CN109389183A - Method for detecting weak signals based on optimum organization support vector machines in Chaotic Background - Google Patents
Method for detecting weak signals based on optimum organization support vector machines in Chaotic Background Download PDFInfo
- Publication number
- CN109389183A CN109389183A CN201811306325.7A CN201811306325A CN109389183A CN 109389183 A CN109389183 A CN 109389183A CN 201811306325 A CN201811306325 A CN 201811306325A CN 109389183 A CN109389183 A CN 109389183A
- Authority
- CN
- China
- Prior art keywords
- support vector
- kernel function
- vector machines
- optimization
- teaching
- 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
Links
Classifications
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the method for detecting weak signals based on optimum organization support vector machines in a kind of Chaotic Background, it include: that Radial basis kernel function and Polynomial kernel function are bonded compound kernel function support vector machines, optimized parameter is obtained using the teaching optimization algorithm optimization compound kernel function support vector machines is improved, final combination SVM prediction model is established using the optimized parameter after optimization, and Single-step Prediction error analyze and therefrom judge in Chaotic Background noise with the presence or absence of weak target signal.The present invention can utilize ITLBO algorithm optimization combination S VM model, improve precision of prediction and forecasting efficiency, can fast and effeciently detect the small-signal in Chaotic Background, and have lower thresholding.
Description
Technical field
The present invention relates to the method fields of the small-signal in detection Chaotic Background, more particularly to by improving teaching optimization
Algorithm optimizes supporting vector machine model parameter.
Background technique
Chaos phenomenon is a kind of irregular movement generated by non-linear determining system, is widely present in meteorology, the hydrology, leads to
The various fields such as letter and economy.Chaos have interior randomness, monolithic stability local instability, it is short-term predictable and for a long time can not be pre-
The features such as the property surveyed.In recent years, deepening continuously and its in signal processing, automatic control, electric power and gold with chaology research
Melt the extensive use in the fields such as short-term forecast, the modeling and prediction of chaos time sequence have become one of chaos field very
Important research direction.
With the appearance of artificial intelligence approach, more and more researchers are applied it in time series forecasting.It is close
Since year, it includes neural network, echo state network (echo state network, letter that researcher, which proposes many methods,
Be denoted as ESN), support vector machines (support vector machine, be abbreviated as SVM) etc..Support vector machines follows structure wind
Dangerous minimization principle has many advantages, such as that dimension is insensitive, generalization ability is good, global optimum, uses and compares in small-sample learning
Extensively.The kernel function for meeting Mercer condition by introducing, converts the nonlinear problem of low-dimensional to linear in higher dimensional space
Classification problem.In support vector machines theory, different kernel functions can generate different algorithms, and prediction effect is also different.Currently,
The kernel function of SVM mainly has: global kernel function and local kernel function.Global kernel function allows to influence core letter apart from farther away point
Number, the point that local kernel function allows to be closer influence kernel function.
Summary of the invention
It is an object of that present invention to provide the Detection of Weak Signals based on optimum organization support vector machines in a kind of Chaotic Background
Method improves precision of prediction and forecasting efficiency, can fast and effeciently detect chaos using ITLBO algorithm optimization combination S VM model
Small-signal in background, and there is lower thresholding.
To reach above-mentioned purpose, in conjunction with Fig. 1, the present invention is proposed in a kind of Chaotic Background based on optimum organization support vector machines
Method for detecting weak signals, which comprises
Radial basis kernel function and Polynomial kernel function are bonded compound kernel function support vector machines, imparted knowledge to students using improving
Optimization algorithm optimizes the compound kernel function support vector machines and obtains optimized parameter, is established using the optimized parameter after optimization final
Combination SVM prediction model, to Single-step Prediction error carry out analyze and therefrom judge whether deposit in Chaotic Background noise
In weak target signal.
In further embodiment, it the described method comprises the following steps:
S1: Radial basis kernel function and Polynomial kernel function are bonded compound kernel function support vector machines, determine combination
The value range of kernel function ratio ρ, penalty coefficient C, polynomial parameters q and radial base width cs, if teaching number g=0, maximum
Teaching number is G；
S2: pairing kernel function ratio ρ, penalty coefficient C, polynomial parameters q and four parameters of radial base width cs carry out real number
Coding；
S3: being predicted using mix vector machine, calculates the fitness of individual；
S4: using optimized parameter is obtained after improving teaching optimization algorithm optimization, teaching number g adds 1；
S5: judging whether teaching number g is equal to maximum teaching number G, and S6 is entered step if g=G, otherwise repeats to walk
Rapid S3 to S5 is until g=G；
S6: the model parameter after output optimization；
S7: combination SVM prediction model is established using the optimized parameter after optimization and to predict chaos sequence
Column judge in Chaotic Background noise with the presence or absence of weak target signal.
In further embodiment, the method also includes:
It in the step S3, is predicted using mix vector machine, the fitness of individual is sought by following formula:
Wherein, n is the sum of training set individual, yiIndicate true value,Indicate predicted value.
In further embodiment, the method also includes:
In the step S7, combination SVM prediction model is established using the optimized parameter after optimization and to pre-
Chaos sequence is surveyed, precision of prediction and predicted time are calculated, is judged in Chaotic Background noise with the presence or absence of weak target signal.
In further embodiment, the method also includes:
In the step S4, obtained after being optimized using the professor in improvement teaching optimization algorithm, study, feedback three phases
Optimized parameter, teaching number g add 1.
In further embodiment, the method also includes:
Emulation experiment is carried out to Lorenz chaos system and Observed sea clutter, to verify combination SVM prediction
The validity of model.
The above technical solution of the present invention, compared with existing, significant beneficial effect is,.
It should be appreciated that as long as aforementioned concepts and all combinations additionally conceived described in greater detail below are at this
It can be viewed as a part of the subject matter of the disclosure in the case that the design of sample is not conflicting.In addition, required guarantor
All combinations of the theme of shield are considered as a part of the subject matter of the disclosure.
Can be more fully appreciated from the following description in conjunction with attached drawing present invention teach that the foregoing and other aspects, reality
Apply example and feature.The features and/or benefits of other additional aspects such as illustrative embodiments of the invention will be below
Description in it is obvious, or learnt in practice by the specific embodiment instructed according to the present invention.
Detailed description of the invention
Attached drawing is not intended to drawn to scale.In the accompanying drawings, identical or nearly identical group each of is shown in each figure
It can be indicated by the same numeral at part.For clarity, in each figure, not each component part is labeled.
Now, example will be passed through and the embodiments of various aspects of the invention is described in reference to the drawings, in which:
Fig. 1 is the method flow diagram of specific embodiments of the present invention one.
Fig. 2 is the method flow diagram of specific embodiments of the present invention two.
Specific embodiment
In order to better understand the technical content of the present invention, special to lift specific embodiment and institute's accompanying drawings is cooperated to be described as follows.
Various aspects with reference to the accompanying drawings to describe the present invention in the disclosure, shown in the drawings of the embodiment of many explanations.
Embodiment of the disclosure need not be defined on including all aspects of the invention.It should be appreciated that a variety of designs and reality presented hereinbefore
Those of apply example, and describe in more detail below design and embodiment can in many ways in any one come it is real
It applies, this is because conception and embodiment disclosed in this invention are not limited to any embodiment.In addition, disclosed by the invention one
A little aspects can be used alone, or otherwise any appropriately combined use with disclosed by the invention.
The traditional SVM prediction model mentioned in background technique there are aiming at the problem that, the present invention by RBF kernel function with it is multinomial
Formula kernel function is bonded compound kernel function support vector machines, using improvement teaching optimization algorithm (improved teaching
Learning based optimization, is abbreviated as ITLBO) optimal prediction model obtains optimized parameter, propose chaos back
The combination support vector machine method based on improvement teaching optimization algorithm of small-signal is detected in scape.
Learning aid optimization algorithm (TLBO) is a kind of novel Swarm Intelligence Algorithm proposed in recent years, and simulation is reality
Teachers ' teaching and student's study is in life to improve the process of school grade, and algorithm has simplicity, scalability, flexibly
The features such as property, robustness, self-organization, implict parallelism, it is widely used in multiple fields.
Relative to basic learning aid optimization algorithm (TLBO), improved learning aid optimization algorithm (ITLBO) is anti-by being added
The feedback stage improves the low optimization accuracy of algorithm so that the students and teacher of low academic carries out feedback communication in time；Meanwhile being
Overcome Premature convergence, introduces accurate sex factor, maintain population diversity, numerical experimentation shows that ITLBO algorithm compares base
This TLBO algorithm is more advantageous in convergence rate and low optimization accuracy.
Specific embodiment one
In conjunction with Fig. 1, the present invention refers to the Detection of Weak Signals based on optimum organization support vector machines in a kind of Chaotic Background
Method, which comprises
Radial basis kernel function and Polynomial kernel function are bonded compound kernel function support vector machines, imparted knowledge to students using improving
Optimization algorithm optimizes the compound kernel function support vector machines and obtains optimized parameter, is established using the optimized parameter after optimization final
Combination SVM prediction model, to Single-step Prediction error carry out analyze and therefrom judge whether deposit in Chaotic Background noise
In weak target signal.
RBF kernel function and Polynomial kernel function are bonded compound kernel function support vector machines by the present invention, and are used
ITLBO algorithm optimization prediction model obtains optimized parameter, effectively prevents the blindness in the selection of SVM model parameter, improves
The performance of working efficiency and SVM in Chaotic time series forecasting.This method can detect weak target signal well,
And detection threshold is low, precision of prediction is high.
Specific embodiment two
In conjunction with Fig. 2, method mentioned by the present invention the following steps are included:
S1: Radial basis kernel function and Polynomial kernel function are bonded compound kernel function support vector machines, determine combination
The value range of kernel function ratio ρ, penalty coefficient C, polynomial parameters q and radial base width cs, if teaching number g=0, maximum
Teaching number is G.
S2: pairing kernel function ratio ρ, penalty coefficient C, polynomial parameters q and four parameters of radial base width cs carry out real number
Coding.
S3: being predicted using mix vector machine, calculates the fitness of individual.
S4: using optimized parameter is obtained after improving teaching optimization algorithm optimization, teaching number g adds 1.
S5: judging whether teaching number g is equal to maximum teaching number G, and S6 is entered step if g=G, otherwise repeats to walk
Rapid S3 to S5 is until g=G.
S6: the model parameter after output optimization.
S7: combination SVM prediction model is established using the optimized parameter after optimization and to predict chaos sequence
Column judge with the presence or absence of weak target signal in Chaotic Background noise, specifically, establishing combination using the optimized parameter after optimization
SVM prediction model and to predict chaos sequence, calculates precision of prediction and predicted time, judges that Chaotic Background is made an uproar
It whether there is weak target signal in sound.By establishing the one-step prediction model of Chaotic Background noise, detected from prediction error
The weak target signal being submerged in Chaotic Background noise, improves signal-to-noise ratio.
Wherein, the precision of prediction of combination S VM is by compound kernel function ratio ρ, penalty coefficient C, polynomial parameters q and RBF wide
It spends tetra- parameters of σ to determine, the value by calculating fitness function judges SVM predictive ability.
In some instances, fitness function is
Wherein, n is the sum of training set individual, yiIndicate true value,Indicate predicted value.
Therefore, in the step S3, predicted using mix vector machine, the suitable of individual can be asked by above-mentioned formula
Response.
It is excellent using the professor in improvement teaching optimization algorithm, study, feedback three phases in the step S4 in conjunction with Fig. 2
Optimized parameter is obtained after change, teaching number g adds 1.
ITLBO algorithm increases the chance of poor students and teacher's exchange by the way that feedback stage is added after the study stage,
Accelerate the speed that poor student draws close to good student, effectively avoids the blindness in the selection of combination S VM model parameter.Pass through
ITLBO algorithm optimization combination S VM model parameter simultaneously establishes prediction model, analyze to Single-step Prediction error and therefrom judgement mixes
It whether there is weak target signal in ignorant ambient noise.
In other examples, it is assumed that aforementioned chaos system is Lorenz chaos system, the method also includes:
Emulation experiment is carried out to Lorenz chaos system and Observed sea clutter, to verify combination SVM prediction
The validity of model.
Although the present invention has been disclosed as a preferred embodiment, however, it is not to limit the invention.Skill belonging to the present invention
Has usually intellectual in art field, without departing from the spirit and scope of the present invention, when can be used for a variety of modifications and variations.Cause
This, the scope of protection of the present invention is defined by those of the claims.
Claims (6)
1. the method for detecting weak signals based on optimum organization support vector machines in a kind of Chaotic Background, which is characterized in that described
Method includes:
Radial basis kernel function and Polynomial kernel function are bonded compound kernel function support vector machines, optimized using teaching is improved
Compound kernel function support vector machines described in algorithm optimization obtains optimized parameter, and final group is established using the optimized parameter after optimization
SVM prediction model is closed, Single-step Prediction error analyze and therefrom judge in Chaotic Background noise with the presence or absence of micro-
Weak signal target signal.
2. the method for detecting weak signals based on optimum organization support vector machines in Chaotic Background according to claim 1,
It is characterized in that, the described method comprises the following steps:
S1: being bonded compound kernel function support vector machines for Radial basis kernel function and Polynomial kernel function, determines group synkaryon letter
The value range of number ratio ρ, penalty coefficient C, polynomial parameters q and radial base width cs, if teaching number g=0, maximum teaching
Number is G；
S2: pairing kernel function ratio ρ, penalty coefficient C, polynomial parameters q and four parameters of radial base width cs carry out real number volume
Code；
S3: being predicted using mix vector machine, calculates the fitness of individual；
S4: using optimized parameter is obtained after improving teaching optimization algorithm optimization, teaching number g adds 1；
S5: whether the number g that judges to impart knowledge to students is equal to maximum teaching number G, and S6 is entered step if g=G, otherwise repeatedly step S3
To S5 until g=G；
S6: the model parameter after output optimization；
S7: using the optimized parameter foundation combination SVM prediction model after optimization and to predict chaos sequence, sentence
It whether there is weak target signal in disconnected Chaotic Background noise.
3. the method for detecting weak signals based on optimum organization support vector machines in Chaotic Background according to claim 2,
It is characterized in that, the method also includes:
It in the step S3, is predicted using mix vector machine, the fitness of individual is sought by following formula:
Wherein, n is the sum of training set individual, yiIndicate true value,Indicate predicted value.
4. the method for detecting weak signals based on optimum organization support vector machines in Chaotic Background according to claim 2,
It is characterized in that, the method also includes:
In the step S7, combination SVM prediction model is established using the optimized parameter after optimization and to predict to mix
Ignorant sequence calculates precision of prediction and predicted time, judges in Chaotic Background noise with the presence or absence of weak target signal.
5. the method for detecting weak signals based on optimum organization support vector machines in Chaotic Background according to claim 2,
It is characterized in that, the method also includes:
In the step S4, obtained after being optimized using the professor in improvement teaching optimization algorithm, study, feedback three phases optimal
Parameter, teaching number g add 1.
6. according to claim 1 based on the faint letter of optimum organization support vector machines in Chaotic Background described in any one of -5
Number detection method, which is characterized in that the method also includes:
Emulation experiment is carried out to Lorenz chaos system and Observed sea clutter, to verify combination SVM prediction model
Validity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811306325.7A CN109389183A (en) | 2018-11-05 | 2018-11-05 | Method for detecting weak signals based on optimum organization support vector machines in Chaotic Background |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811306325.7A CN109389183A (en) | 2018-11-05 | 2018-11-05 | Method for detecting weak signals based on optimum organization support vector machines in Chaotic Background |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109389183A true CN109389183A (en) | 2019-02-26 |
Family
ID=65428327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811306325.7A Pending CN109389183A (en) | 2018-11-05 | 2018-11-05 | Method for detecting weak signals based on optimum organization support vector machines in Chaotic Background |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109389183A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109080A (en) * | 2019-05-29 | 2019-08-09 | 南京信息工程大学 | Method for detecting weak signals based on IA-SVM model |
| CN112668930A (en) * | 2021-01-12 | 2021-04-16 | 中国科学院微小卫星创新研究院 | Multi-star task scheduling planning method based on improved teaching optimization method |
| CN117974991A (en) * | 2024-04-01 | 2024-05-03 | 清华大学苏州汽车研究院（相城） | Method for generating target detection model, target detection method and device thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011048269A1 (en) * | 2009-10-22 | 2011-04-28 | Valtion Teknillinen Tutkimuskeskus | Application of weak signal detectors using a nonlinear oscillator for controlling and synchronizing wireless sensors and actuators |
| CN102914325A (en) * | 2012-10-19 | 2013-02-06 | 南京信息工程大学 | Dissipation synchronization-based detection method of small signal under chaos background |
| CN107145943A (en) * | 2017-04-25 | 2017-09-08 | 南京信息工程大学 | Method based on the detection echo state network small-signal for improving teaching optimized algorithm in Chaotic Background |
-
2018
- 2018-11-05 CN CN201811306325.7A patent/CN109389183A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011048269A1 (en) * | 2009-10-22 | 2011-04-28 | Valtion Teknillinen Tutkimuskeskus | Application of weak signal detectors using a nonlinear oscillator for controlling and synchronizing wireless sensors and actuators |
| CN102914325A (en) * | 2012-10-19 | 2013-02-06 | 南京信息工程大学 | Dissipation synchronization-based detection method of small signal under chaos background |
| CN107145943A (en) * | 2017-04-25 | 2017-09-08 | 南京信息工程大学 | Method based on the detection echo state network small-signal for improving teaching optimized algorithm in Chaotic Background |
Non-Patent Citations (4)
| Title |
|---|
| 曹骏: "基于加权精英TLBO-SVM的化工过程故障诊断方法", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 田中大等: "用于混沌时间序列预测的组合核函数最小二乘支持向量机", 《物理学报》 * |
| 行鸿彦等: "一种基于改进教学优化的微弱信号检测方法", 《现代雷达》 * |
| 行鸿彦等: "基于多参数组合优化的微弱信号检测方法", 《探测与控制学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109080A (en) * | 2019-05-29 | 2019-08-09 | 南京信息工程大学 | Method for detecting weak signals based on IA-SVM model |
| CN110109080B (en) * | 2019-05-29 | 2022-11-08 | 南京信息工程大学 | Weak signal detection method based on IA-SVM model |
| CN112668930A (en) * | 2021-01-12 | 2021-04-16 | 中国科学院微小卫星创新研究院 | Multi-star task scheduling planning method based on improved teaching optimization method |
| CN112668930B (en) * | 2021-01-12 | 2024-05-17 | 中国科学院微小卫星创新研究院 | Multi-star task scheduling planning method based on improved teaching optimization method |
| CN117974991A (en) * | 2024-04-01 | 2024-05-03 | 清华大学苏州汽车研究院（相城） | Method for generating target detection model, target detection method and device thereof |
| CN117974991B (en) * | 2024-04-01 | 2024-06-14 | 清华大学苏州汽车研究院（相城） | Method for generating target detection model, target detection method and device thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | Nonlinear model predictive control based on a self-organizing recurrent neural network | |
| Sun et al. | Elman neural network soft-sensor model of conversion velocity in polymerization process optimized by chaos whale optimization algorithm | |
| Lermusiaux et al. | Uncertainties | |
| Azami et al. | Classification of GPS satellites using improved back propagation training algorithms | |
| CN109389183A (en) | Method for detecting weak signals based on optimum organization support vector machines in Chaotic Background | |
| CN102129259B (en) | Neural network proportion integration (PI)-based intelligent temperature control system and method for sand dust environment test wind tunnel | |
| Wang et al. | A prediction model of vessel trajectory based on generative adversarial network | |
| CN105260786B (en) | A kind of simulation credibility of electric propulsion system assessment models comprehensive optimization method | |
| Gan et al. | Long-term ship speed prediction for intelligent traffic signaling | |
| Zhou et al. | Optimization of PID controller based on water wave optimization for an automatic voltage regulator system | |
| Huang et al. | A Hybrid Fuzzy Wavelet Neural Network Model with Self‐Adapted Fuzzy c‐Means Clustering and Genetic Algorithm for Water Quality Prediction in Rivers | |
| CN101799888B (en) | Industrial soft measurement method based on bionic intelligent ant colony algorithm | |
| CN111723523B (en) | Estuary surplus water level prediction method based on cascade neural network | |
| CN104376361A (en) | Nuclear accident source item inversion method based on BP neural network algorithm | |
| Suryo et al. | Improved time series prediction using LSTM neural network for smart agriculture application | |
| Yan et al. | Real-time localization of pollution source for urban water supply network in emergencies | |
| CN103675011A (en) | Soft industrial melt index measurement instrument and method of optimal support vector machine | |
| CN103674778A (en) | Industrial melt index soft measuring meter and method based on RBF (radial basis function) particle swarm optimization | |
| Quarteroni et al. | Reduced basis methods for optimal control of advection-diffusion problems | |
| Li et al. | Prediction and elucidation of the population dynamics of Microcystis spp. in Lake Dianchi (China) by means of artificial neural networks | |
| CN112068033B (en) | On-line identification method for open-circuit faults of inverter power tube based on 1/6 period current | |
| CN117254981B (en) | Industrial control network security situation prediction method and device | |
| CN106339357A (en) | Optimizing parameterized network information security detection system and method | |
| CN112881869A (en) | Cable joint partial discharge ultrasonic sequence prediction method | |
| Zhao et al. | A Hybrid Time Series Model based on Dilated Conv1D and LSTM with Applications to PM2. 5 Forecasting. |
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 | ||
| CB02 | Change of applicant information |
Address after: 210044 No. 219 Ningliu Road, Jiangbei New District, Nanjing City, Jiangsu Province Applicant after: Nanjing University of Information Science and Technology Address before: 211500 Yuting Square, 59 Wangqiao Road, Liuhe District, Nanjing City, Jiangsu Province Applicant before: Nanjing University of Information Science and Technology |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190226 |
|
| RJ01 | Rejection of invention patent application after publication |