CN110312092A - Channel scan device and channel scan method in satellite TV system - Google Patents

Channel scan device and channel scan method in satellite TV system Download PDF

Info

Publication number
CN110312092A
CN110312092A CN201810257862.0A CN201810257862A CN110312092A CN 110312092 A CN110312092 A CN 110312092A CN 201810257862 A CN201810257862 A CN 201810257862A CN 110312092 A CN110312092 A CN 110312092A
Authority
CN
China
Prior art keywords
channel
signal
frequency spectrum
frequency
group
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
Application number
CN201810257862.0A
Other languages
Chinese (zh)
Inventor
童泰来
廖懿颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
MStar Semiconductor Inc Taiwan
Original Assignee
MStar Semiconductor Inc Taiwan
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by MStar Semiconductor Inc Taiwan filed Critical MStar Semiconductor Inc Taiwan
Priority to CN201810257862.0A priority Critical patent/CN110312092A/en
Publication of CN110312092A publication Critical patent/CN110312092A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/438Interfacing the downstream path of the transmission network originating from a server, e.g. retrieving encoded video stream packets from an IP network
    • H04N21/4383Accessing a communication channel
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/44Receiver circuitry for the reception of television signals according to analogue transmission standards
    • H04N5/50Tuning indicators; Automatic tuning control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/20Adaptations for transmission via a GHz frequency band, e.g. via satellite

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Astronomy & Astrophysics (AREA)
  • General Physics & Mathematics (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The present invention provides the channel scan device in a kind of satellite TV system, wherein including a frequency spectrum generation circuit, a memory and an artificial neural networks.The frequency spectrum generation circuit is to carry out a spectrum analysis to receive a TV signal, and to the TV signal, to generate a frequency spectrum.The memory is to store the one group of operational parameter generated in advance according to multiple spectral samples.The artificial neural networks include multiple neuron circuits, and are to impose a neural network computing according to the frequency spectrum of this group of operational parameter to the TV signal, to generate a channel scanning result.This group of operational parameter includes the offset that each neuron circuit uses when carrying out the neural network computing in multiple neuron circuit and one or more weights.

Description

Channel scan device and channel scan method in satellite TV system
Technical field
The present invention is related to satellite television, and especially in satellite TV system be located at user terminal channel scanning technology It is related.
Background technique
With the progress of the communication technology, the development of digital television broadcasting is gradually mature.In addition to base station and cable run, number TV signal also can pass through artificial satellite transmission.The functional block diagram of a satellite TV signal receiving end is presented in Fig. 1.Dish-like day The TV signal that line 110 receives can first be sent to front-end circuit 120 and carry out the processing journey such as preliminary demodulation, low noise frequency reducing Sequence, then through cable 130 be transferred to TV signal receiver 140 (may be cooperate television equipment running set-top box, can also It can be television equipment itself).
According to existing technical specification, the centre frequency and channel size of each channel in DTV satellite broadcasting, for It is all unknown number for receiving end.Therefore, many TV signal receivers 140 can provide channel scanning (channel scan) Function, for found out which television channel for user viewing.In other words, TV signal receiver 140 must be voluntarily The frequency of there may be TV signal is scanned, there are TV signals to detect which frequency.Fig. 2 is presented a channel and sweeps The functional block diagram of imaging apparatus, wherein including a tuner 210, a frequency spectrum generation circuit 220 and a channel decision circuit 230.The function of following each circuit of division.
The frequency for the TV signal that disc-shaped antenna 110 receives is usually more than 3 gigahertz (GHZ)s.By the drop of front-end circuit 120 After frequency is handled, the frequency into the reception signal y of tuner 210 is fallen between 950 megahertzs to 2150 megahertzs.This frequency range Namely there may be the frequency ranges of TV signal.Tuner 210 captures in a small range frequency range from reception signal y every time Signal z gives the analysis of frequency spectrum generation circuit 220.By taking the frequency range that tuner 210 can capture every time is 50 megahertzs as an example, 950 Megahertz it can be divided into the section that 24 sizes are respectively 50 megahertzs to 2150 megahertzs of frequency range, sequentially be subtracted out It gives frequency spectrum generation circuit 220 and generates its frequency spectrum S.
The frequency spectrum S in one section of ideal is presented in Fig. 3 A.The frequency zone of appearance higher-energy is the frequency there are TV signal Section.Frequency spectrum S in Fig. 3 A covers five television channels, corresponds respectively to frequency zone 310~350.It is with frequency zone 340 Example, the centre frequency of this television channel is the corresponding frequency F of central point of frequency zone 340C, and its channel size is frequency The width of rate section 340.In the ideal case, as long as channel decision circuit 230 finds out energy higher than a predetermined threshold level ETH's Frequency zone can directly define the centre frequency and channel size of each television channel.
In practical communication environment, in addition to the noise jamming being subject in transmittance process, front-end circuit 120 it is non-linear (non-linearity) signal reflex caused by effect and cable 130, can all cause the distortion of frequency spectrum S.Fig. 3 B is presented one section Actually issuable frequency spectrum S.The problem of comparing Fig. 3 A and Fig. 3 B can be seen that, distortion spectrum can greatly improve channel scanning Degree of difficulty.More specifically, energy is being found out higher than predetermined threshold level ETHFrequency zone after, channel decision circuit 230 can not The right boundary of section where directly determining television channel accordingly.In order to which various possible distortion phenomenons are accounted for, channel Test condition that decision circuit 230 generally requires in advance to summarize up to tens of kinds (such as spectrum energy rise/fall is oblique Whether rate, spectrum energy go up again in a short time after beginning to decline ... etc.) it is covered one by one used in each possibility in frequency spectrum S Channel boundary on test, the beginning can complete its determine work.In practice, as shown in Fig. 2, existing channel decision circuit 230 generally comprise multiple inspection circuit 230A, for respectively examining frequency spectrum S according to different test conditions.
Summary of the invention
The present invention proposes a kind of new channel scan device and channel scan method.
An embodiment according to the present invention is the channel scan device in a kind of satellite TV system, wherein including a frequency spectrum Generation circuit, a memory and an artificial neural networks.The frequency spectrum generation circuit is to receive a TV signal, and to this TV signal carries out a spectrum analysis, to generate a frequency spectrum.The memory is to be produced in advance to store according to multiple spectral samples One group of raw operational parameter.The artificial neural networks include multiple neuron circuits, and are to according to this group of operational parameter pair The frequency spectrum of the TV signal imposes a neural network computing, to generate a channel scanning result.This group of operational parameter includes should Each neuron circuit uses when carrying out the neural network computing in multiple neuron circuits a offset with one or Multiple weights.
It is according to another embodiment of the present invention the channel scan method in a kind of satellite TV system, cooperation is comprising multiple One artificial neural networks of neuron circuit operate.Firstly, a TV signal is received and carries out a spectrum analysis, to generate one Frequency spectrum.The artificial neural networks are provided to according to one group of operational parameter that multiple spectral samples generate in advance.This group of operation ginseng The offset that number uses when carrying out a neural network computing comprising each neuron circuit in multiple neuron circuit With one or more weights.Then, the frequency spectrum of the TV signal is provided to the artificial neural networks as input signal, by The artificial neural networks impose the neural network computing to the frequency spectrum according to this group of operational parameter, to generate a channel scanning knot Fruit.
It can be further understood by following detailed description of the invention and institute's accompanying drawings about the advantages and spirit of the present invention.
Detailed description of the invention
The functional block diagram of a satellite TV signal receiving end is presented in Fig. 1.
The functional block diagram of an actual channel scanning means is presented in Fig. 2.
The frequency spectrum example in an ideal is presented in Fig. 3 A;An actually issuable frequency spectrum example is presented in Fig. 3 B.
Fig. 4 is the functional block diagram according to the channel scan device in one embodiment of the invention.
Fig. 5 is the schematic diagram of an artificial neural networks with multi-layer structure.
Fig. 6 is channel scanning result example according to the present invention is presented.
Fig. 7 is the flow chart according to the channel scan method in one embodiment of the invention.
Symbol description
110: disc-shaped antenna 120: front-end circuit
130: cable 140: TV signal receiver
210: tuner 220: frequency spectrum generation circuit
230: channel decision circuit 230A: examining circuit
310~350: frequency zone 400: channel scan device
410: tuner 420: frequency spectrum generation circuit
430: artificial neural networks 430A: input layer
430B: hidden layer 430C: output layer
440: memory S71~S74: process step
It should be noted that schema of the invention includes that the functional block diagram of a variety of functional modules associated with each other is presented. The schemas such as this are not thin portion circuit diagram, and connecting line therein is only to indicate signal stream.Between functional element and/or program A variety of interactive relationship are not necessarily intended to reach through the direct electrical connection beginning.In addition, the function of individual component be not necessarily intended to as The mode being painted in schema is distributed, and distributed block is not necessarily intended to the realization of electronic component in a distributed manner.
Specific embodiment
An embodiment according to the present invention is the channel scan device in a kind of satellite TV system, and functional block diagram is It is illustrated in Fig. 4.Channel scan device 400 includes a tuner 410, a frequency spectrum generation circuit 420, an artificial neural networks 430, An and memory 440.In practice, channel scan device 400 can be individually present, and can also be incorporated into various need to defending Star TV signal carries out in the circuit of channel scanning.The function mode of following each circuit of division.
Tuner 410 is to give frequency spectrum generation circuit 420 from the signal z captured in special frequency channel in signal y is received Carry out spectrum analysis.After the completion of the frequency range of there may be TV signal is all analyzed in receiving signal y, it can produce Raw corresponding frequency spectrum S.In practice, receiving signal y can be but be not limited to the front-end circuit institute by being connected to a disc-shaped antenna The TV signal of generation.
As shown in figure 5, artificial neural networks 430 include multiple neuron circuits (being indicated with pie chart sample), and can be by group State is with multilayer (multi-layer) structure.It should be noted that although the nerve that the artificial neural networks in practice are included First quantity and connection complexity are all much higher than that shown in Figure 5, but those skilled in the art introduces through subsequent it is understood that this hair Bright scope is not limited to particular network architecture.For example, artificial neural networks 430 can be used but be not limited to following several nerves The network architecture: the LeNet that is proposed by Yann LeCun, the AlexNet proposed by Alex Krizhevsky et al., by Matthew ZF Net of Zeiler et al. proposition, the GoogLeNet proposed by Szegedy et al., it is proposed by Karen Simonyan et al. VGGNet, and by Kaiming He et al. propose ResNet.
In artificial neural networks 430, in addition to the input layer 430A of the front end and output layer 430C of rearmost end, separately there is string Meet one or more hidden layer 430B between input layer 430A and output layer 430C.Input layer 430A is to received spectrum S, and the operation result of output layer 430C output is that artificial neural networks 430 are responsible for the channel scanning result R generated.Assuming that frequency Spectrum S includes the corresponding energy value of N number of frequency (N be positive integer) greater than one altogether, then input layer 430A can correspondingly by It is designed as comprising N number of neuron circuit, the corresponding energy value of N number of frequency on respective received spectrum.Hidden layer 430B and output layer 430C is to carry out operation as the input signal of this layer with the output signal of preceding layer.In practice, single a neuron circuit The operation of progress can be indicated by mathematicization are as follows:
Wherein symbol xiIndicate i-th of input signal (each neuron circuit each own one of the neuron circuit Or multiple input signals), it is added to input signal xiWeight wiIt is that emulation provides input signal xiNeuron circuit for The influence degree of this neuron circuit;Symbol b indicates the offset (bias) that this neuron circuit itself is contributed;Symbol f is represented One specific non-linear function can use Σ function (sigmoid function), hyperbolic tangent function (tanh in practice Function), or rectification after linear function (rectified linear function) Lai Shixian.
All weight w and offset b of all neuron circuits in hidden layer 430B and output layer 430C can be common It is considered as one group of operational parameter of the use of artificial neural networks 430.In channel scan device 400, this group of operational parameter is basis Multiple spectral samples generate in advance, and are stored in memory 440.More specifically, in training stage, circuit designers Advance with the spectral samples S of a large amount of known channel scanning resultsSAMPLEIt goes to train artificial neural networks 430, to obtain to enable frequency Road scanning result and spectral samples SSAMPLEOne group of operational parameter being consistent.It should be noted that by sample data to Artificial neural Network is trained to be known to those skilled in the art in a manner of generating operational parameter, is not repeated in this.
After the training stage completes, artificial neural networks 430 can join according to the operation for the fixation that memory 440 provides Number imposes a neural network computing for unknown frequency spectrum S, to generate its channel scanning result R.Fig. 6 is presented one and corresponds to figure The channel scanning result example of the frequency spectrum S of 3B.In this example, channel scanning result R includes multiple binary digits.Assuming that frequency Compose S includes the corresponding energy value of N number of frequency altogether, then output layer 430C also can correspondingly be designed to include N number of nerve First circuit respectively generates the channel scanning result for corresponding to N number of specific frequency.In other words, channel scanning result R may include N A binary digit, each binary digit correspond to a specific frequency.In this example, binary digit 1 represents the specific frequency Rate is there are television channel, and binary digit 0 represents the specific frequency, and there is no television channels.It is subsequent according to this channel scanning result R Circuit can directly and clearly define the centre frequency and channel size of each television channel.
In practice, scope of the invention is not limited to specific storage mechanism.Memory 440 may include that one or more is waved Hair property or nonvolatile memory device, such as random-access semiconductor memory, read-only memory, magnetism and/or optics are deposited Reservoir, flash memory etc..In addition, memory 440 can also be broken up into multiple memory cells in practice, it is incorporated into artificial mind Through in network 430.
It is according to another embodiment of the present invention the channel scan method in a kind of satellite TV system, cooperation is comprising multiple One artificial neural networks of neuron circuit operate.The flow chart of the channel scan method is presented in Fig. 7.Firstly, step S71 is to connect A TV signal is received, and a spectrum analysis is carried out to the TV signal, to generate a frequency spectrum.Then, step S72 is by the electricity The frequency spectrum depending on signal is provided to the artificial neural networks as input signal.On the other hand, step S73 be will be according to multiple frequencies One group of operational parameter that spectrum sample generates in advance is provided to the artificial neural networks.Step S74 is then to control the artificial neural netrwork Network imposes a neural network computing to the frequency spectrum according to this group of operational parameter, to generate a channel scanning result.This group of operation ginseng The offset that number uses when carrying out the neural network computing comprising each neuron circuit in multiple neuron circuit With one or more weights.
It will be understood by those skilled in the art that the various operation changes previously described when introducing channel scan device 400 Also the channel scan method that can be applied in Fig. 7, details repeat no more.
By the detailed description of embodiments above, it is intended to more clearly describe feature and spirit of the invention, and simultaneously It is non-that scope of the invention is limited with above-mentioned disclosed specific embodiment.On the contrary, the purpose is to wish to cover Various changes and tool equality are arranged in the scope of the claims to be applied of the invention.In addition, in this exposure book Mathematical representation be to illustrate principle relevant to the embodiment of the present invention and logic, the case where unless there are specializing, Otherwise scope of the invention is not construed as limiting.It will be understood by those skilled in the art that can realize the grade mathematics there are many technology Physical manifestation corresponding to formula.

Claims (6)

1. the channel scan device in a kind of satellite TV system, includes:
One frequency spectrum generation circuit carries out a spectrum analysis to receive a TV signal, and to the TV signal, to generate one Frequency spectrum;
One memory, to store the one group of operational parameter generated in advance according to multiple spectral samples;And
One artificial neural networks include multiple neuron circuits, to the frequency according to this group of operational parameter to the TV signal Spectrum imposes a neural network computing, to generate a channel scanning result, wherein this group of operational parameter includes multiple neuron electricity The offset and one or more weights that each neuron circuit uses when carrying out the neural network computing in road.
2. channel scan device as described in claim 1, which is characterized in that the channel scanning result includes multiple binary systems Position, corresponds respectively to multiple specific frequencies on the frequency spectrum, each multiple binary digit represents each multiple specific frequency On there are whether television channel.
3. channel scan device as claimed in claim 2, which is characterized in that the artificial neural networks include an input layer and The number for the neuron circuit that one output layer, the input layer and the output layer separately include is equal to multiple specific frequency of the frequency spectrum The number of rate.
4. channel scan device as claimed in claim 2, which is characterized in that binary digit 1 represents the corresponding specific frequency and deposits In television channel, binary digit 0 represents the corresponding specific frequency, and there is no television channels.
5. the channel scan method in a kind of satellite TV system, cooperation includes an artificial neural networks of multiple neuron circuits Running, which includes:
A TV signal is received, and a spectrum analysis is carried out to the TV signal, to generate a frequency spectrum;
Generate in advance according to multiple spectral samples one group of operational parameter is provided to the artificial neural networks, wherein group fortune It is inclined to calculate parameter includes that each neuron circuit uses when carrying out a neural network computing in multiple neuron circuit one Shifting amount and one or more weights;And
The frequency spectrum of the TV signal is provided to the artificial neural networks as input signal, and controls the artificial neural networks The neural network computing is imposed to the frequency spectrum according to this group of operational parameter, to generate a channel scanning result.
6. channel scan method as claimed in claim 5, which is characterized in that the channel scanning result includes multiple binary systems Position, corresponds respectively to multiple specific frequencies on the frequency spectrum, each multiple binary digit represents each multiple specific frequency On there are whether television channel.
CN201810257862.0A 2018-03-27 2018-03-27 Channel scan device and channel scan method in satellite TV system Pending CN110312092A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810257862.0A CN110312092A (en) 2018-03-27 2018-03-27 Channel scan device and channel scan method in satellite TV system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810257862.0A CN110312092A (en) 2018-03-27 2018-03-27 Channel scan device and channel scan method in satellite TV system

Publications (1)

Publication Number Publication Date
CN110312092A true CN110312092A (en) 2019-10-08

Family

ID=68073670

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810257862.0A Pending CN110312092A (en) 2018-03-27 2018-03-27 Channel scan device and channel scan method in satellite TV system

Country Status (1)

Country Link
CN (1) CN110312092A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200514430A (en) * 2003-10-14 2005-04-16 Realtek Semiconductor Corp Apparatus for channel scanning and method thereof
CN101399930A (en) * 2007-09-25 2009-04-01 晨星半导体股份有限公司 Method for intelligently channel scanning and related apparatus
CN102027730A (en) * 2008-05-13 2011-04-20 At&T移动第二有限责任公司 Commerce and services in a femtocell network
CN102196211A (en) * 2011-05-25 2011-09-21 冠捷显示科技(厦门)有限公司 Method for searching for broadcasting television program channel
US20120246178A1 (en) * 2011-03-21 2012-09-27 Aol Inc. Evaluating supply of electronic content relating to keywords
CN103873176A (en) * 2012-12-11 2014-06-18 晨星软件研发(深圳)有限公司 Channel scanning method of satellite digital image broadcast signal
CN203827472U (en) * 2014-05-14 2014-09-10 潍坊东升电子股份有限公司 Ground reception digital STB tuner circuit
CN104519287A (en) * 2013-09-26 2015-04-15 晨星半导体股份有限公司 Television signal receiving device and method for judging whether channel comprises television program signal or not
CN107229710A (en) * 2017-05-27 2017-10-03 深圳市唯特视科技有限公司 A kind of video analysis method accorded with based on local feature description

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200514430A (en) * 2003-10-14 2005-04-16 Realtek Semiconductor Corp Apparatus for channel scanning and method thereof
CN101399930A (en) * 2007-09-25 2009-04-01 晨星半导体股份有限公司 Method for intelligently channel scanning and related apparatus
CN102027730A (en) * 2008-05-13 2011-04-20 At&T移动第二有限责任公司 Commerce and services in a femtocell network
US20120246178A1 (en) * 2011-03-21 2012-09-27 Aol Inc. Evaluating supply of electronic content relating to keywords
CN102196211A (en) * 2011-05-25 2011-09-21 冠捷显示科技(厦门)有限公司 Method for searching for broadcasting television program channel
CN103873176A (en) * 2012-12-11 2014-06-18 晨星软件研发(深圳)有限公司 Channel scanning method of satellite digital image broadcast signal
CN104519287A (en) * 2013-09-26 2015-04-15 晨星半导体股份有限公司 Television signal receiving device and method for judging whether channel comprises television program signal or not
CN203827472U (en) * 2014-05-14 2014-09-10 潍坊东升电子股份有限公司 Ground reception digital STB tuner circuit
CN107229710A (en) * 2017-05-27 2017-10-03 深圳市唯特视科技有限公司 A kind of video analysis method accorded with based on local feature description

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Y. M. FLEMING LURE等: "Data fusion with artificial neural networks (ANN)for classification of earth surface from microwave satellite measurements", 《GODDARD CONFERENCE ON SPACE APPLICATIONS OF ARTIFICIAL INTELLIGENCE》 *
张一弓: "基于DMB-TH标准的无线数字电视接收机的设计", 《中国优秀硕士学位论文全文数据库》 *

Similar Documents

Publication Publication Date Title
CN110826693B (en) Three-dimensional atmospheric temperature profile inversion method and system based on DenseNet convolutional neural network
CN106936742A (en) Multi gear bit rate adaptive demodulation system and method based on neutral net
CN111050315B (en) Wireless transmitter identification method based on multi-core two-way network
CN114881093B (en) Signal classification and identification method
CN114268388B (en) Channel estimation method based on improved GAN network in large-scale MIMO
CN109409442A (en) Convolutional neural networks model selection method in transfer learning
Kummerow et al. Hyperspectral microwave sensors—Advantages and limitations
Cai et al. Jamming pattern recognition using spectrum waterfall: A deep learning method
Ma et al. CNN-based automatic modulation recognition of wireless signal
CN113109782A (en) Novel classification method directly applied to radar radiation source amplitude sequence
CN114861730A (en) Interference cognition method based on multi-task learning
CN113343796B (en) Knowledge distillation-based radar signal modulation mode identification method
Zhu et al. Proactive network maintenance using fast, accurate anomaly localization and classification on 1-d data series
CN110312092A (en) Channel scan device and channel scan method in satellite TV system
CN113037668A (en) Millimeter wave point-to-point communication channel equalization method
Wu et al. Interference detection and recognition based on signal reconstruction using recurrent neural network
CN117544272A (en) Signal type and azimuth joint reasoning method
CN112488092B (en) Navigation frequency band signal type identification method and system based on deep neural network
CN112232120B (en) Radar radiation source signal classification system and method based on software radio
CN112616160B (en) Intelligent short-wave frequency cross-frequency-band real-time prediction method and system
CN112566129A (en) Radio frequency fingerprint extraction and identification method capable of resisting multipath interference
Bhavana et al. Low Complex Hybrid Deep Learning Model for Automatic Modulation Classification
TW201941590A (en) Channel scan apparatus and channel scan method in satellite TV system
Makled et al. Identification of Cellular Measurements: A Neural Network Approach
Sanchez Utilizing Machine Learning for Signal Classification and Noise Reduction in Amateur Radio

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20191008

WD01 Invention patent application deemed withdrawn after publication