CN109034898A - A kind of BP neural network used car price evaluation algorithm based on improvement ant colony - Google Patents

A kind of BP neural network used car price evaluation algorithm based on improvement ant colony Download PDF

Info

Publication number
CN109034898A
CN109034898A CN201810825158.0A CN201810825158A CN109034898A CN 109034898 A CN109034898 A CN 109034898A CN 201810825158 A CN201810825158 A CN 201810825158A CN 109034898 A CN109034898 A CN 109034898A
Authority
CN
China
Prior art keywords
neural network
weight
value
ant
formula
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
CN201810825158.0A
Other languages
Chinese (zh)
Inventor
杜鹏
孙宁
钱玉洁
石慧珠
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.)
Changzhou Campus of Hohai University
Original Assignee
Changzhou Campus of Hohai University
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 Changzhou Campus of Hohai University filed Critical Changzhou Campus of Hohai University
Priority to CN201810825158.0A priority Critical patent/CN109034898A/en
Publication of CN109034898A publication Critical patent/CN109034898A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0278—Product appraisal
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Neurology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a kind of BP neural network used car price evaluation algorithms based on ant group algorithm optimization, choosing three layers of BP neural network is prototype, it is optimized using weight initialization process of the improved ant group algorithm to BP neural network, establish used car price evaluation model, step 1 that specific step is as follows: data are acquired and are pre-processed；Step 2: determining network topology structure；Step 3: the weight initialization process of BP neural network being optimized using improved ant group algorithm；Step 4: further the BP neural network after training optimization predicts used car price.The present invention provides a kind of BP neural network used car price evaluation algorithm based on ant group optimization, compared to traditional algorithm, it can improve in BP neural network and be easy to fall into that local optimum, convergence rate are slow, cause the defects of oscillation effect, to set up a set of online vehicle value appraisal system with practical value.

Description

A kind of BP neural network used car price evaluation algorithm based on improvement ant colony
Technical field
The present invention relates to a kind of based on the BP neural network used car price evaluation algorithm for improving ant colony, belongs to computer and answers Use field.
Background technique
It is growing to private car in conjunction with compatriots under network marketing and the theoretical increasingly developed background of internet big data Demand, it is neural network based large size Second-hand Vehicle Transaction platform be able to promote rapidly and apply.It trades in such platform and is Under system, by analyzing and adjust second-hand automobile market parameters in need of consideration, suitable neural network model is established, it can So that the precision of entire Second-hand Vehicle Transaction price evaluation improves.And with big data the relevant technologies be widely used in machine learning and The fields such as cognitive science, BP neural network algorithm are mainly used for carrying out function estimation and approximate computation model as one kind, It is coupled a large amount of neuron to be calculated, is able to achieve a kind of effectively considerable prediction model.
Used car is as a kind of physical assets, and more commonly used price evaluation method has replacement cost approach, receives in transaction Beneficial present value method, Market comparison approach and Liquidation-price Method.These existing appraisal algorithms excessively empirical mostly, without too many theoretical Basis, and not actively public algorithm details, low, appraisal low efficiency that there is algorithm transparencies, the defects of computational accuracy is not high, and Not by the reflection of the dynamic change of the surge of transaction data and trade market into calculating process, and these are all to determine two The key factor of handcart price.
Summary of the invention
In order to overcome the drawbacks of the prior art, the present invention proposes to disclose a kind of based on the BP neural network two for improving ant colony Handcart price evaluation algorithm substantially searches out certain weight range using the searching characteristic of ant group algorithm, at this time Initial weight of the weight as BP neural network recycles BP algorithm to advanced optimize network weight, can improve BP mind Be easy to fall into that local optimum, convergence rate are slow, cause the defects of oscillation effect in network, thus set up it is a set of have it is practical The online vehicle value appraisal system of value.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
One kind being based on the improved BP neural network used car price evaluation algorithm of ant group algorithm, chooses three layers of BP neural network For prototype, is optimized using weight initialization process of the improved ant group algorithm to BP neural network, establish used car price Assessment models, the specific steps are as follows:
Step 1: data are acquired and are pre-processed；
Step 2: determining network topology structure；
Step 3: the weight initialization process of BP neural network being optimized using improved ant group algorithm；
Step 4: further the BP neural network after training optimization predicts used car price.
Preferably, the data of step (1) acquisition are second-hand vehicle data and its transaction data as sample data, packet It includes car number, productive year, sell a year month, city, discharge capacity, new car price, mileage, vehicular applications, the degree of wear and a People's guiding price；The sample data of acquisition is pre-processed in the step (1): place is normalized in the sample data of acquisition Reason, specifically normalizes in [0,1] section, and normalization formula is as follows:
X0=(X-Xmin)/(Xmax-Xmin) (1)
In formula (1), X0For the data after normalization, X is initial data, Xmax、XminThe respectively maximum of raw data set Value and minimum value.
Preferably, in the step (2) network topology structure be three layers of BP neural network structure, including input layer, hide Layer, output layer, wherein
Input layer: inputting pretreated sample data, and each input node is mapped to a vehicle association attributes, Specially car number, productive year, sell a year month, city, discharge capacity, new car price, mileage, vehicular applications, the degree of wear With personal guiding price totally 10 neurons；
Hidden layer: rule of thumb formula (2) estimates best hidden layer neuron number,
In formula (2), H is hidden layer neuron number, and I is input layer number, and O is output layer neuron number, a For the constant in [1,10]；
Output layer: output used car activity price is as a result, Real-time Feedback is for reference.
Preferably, the optimization process of the weight initialization in the step (3) is as follows:
The weight section [- 5,5] of BP neural network is evenly dividing as 100 equal parts, for each power by (3a) parameter setting Value parameter establishes a pheromones table, remembers wsThe weighting parameter for needing to optimize for s-th, the value range of s are [1, N], and N is indicated For the total number of weight, i is to divide scale value, and every two divides adjacent scale value and constitutes a sub-regions；τ (i) is corresponding to i Pheromones value, wherein weight section [- 5,5] are evenly dividing as 100 equal parts, then divide scale value and share 101；
The total number N of the weight is by input layer number I, hidden layer neuron number H and output layer neuron Number O determines that calculation formula is as follows:
N=H* (I+O+1)+O (3)；
Meanwhile setting information element initial value is τ (i)=C, C ≠ 0, pheromones volatility coefficient ρ, pheromones incremental intensity Q, ACO Maximum number of iterations countmax and ACO optimize termination condition εACO；
(3b) discharges m ant, for any weighting parameter ws, n-th ant according to following new probability formula (4) from a bit It is moved to next point:
In formula (4), i indicates weighting parameter wsI-th of division scale value, the value range of i is [1,101],Indicate weighting parameter wsIn all ants the sum of pheromones, j represents jth ant, and ant is in neural network Iteration each time in, can be 101 above-mentioned divisions according to the pheromones value of error update oneself, pheromones value here Some value in scale value.
N-th ant is from weighting parameter wsDivision scale value by and merely through primary, the division for recording respective point is carved The division scale value combination of angle value, these points constitutes neural network weight parameter wsOne group of weighting parameter；
(3c) using Second-hand Vehicle Transaction data and its vehicle data as input training sample, the power obtained using step (3b) Parameter of the value combination as neural network, the input layer of BP neural network are all made of to hidden layer, hidden layer to output layer The output that Sigmoid S type excitation function carries out neural network calculates, as shown in formula (5):
In formula (5), net expression is hidden layer and output layer, input layer and hidden layer, functional relation between layers, Neural network excitation function belongs to conventional technical means and is described in detail so not adding in the present invention；
After SH obtains the output of neural network, mean square error is calculated, and take the maximum value of mean square error, such as formula (6) institute Show:
In formula (6), SampleNum is number of samples, and y is desired output, that is, training sample true value, and o is nerve net The real output value of network, o are determined by formula (5), belong to the basic fundamental scope of neural network；
The smallest one group of weight of E is recorded after (3d) all ant construction solutions, compares minimal error EminWith εACOSize, If Emin<εACO, then it is done directly initialization procedure and exits, otherwise goes to step (3e)；
(3e) Pheromone update: weight wsI-th division scale value pheromone update strategy such as formula (7) shown in:
In formula (7),For weight wsThe corresponding t of i-th of division scale value for n-th ant in ant colony The pheromones value that ant warp updates later, the value range of μ are [10,100]；
(3f) repeats step (3b)-(3d), until meeting maximum number of iterations countmax, completes initialization procedure.
Preferably, the process of the BP neural network after further training optimizes in the step (4) are as follows: according to ant group algorithm The smallest one group of weight of E and deviation (as weighting parameter w found by step 3 (d)s) as BP algorithm initial weight and partially Difference calculates the error between network output and reality output, and error is propagated backward to input layer by output layer, further adjusts Whole weight and deviation repeat above procedure, until meeting training exit criteria.
The process of BP neural network after further training optimizes in step (4) in the present invention belongs to conventional technical means, So not plus being described in detail.
It is calculated the utility model has the advantages that the present invention provides one kind based on the improved BP neural network used car price evaluation of ant group algorithm Method introduces in ant group algorithmImprove the ability of searching optimum of algorithm.Compared with prior art, the present invention has Following advantage:
(1) compared to the assessment algorithm of tradition machinery formula (vehicle assessed value=replacement cost * newness rate * regulation coefficient), Precision based on the BP neural network used car price evaluation algorithm prediction for improving ant colony is higher；
(2) present invention takes the power of improved ant group algorithm Optimized BP Neural Network on the basis of original BP neural network It is worth initialization procedure, improves and be easy to fall into that local optimum, convergence rate are slow, cause the defects of oscillation effect in BP neural network, To set up a set of online vehicle value appraisal system with practical value.
(3) after user completes transaction, new transaction data is put into training to maintain the high-accuracy of model, is allowed to more hold Service is provided long for user.
Detailed description of the invention
Fig. 1 is data parameters table of the invention.
Fig. 2 is the neural network structure figure of specific example of the invention.
Fig. 3 is of the invention based on the BP neural network algorithm flow chart for improving ant colony.
Specific embodiment
In order to make those skilled in the art better understand the technical solutions in the application, below to the embodiment of the present application In technical solution be clearly and completely described, it is clear that described embodiments are only a part of embodiments of the present application, Instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not making creative labor Every other embodiment obtained under the premise of dynamic, shall fall within the protection scope of the present application.
One kind being based on the improved BP neural network used car price evaluation algorithm of ant group algorithm, chooses three layers of BP neural network For prototype, is optimized using weight initialization process of the improved ant group algorithm to BP neural network, establish used car price Assessment models, the specific steps are as follows:
Step 1: data are acquired and are pre-processed；
Step 2: determining network topology structure；
Step 3: the weight initialization process of BP neural network being optimized using improved ant group algorithm；
Step 4: further the BP neural network after training optimization predicts used car price.
Preferably, the data of step (1) acquisition are second-hand vehicle data and its transaction data as sample data, packet It includes car number, productive year, sell a year month, city, discharge capacity, new car price, mileage, vehicular applications, the degree of wear and a People's guiding price；The sample data of acquisition is pre-processed in the step (1): place is normalized in the sample data of acquisition Reason, specifically normalizes in [0,1] section, and normalization formula is as follows:
X0=(X-Xmin)/(Xmax-Xmin) (1)
In formula (1), X0For the data after normalization, X is initial data, Xmax、XminThe respectively maximum of raw data set Value and minimum value.
Preferably, in the step (2) network topology structure be three layers of BP neural network structure, including input layer, hide Layer, output layer, wherein
Input layer: inputting pretreated sample data, and each input node is mapped to a vehicle association attributes, Specially car number, productive year, sell a year month, city, discharge capacity, new car price, mileage, vehicular applications, the degree of wear With personal guiding price totally 10 neurons；
Hidden layer: rule of thumb formula (2) estimates best hidden layer neuron number,
In formula (2), H is hidden layer neuron number, and I is input layer number, and O is output layer neuron number, a For the constant in [1,10]；
Output layer: output used car activity price is as a result, Real-time Feedback is for reference.
Preferably, the optimization process of the weight initialization in the step (3) is as follows:
The weight section [- 5,5] of BP neural network is evenly dividing as 100 equal parts, for each power by (3a) parameter setting Value parameter establishes a pheromones table, as shown in Table 1,
One parameter information table of table
Remember wsThe value range of the weighting parameter for needing to optimize for s-th, s is [1, N], and N is expressed as the total number of weight, Ai is to divide scale value, is counted as a point, and every two divides adjacent scale value and constitutes a sub-regions；τ (i) is corresponding to Ai Pheromones value, wherein weight section [- 5,5] are evenly dividing as 100 equal parts, then divide scale value and share 101；
The total number N of the weight is by input layer number I, hidden layer neuron number H and output layer neuron Number O determines that calculation formula is as follows:
N=H* (I+O+1)+O (3)；
Meanwhile setting information element initial value is τ0, pheromones volatility coefficient ρ, the greatest iteration of pheromones incremental intensity Q, ACO Number countmax and ACO optimize termination condition εACO；
(3b) discharges m ant, for any weighting parameter ws, n-th ant according to following new probability formula (4) from a bit It is moved to next point:
In formula (4), i indicates weighting parameter wsI-th of division scale value, the value range of i is [1,101],Indicate weighting parameter wsIn all ants the sum of pheromones, j represents jth ant, and ant is in neural network Iteration each time in, can be according to the pheromones value of error update oneself, the pheromones value in the present invention is above-mentioned 101 Divide some value in scale value；
N-th ant is from weighting parameter wsDivision scale value by and merely through primary, the division for recording respective point is carved The combination of angle value, these points constitutes one group of weighting parameter of neural network；
(3c) using Second-hand Vehicle Transaction data and its vehicle data as input training sample, the power obtained using step (3b) Parameter of the value combination as neural network, the input layer of BP neural network are all made of to hidden layer, hidden layer to output layer The output that Sigmoid S type excitation function carries out neural network calculates, as shown in formula (5):
After obtaining the output of neural network, mean square error is calculated, and take the maximum value of mean square error, as shown in formula (6):
In formula (6), SampleNum is number of samples, and y and o are the reality for being respectively desired output and neural network Output valve；
The smallest one group of weight of E is recorded after (3d) all ant construction solutions, compares minimal error EminWith εACOSize, If Emin<εACO, then it is done directly initialization procedure and exits, otherwise goes to step (3e)；
(3e) Pheromone update: weight wsI-th point (divide scale value) pheromone update strategy such as formula (7) institute Show:
In formula,For weight wsI-th point of corresponding t in ant colony n-th ant warp later update Pheromones value, the value range of μ is [10,100]；
(3f) repeats step (3b)-(3d), until meeting maximum number of iterations countmax, completes initialization procedure.
Preferably, the process of the BP neural network after further training optimizes in the step (4) are as follows: look for ant group algorithm The one group of E arrivedminInitial weight and deviation of the smallest weighting parameter as BP algorithm, calculate network output and reality output it Between error, and error is propagated backward into input layer by output layer, further adjusts weight and deviation, repeat above procedure, Until meeting training exit criteria.
In traditional ACO pheromone update strategy, offspring ant according to the pheromones table updated after former generation Ant Search come Probability selection path is carried out, since pheromones volatility coefficient ρ is a fixed value, on those paths being never searched Pheromones can fade away, and the probability for causing these paths to be selected reduces, and the probability in the increased non-optimal path of pheromones But increase, and then algorithm is made to fall into local optimum.Therefore the ability of searching optimum that improve algorithm, finds algorithm as far as possible optimal Solution just must suitably reduce the pheromones quantity on routed, i.e., the pheromones for suitably weakening offspring ant contribute ability, Introduce Dynamic geneWherein the value of μ is generally in [10,100] range.In the present embodiment, μ Take 10.
The transmission function of hidden layer and the activation primitive of output layer are Sigmoid S in BP neural network in the present embodiment Type tangent cutve excitation function.
The routine techniques hand that BP neural network training process involved in the present invention is grasped by those skilled in the art Section is described in detail so not adding.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Two kinds of modifications of these embodiments will be readily apparent to those skilled in the art, it is as defined herein General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one The widest scope of cause.

Claims (5)

1. one kind is based on the improved BP neural network used car price evaluation algorithm of ant group algorithm, which is characterized in that choose three layers BP neural network is prototype, is optimized using weight initialization process of the improved ant group algorithm to BP neural network, is established Used car price evaluation model, the specific steps are as follows:
Step 1: data are acquired and are pre-processed；
Step 2: determining network topology structure；
Step 3: the weight initialization process of BP neural network being optimized using improved ant group algorithm；
Step 4: further the BP neural network after training optimization predicts used car price.
2. one kind according to claim 1 is based on the improved BP neural network used car price evaluation algorithm of ant group algorithm, It is characterized in that, the data of step (1) acquisition are second-hand vehicle data and its transaction data as sample data, including vehicle Number, productive year sell a year month, city, discharge capacity, new car price, mileage, vehicular applications, the degree of wear and individual and refer to Lead valence；The sample data of acquisition is pre-processed in the step (1): the sample data of acquisition is normalized, It specifically normalizes in [0,1] section, normalization formula is as follows:
X0=(X-Xmin)/(Xmax-Xmin) (1)
In formula (1), X0For the data after normalization, X is initial data, Xmax、XminThe respectively maximum value of raw data set and most Small value.
3. according to claim 1 or 2 a kind of based on the improved BP neural network used car price evaluation calculation of ant group algorithm Method, which is characterized in that in the step (2) network topology structure be three layers of BP neural network structure, including input layer, hide Layer, output layer, wherein
Input layer: inputting pretreated sample data, and each input node is mapped to a vehicle association attributes, specifically For car number, productive year, sell a year month, city, discharge capacity, new car price, mileage, vehicular applications, the degree of wear and a People's guiding price totally 10 neurons；
Hidden layer: rule of thumb formula (2) estimates best hidden layer neuron number,
In formula (2), H is hidden layer neuron number, and I is input layer number, and O is output layer neuron number, and a is [1,10] constant in；
Output layer: output used car activity price is as a result, Real-time Feedback is for reference.
4. one kind according to claim 3 is based on the improved BP neural network used car price evaluation algorithm of ant group algorithm, It is characterized in that, the optimization process of the weight initialization in the step (3) is as follows:
The weight section [- 5,5] of BP neural network is evenly dividing as 100 equal parts, joins for each weight by (3a) parameter setting Number establishes a pheromones table, remembers wsThe value range of the weighting parameter for needing to optimize for s-th, s is [1, N], and N is expressed as weighing The total number of value, i are to divide scale value, and every two divides adjacent scale value and constitutes a sub-regions；τ (i) is letter corresponding to i Breath element value, wherein weight section [- 5,5] are evenly dividing as 100 equal parts, then divide scale value and share 101；
The total number N of the weight is by input layer number I, hidden layer neuron number H and output layer neuron number O It determines, calculation formula is as follows:
N=H* (I+O+1)+O (3)；
Meanwhile setting information element initial value is τ (i)=C, C ≠ 0, pheromones volatility coefficient ρ, pheromones incremental intensity Q, ACO are most Big the number of iterations countmax and ACO optimize termination condition εACO；
(3b) discharges m ant, for any weighting parameter ws, n-th ant according to following new probability formula (4) from some movement To next point:
In formula (4), i indicates weighting parameter wsI-th of division scale value, the value range of i is [1,101], Indicate weighting parameter wsIn all ants the sum of pheromones；
N-th ant is from weighting parameter wsDivision scale value by and merely through primary, record the division scale value of respective point, The combination of these points constitutes neural network weight parameter wsOne group of weighting parameter；
(3c) using Second-hand Vehicle Transaction data and its vehicle data as input training sample, the weight group obtained using step (3b) Cooperation is the parameter of neural network, and the input layer of BP neural network is all made of Sigmoid S to hidden layer, hidden layer to output layer The output that type excitation function carries out neural network calculates, as shown in formula (5):
After SH obtains the output of neural network, mean square error is calculated, and take the maximum value of mean square error, as shown in formula (6):
In formula (6), SampleNum is number of samples, and y is desired output, and o is the real output value of neural network；
The smallest one group of weight of E is recorded after (3d) all ant construction solutions, compares minimal error EminWith εACOSize, if Emin<εACO, then it is done directly initialization procedure and exits, otherwise goes to step (3e)；
(3e) Pheromone update: weight wsI-th division scale value pheromone update strategy such as formula (7) shown in:
In formula (7),For weight wsDivide the corresponding t of scale value i-th and passed through for n-th ant in ant colony Later the pheromones value updated, the value range of μ are [10,100]；
(3f) repeats step (3b)-(3d), until meeting maximum number of iterations countmax, completes initialization procedure.
5. it is according to claim 4 a kind of based on the BP neural network used car price evaluation algorithm for improving ant colony, it is special Sign is, the process of the BP neural network after optimization is further trained in the step (4) are as follows: according to ant group algorithm by step 3 (d) E foundminThe initial weight and deviation of the smallest one group of weight and deviation as BP algorithm calculate network output and reality Error between output, and error is propagated backward to input layer by output layer further adjusts weight and deviation, repeat more than Process, until meeting training exit criteria.
CN201810825158.0A 2018-07-25 2018-07-25 A kind of BP neural network used car price evaluation algorithm based on improvement ant colony Pending CN109034898A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810825158.0A CN109034898A (en) 2018-07-25 2018-07-25 A kind of BP neural network used car price evaluation algorithm based on improvement ant colony

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810825158.0A CN109034898A (en) 2018-07-25 2018-07-25 A kind of BP neural network used car price evaluation algorithm based on improvement ant colony

Publications (1)

Publication Number Publication Date
CN109034898A true CN109034898A (en) 2018-12-18

Family

ID=64645947

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810825158.0A Pending CN109034898A (en) 2018-07-25 2018-07-25 A kind of BP neural network used car price evaluation algorithm based on improvement ant colony

Country Status (1)

Country Link
CN (1) CN109034898A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110322297A (en) * 2019-07-16 2019-10-11 山东科技大学 Medium-and-large-sized stamping die quotation prediction technique based on BP neural network
CN110544135A (en) * 2019-09-10 2019-12-06 金瓜子科技发展（北京）有限公司 Data processing method and device
CN110909670A (en) * 2019-11-21 2020-03-24 江苏理工学院 Unstructured road identification method
CN111523916A (en) * 2019-02-01 2020-08-11 上汽通用汽车有限公司 Vehicle price evaluation system and method
CN111598620A (en) * 2020-05-20 2020-08-28 上海贤合汽车信息咨询服务有限公司 Remote accurate pricing system for second-hand vehicles
CN111724189A (en) * 2019-06-27 2020-09-29 上海妃鱼网络科技有限公司 Big data-based second-hand commodity valuation method
CN112631890A (en) * 2020-12-31 2021-04-09 西安理工大学 Method for predicting cloud server resource performance based on LSTM-ACO model
CN112949813A (en) * 2019-11-26 2021-06-11 张汉威 Artificial intelligence training parameter iteration method
CN113283161A (en) * 2021-04-28 2021-08-20 江西核工业测绘院集团有限公司 Landslide deformation displacement prediction method for improving BP neural network
CN115619030A (en) * 2022-10-28 2023-01-17 清华大学 Factory network collaborative optimization method and device for urban sewage system and electronic equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103955743A (en) * 2014-04-22 2014-07-30 江苏大学 Ultrahigh-pressure water jet road mark line cleaning effect forecasting method and device
CN106934451A (en) * 2015-12-29 2017-07-07 扬州大学 A kind of BP neural network WSN forest fire crime prevention systems based on ant group optimization
CN107369043A (en) * 2017-07-19 2017-11-21 河海大学常州校区 A kind of used car price evaluation optimized algorithm based on BP neural network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103955743A (en) * 2014-04-22 2014-07-30 江苏大学 Ultrahigh-pressure water jet road mark line cleaning effect forecasting method and device
CN106934451A (en) * 2015-12-29 2017-07-07 扬州大学 A kind of BP neural network WSN forest fire crime prevention systems based on ant group optimization
CN107369043A (en) * 2017-07-19 2017-11-21 河海大学常州校区 A kind of used car price evaluation optimized algorithm based on BP neural network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张艳蕊: "基于改进蚁群算法的BP神经网络优化的研究与应用", 《中国优秀硕士学位论文全文数据库》 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111523916A (en) * 2019-02-01 2020-08-11 上汽通用汽车有限公司 Vehicle price evaluation system and method
CN111724189A (en) * 2019-06-27 2020-09-29 上海妃鱼网络科技有限公司 Big data-based second-hand commodity valuation method
CN110322297A (en) * 2019-07-16 2019-10-11 山东科技大学 Medium-and-large-sized stamping die quotation prediction technique based on BP neural network
CN110544135A (en) * 2019-09-10 2019-12-06 金瓜子科技发展（北京）有限公司 Data processing method and device
CN110909670A (en) * 2019-11-21 2020-03-24 江苏理工学院 Unstructured road identification method
CN112949813A (en) * 2019-11-26 2021-06-11 张汉威 Artificial intelligence training parameter iteration method
CN111598620A (en) * 2020-05-20 2020-08-28 上海贤合汽车信息咨询服务有限公司 Remote accurate pricing system for second-hand vehicles
CN112631890A (en) * 2020-12-31 2021-04-09 西安理工大学 Method for predicting cloud server resource performance based on LSTM-ACO model
CN113283161A (en) * 2021-04-28 2021-08-20 江西核工业测绘院集团有限公司 Landslide deformation displacement prediction method for improving BP neural network
CN115619030A (en) * 2022-10-28 2023-01-17 清华大学 Factory network collaborative optimization method and device for urban sewage system and electronic equipment

Similar Documents

Publication Publication Date Title
CN109034898A (en) A kind of BP neural network used car price evaluation algorithm based on improvement ant colony
CN111428147B (en) Social recommendation method of heterogeneous graph volume network combining social and interest information
CN109886589A (en) A method of low-carbon Job-Shop is solved based on whale optimization algorithm is improved
Liu et al. Predicting housing prices in China based on modified Holt's exponential smoothing incorporating whale optimization algorithm
CN109377260A (en) User behavior analysis system towards apparel industry
CN108876001B (en) Short-term power load prediction method based on twin support vector machine
CN101694652A (en) Network resource personalized recommended method based on ultrafast neural network
CN109783738A (en) A kind of double extreme learning machine mixing collaborative filtering recommending methods based on more similarities
CN111581516A (en) Investment product recommendation method and related device
Xiao et al. A novel sub-models selection algorithm based on max-relevance and min-redundancy neighborhood mutual information
CN108009925A (en) A kind of fund asset configuration system and method based on network clustering
CN107481135A (en) A kind of personal credit evaluation method and system based on BP neural network
CN108229750A (en) A kind of stock yield Forecasting Methodology
CN109214546A (en) A kind of Power Short-Term Load Forecasting method based on improved HS-NARX neural network
CN109271424A (en) A kind of parameter adaptive clustering method based on density
Liu et al. Financial data forecasting using optimized echo state network
Alemdar et al. A genetic game of trade, growth and externalities
Baker et al. Machine learning: factorization machines and normalized discounted cumulative gain for tourism recommender system optimisation
CN109919374A (en) Prediction of Stock Price method based on APSO-BP neural network
CN117764227A (en) Customer loss prediction device for gas station
Wang et al. Predictions models of Taiwan dollar to US dollar and RMB exchange rate based on modified PSO and GRNN
Zhang et al. Daily tourism forecasting through a novel method based on principal component analysis, grey wolf optimizer, and extreme learning machine
CN112288187A (en) Big data-based electricity sales amount prediction method
CN111028086A (en) Enhanced index tracking method based on clustering and LSTM network
CN115687757A (en) Recommendation method fusing hierarchical attention and feature interaction and application system thereof

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20181218