CN107181494A - A kind of method based on ANN Control emitter mode of operation - Google Patents
A kind of method based on ANN Control emitter mode of operation Download PDFInfo
- Publication number
- CN107181494A CN107181494A CN201710341493.9A CN201710341493A CN107181494A CN 107181494 A CN107181494 A CN 107181494A CN 201710341493 A CN201710341493 A CN 201710341493A CN 107181494 A CN107181494 A CN 107181494A
- Authority
- CN
- China
- Prior art keywords
- emitter
- signal
- neutral net
- input
- control
- 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
Links
Classifications
-
- 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
- H04B1/005—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 adapting radio receivers, transmitters andtransceivers for operation on two or more bands, i.e. frequency ranges
- H04B1/0053—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 adapting radio receivers, transmitters andtransceivers for operation on two or more bands, i.e. frequency ranges with common antenna for more than one band
- H04B1/006—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 adapting radio receivers, transmitters andtransceivers for operation on two or more bands, i.e. frequency ranges with common antenna for more than one band using switches for selecting the desired band
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- H04B1/02—Transmitters
- H04B1/04—Circuits
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0251—Power saving arrangements in terminal devices using monitoring of local events, e.g. events related to user activity
- H04W52/0258—Power saving arrangements in terminal devices using monitoring of local events, e.g. events related to user activity controlling an operation mode according to history or models of usage information, e.g. activity schedule or time of day
-
- 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
- H04B1/02—Transmitters
- H04B1/04—Circuits
- H04B2001/0408—Circuits with power amplifiers
-
- 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
- H04B1/02—Transmitters
- H04B1/04—Circuits
- H04B2001/0491—Circuits with frequency synthesizers, frequency converters or modulators
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (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)
- Transmitters (AREA)
Abstract
A kind of method based on ANN Control emitter mode of operation, is related to electrical communication technology and nerual network technique.The input signal of emitter is used for controlling the mode of operation of emitter by producing different control signals after neural network classification, and wherein control signal includes but is not limited to power control signal, frequency control signal, gain control signal, linearity control signal, data rate control signal, modulation system control signal.The present invention can be classified in the application environment for multi-emitting target by neutral net to input signal, for the mode of operation of each transmitting target adjustment emitter, to reach the purpose of automatic channel switching and energy-conservation.
Description
Technical field
The present invention relates to the communication technology and nerual network technique, particularly relate to a kind of based on ANN Control hair
The method for penetrating machine mode of operation.
Background technology
The communication technology is the important branch of electronic engineering, while being also one of basic subject.Wherein emitter is logical
Indispensable part in letter technology.One emitter will complete modulation, up conversion and power amplification, and the purpose of modulation is that handle will
The analog signal or data signal of transmission become suitable for the signal of transmission, the analog signal referred to as modulated signal to be transmitted.
In the transmitting terminal of communication system, the frequency spectrum shift of baseband signal is called modulating to the process in specific given channel passband.Adjust
It is formed with the modulator approaches such as amplitude modulation, frequency modulation, phase modulation.According to different input signals, the transmitting terminal of emitter need different power,
Different modulator approach, different carrier signals etc..
In general, in the application environment for multi-emitting target, input signal has uncertainty.Different inputs
Signal needs to take different emission modes, can be only achieved the maximization of efficiency of transmission.In order to solve this problem, solution is first had to
The circuit that seeks to certainly identifies different types of input signal, and then emitter is adjusted into corresponding mode of operation.And pass
System circuit is difficult the difference and the mode of operation of adjust automatically emitter of identified input signal, so that the power consumption of whole circuit
Increase and the waste of transmission channel.Therefore, it is necessary to provide a kind of species of energy Intelligent Recognition input signal, and change accordingly
The circuit of emitter mode of operation.
The content of the invention
The present invention in order to solve due to prior art limit cause can not automatic identification input signal and adjust automatically hair
The defect of mode of operation of machine is penetrated there is provided a kind of method based on ANN Control emitter mode of operation, can be reduced
The power consumption of circuit and the utilization rate for lifting channel.
The technical scheme is that:
A kind of method based on ANN Control emitter mode of operation, comprises the following steps:
Step one:The input signal X of emitter by neutral net classify to obtain the emitter input signal X
Classification information;
Step 2:The classification information obtained according to step one produces different control signals, the control signal include but
It is not limited to power control signal, frequency control signal, gain control signal, linearity control signal, data rate control signal, tune
Mode control signal processed;
Step 3:Will be defeated with the control signal of the input signal X and step 2 of identical emitter described in step one generation
Enter to emitter, emitter changes its mode of operation according to the control signal, and in this operating mode to the emitter
Input signal X processing.
Specifically, the course of work of the input signal X in the step one by neural network classification emitter is divided into instruction
Practice stage and working stage;
Training stage:
A, by the input signal X of emitter all samples input neutral net;
B, emitter working condition set Y, the emitter are set up in neutral net according to the input signal X of emitter
The variable in each element in working condition set Y determines according to the input signal X of the emitter, the variable include but
Each element is not limited in power, frequency, gain, the linearity, data transfer rate, modulation system, the emitter working condition set Y
Including one or more variable;
C, neutral net are learnt to a part of sample and adjust network weight matrix W, obtain function f (X), i.e., neural
The output valve of network, the network weight matrix W is function f (X) weighted value;
D, using the remaining sample not learnt as test set, be that function f (X) and target are defeated to neutral net output valve
Go out the emitter working condition set Y set up in i.e. step b to compare, judge whether both errors are less than default precision, if two
Return to step a when person's error is not less than default precision, is less than default precision until neutral net exports the error exported with target,
Network weight matrix W is preserved, training terminates;
Working stage:Input signal X of the network weight matrix W of the neutral net obtained according to the training stage to emitter
Classification, is input to one in the input signal X of the emitter of the neutral net correspondences emitter working condition set Y each time
Individual element.
Specifically, the emitter working condition set Y includes element Y1, element Y2, element Y3, the element Y1 is represented
Emitter working condition is that 2.4GHz, power output are that -20dB, transmitted data rate are 100kbps including working frequency;The member
Plain Y2 represents that emitter working condition is that 400MHz, gain are that 10dB, transmitted data rate are 10kbps including working frequency;It is described
Element Y3 represents that emitter working condition is that 5-6GHz, gain are that 15dB, output IP3 are 10dBm, modulation methods including working frequency
Formula is FSK.
Element in emitter working condition set Y includes the working condition of all emitters, and three above element is only
With reference to.
Specifically, the neutral net is convolutional neural networks.
Specifically, the neural network module is feedforward neural network.
Specifically, the input signal of the emitter is before the neutral net is input to, two choosings are also passed through
One MUX, first register and second register, the data input pin of the alternative MUX
The input signal of emitter is connected, the data of the first data output end output of the alternative MUX are posted by first
The data input pin of neutral net, the number of the second data output end output of the alternative MUX are input to after storage
According to the data input pin by being input to neutral net after the second register, the alternative MUX passes through an enable
Signal controls the first register and the second register, when the enable signal is 0, and the input signal of the emitter passes through two choosings
The first register is input to after one MUX, while the second register is by the signal afferent nerve network of storage, first posts
Storage is filled with the rear enable signal and is changed into 1, and now the input signal of emitter after alternative MUX by being input to
Second register, while the first register replaces the signal afferent nerve network of storage, the first register and the second register
Work, the continual afferent nerve network of input signal of emitter.
Specifically, the neutral net includes Recognition with Recurrent Neural Network and long memory models neutral net in short-term.
Specifically, the frequency control signal is produced by phaselocked loop, the phaselocked loop is connected to the neutral net and hair
Penetrate between machine, the signal in the classification information that the phaselocked loop is exported according to the neutral net on FREQUENCY CONTROL classification changes
The frequency of phaselocked loop, so as to change the working frequency of emitter.
Specifically, the power control signal and the linearity control signal are produced by power amplifier, the power
Amplifier is connected between the neutral net and emitter, the classification that the power amplifier is exported according to the neutral net
Signal in information on Power Control classification and linearity control category changes the power and the linearity of power amplifier, so that
Change the power and the linearity of emitter.
Above phaselocked loop and power amplifier are as the bridge between neutral net and emitter, and correspondence neutral net is produced
Classification information produce control emitter mode of operation control signal.
Neutral net be one based on the 26S Proteasome Structure and Function of biological brain, it is thin with the nerve that network node imitates brain
Born of the same parents, the technology for the level of drive for imitating brain is weighed with network connection.Non-linear, the ambiguity of the effective process problem of technology energy
And uncertainty relationship.The neural network module can be made up of one or more neutral nets, such as the long god of memory models in short-term
Through network (LSTM), Recognition with Recurrent Neural Network (RNN), feedforward neural network (FNN) or convolutional neural networks (CNN).Neutral net
Module realizes that sample during to by the input signal of system based on training is classified using numeral or analog circuit.Transmitting
The classification that machine control module can be divided based on neural network module to input signal produces different control signals, for each
The mode of operation of individual transmitting target adjustment emitter.Transmitter module is believed according to the control of input signal and emitter control module
Number, change one or more performances in power output, working frequency, gain, the linearity and the data transfer rate of emitter.The lock
Phase ring belongs in emitter stage control module the device for controlling frequency, and the power amplifier, which belongs in emitter stage control module, to be controlled
The device of power and the linearity.
Beneficial effects of the present invention are:, can be by neutral net to defeated in the application environment for multi-emitting target
Enter signal to be classified, for the mode of operation of each transmitting target adjustment emitter, to reach automatic channel switching and save
The purpose of energy;The present invention need not be known a priori by the data structure of input signal, and operation is simpler, and compared to prior art energy
The mode of operation of judgement is more;Present invention is particularly suitable for high speed, high integration application environment.
Brief description of the drawings
Fig. 1 is the workflow diagram that the present invention controls emitter mode of operation based on a kind of neural network classification mode;
Fig. 2 is a kind of transmitter circuitry structural representation based on neutral net proposed in the present invention;
Fig. 3 is the transmitter circuitry structural representation based on neutral nets such as CNN/FNN in the embodiment of the present invention 1;
Fig. 4 is the transmitter circuitry structural representation based on RNN/LSTM neutral nets in the embodiment of the present invention 2;
Fig. 5 is that the control PLL adjustment transmitter frequency structure of the emitter based on neutral net in the embodiment of the present invention 3 is shown
It is intended to;
Fig. 6 is that the control of the emitter based on the neutral net PA in the embodiment of the present invention 4 adjusts transmitter power and linear
Spend schematic diagram.
Embodiment
The detailed description that connection with figures is illustrated below is intended to the description as currently preferred embodiment of the invention, and not
The sole mode of the present invention can be implemented by being intended to indicate that.It should be understood that:Identical or of equal value function can be by being intended to be included in the present invention
Spirit and scope in not be the same as Example complete.
As shown in Fig. 2 a kind of transmitter circuitry based on neutral net provided in the embodiment of the present invention, including nerve net
Network module, emitter control module and transmitter module.Input signal can directly input transmitter module, can also pass through nerve net
Emitter stage module is input to after network module, wherein the data for the input signal for passing through neural network module are not changed, nerve
Mixed-media network modules mixed-media is classified input signal, and based on it is sub-category by emitter control module adjust emitter work shape
State and mode of operation.
Below in conjunction with the accompanying drawings and embodiment, technical scheme is described in detail.
Embodiment 1
It is illustrated in figure 3 the neural based on CNN (convolutional neural networks) or FNN (fuzzy neural network) of the present embodiment proposition
The transmitter circuitry structure chart of network, including an alternative MUX, the first register, the second register, a CNN
Or FNN neural network modules, emitter control module and transmitter module.When starting input signal, alternative multi-path choice
Device enables the first register, and input signal is stored in into the first register, after the first register is filled with, alternative MUX
The second register is enabled, input signal is stored in the second register, while the signal parallel afferent nerve of the first register storage
Network.After the second register is filled with, alternative MUX enables the first register, and input signal deposit first is deposited
Device, while the signal parallel afferent nerve network that the second register is stored.First register and the second register alternation,
The continual afferent nerve network of input signal.Neutral net obtains network weight after learning to incoming input signal
Value W.Under network weight weight values W, identical input signal can realize the classification to signal, and be sent out based on sub-category pass through of institute
Working condition and mode of operation that machine control module adjusts emitter are penetrated, changes the power output, working frequency, increasing of emitter
One or more performances in benefit, the linearity and data transfer rate.
Embodiment 2
Be as shown in Figure 4 the present embodiment propose based on RNN (Recognition with Recurrent Neural Network), LSTM (the long god of memory models in short-term
Through network) etc. neutral net transmitter circuitry structure chart, including Recognition with Recurrent Neural Network RNN and long memory models nerve net in short-term
Network LSTM etc. neural network module, emitter stage control module and transmitter module.The direct afferent nerve network of input signal, god
Network weight weight values W is obtained after learning through network to input signal.Under network weight weight values W, identical input signal can
To realize the classification to signal, and based on sub-category working condition and the work that emitter is adjusted by emitter control module
Pattern, changes one or more performances in power output, working frequency, gain, the linearity and the data transfer rate of emitter.
Embodiment 3
Fig. 5 is the transmitter circuitry structure chart based on neutral net that the present embodiment is proposed, it includes a phaselocked loop
PLL, a neural network module and a transmitter module, wherein phase-locked loop pll belongs to emitter control module, for controlling
The working frequency of emitter.Input signal inputs phase-locked loop pll and neural network module, and neutral net is to input signal
Network weight weight values W is obtained after habit.Under network weight weight values W, identical input signal can realize the letter of neutral net output
Number control phase-locked loop pll frequency, and then change emitter working frequency.Input signal passes through emitter control in the present embodiment
Molding block is input to transmitter module, wherein the data for the input signal for passing through emitter control module are not changed.
Embodiment 4
Fig. 6 is the transmitter circuitry structure chart based on neutral net that the present embodiment is proposed, it includes a power amplification
Module PA, a neural network module and a transmitter module, wherein power amplifier module PA belong to emitter control module,
For controlling the power and the linearity of emitter.Input signal input power amplification module PA and neural network module, nerve net
Network module obtains network weight weight values W after learning to input signal.Under network weight weight values W, identical input signal can
To realize that the signal of neural network module output controls power amplifier module PA power and the linearity, so as to change emitter
Power and the linearity.Input signal is input to transmitter module by emitter control module in the present embodiment, wherein passing through hair
The data for penetrating the input signal of machine control module are not changed.
Claims (9)
1. a kind of method based on ANN Control emitter mode of operation, it is characterised in that comprise the following steps:
Step one:The input signal X of emitter by neutral net classify and obtains point of the emitter input signal X
Category information;
Step 2:Different control signals are produced according to the classification information that step one is obtained, the control signal includes but do not limited
In power control signal, frequency control signal, gain control signal, linearity control signal, data rate control signal, modulation methods
Formula control signal;
Step 3:Control signal with the input signal X and step 2 of identical emitter described in step one generation is input to
Emitter, emitter changes its mode of operation according to the control signal, and in this operating mode to the defeated of the emitter
Enter signal X processing.
2. the method according to claim 1 based on ANN Control emitter mode of operation, it is characterised in that described
The course of work of input signal X in step one by neural network classification emitter is divided into training stage and working stage;
Training stage:
A, by the input signal X of emitter all samples input neutral net;
B, emitter working condition set Y, the emitter work are set up according to the input signal X of emitter in neutral net
The variable in each element in state set Y determines that the variable includes but do not limited according to the input signal X of the emitter
Each element includes in power, frequency, gain, the linearity, data transfer rate, modulation system, the emitter working condition set Y
One or more variable;
C, neutral net are learnt to a part of sample and adjust network weight matrix W, obtain function f (X), i.e. neutral net
Output valve, the network weight matrix W be function f (X) weighted value;
D, using the remaining sample not learnt as test set, be to neutral net output valve function f (X) and target output i.e.
The emitter working condition set Y set up in step b is compared, and judges whether both errors are less than default precision, if both are by mistake
Return to step a when difference is not less than default precision, until the error that neutral net is exported and target is exported is less than default precision, is preserved
Network weight matrix W, training terminates;
Working stage:Input signal X point of the network weight matrix W of the neutral net obtained according to the training stage to emitter
Class, is input to one in the input signal X of the emitter of the neutral net correspondences emitter working condition set Y each time
Element.
3. the method according to claim 2 based on ANN Control emitter mode of operation, it is characterised in that described
Emitter working condition set Y represents that emitter working condition includes including element Y1, element Y2, element Y3, the element Y1
Working frequency is that 2.4GHz, power output are that -20dB, transmitted data rate are 100kbps;The element Y2 represents that emitter works
State is that 400MHz, gain are that 10dB, transmitted data rate are 10kbps including working frequency;The element Y3 represents emitter work
It is that 5-6GHz, gain are that 15dB, output IP3 are that 10dBm, modulation system are FSK to make state including working frequency.
4. the method according to claim 1 based on ANN Control emitter mode of operation, it is characterised in that described
Neutral net is convolutional neural networks.
5. the method according to claim 1 based on ANN Control emitter mode of operation, it is characterised in that described
Neutral net is feedforward neural network.
6. the method based on ANN Control emitter mode of operation according to claim 4 or 5, it is characterised in that
The input signal X of the emitter has passed through alternative MUX, one before the neutral net is input to, also
Individual first register and second register, the data input pin of the alternative MUX connect the input of emitter
Signal, the data of the first data output end output of the alternative MUX after the first register by being input to nerve
The data input pin of network, the data of the second data output end output of the alternative MUX pass through the second register
The data input pin of neutral net is input to afterwards, and the alternative MUX enables signal control first by one and deposited
Device and the second register, when the enable signal is 0, after the input signal X of the emitter is by alternative MUX
The first register is input to, while the second register is by the signal afferent nerve network of storage, the first register is described after being filled with
Enable signal and be changed into 1, now the input signal X of emitter after alternative MUX by being input to the second register, together
When the first register by the signal afferent nerve network of storage, the second register be filled with it is rear it is described enable signal be changed into 0, first posts
Storage and the second register alternation, the continual afferent nerve networks of input signal X of emitter.
7. the method according to claim 1 based on ANN Control emitter mode of operation, it is characterised in that described
Neutral net includes Recognition with Recurrent Neural Network and long memory models neutral net in short-term.
8. the method according to claim 1 based on ANN Control emitter mode of operation, it is characterised in that described
Frequency control signal is produced by phaselocked loop, and the phaselocked loop is connected between the neutral net and emitter, the phaselocked loop
Signal in the classification information exported according to the neutral net on FREQUENCY CONTROL classification changes the frequency of phaselocked loop, so as to change
Become the working frequency of emitter.
9. the method according to claim 1 based on ANN Control emitter mode of operation, it is characterised in that described
Power control signal and the linearity control signal are produced by power amplifier, and the power amplifier is connected to the nerve
Between network and emitter, on Power Control class in the classification information that the power amplifier is exported according to the neutral net
The signal of other and linearity control category changes the power and the linearity of power amplifier, so as to change the power and line of emitter
Property degree.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710341493.9A CN107181494B (en) | 2017-05-16 | 2017-05-16 | A method of based on ANN Control transmitter operating mode |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710341493.9A CN107181494B (en) | 2017-05-16 | 2017-05-16 | A method of based on ANN Control transmitter operating mode |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107181494A true CN107181494A (en) | 2017-09-19 |
CN107181494B CN107181494B (en) | 2019-04-12 |
Family
ID=59831670
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710341493.9A Active CN107181494B (en) | 2017-05-16 | 2017-05-16 | A method of based on ANN Control transmitter operating mode |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107181494B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107769801A (en) * | 2017-10-16 | 2018-03-06 | 成都市深思创芯科技有限公司 | A kind of method of the lifting radio-frequency transmitter intermediate frequency signal to noise ratio based on neutral net |
CN109245861A (en) * | 2018-10-29 | 2019-01-18 | 广州海格通信集团股份有限公司 | A kind of physical layer communication method using deep layer artificial neural network |
WO2020087293A1 (en) * | 2018-10-30 | 2020-05-07 | 华为技术有限公司 | Communication receiver and method for processing signal |
CN111539178A (en) * | 2020-04-26 | 2020-08-14 | 成都市深思创芯科技有限公司 | Chip layout design method and system based on neural network and manufacturing method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1241881A (en) * | 1998-05-27 | 2000-01-19 | 诺基亚流动电话有限公司 | Transmitter |
WO2006006909A1 (en) * | 2004-07-08 | 2006-01-19 | Andrew Corporation | A radio transmitter and a method of operating a radio transmitter |
CN101557206A (en) * | 2000-03-04 | 2009-10-14 | 高通股份有限公司 | Transmitter architecture for communications system |
CN103516371A (en) * | 2013-09-18 | 2014-01-15 | 清华大学 | Configurable wireless transmitter |
-
2017
- 2017-05-16 CN CN201710341493.9A patent/CN107181494B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1241881A (en) * | 1998-05-27 | 2000-01-19 | 诺基亚流动电话有限公司 | Transmitter |
CN101557206A (en) * | 2000-03-04 | 2009-10-14 | 高通股份有限公司 | Transmitter architecture for communications system |
WO2006006909A1 (en) * | 2004-07-08 | 2006-01-19 | Andrew Corporation | A radio transmitter and a method of operating a radio transmitter |
CN103516371A (en) * | 2013-09-18 | 2014-01-15 | 清华大学 | Configurable wireless transmitter |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107769801A (en) * | 2017-10-16 | 2018-03-06 | 成都市深思创芯科技有限公司 | A kind of method of the lifting radio-frequency transmitter intermediate frequency signal to noise ratio based on neutral net |
CN107769801B (en) * | 2017-10-16 | 2019-04-26 | 成都市深思创芯科技有限公司 | A kind of method neural network based promoting radio-frequency transmitter intermediate frequency signal-to-noise ratio |
CN109245861A (en) * | 2018-10-29 | 2019-01-18 | 广州海格通信集团股份有限公司 | A kind of physical layer communication method using deep layer artificial neural network |
WO2020087293A1 (en) * | 2018-10-30 | 2020-05-07 | 华为技术有限公司 | Communication receiver and method for processing signal |
CN111539178A (en) * | 2020-04-26 | 2020-08-14 | 成都市深思创芯科技有限公司 | Chip layout design method and system based on neural network and manufacturing method |
Also Published As
Publication number | Publication date |
---|---|
CN107181494B (en) | 2019-04-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107181494B (en) | A method of based on ANN Control transmitter operating mode | |
CN110855591B (en) | QAM and PSK signal intra-class modulation classification method based on convolutional neural network structure | |
CN112702294B (en) | Modulation recognition method for multi-level feature extraction based on deep learning | |
CN107147600B (en) | Digital modulation signal demodulator based on neural network and demodulation method thereof | |
CN112153616B (en) | Power control method in millimeter wave communication system based on deep learning | |
CN113435247B (en) | Intelligent recognition method, system and terminal for communication interference | |
Wang et al. | A convolutional neural network-based RF fingerprinting identification scheme for mobile phones | |
CN105099553B (en) | A kind of visible light communication method of reseptance and its system based on neuroid | |
CN110535486A (en) | The direct processing formula transceiver of radiofrequency signal based on super surface neural network | |
CN116257750A (en) | Radio frequency fingerprint identification method based on sample enhancement and deep learning | |
CN108566253A (en) | It is a kind of based on the signal recognition method extracted to power spectrum signal fit characteristic | |
CN112153617B (en) | Terminal equipment transmission power control method based on integrated neural network | |
Chen et al. | Abandon locality: Frame-wise embedding aided transformer for automatic modulation recognition | |
CN107769801B (en) | A kind of method neural network based promoting radio-frequency transmitter intermediate frequency signal-to-noise ratio | |
Ya et al. | Modulation recognition of digital signal based on deep auto-ancoder network | |
CN113239788A (en) | Mask R-CNN-based wireless communication modulation mode identification method | |
CN207427100U (en) | A kind of negative-feedback automatic gain control circuit based on neutral net | |
Morehouse et al. | Baseband modulation classification using incremental learning | |
CN115834310B (en) | LGTransformer-based communication signal modulation identification method | |
CN108471624A (en) | The communication pattern switching method and device of wireless body area network | |
CN113572340B (en) | Method and device for predicting and generating control reference signal of envelope tracking power supply | |
CN112564834B (en) | Intelligent cognition and interference method and system for wireless communication system | |
Yin et al. | Short-time modulation classification of complex wireless communication signal based on deep neural network | |
Wong et al. | Distributed automatic modulation classification with compressed data | |
CN108156105B (en) | Narrow-band FSK signal modulation system and method with variable power/frequency |
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 |