CN111209815B - Non-contact fatigue driving detection method based on BP neural network with momentum optimization - Google Patents
Non-contact fatigue driving detection method based on BP neural network with momentum optimization Download PDFInfo
- Publication number
- CN111209815B CN111209815B CN201911382375.8A CN201911382375A CN111209815B CN 111209815 B CN111209815 B CN 111209815B CN 201911382375 A CN201911382375 A CN 201911382375A CN 111209815 B CN111209815 B CN 111209815B
- Authority
- CN
- China
- Prior art keywords
- momentum
- neural network
- algorithm
- driver
- detecting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- 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
-
- 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
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Data Mining & Analysis (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Cardiology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pulmonology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a non-contact fatigue driving detection method based on a BP neural network with momentum optimization, which comprises the following steps: s10, acquiring physiological signals of a driver through a Doppler radar module; s20, classifying physiological signals; s30, filtering the physiological signals and decomposing the physiological signals by using a CEEMD algorithm to obtain signals of which the two sections of heart beat and respiration contain complete time-frequency domain characteristics; s40, designing a BP neural network model with optimized momentum to train the data set, so as to obtain an algorithm model for detecting the fatigue state of the driver; s50, detecting the fatigue state through an algorithm model for detecting the fatigue state of the driver. The invention can efficiently and accurately detect the fatigue state of the driver while avoiding influencing the normal driving of the driver.
Description
Technical Field
The invention belongs to the field of modeling detection, and particularly relates to a non-contact fatigue driving detection method based on a BP neural network with momentum optimization.
Background
Fatigue driving is one of the most common causes of traffic accidents worldwide. According to WHO (world health organization) reports, more than 130 tens of thousands of people die each year from traffic accidents, and 2 to 5 tens of thousands of people suffer non-fatal injuries due to traffic accidents, of which about 20% of fatal traffic accidents are caused by fatigue driving. Therefore, if a system for automatically detecting the fatigue driving can be developed and a driver can be warned in advance that the system is in the fatigue driving state, a large number of traffic accidents can be effectively avoided, and the occurrence rate of the traffic accidents is reduced.
The current methods for detecting fatigue states are mainly divided into two main categories: 1. detecting contact fatigue state; 2 non-contact fatigue state detection.
The contact fatigue detection method mainly detects the physiological state of a driver. Although the data obtained by the method is reliable, the error is small and the external interference is small, the method needs to install a device for detecting the physiological signal on the driver, and the interference to the driver is too large. For this reason, researchers have matured by using radio to measure physiological signals and by ZigBee, bluetooth, etc. to acquire signals, but the accuracy has been greatly reduced and the artificial interference has caused detection artefacts and errors.
The non-contact fatigue detection method mainly monitors facial features of a driver and vehicle parameter detection. The analysis individual difference of the facial features of the driver is large, and the change of brightness or the wearing of sunglasses, masks and other articles shielding the face by the driver can cause great interference to detection, so that the cost required by the whole device can be increased; for detecting the state and the running track of the vehicle, the required hardware support is high and the cost is high. And the requirements on the external conditions are severe (such as road signs, climates, illumination conditions and the like). One of the great limitations of this approach is that it is a vehicle detection, not a direct detection of the driver, which is greatly reduced in reliability and accuracy.
In summary, although there are various methods for measuring the fatigue state of the driver in real time at present, most of the methods are limited to theoretical research level, and the existing monitoring devices have various limitations and have various problems to be solved. Each method for detecting fatigue driving has advantages and limitations, so that the method for detecting fatigue driving of a driver should not be used in a single way. Many studies have shown that the reliability and accuracy of the hybrid detection method is higher than that of the single detection method. Therefore, to develop an effective fatigue driving detection system, various detection methods should be combined in one hybrid system for detection. The reliability of the data obtained by the detection of the physiological condition is high, but the interference to the driver is large. Therefore, a non-contact device for detecting the physiological signals of the driver is designed, and the physiological signals are trained and learned by combining the neural network model to obtain an algorithm model for detecting the fatigue state of the driver.
Disclosure of Invention
In view of the technical problems, the invention realizes non-contact detection of the physiological state of the driver, avoids physical and driving interference to the driver and improves the accuracy; the data can be processed rapidly and efficiently; the algorithm model adopts a BP neural network model with momentum optimization, and has faster learning efficiency and high accuracy compared with the traditional BP neural network.
Based on the above purpose, the invention provides a non-contact fatigue driving detection method based on a BP neural network with momentum optimization.
The method comprises the following steps:
s10, acquiring physiological signals of a driver through a Doppler radar module;
s20, classifying physiological signals;
s30, filtering the physiological signals and decomposing the physiological signals by using a CEEMD algorithm to obtain signals of which the two sections of heart beat and respiration contain complete time-frequency domain characteristics;
s40, designing a BP neural network model with optimized momentum to train the data set, so as to obtain an algorithm model for detecting the fatigue state of the driver;
s50, detecting the fatigue state through an algorithm model for detecting the fatigue state of the driver.
Preferably, the physiological signal includes at least a respiratory signal and a heartbeat signal of the driver.
Preferably, the momentum-optimized BP neural network iteratively updates a weight matrix according to an error back propagation algorithm, and minimizes a mean square error between an actual output value and an expected output value of the network by utilizing gradient descent, so as to obtain an algorithm model for detecting the fatigue state of the driver.
Preferably, in the BP neural network model with optimized design momentum, the BP neural network weight iterative equation is:
where alpha is the learning rate, m is the total sample size, beta is the momentum coefficient, and beta epsilon (0, 1),for the momentum gradient value of the previous iteration, +.>Is the weight error accumulated value.
Preferably, the doppler radar module employs a microwave doppler radar detector probe sensor HB100 module.
Compared with the prior art, the Doppler radar module adopted by the invention can realize non-contact accurate detection of the physiological signals of the driver, and the physiological signals can accurately reflect the fatigue state of the driver, so that the difference of the physiological signals of different individuals in different fatigue states can be effectively solved. The used momentum-optimized BP neural network model has the advantages of high learning efficiency, less iteration times, high accuracy and greatly reduced calculated amount.
Drawings
FIG. 1 is a flow chart of steps of a non-contact fatigue driving detection method based on a BP neural network with momentum optimization according to an embodiment of the invention;
FIG. 2 is a standard chart of an expert evaluation method of a non-contact fatigue driving detection method based on a BP neural network with momentum optimization according to an embodiment of the invention;
FIG. 3 is a time-frequency analysis chart of heartbeat and respiratory signals of a driver, which are acquired, processed and sampled by a Doppler radar, through CEEMD algorithm decomposition in a non-contact fatigue driving detection method based on a BP neural network according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a momentum-optimized BP neural network model of a non-contact fatigue driving detection method based on a momentum-optimized BP neural network according to an embodiment of the invention;
fig. 5 is a momentum-optimized BP neural network training result diagram of a non-contact fatigue driving detection method based on a momentum-optimized BP neural network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The method comprises data acquisition, data processing and data training. The data acquisition part mainly comprises a Doppler radar module as a core and a simulated driving software system matched with a simulated driver and is used for acquiring respiration and heartbeat signals of the driver. The data processing part is mainly used for classifying the acquired respiratory and heartbeat signals by the class of the signals through an expert judging method, then carrying out filtering processing on each group of signals, and then carrying out CEEMD algorithm decomposition on the signals to obtain the heartbeat signals and respiratory signals without phase distortion. The data training part mainly designs a BP neural network model with optimized momentum, trains the acquired data and obtains an algorithm model for detecting the fatigue state of the driver.
Example 1
Referring to fig. 1, a flow chart of steps of a non-contact fatigue driving detection method based on a momentum-optimized BP neural network is shown, and S10, physiological signals of a driver are collected through a doppler radar module;
s20, classifying physiological signals;
s30, filtering the physiological signal and decomposing the physiological signal by CEEMD algorithm to obtain a signal x containing complete time-frequency domain characteristics of two sections of heart beat and respiration 1 And x 2 ；
S40, designing a BP neural network model with optimized momentum to train the data set, so as to obtain an algorithm model for detecting the fatigue state of the driver;
s50, detecting the fatigue state through an algorithm model for detecting the fatigue state of the driver.
The physiological signal includes at least a respiration signal and a heartbeat signal of the driver.
The momentum-optimized BP neural network iteratively updates a weight matrix according to an error back propagation algorithm, and minimizes the mean square error between the actual output value and the expected output value of the network by utilizing gradient descent, so that an algorithm model for detecting the fatigue state of the driver is obtained.
In the BP neural network model with the momentum optimization, the BP neural network weight iterative equation is as follows:
where alpha is the learning rate, m is the total sample size, beta is the momentum coefficient, and beta epsilon (0, 1),for the momentum gradient value of the previous iteration, +.>Is the weight error accumulated value.
The Doppler radar module adopts a microwave Doppler radar detector probe sensor HB100 module.
See fig. 2 for expert criteria for fatigue grade. Driver fatigue status grade classification 4 grades: an awake state, a stage I fatigue state, a stage II fatigue state, and a stage III fatigue state. Each fatigue level has corresponding characteristic expression, such as blink frequency, and the number of times of breathing, and the like, and the fatigue level of the driver in the video information is judged by expert analysis on the video information, so that the fatigue level of the physiological signal corresponding to the video information can be obtained. All physiological signals acquired are classified by this method.
Referring to fig. 3, a diagram of physiological signals collected by the doppler radar module and their spectral characteristics is shown. It can be seen that the physiological signals of the human body can be successfully acquired through the radar module. The physiological signals comprise respiratory signals and heartbeat signals, and signals of two sections of heart beats and respiration, which contain complete time-frequency domain characteristics, are obtained through CEEMD algorithm decomposition.
See fig. 4BP neural network model diagram. The BP neural network iteratively updates the weight matrix theta according to an error back propagation algorithm. The basic idea of BP neural networks is a gradient descent algorithm that utilizes gradient descent to minimize the mean square error between the actual and desired output values of the network. The BP neural network is a training weight based on a standard gradient descent algorithm, and the problem of local optimal solution often exists. By performing momentum optimization on the basis of the BP neural network, the problem of local optimal solution can be effectively solved, and training is more efficient. The specific model building process is as follows:
first, forward propagation is achieved. Setting the weight matrix of each layer as H (l-1) . l is an integer, l is [2, L ]]. The activation items of the hidden layer and the output layer are a (l) Representing, therefore:
the activation function selected by the network is a sigmoid function, which is defined as:
by using the activation function, nonlinear characteristics can be added, so that the learning speed is faster, the learning efficiency is higher, and the whole sample set is provided with:
a (2) ＝g(H (1) X (i) ) (3)
a (l) ＝g(H (l-1) a (l-1) ) (4)
calculating activation term a of each layer by using forward propagation algorithm (l) According to the back propagation algorithm, the error term delta of the hidden layer and the output layer needs to be calculated (l) The calculation process is as follows:
δ (L) ＝a (L) -T (i) (5)
δ (l) ＝(H (l) ) (T) δ (l+1) ×g'(H (l) a (l) ) (6)
δ (2) ＝(H (1) ) (T) δ (2) ×g'(H (1) X (i) ) (7)
g' (H) (l) a (l) ) G (H) (l) a (l) ) Is the first derivative of (a):
g'(H (l) a (l) )＝a (l) ×(1-a (l) ) (8)
at the time of calculating the activation item a (l) And error term delta (l) Then, according to the gradient descent algorithm, it is necessary to obtain a desired output by iterating and updating the weight matrix. Thus, a new variable is definedThe weight errors of the r row and the c column of the first layer of the neural network are represented, namely the weight error accumulation value.
According to the back propagation principle, the first partial derivative of the cost function J (θ) has the following properties:
the weight matrix is obtained according to the gradient descent algorithm as follows:
it can be seen from equation (11) that each weight update is only related to the current gradient value, not to the previous gradient. The momentum gradient descent algorithm obtains a current gradient value using an exponentially weighted average of previous gradient values and updates the weights using the current gradient value.
By usingTo represent the momentum gradient value. The specific algorithm is as follows:
initialization ofIs 0:
as the number of exercises increases,continuously updating:
wherein, beta is momentum coefficient, beta epsilon (0, 1);is the current momentum gradient value; />Momentum gradient value of last iteration; />Is the weight error accumulation.
And using a momentum gradient algorithm to replace a standard gradient descent algorithm to obtain a final weight iteration formula:
through multiple training, the network depth and the number of neurons per layer are finally determined, and are expressed by NN:
NN＝[2n 50 60 60 50 4] (15)
learning rate α=0.3, momentum coefficient β=0.9. See fig. 5 for momentum-optimized BP neural network training results. In FIG. 5, the entire canvas is divided into four sections, each section displaying the output of each fatigue level. The abscissa represents the fatigue level and the ordinate represents the corresponding probability. In practice, for each input, the corresponding output is 4 points, for example, the output of the input signal is represented as follows:
T＝(0.2，0.1，0.4，0.3) (16)
the meaning of T is: the input signal X corresponds to a fatigue level of 0 with a probability of 0.2, a level I with a probability of 0.1, a level II with a probability of 0.4, and a level III with a probability of 0.3, so this signal corresponds to a fatigue level II. The predicted and total predicted results for each fatigue level test set sample are as follows:
1) Awake state: 0.950
2) I fatigue state: 0.897
3) II fatigue state: 0.917
4) III fatigue status: 0.943
Total probability: 0.927.
it should be understood that the exemplary embodiments described herein are illustrative and not limiting. Although one or more embodiments of the present invention have been described with reference to the accompanying drawings, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the following claims.
Claims (3)
1. The non-contact fatigue driving detection method based on the momentum optimization BP neural network is characterized by comprising the following steps of:
s10, acquiring physiological signals of a driver through a Doppler radar module;
s20, classifying physiological signals;
s30, filtering the physiological signals and decomposing the physiological signals by using a CEEMD algorithm to obtain signals of which the two sections of heart beat and respiration contain complete time-frequency domain characteristics;
s40, designing a BP neural network model with optimized momentum to train the data set, so as to obtain an algorithm model for detecting the fatigue state of the driver;
s50, detecting the fatigue state through an algorithm model for detecting the fatigue state of the driver;
the momentum-optimized BP neural network iteratively updates a weight matrix according to an error back propagation algorithm, and minimizes the mean square error between the actual output value and the expected output value of the network by utilizing gradient descent, so that an algorithm model for detecting the fatigue state of a driver is obtained;
in the BP neural network model for designing momentum optimization, the BP neural network weight iterative equation is as follows:
where alpha is the learning rate, m is the total sample size, beta is the momentum coefficient, and beta epsilon (0, 1),momentum gradient for previous iterationValue of->The weight error accumulated value;
the model building process is as follows:
first, forward propagation is realized, and the weight matrix of each layer is set as H (l-1) L is an integer, l.epsilon.2, L]The activation items of the hidden layer and the output layer are a (l) Representing, therefore:
the activation function selected by the network is a sigmoid function, which is defined as:
with the activation function, a nonlinear feature is added, for the whole sample set:
a (2) ＝g(H (1) X (i) )
a (l) ＝g(H (l-1) a (l-1) )
calculating activation term a of each layer by using forward propagation algorithm (l) According to the back propagation algorithm, the error term delta of the hidden layer and the output layer needs to be calculated (l) The calculation process is as follows:
δ (L) ＝a (L) -T (i)
δ (l) ＝(H (l) ) (T) δ (l+1) ×g'(H (l) a (l) )
δ (2) ＝(H (1) ) (T) δ (2) ×g'(H (1) X (i) )
g' (H) (l) a (l) ) G (H) (l) a (l) ) Is the first derivative of (a):
g'(H (l) a (l) )＝a (l) ×(1-a (l) )
at the time of calculating the activation item a (l) And error term delta (l) Then, according to the gradient descent algorithm, it is necessary to obtain the desired output by iterating and updating the weight matrix, thus defining a new variableThe weight errors of the r row and the c column of the first layer of the neural network, namely the weight error accumulation value,
according to the back propagation principle, the first partial derivative of the cost function J (θ) has the following properties:
the weight matrix is obtained according to the gradient descent algorithm as follows:
where alpha is the learning rate, m is the total sample size, the momentum gradient descent algorithm obtains a current gradient value using an exponentially weighted average of previous gradient values, and updates the weights using the current gradient value,
by usingTo represent the momentum gradient values, the specific algorithm is as follows:
initialization ofIs 0:
as the number of exercises increases,continuously updating:
wherein, beta is momentum coefficient, beta epsilon (0, 1);is the current momentum gradient value; />Momentum gradient value of last iteration; />For the weight error cumulative value,
and using a momentum gradient algorithm to replace a standard gradient descent algorithm to obtain a final weight iteration formula:
through multiple training, the network depth and the number of neurons per layer are finally determined, and are expressed by NN:
NN＝[2n 50 60 60 50 4]。
2. the method for detecting non-contact fatigue driving based on a momentum-optimized BP neural network according to claim 1, wherein the physiological signals at least comprise a respiration signal and a heartbeat signal of the driver.
3. The method for detecting the non-contact fatigue driving based on the BP neural network with momentum optimization according to claim 1, wherein the Doppler radar module adopts a microwave Doppler radar detector probe sensor HB100 module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911382375.8A CN111209815B (en) | 2019-12-28 | 2019-12-28 | Non-contact fatigue driving detection method based on BP neural network with momentum optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911382375.8A CN111209815B (en) | 2019-12-28 | 2019-12-28 | Non-contact fatigue driving detection method based on BP neural network with momentum optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111209815A CN111209815A (en) | 2020-05-29 |
| CN111209815B true CN111209815B (en) | 2023-08-22 |
Family
ID=70789433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911382375.8A Active CN111209815B (en) | 2019-12-28 | 2019-12-28 | Non-contact fatigue driving detection method based on BP neural network with momentum optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111209815B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111968341A (en) * | 2020-08-21 | 2020-11-20 | 无锡威孚高科技集团股份有限公司 | Fatigue driving detection system and method |
| CN117786513B (en) * | 2023-12-26 | 2024-08-02 | 深圳市龙华区妇幼保健院(深圳市龙华区妇幼保健计划生育服务中心、深圳市龙华区健康教育所) | Method and system for monitoring intelligent ultraviolet lamp capable of timing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106128032A (en) * | 2016-07-05 | 2016-11-16 | 北京理工大学珠海学院 | A kind of fatigue state monitoring and method for early warning and system thereof |
| CN106297194A (en) * | 2016-10-13 | 2017-01-04 | 杭州电子科技大学 | A kind of fatigue drive of car monitoring system |
| CN106504475A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
| CN106991531A (en) * | 2017-03-30 | 2017-07-28 | 国家电网公司 | Power distribution network project construction effect Post-assessment Method based on BP neural network |
| CN108013884A (en) * | 2018-01-26 | 2018-05-11 | 辽宁工业大学 | A kind of fatigue of automobile driver drives active safety monitoring system and its monitoring method |
| CN109886154A (en) * | 2019-01-30 | 2019-06-14 | 电子科技大学 | Most pedestrian's appearance attribute recognition methods according to collection joint training based on Inception V3 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10572800B2 (en) * | 2016-02-05 | 2020-02-25 | Nec Corporation | Accelerating deep neural network training with inconsistent stochastic gradient descent |
| US20180341851A1 (en) * | 2017-05-24 | 2018-11-29 | International Business Machines Corporation | Tuning of a machine learning system |
| US10803565B2 (en) * | 2018-07-10 | 2020-10-13 | Intel Corporation | Low-light imaging using trained convolutional neural networks |
-
2019
- 2019-12-28 CN CN201911382375.8A patent/CN111209815B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106128032A (en) * | 2016-07-05 | 2016-11-16 | 北京理工大学珠海学院 | A kind of fatigue state monitoring and method for early warning and system thereof |
| CN106297194A (en) * | 2016-10-13 | 2017-01-04 | 杭州电子科技大学 | A kind of fatigue drive of car monitoring system |
| CN106504475A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
| CN106991531A (en) * | 2017-03-30 | 2017-07-28 | 国家电网公司 | Power distribution network project construction effect Post-assessment Method based on BP neural network |
| CN108013884A (en) * | 2018-01-26 | 2018-05-11 | 辽宁工业大学 | A kind of fatigue of automobile driver drives active safety monitoring system and its monitoring method |
| CN109886154A (en) * | 2019-01-30 | 2019-06-14 | 电子科技大学 | Most pedestrian's appearance attribute recognition methods according to collection joint training based on Inception V3 |
Non-Patent Citations (1)
| Title |
|---|
| 基于多源信息融合的非接触式疲劳驾驶检测系统研究;杨希宁;《中国优秀硕士学位论文全文数据库信息科技辑》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111209815A (en) | 2020-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109124625B (en) | Driver fatigue state level grading method | |
| CN109567793B (en) | Arrhythmia classification-oriented ECG signal processing method | |
| CN113743471B (en) | Driving evaluation method and system | |
| CN107832737A (en) | Electrocardiogram interference identification method based on artificial intelligence | |
| CN108062561A (en) | A kind of short time data stream Forecasting Methodology based on long memory network model in short-term | |
| CN111209815B (en) | Non-contact fatigue driving detection method based on BP neural network with momentum optimization | |
| CN104523268A (en) | Electroencephalogram signal recognition fuzzy system and method with transfer learning ability | |
| CN103699873A (en) | Lower-limb flat ground walking gait recognition method based on GA-BP (Genetic Algorithm-Back Propagation) neural network | |
| CN111436929B (en) | Method for generating and identifying neurophysiological signals | |
| IT201900005868A1 (en) | Process of processing an electrophysiological signal, corresponding system, computer product and vehicle | |
| CN106127263A (en) | The human brain magnetic resonance image (MRI) classifying identification method extracted based on three-dimensional feature and system | |
| CN105868532B (en) | A kind of method and system of intelligent evaluation heart aging degree | |
| CN109770912A (en) | A kind of abnormal gait classification method based on depth convolutional neural networks | |
| CN109741007A (en) | A kind of subject personnel's screening technique of aviation cockpit workload test | |
| CN104834828A (en) | Method for diagnosing physiological abnormality of old people based on DS evidence theory-neural network algorithm | |
| CN110491506A (en) | Auricular fibrillation prediction model and its forecasting system | |
| CN114386707A (en) | Method and device for predicting track unevenness | |
| CN113988123A (en) | Electroencephalogram fatigue prediction method based on self-weighted increment RVFL network | |
| CN113409943A (en) | Psychological health intelligent screening system based on BP neural network | |
| CN115760210A (en) | Medicine sales prediction system and method based on IPSO-LSTM model | |
| CN113520319A (en) | Epileptic event risk management method and system based on logistic regression | |
| CN114464319B (en) | AMS susceptibility assessment system based on slow feature analysis and deep neural network | |
| El-Shafai et al. | Efficient Deep CNN Model for COVID-19 Classification. | |
| CN110836783A (en) | GA-BP magnetic suspension train fault detection method based on threshold judgment | |
| CN110916672A (en) | Old people daily activity monitoring method based on one-dimensional convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |