CN113158746B - Weak signal sensing method based on random resonance of small-world network of nerve cells - Google Patents
Weak signal sensing method based on random resonance of small-world network of nerve cells Download PDFInfo
- Publication number
- CN113158746B CN113158746B CN202110143648.4A CN202110143648A CN113158746B CN 113158746 B CN113158746 B CN 113158746B CN 202110143648 A CN202110143648 A CN 202110143648A CN 113158746 B CN113158746 B CN 113158746B
- Authority
- CN
- China
- Prior art keywords
- node
- world network
- small
- nodes
- small world
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 210000002569 neuron Anatomy 0.000 title claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 230000008447 perception Effects 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims abstract description 11
- 238000011084 recovery Methods 0.000 claims abstract description 11
- 230000000946 synaptic effect Effects 0.000 claims abstract description 11
- 239000012528 membrane Substances 0.000 claims abstract description 10
- 230000004888 barrier function Effects 0.000 claims abstract description 5
- 230000007704 transition Effects 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 13
- 230000000737 periodic effect Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 241000540325 Prays epsilon Species 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims 2
- 230000000638 stimulation Effects 0.000 claims 1
- 210000000225 synapse Anatomy 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 238000007500 overflow downdraw method Methods 0.000 abstract description 2
- 210000000653 nervous system Anatomy 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 210000005036 nerve Anatomy 0.000 description 3
- 230000001537 neural effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Neurology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Signal Processing (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a weak signal perception method based on random resonance of a small-world network of neurons, which firstly improves parameter setting of an FHN neuron calculation model, and changes the condition that the membrane potential and the recovery variable characteristic time are set to be the same value in the conventional consideration of simple calculation. The improved parameter setting method enhances the potential function barrier of the membrane potential so as to improve the transition probability between potential wells; then constructing an FHN neuron calculation model containing weak signal input and background noise, setting the FHN neuron calculation model as a small-world network node, and giving and realizing a dynamic synaptic interconnection rule for representing the relation between the nodes; and for the output of each node of the small-world network, adopting a mean value fusion method based on cross-correlation coefficients to screen and fuse the output of each node of the network so as to improve the performance and robustness of the system, thereby obtaining the weak signal perception effect in the sense of the small-world network system.
Description
Technical Field
The invention belongs to the field of application of nerve computation models, and particularly relates to a weak signal perception method based on random resonance of a small-world network of neurons.
Background
The visual neurophysiologic experiment and the calculation simulation show that a stochastic resonance mechanism exists in the nervous system, namely, partial background noise energy of the nervous system is converted into weak signal energy by utilizing the nonlinear characteristics of nerve coding and dynamic synaptic connection, so that the perception of weak signals is realized. At present, many researches apply stochastic resonance mechanisms to weak signal processing, but most of selected nonlinear systems are ideal physical systems represented by bistable states or simplified nervous systems represented by single neuron computational models, and characterization, nonlinear fitting and anti-interference capabilities of neuron clusters are ignored, so that stochastic resonance inherent mechanisms in the visual and auditory perception process of the nervous systems are not fully mined and applied. In addition, with the continuous development of computing power and algorithms in recent years, a complex network has become one of research hotspots for computing nerves, and more neurophysiologic experimental results show that the nervous system has the characteristics of a small world network and plays an important role in maintaining the normal physiological functions of the nervous system.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a weak signal sensing method based on random resonance of a small-world network of neurons.
The invention firstly improves the parameter setting of the FHN neuron calculation model, and changes the condition that the membrane potential and the recovery variable characteristic time are set to the same value in the conventional consideration of simple calculation. The improved parameter setting method enhances the potential function barrier of the membrane potential so as to improve the transition probability between potential wells; then constructing an FHN neuron calculation model containing weak signal input and background noise, setting the FHN neuron calculation model as a small-world network node, and giving and realizing a dynamic synaptic interconnection rule for representing the relation between the nodes; and for the output of each node of the small-world network, adopting a mean value fusion method based on cross-correlation coefficients to screen and fuse the output of each node of the network so as to improve the performance and robustness of the system, thereby obtaining the weak signal perception effect in the sense of the small-world network system.
The method comprises the following steps:
and 1, constructing a small world network based on probability random connection. The nodes in the small world network are distributed according to a ring rule, each node in the network corresponds to a unique label l, l epsilon [1, N ], and N is the total number of the nodes in the small world network. The labels are sequentially increased in a clockwise direction according to the positions of the nodes in the network and are connected end to end, so that a closed annular structure is finally formed. The distance d i,j between two small world network nodes labeled i and j is defined as shown in equation (1), where |·| represents taking the absolute function.
di,j＝min(|j-i|，|N-j+i|)，i，j∈[1，N]，i≠j (1)
For the node labeled i, i e [1, N ], it is randomly connected with the node labeled j according to the probability p i,j, and p i,j is set according to the following rule.
ifj＝＝mod((i+1)，N)
pi,j＝1；
else
pi,j＝p；
Wherein mod is a remainder function, p is a random number, and p.epsilon.0, 1.
And 2, constructing an FHN neuron calculation model, and taking the FHN neuron calculation model as a basic node of the small world network. Wherein only one node of the small world network receives external input stimulus, the node label is marked as in, in epsilon [1, N ], and the FHN neuron calculation model adopted by the node is shown as a formula (2).
In the formula, epsilon v、εw respectively represents the characteristic time of the membrane potential and the recovery variable, the invention changes the traditional thought of setting the two characteristic times to the same value, epsilon v、εw can be independently set, thereby flexibly changing the potential function barrier of the membrane potential so as to improve the transition probability between potential wells; v in and ω in represent a node output signal and a recovery variable, respectively, labeled in; b represents a dimensionless positive number; i sig represents external input stimulus, and corresponds to a periodic weak signal to be sensed, and the period of I sig is marked as T sig; ζ represents gaussian white noise with a mean value of 0 and a noise intensity of σ; i sig, ζThe sum corresponds to the node input signal labeled in, denoted S in, i.e./>Wherein/>For the coupled term of the node dynamic synaptic interconnection pattern labeled in, the calculation process is shown in formula (3).
Where L in,j represents the connection between two small world network nodes labeled in and j, and L in,j = 1 or 0 represents the presence or absence of a synaptic connection between the two nodes, respectively. α in,j represents the connection strength between two small world network nodes labeled in and j, inversely proportional to the distance d in,j between them, as shown in equation (4).
For the nodes marked as i in the small world network, i epsilon [1, N ], i not equal to in, which do not receive external input stimulus, the FHN neuron calculation model is shown as a formula (5).
Wherein v i、ωi andCoupling terms respectively representing node output signals, recovery variables, and dynamic synaptic interconnection patterns labeled i; the node input signal labeled i is denoted S i, i.e./>Wherein/>Calculation is performed with reference to formula (3).
Step 3, calculating the cross-correlation coefficient of the small world network nodeAnd/>Outputs v in and v i of the small-world network nodes are calculated according to equation (2) and equation (5). Wherein for gaussian white noise ζ in formula (2), there are set (m+1) possible noise intensities σ z =0.01 z, z=0, 1,..m, default M is taken as 50. For a particular σ z, the cross-correlation coefficients for all nodes of the small-world network are calculated based on the correlation between the input and output signals.
For the in node, the cross correlation coefficient calculation is shown in equation (6).
In the method, in the process of the invention,A node denoted as in, means the input signal S in over a time T sig; /(I)The node denoted in outputs the average value of signal v in during time T sig.
For the nodes marked with i in the small world network, i epsilon [1, N ], i not equal to in, and the cross correlation coefficient is calculated as shown in a formula (7).
In the method, in the process of the invention,The node labeled i represents the average of the input signal S i over time T sig. /(I)The node denoted i outputs the mean value of signal v i during time T sig.
And 4, determining zeta noise intensity sigma corresponding to the optimal cross correlation coefficient. And (3) on the basis of the step (3), calculating the cross-correlation coefficient of each node in the small world network under different Gaussian white noise intensities, summing and taking the maximum value, wherein the cross-correlation coefficient is specifically shown as a formula (8).
The corresponding parameter z at the time of obtaining the maximum value of C sum is obtained, so that the noise intensity σ=0.01z of ζ is determined.
And 5, obtaining optimized outputs v 'in and v' i of the small world network node, wherein i epsilon [1, N ], i not equal to in. And (3) discarding abnormal node output information with too low cross-correlation coefficient on the basis of the sigma calculated in the step (4), and obtaining optimized outputs v 'in and v' i, wherein i epsilon [1, N ], i not equal to in. The calculation process is shown in formulas (9) and (10).
In the formula, threshold represents an adaptive Threshold value, and the cross-correlation coefficient median value of all nodes of the small world network is taken by default.
And 6, determining the output of the whole small-world network, namely a weak signal perception result v out. In order to improve the robustness of the enhancement performance of the weak signal, the output signals of all nodes of the small world network are subjected to mean value fusion to obtain a final weak signal perception result v out, which is specifically shown in a formula (11).
Where k in、ki is used to represent whether the output of the small world network node in, and the remaining nodes i of the small world network are valid, as shown in equations (12) and (13).
The invention has the beneficial effects that:
According to the invention, a small world network based on probability random reconnection with FHN neurons as nodes is constructed, the random resonance characteristic is fully utilized, effective reduction and enhancement of periodic weak signals and non-periodic signals with noise can be realized, the consistency of periodic signal frequency spectrums can be maintained, the original weak signals and system output signals can reach higher cross-correlation coefficients, and the actual requirements are met; the defect that a nonlinear system model is over-idealized in the traditional random resonance research is overcome, and the performance of the system for sensing weak signals is effectively improved.
Drawings
Fig. 1 (a) shows a schematic diagram of a small-world network structure when the reconnection probability p=0 between neuron nodes;
Fig. 1 (b) shows a schematic diagram of a small-world network structure when the reconnection probability p=0.2 between neuron nodes.
Detailed Description
A weak signal perception method based on random resonance of a small-world network of neurons specifically comprises the following steps:
and 1, constructing a small world network based on probability random connection.
The nodes in the small world network are distributed according to a ring rule, each node in the network corresponds to a unique label l, l epsilon [1, N ], N is the total number of nodes of the small world network, as shown in fig. 1 (a), and the total number of nodes is 20, namely, the small world network structure diagram when N=20. The labels are sequentially increased in a clockwise direction according to the positions of the nodes in the network and are connected end to end, so that a closed annular structure is finally formed. The distance d i,j between two small world network nodes labeled i and j is defined as shown in equation (1), where |·| represents taking the absolute function.
di,j＝min(|j-i|，|N-j+i|)，i，j∈[1，N]，i≠j (1)
For the node labeled i, i e [1, N ], it is randomly connected with the node labeled j according to the probability p i,j, and p i,j is set according to the following rule.
if j＝＝mod((i+1)，N)
pi,j＝1；
else
pi,j＝p；
Wherein mod is a remainder function, p is a random number, and p.epsilon.0, 1.
As shown in fig. 1 (a), that is, the probability of reconnection between neuron nodes p=0; graph (b) shows the probability of reconnection between neuronal nodes p=0.2.
And 2, constructing an FHN neuron calculation model, and taking the FHN neuron calculation model as a basic node of the small world network. Wherein only one node of the small world network receives external input stimulus, the node label is marked as in, in epsilon [1, N ], and the FHN neuron calculation model adopted by the node is shown as a formula (2).
In the formula, epsilon v、εw respectively represents the characteristic time of the membrane potential and the recovery variable, the invention changes the traditional thought of setting the two characteristic times to the same value, epsilon v、εw can be independently set, thereby flexibly changing the potential function barrier of the membrane potential so as to improve the transition probability between potential wells; v in and ω in represent a node output signal and a recovery variable, respectively, labeled in; b represents a dimensionless positive number; i sig represents external input stimulus, and corresponds to a periodic weak signal to be sensed, and the period of I sig is marked as T sig; ζ represents gaussian white noise with a mean value of 0 and a noise intensity of σ; i sig, ζThe sum corresponds to the node input signal labeled in, denoted S in, i.e./>Wherein/>For the coupled term of the node dynamic synaptic interconnection pattern labeled in, the calculation process is shown in formula (3).
Where L in,j represents the connection between two small world network nodes labeled in and j, and L in,j = 1 or 0 represents the presence or absence of a synaptic connection between the two nodes, respectively. α in,j represents the connection strength between two small world network nodes labeled in and j, inversely proportional to the distance d in,j between them, as shown in equation (4).
For the nodes marked as i in the small world network, i epsilon [1, N ], i not equal to in, which do not receive external input stimulus, the FHN neuron calculation model is shown as a formula (5).
Wherein v i、ωi andCoupling terms respectively representing node output signals, recovery variables, and dynamic synaptic interconnection patterns labeled i; the node input signal labeled i is denoted S i, i.e./>Wherein/>Calculation is performed with reference to formula (3).
Step 3, calculating the cross-correlation coefficient of the small world network nodeAnd/>Outputs v in and v i of the small-world network nodes are calculated according to equation (2) and equation (5). Wherein for gaussian white noise ζ in formula (2), there are set (m+1) possible noise intensities σ z =0.01 z, z=0, 1,..m, default M is taken as 50. For a particular σ z, the cross-correlation coefficients for all nodes of the small-world network are calculated based on the correlation between the input and output signals.
For the in node, the cross correlation coefficient calculation is shown in equation (6).
In the method, in the process of the invention,A node denoted as in, means the input signal S in over a time T sig; /(I)The node denoted in outputs the average value of signal v in during time T sig.
For the nodes marked with i in the small world network, i epsilon [1, N ], i not equal to in, and the cross correlation coefficient is calculated as shown in a formula (7).
In the method, in the process of the invention,The node labeled i represents the average of the input signal S i over time T sig. /(I)The node denoted i outputs the mean value of signal v i during time T sig.
And 4, determining zeta noise intensity sigma corresponding to the optimal cross correlation coefficient. And (3) on the basis of the step (3), calculating the cross-correlation coefficient of each node in the small world network under different Gaussian white noise intensities, summing and taking the maximum value, wherein the cross-correlation coefficient is specifically shown as a formula (8).
The corresponding parameter z at the time of obtaining the maximum value of C sum is obtained, so that the noise intensity σ=0.01z of ζ is determined.
And 5, obtaining optimized outputs v 'in and v' i of the small world network node, wherein i epsilon [1, N ], i not equal to in. And (3) discarding abnormal node output information with too low cross-correlation coefficient on the basis of the sigma calculated in the step (4), and obtaining optimized outputs v 'in and v' i, wherein i epsilon [1, N ], i not equal to in. The calculation process is shown in formulas (9) and (10).
In the formula, threshold represents an adaptive Threshold value, and the cross-correlation coefficient median value of all nodes of the small world network is taken by default.
And 6, determining the output of the whole small-world network, namely a weak signal perception result v out. In order to improve the robustness of the enhancement performance of the weak signal, the output signals of all nodes of the small world network are subjected to mean value fusion to obtain a final weak signal perception result v out, which is specifically shown in a formula (11).
Where k in、ki is used to represent whether the output of the small world network node in, and the remaining nodes i of the small world network are valid, as shown in equations (12) and (13).
Claims (3)
1. The weak signal perception method based on the random resonance of the small-world network of the neuron is characterized by comprising the following steps of:
Step 1, constructing a small world network based on probability random connection;
Nodes in the small world network are distributed according to a ring rule, each node in the network corresponds to a unique label l, l epsilon [1, N ], and N is the total number of the nodes in the small world network; the labels are sequentially increased in a clockwise direction according to the positions of the nodes in the network and are connected end to end, so that a closed annular structure is finally formed; defining a distance d i,j between two small world network nodes marked as i and j, as shown in formula (1), wherein |·| represents taking an absolute value function;
di,j＝min(|j-i|，|N-j+i|)，i，j∈[1，N]，i≠j (1)
For the node with the index i, i epsilon [1, N ], the node with the index j is randomly connected according to the probability p i,j, and p i,j is set according to the following rule;
if j＝＝mod((i+1)，N)
pi,j＝1；
else
pi,j＝p；
Wherein mod is a remainder function, p is a random number, p.epsilon.0, 1;
Step 2, constructing an FHN neuron calculation model, and taking the FHN neuron calculation model as a basic node of a small world network; wherein, only one node of the small world network receives external input stimulus, the node label is marked as in, in epsilon [1, N ], and the FHN neuron calculation model adopted by the node is shown as formula (2);
wherein epsilon v、εw respectively represents the characteristic time of the membrane potential and the recovery variable, wherein epsilon v、εw is independently arranged, so that the potential function barrier of the membrane potential can be flexibly changed to improve the transition probability between potential wells; v in and ω in represent a node output signal and a recovery variable, respectively, labeled in; b represents a dimensionless positive number; i sig represents external input stimulus, and corresponds to a periodic weak signal to be sensed, and the period of I sig is marked as T sig; ζ represents gaussian white noise with a mean value of 0 and a noise intensity of σ; i sig, ζ The sum corresponds to the node input signal labeled in, denoted S in, i.e./>Wherein/>As the coupling term of the node dynamic synapse interconnection mode with the reference number of in, the calculation process is shown in a formula (3);
Wherein L in,j represents a connection relationship between two small world network nodes labeled in and j, and L in,j = 1 or 0 represents the presence or absence of a synaptic connection between the two nodes, respectively; α in,j represents the connection strength between two small world network nodes labeled in and j, inversely proportional to the distance d in,j between them, as shown in equation (4);
for nodes marked as i in the small world network, i epsilon [1, N ], i not equal to in, which do not receive external input stimulation, the FHN neuron calculation model is shown as a formula (5);
Wherein v i、ωi and Coupling terms respectively representing node output signals, recovery variables, and dynamic synaptic interconnection patterns labeled i; the node input signal labeled i is denoted S i, i.e./>Wherein/>Performing calculation with reference to formula (3);
step 3, calculating the cross-correlation coefficient of the small world network node And/>Calculating the outputs v in and v i of the small-world network nodes according to formula (2) and formula (5); wherein for gaussian white noise ζ in equation (2), setting (m+1) possible noise intensities σ z =0.01 z, z=0, 1,..m, for a certain σ z, calculating cross-correlation coefficients of all nodes of the small world network based on the correlation between the input and output signals;
For an in node, calculating a cross correlation coefficient as shown in a formula (6);
in the method, in the process of the invention, A node denoted as in, means the input signal S in over a time T sig; /(I)The node denoted in outputs the mean value of signal v in during time T sig;
For nodes marked as i in the small world network, i epsilon [1, N ], i not equal to in, and calculating a cross correlation coefficient as shown in a formula (7);
in the method, in the process of the invention, A node denoted i, means the input signal S i during time T sig; /(I)A node denoted i outputs the mean value of signal v i during time T sig;
Step 4, determining zeta noise intensity sigma corresponding to the optimal cross correlation coefficient; on the basis of the step 3, the cross-correlation coefficient of each node in the small world network under different Gaussian white noise intensities is obtained, and the cross-correlation coefficients are summed and taken as the maximum value, and the method is specifically shown as a formula (8);
Obtaining a parameter z corresponding to the maximum value of C sum, so as to determine the noise intensity sigma=0.01z of ζ;
Step 5, obtaining optimized outputs v 'in and v' i of the small world network node, wherein i is E [1, N ], i is not equal to in; on the basis of the sigma obtained by calculation in the step 4, discarding abnormal node output information with too low cross-correlation coefficient to obtain optimized outputs v 'in and v' i, wherein i epsilon [1, N ], i not equal to in; the calculation process is shown in formulas (9) and (10);
Wherein Threshold represents an adaptive Threshold;
Step 6, determining the output of the whole small world network, namely a weak signal perception result v out; in order to improve the robustness of the enhancement performance of the weak signals, the output signals of all nodes of the small world network are subjected to mean value fusion to obtain a final weak signal perception result v out, wherein the final weak signal perception result v out is shown in a formula (11);
Wherein k in、ki is used to represent whether the output of the small world network node in and the other nodes i of the small world network are valid, and specifically shown in formulas (12) and (13);
2. the method for sensing weak signals based on stochastic resonance of a small-world network of neurons according to claim 1, wherein the method comprises the following steps: and the Threshold takes the median value of the cross-correlation coefficients of all nodes of the small world network.
3. The method for sensing weak signals based on stochastic resonance of a small-world network of neurons according to claim 1, wherein the method comprises the following steps: m is taken as 50.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110143648.4A CN113158746B (en) | 2021-02-02 | 2021-02-02 | Weak signal sensing method based on random resonance of small-world network of nerve cells |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110143648.4A CN113158746B (en) | 2021-02-02 | 2021-02-02 | Weak signal sensing method based on random resonance of small-world network of nerve cells |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113158746A CN113158746A (en) | 2021-07-23 |
| CN113158746B true CN113158746B (en) | 2024-04-30 |
Family
ID=76879068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110143648.4A Active CN113158746B (en) | 2021-02-02 | 2021-02-02 | Weak signal sensing method based on random resonance of small-world network of nerve cells |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158746B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240802B (en) * | 2021-12-24 | 2023-08-01 | 西安交通大学 | Visual perception method and system based on biological neuron network and stochastic resonance |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102327116A (en) * | 2011-09-28 | 2012-01-25 | 杭州电子科技大学 | Network system random resonance restoration method of cortex electroencephalographic signal |
| CN102499675A (en) * | 2011-10-27 | 2012-06-20 | 杭州电子科技大学 | Feedback system random resonance intensification method of electro-corticogram signal |
| CN110348625A (en) * | 2019-07-04 | 2019-10-18 | 浙江树人学院（浙江树人大学） | Forecast of Nonlinear Time Series method based on worldlet scales-free network |
-
2021
- 2021-02-02 CN CN202110143648.4A patent/CN113158746B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102327116A (en) * | 2011-09-28 | 2012-01-25 | 杭州电子科技大学 | Network system random resonance restoration method of cortex electroencephalographic signal |
| CN102499675A (en) * | 2011-10-27 | 2012-06-20 | 杭州电子科技大学 | Feedback system random resonance intensification method of electro-corticogram signal |
| CN110348625A (en) * | 2019-07-04 | 2019-10-18 | 浙江树人学院（浙江树人大学） | Forecast of Nonlinear Time Series method based on worldlet scales-free network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113158746A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113158746B (en) | Weak signal sensing method based on random resonance of small-world network of nerve cells | |
| Guo et al. | A cross-correlated delay shift supervised learning method for spiking neurons with application to interictal spike detection in epilepsy | |
| US9014416B1 (en) | Sensory processing apparatus and methods | |
| Ma et al. | EMG-based gestures classification using a mixed-signal neuromorphic processing system | |
| CN106912067B (en) | WSN wireless communication module fault diagnosis method based on fuzzy neural network | |
| CN110175510B (en) | Multi-mode motor imagery identification method based on brain function network characteristics | |
| CN111130909B (en) | Network flow prediction method based on self-adaptive reserve pool ESN | |
| CN108805879A (en) | A kind of image partition method based on Spiking neural networks | |
| Xie et al. | Effect of spike-timing-dependent plasticity on coherence resonance and synchronization transitions by time delay in adaptive neuronal networks | |
| Reis et al. | Suppression of chaotic bursting synchronization in clustered scale-free networks by an external feedback signal | |
| Guo et al. | Encoding specificity of scale-free spiking neural network under different external stimulations | |
| CN116094758B (en) | Large-scale network flow acquisition method and system | |
| CN115695025B (en) | Training method and device for network security situation prediction model | |
| CN116403054A (en) | Image optimization classification method based on brain-like network model | |
| Sun et al. | Simplified spike-timing dependent plasticity learning rule of spiking neural networks for unsupervised clustering | |
| CN108021873B (en) | Electroencephalogram signal epilepsy classification method and system for clustering asymmetric mutual information | |
| US20160321538A1 (en) | Pattern Recognition System and Method | |
| An et al. | Enhancing visual coding through collaborative perception | |
| Sung et al. | Enhance the efficient of WSN data fusion by neural networks training process | |
| CN111582470A (en) | Self-adaptive unsupervised learning image identification method and system based on STDP | |
| Lv et al. | A novel spiking neural network with the learning strategy of biomimetic structure | |
| CN115919327A (en) | Dynamic brain network modeling method based on attention ERP characteristics | |
| JP2518939B2 (en) | Speaker verification system | |
| CN112819142B (en) | Short-time synaptic plasticity work memory computing system and method | |
| CN116530996B (en) | Low-measurement-load-oriented electrocardiographic data abnormality early warning method and system |
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 |