CN113726376B (en) | 1bit compression superposition CSI feedback method based on feature extraction and mutual-difference fusion | |
CN114499601B (en) | Large-scale MIMO signal detection method based on deep learning | |
CN109617655B (en) | Polarization code wireless data secure transmission method based on random scrambling code assistance | |
WO2010146774A1 (en) | Wireless communication apparatus, wireless communication system and communication method | |
Sun et al. | Deep joint source-channel coding for wireless image transmission with semantic importance | |
CN115189742A (en) | Differential coding assisted machine learning channel state information feedback method and device | |
CN115250217B (en) | OFDM system channel estimation method and device assisted by differential coding and neural network | |
US20090097532A1 (en) | Feedback of decoded data characteristics | |
US7890059B2 (en) | Successive interference cancellation in code division multiple access system using variable interferer weights | |
EP2342876B1 (en) | Decentralized and cooperative data reception through base stations | |
CN111212001B (en) | Joint channel estimation method for translation special QPSK system | |
CN113259277B (en) | Channel estimation method for 5G uplink PUSCH receiver | |
CN114900267B (en) | Optimization method for eliminating abrupt change of frequency domain data symbol power by NR-5G | |
US20100246634A9 (en) | Acquisition of spreading factors (SFS) of multiple transmitted signals in code division multiple access system | |
CN112910519B (en) | Large-scale MIMO base station receiving end signal recovery method based on residual error homogeneous sequencing technology | |
EP1113585A2 (en) | Method for radio reception in a mobile station and mobile station | |
WO2023272653A1 (en) | Channel estimation compensation with constellation | |
CN114938320A (en) | Self-interference elimination method and system in 5G dual-connection scene | |
CN116933066A (en) | Wireless signal single-channel blind source separation method and device based on deep neural network |
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 |