CN106656426B - A kind of communication means with information transmission weight - Google Patents
A kind of communication means with information transmission weight Download PDFInfo
- Publication number
- CN106656426B CN106656426B CN201710054593.3A CN201710054593A CN106656426B CN 106656426 B CN106656426 B CN 106656426B CN 201710054593 A CN201710054593 A CN 201710054593A CN 106656426 B CN106656426 B CN 106656426B
- Authority
- CN
- China
- Prior art keywords
- group
- data code
- domain
- judgement
- stream
- 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.)
- Active
Links
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
- H04L1/0006—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format
-
- 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
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0045—Arrangements at the receiver end
- H04L1/0052—Realisations of complexity reduction techniques, e.g. pipelining or use of look-up tables
- H04L1/0053—Realisations of complexity reduction techniques, e.g. pipelining or use of look-up tables specially adapted for power saving
-
- 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
- H04L1/0078—Avoidance of errors by organising the transmitted data in a format specifically designed to deal with errors, e.g. location
- H04L1/0079—Formats for control data
-
- 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
- H04L1/24—Testing correct operation
- H04L1/245—Testing correct operation by using the properties of transmission codes
- H04L1/246—Testing correct operation by using the properties of transmission codes two-level transmission codes, e.g. binary
Abstract
The present invention relates to a kind of communication means with information transmission weight, by the serial data bit stream of multiple groups transmitting to be modulated according to weighted coefficient distribution modulation domain；Secondly generated data stream is formed after serial data bit stream being handled by corresponding modulating domain；Then generated data stream is subjected to modulate emission, is received from channel finally by two kinds of distinct methods and restores merging data code stream.The present invention can enable the higher data code flow of information weight weight occupy wider modulation domain under limited channel resources, from making it have more preferably signal-to-noise ratio.
Description
Technical field
The present invention relates to the communications field, especially a kind of communication means with information transmission weight.
Background technique
In communication applications various information have different importance, Conventional communication techniques often to the importance of information not
Add differentiation, and uses impartial transmission.It is since all information equalizations are transmitted, then important in channel there are in the case where noise jamming
The loss of information will greatly reduce communication quality.
Summary of the invention
In view of this, the purpose of the present invention is to propose to a kind of communication means with information transmission weight, it is existing to overcome
Defect present in technology.
The present invention is realized using following scheme: a kind of communication means with information transmission weight, comprising the following steps:
Step S1: by the serial data bit stream S of n group transmitting to be modulated1(t),S2(t),...,Sn(t), according to every group of string
Row data code flow is corresponding and is used to measure the weighted coefficient distribution modulation domain of data information importance；
Step S2: a generated data stream is formed after n group serial data bit stream is carried out numerical value processing according to corresponding modulating domain；
Step S3: the generated data stream is modulated, is concurrently incident upon in channel；
Step S4: it is received from channel and restores the merging data code stream and n group serial data bit stream.
In an embodiment of the present invention, the modulation domain that every group of serial data bit stream is distributed is directly proportional to its weight coefficient,
And weight coefficient is bigger, the modulation domain distributed is bigger.
In an embodiment of the present invention, in step S1, have such as between the modulation domain that the serial data bit stream is distributed
Lower relationship:
(1) the sum of modulation domain of each group serial data bit stream is no more than the total modulation domain M of systemt；
(2) n group serial data bit stream S1(t),S2(t),...,Sn(t) by weight coefficient from small to large arrange, it is full
Sufficient j > i, then serial data bit stream Sj(t) weight coefficient AjGreater than serial data bit stream Si(t) weight coefficient Ai；It is the smallest
Weight coefficient is A1=1；
(3) jth group serial data bit stream Sj(t) weight coefficient AjFor less than AjAll weight coefficient (Aj-1:A1)
Summation adds a surplus kj, kjGreater than 1；
(4) jth group serial data bit stream Sj(t) modulation domain occupied is its weight coefficient AjWith minimum weighting coefficient A1
Corresponding modulation domain M1Product.
In an embodiment of the present invention, in the step S2, by every group of serial data bit stream instantaneous value and its modulation domain
Numerical value multiplication is carried out, and the results added of multiplication is merged into the generated data stream.
In an embodiment of the present invention, further include following steps in the step S4:
Step S411: current time receives the reception for restoring and being made of n group weight binary data code stream from channel
The numerical value of merging data code stream Cr (t), and remember the weight coefficient of n group data code flow from greatly to small for An>An-1>An-2…>A1；
Step S412: n-th group is set by reception merging data code stream Cr (t) current value and receives data code flow Srn
(t) judgement input Cin, and judgment threshold is arranged are as follows:
P=Mn-h×kn×M1；
Wherein, h is the judgement factor greater than 0 and less than 1；
Step S413: judge current CinWhether numerical value is greater than P；If it is greater, then n-th group is received data code flow Srn(t)
Current value is set as binary value 1, is otherwise binary value 0；
Step S414: judge whether the reduction that current time n group data code flow numerical value is completed, if it is not, then going to step
Otherwise S415 goes to step step S417；
Step S415: the (n+1)th-j of setting, which is organized, receives data code flow Srn+1-j(t) judgement input is Cin=Cin-Srn-j+2(t)
×Mn-j+2；Judgment threshold is arranged are as follows:
P=Mn+1-j-h×kn+1-j×M1；
Step S416: judge current CinWhether P is greater than；If it is greater, then the (n+1)th-j group is enabled to receive data code flow Srn+1-j
(t) current value is binary value 1, is otherwise binary value 0, and go to step S414；
Step S417: the numerical value of merging data code stream Cr (t) subsequent time is obtained, and goes to step S412.
In an embodiment of the present invention, further include following steps in the step S4:
Step S421: it is received from channel and restores merging data code stream Cr(t), Cr(t) by n group weight binary data
Code stream is constituted, and the weight coefficient of n group data code flow is from greatly to small for An>An-1>An-2…>A1；
Step S422: jth group reception data code flow S to be restored is calculatedrj(t) 2 required forn-jA judgement domain；
Step S423: continuously judge Cr(t) whether numerical value is in judgement domain, if in judgement domain, by phase
The S answeredrj(t) value is 1, is otherwise 0.
In an embodiment of the present invention, in the step S422, there are 2n-jA judgement domain, each judgement domain is by adjudicating
Bias PBWith decision range (PL:PH) it is added composition, the decision range in each judgement domain is identical, and adjudicates bias difference.
In an embodiment of the present invention, the lower limit value P of the decision rangeLFor jth group code stream modulation domain MjSubtract h × kj
×M1, h is the judgement factor greater than 0 and less than 1, the ceiling value P of the decision rangeHA is not higher than for all weight coefficientsj's
Modulation domain adds h × k after being addedj×M1；
The judgement bias PBIt is greater than A for all weight coefficientsjModulation domain combination coefficient be 1 or 0 in the case where
Whole linear combinations；
Compared with prior art, the invention has the following beneficial effects: proposed by the present invention with the logical of information transmission weight
Letter mechanism can enable the higher data code flow of information weight weight occupy wider modulation domain under limited channel resources, from making it
With more preferably signal-to-noise ratio.In the higher data code flow of demodulating information weight ratio, the present invention be can be realized for identical receiving end
The more preferably quality of reception；Or in the case where data reception quality is constant, more low-power consumption or less hard is can be used in the present invention
Part expense realizes the reduction of important information.
Detailed description of the invention
Fig. 1 is communication mechanism transmitting terminal schematic diagram in the embodiment of the present invention.
Fig. 2 is the flow diagram of the demodulation method one in the embodiment of the present invention.
Fig. 3 is S in one embodiment of the invention1(t)、S2(t)、S3(t), C (t) and the final output y after frequency modulation(PFM)
(t) waveform.
Fig. 4 is that demodulation method two parses it to obtain Sr in one embodiment of the invention3(t) waveform.
Fig. 5 is that demodulation method two parses it to obtain Sr in one embodiment of the invention2(t) waveform.
Fig. 6 is that demodulation method two parses it to obtain Sr in one embodiment of the invention1(t) waveform.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and embodiments.
As shown in Figure 1, present embodiments providing a kind of communication means with information transmission weight, following step is specifically included
It is rapid:
Step S1: by the serial data bit stream S of n group transmitting to be modulated1(t),S2(t),...,Sn(t), according to every group of string
Row data code flow is corresponding and is used to measure the weighted coefficient distribution modulation domain of data information importance；In the present embodiment, each group
Data code flow information contained importance differs, and carrys out the importance of scaling information using weight coefficient, and by jth group data code flow Sj
(t) weight coefficient having is denoted as Aj；
Step S2: a generated data stream is formed after n group serial data bit stream is carried out numerical value processing according to corresponding modulating domain；
Step S3: the generated data stream is modulated, is concurrently incident upon in channel；
Step S4: it is received from channel and restores the merging data code stream and n group serial data bit stream.
Further, in the present embodiment, the modulation domain that every group of serial data bit stream is distributed is with its weight coefficient at just
Than, and weight coefficient is bigger, the modulation domain distributed is bigger.When being modulated transmitting, data code flow Sj(t) occupied tune
Domain M processedjWith weight coefficient AjIt is directly proportional.
Further, in the present embodiment, have in step S1, between the modulation domain that serial data bit stream is distributed as follows
Relationship:
(1) the sum of modulation domain of each group serial data bit stream is no more than the total modulation domain M of systemt；
(2) n group serial data bit stream S1(t),S2(t),...,Sn(t) by weight coefficient from small to large arrange, it is full
Sufficient j > i, then serial data bit stream Sj(t) weight coefficient AjGreater than serial data bit stream Si(t) weight coefficient Ai；It is the smallest
Weight coefficient is A1=1；
(3) jth group serial data bit stream Sj(t) weight coefficient AjFor less than AjAll weight coefficient (Aj-1:A1)
Summation adds a surplus kj, kjHave to be larger than 1；
(4) modulation domain that jth group serial data bit stream is occupied is its weight coefficient AjWith A1Corresponding lowest modulation domain
M1Product.
Further, in the present embodiment, in step s 2, by every group of serial data bit stream instantaneous value and its modulation domain into
Line number value is multiplied, and the results added of multiplication is merged into the generated data stream.
Further, in the present embodiment, in step s 4, as shown in Fig. 2, providing a kind of demodulation method, including it is as follows
Step:
Step S411: current time receives the reception for restoring and being made of n group weight binary data code stream from channel
The numerical value of merging data code stream Cr (t), and remember the weight coefficient of n group data code flow from greatly to small for An>An-1>An-2…>A1；
Step S412: merging data code stream Cr (t) current value will be received and be set as n-th group reception data code flow Srn(t) sentence
Certainly input CinAnd judgment threshold is arranged are as follows:
P=Mn-h×kn×M1；
Wherein, h is the judgement factor greater than 0 and less than 1；
Step S413: judge current CinWhether numerical value is greater than P；If it is greater, then n-th group is received data code flow Srn(t)
Current value is set as binary value 1, is otherwise binary value 0；
Step S414: judging whether to have restored the current value of the n group data code flow, if it is not, step S415 is then gone to, it is no
Then, step step S417 is gone to；
Step S415: the (n+1)th-j of setting, which is organized, receives data code flow Srn+1-j(t) judgement input is Cin=Cin-Srn-j+2
(t)×Mn-j+2；Judgment threshold is arranged are as follows:
P=Mn+1-j-h×kn+1-j×M1；
Step S416: judge current CinWhether numerical value is greater than P；If it is greater, then the (n+1)th-j group is enabled to receive data code flow
Srn+1-j(t) current value is binary value 1, is otherwise binary value 0, and go to step S414；
Step S417: obtaining the merging data code stream Cr (t) of subsequent time, and goes to step S412.
Further, in the present embodiment, in step s 4, another demodulation method is provided, is included the following steps:
Step S421: it is received from channel and restores reception merging data code stream Cr (t), Cr (t) is by n group weight binary system
Data code flow is constituted, and the weight coefficient of n group data code flow is from greatly to small for An>An-1>An-2…>A1；
Step S422: jth group reception data code flow S to be restored is calculatedrj(t) 2 required forn-jA judgement domain；At this
In embodiment, for 2n-jA judgement domain, each judgement domain is by judgement bias PBWith decision range (PL:PH) it is added composition, often
The decision range in a judgement domain is identical, and adjudicates bias difference；Preferably, decision range lower limit value PLFor jth group code stream tune
Domain M processedjSubtract h × kj×M1, h is the judgement factor greater than 0 and less than 1, decision range ceiling value PHNot for all weight coefficients
Higher than AjModulation domain be added after, add h × kj×M1；Judgement biasing PBIt is greater than A for all weight coefficientsjModulation domain,
Combination coefficient is whole linear combinations in the case where 1 or 0.
Step S423: continuously judge Cr(t) whether numerical value is in judgement domain, if in judgement domain, by phase
Answer the S at momentrj(t) value is 1, is otherwise 0.
In order to allow skilled in the art realises that method proposed by the invention, below with reference to provided by the present invention above-mentioned
It is illustrated in method and specific embodiment.
The following are the communication means provided using invention to realize that 3 groups of binary code datas spread defeated process, and there are 3 groups for note
Binary data code stream S1(t)、S2(t)、S3(t) need to carry out frequency modulation(PFM) transmitting, respective weights Relationship of Coefficients is A1=1, A2
=2.5, A3=7.System uses frequency modulated mode, entire modulation domain width MtFor 80kHz, then the modulation of each group code stream is acquired
Domain is M1=7.62kHz, M2=19.05kHz, M3=53.33kHz.Fig. 3 is S in the present embodiment1(t)、S2(t)、S3(t), merge
Data flow C (t) and after frequency modulation(PFM) final output y (t) waveform.
Y (t) is received demodulation after noisy channel transmits and obtains receiving merging data code stream Cr (t), according to this implementation
Second of demodulation method described in example, parses it to obtain Sr3(t)、Sr2(t) and Sr1(t), respectively such as the institute of Fig. 4,5,6
Show.It can be seen that since 3 groups of code stream weights are different, under identical noise circumstance, the highest Sr of weight3(t) go out without error code
It is existing, the Sr of weight second2(t) there are a small amount of error code and the minimum Sr of weight3(t) bit error rate is very high.
The foregoing is merely presently preferred embodiments of the present invention, all equivalent changes done according to scope of the present invention patent with
Modification, is all covered by the present invention.
Claims (7)
1. a kind of communication means with information transmission weight, it is characterised in that: the following steps are included:
Step S1: by the serial data bit stream S of n group transmitting to be modulated1(t),S2(t),...,Sn(t), according to every group of serial number
The weighted coefficient distribution modulation domain corresponding and for measuring data information importance according to code stream；
Step S2: a generated data code stream is formed after n group serial data bit stream is carried out numerical value processing according to corresponding modulating domain；It will
Every group of serial data bit stream instantaneous value carries out numerical value with its modulation domain and is multiplied, and the results added of multiplication is merged into the synthesis
Data code flow；
Step S3: the generated data code stream is modulated, is concurrently incident upon in channel；
Step S4: it is received from channel and restores the generated data code stream and n group serial data bit stream.
2. a kind of communication means with information transmission weight according to claim 1, it is characterised in that: every group of serial number
The modulation domain distributed according to code stream is directly proportional to its weight coefficient, and weight coefficient is bigger, and the modulation domain distributed is bigger.
3. a kind of communication means with information transmission weight according to claim 1 or 2, it is characterised in that: step S1
In, there is following relationship between the modulation domain that the serial data bit stream is distributed:
(1) the sum of modulation domain of each group serial data bit stream is no more than the total modulation domain M of systemt；
(2) n group serial data bit stream S1(t),S2(t),...,Sn(t) by weight coefficient from small to large arrange, meet j >
I, then serial data bit stream Sj(t) weight coefficient AjGreater than serial data bit stream Si(t) weight coefficient Ai；The smallest weight
Coefficient is A1=1；(3) jth group serial data bit stream Sj(t) weight coefficient AjFor less than AjAll weight coefficient (Aj-1:A1)
Summation adds a surplus kj, kjGreater than 1；
(4) jth group serial data bit stream Sj(t) modulation domain occupied is its weight coefficient AjWith A1Corresponding lowest modulation
Domain M1Product.
4. a kind of communication means with information transmission weight according to claim 3, it is characterised in that: in the step
Further include following steps in S4:
Step S411: current time receives the reception for restoring and being made of n group weight binary data code stream from channel and merges
The numerical value of data code flow Cr (t), and remember the weight coefficient of n group data code flow from greatly to small for An>An-1>An-2…>A1；
Step S412: n-th group is set by reception merging data code stream Cr (t) current value and receives data code flow Srn(t) sentence
Certainly input Cin, and judgment threshold is arranged are as follows:
P=Mn-h×kn×M1；
Wherein, h is the judgement factor greater than 0 and less than 1；MnModulation domain possessed by data code flow is received for n-th group；
Step S413: judge current CinWhether numerical value is greater than P；If it is greater, then n-th group is received data code flow Srn(t) current
Value is set as binary value 1, is otherwise binary value 0；
Step S414: judging whether to have restored the current value of the n group data code flow, if it is not, step S415 is then gone to, otherwise,
Go to step step S417；
Step S415: the (n+1)th-j of setting, which is organized, receives data code flow Srn+1-j(t) judgement input is Cin=Cin-Srn-j+2(t)×
Mn-j+2；Judgment threshold is arranged are as follows:
P=Mn+1-j-h×kn+1-j×M1；
Wherein Mn-j+2The modulation domain for receiving data code flow is organized for the n-th-j+2；Mn+1-jThe modulation for receiving data code flow is organized for the (n+1)th-j
Domain；
Step S416: judge current CinWhether numerical value is greater than P；If it is greater, then the (n+1)th-j group is enabled to receive data code flow Srn+1-j
(t) current value is binary value 1, is otherwise binary value 0, and go to step S414；
Step S417: merging data code stream C is obtainedr(t) numerical value of subsequent time, and go to step S412.
5. a kind of communication means with information transmission weight according to claim 3, it is characterised in that: in the step
Further include following steps in S4:
Step S421: it is received from channel and restores reception merging data code stream Cr (t), Cr (t) is by n group weight binary data
Code stream is constituted, and the weight coefficient of n group data code flow is from greatly to small for An>An-1>An-2…>A1；
Step S422: jth group reception data code flow Sr to be restored is calculatedj(t) 2 required forn-jA judgement domain；
Step S423: continuously judging whether the numerical value of Cr (t) is in judgement domain, if in judgement domain, when will be corresponding
The Sr at quarterj(t) value is 1, is otherwise 0.
6. a kind of communication means with information transmission weight according to claim 5, it is characterised in that: in the step
In S422, there are 2n-jA judgement domain, each judgement domain is by judgement bias PBWith decision range (PL:PH) it is added composition, each
The decision range for adjudicating domain is identical, and adjudicates bias difference.
7. a kind of communication means with information transmission weight according to claim 6, it is characterised in that: the judgement model
Enclose lower limit value PLFor jth group code stream modulation domain MjSubtract h × kj×M1, h is the judgement factor greater than 0 and less than 1, the judgement
Range ceiling value PHA is not higher than for all weight coefficientsjModulation domain be added after add h × kj×M1；
The judgement biases PBIt is greater than A for all weight coefficientsjModulation domain, combination coefficient be 1 or 0 in the case where whole
Linear combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710054593.3A CN106656426B (en) | 2017-01-22 | 2017-01-22 | A kind of communication means with information transmission weight |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710054593.3A CN106656426B (en) | 2017-01-22 | 2017-01-22 | A kind of communication means with information transmission weight |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106656426A CN106656426A (en) | 2017-05-10 |
| CN106656426B true CN106656426B (en) | 2019-09-13 |
Family
ID=58841185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710054593.3A Active CN106656426B (en) | 2017-01-22 | 2017-01-22 | A kind of communication means with information transmission weight |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106656426B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1326624A (en) * | 1998-09-16 | 2001-12-12 | 科学研究公司 | Systems and methods for asynchronous transfer mode and internet protocol |
| CN1741412A (en) * | 2004-08-27 | 2006-03-01 | 清华大学 | Sub-channel distributing method in radio network |
| CN1832613A (en) * | 2006-04-26 | 2006-09-13 | 电子科技大学 | Parallel frequency spectrum distribution method for preventing interference in cognitive radio system |
| CN104113406A (en) * | 2014-08-01 | 2014-10-22 | 黑龙江科技大学 | User bandwidth requirement based OFDMA (Orthogonal Frequency Division Multiple Access) system downlink resource allocation method under imperfect channel state information |
-
2017
- 2017-01-22 CN CN201710054593.3A patent/CN106656426B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1326624A (en) * | 1998-09-16 | 2001-12-12 | 科学研究公司 | Systems and methods for asynchronous transfer mode and internet protocol |
| CN1741412A (en) * | 2004-08-27 | 2006-03-01 | 清华大学 | Sub-channel distributing method in radio network |
| CN1832613A (en) * | 2006-04-26 | 2006-09-13 | 电子科技大学 | Parallel frequency spectrum distribution method for preventing interference in cognitive radio system |
| CN104113406A (en) * | 2014-08-01 | 2014-10-22 | 黑龙江科技大学 | User bandwidth requirement based OFDMA (Orthogonal Frequency Division Multiple Access) system downlink resource allocation method under imperfect channel state information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106656426A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Van Luong et al. | Deep learning-based detector for OFDM-IM | |
| Lee et al. | Graph embedding-based wireless link scheduling with few training samples | |
| Zhang et al. | Overfitting and underfitting analysis for deep learning based end-to-end communication systems | |
| Ye et al. | Channel agnostic end-to-end learning based communication systems with conditional GAN | |
| Lee et al. | Deep power control: Transmit power control scheme based on convolutional neural network | |
| CN108462517B (en) | MIMO link self-adaptive transmission method based on machine learning | |
| McClure et al. | Mass functions for globular cluster main sequences based on CCD photometry and stellar models | |
| US11831474B2 (en) | Methods and circuits for decision-feedback equalization using compensated decision regions | |
| CN110233810B (en) | MSK signal demodulation method based on deep learning under mixed noise | |
| US20090303096A1 (en) | Systems and methods for analog to digital conversion | |
| JP2021536078A (en) | Methods for decryption, computer program products, and devices | |
| Li et al. | Deep learning based end-to-end visible light communication with an in-band channel modeling strategy | |
| CN103916355A (en) | Distribution method for sub carriers in cognitive OFDM network | |
| Guo et al. | An intelligent image agent based on soft-computing techniques for color image processing | |
| Park et al. | Learning how to demodulate from few pilots via meta-learning | |
| CN101641899A (en) | Simplified equalization for correlated channels in OFDMA | |
| Smith et al. | A communication channel density estimating generative adversarial network | |
| Schmitz et al. | A deep learning wireless transceiver with fully learned modulation and synchronization | |
| CN106656426B (en) | A kind of communication means with information transmission weight | |
| CN110278570A (en) | A kind of wireless communication system based on artificial intelligence | |
| Anis et al. | A reframed watermark extraction approach using the ABC algorithm | |
| Chen et al. | Blind nonlinear system identification based on a constrained hybrid genetic algorithm | |
| CN114124223B (en) | Convolutional neural network optical fiber equalizer generation method and system | |
| Amirabadi | A deep learning based solution for imperfect CSI problem in correlated FSO communication channel | |
| CN110414755A (en) | The method and apparatus that a kind of pair of evaluation object is evaluated |
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 |