CN112069717A - Magnetic storm prediction method and device based on multi-mode representation learning and storage medium - Google Patents
Magnetic storm prediction method and device based on multi-mode representation learning and storage medium Download PDFInfo
- Publication number
- CN112069717A CN112069717A CN202010839412.XA CN202010839412A CN112069717A CN 112069717 A CN112069717 A CN 112069717A CN 202010839412 A CN202010839412 A CN 202010839412A CN 112069717 A CN112069717 A CN 112069717A
- Authority
- CN
- China
- Prior art keywords
- geomagnetic
- feature
- extracting
- module
- features
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a magnetic storm prediction method, a device and a storage medium based on multi-modal characterization learning, wherein the method comprises the steps of inputting satellite magnetic measurement data and solar high-energy particle data through an input module; the extraction module extracts a first feature of the satellite magnetic measurement data; extracting a second feature of the solar high-energy particle data; extracting geomagnetic discrimination characteristics according to the first characteristics and the second characteristics; obtaining geomagnetic indexes by classification according to geomagnetic distinguishing characteristics; and the redundancy of the first characteristic and the second characteristic is eliminated by utilizing the complementarity of the first characteristic and the second characteristic so as to learn better characteristic representation, improve the classification accuracy and further improve the magnetic storm prediction effect.
Description
Technical Field
The invention relates to the field of geomagnetic prediction, in particular to a magnetic storm prediction method, a device and a storage medium based on multi-mode representation learning.
Background
The geomagnetic storm is mainly caused by that a large amount of high-energy particle flows such as ultraviolet rays, X rays and the like are radiated outwards when solar flares burst, and reach the earth to seriously interfere the earth magnetic field. The occurrence of the geomagnetic storm can cause a major power failure accident, interfere the operation of radio communication and satellites and carry out aviation navigation positioning, so that the method has very important scientific and economic significance for forecasting the geomagnetic storm. Since the occurrence of geomagnetic storm has a complex relationship with various factors, if the prediction of geomagnetic storm is only estimated by one of the factors, the result is easy to deviate.
Disclosure of Invention
The present invention is directed to solve at least one of the problems in the prior art, and provides a method, an apparatus and a storage medium for predicting a magnetic storm based on multi-modal characterization learning.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect of the present invention, a magnetic storm prediction apparatus based on multi-modal characterization learning comprises:
the input module is used for inputting satellite magnetic measurement data and solar high-energy particle data;
the first feature extraction module is used for extracting first features of the satellite magnetic measurement data;
the second characteristic extraction module is used for extracting second characteristics of the solar energetic particle data;
the multi-mode deep learning module is used for extracting geomagnetic discriminant features according to the first features and the second features; and
and the classifier is used for classifying according to the geomagnetic distinguishing characteristics to obtain the geomagnetic index.
According to a first aspect of the invention, the multimodal deep learning module is a bi-directional auto-encoder.
According to a first aspect of the invention, the classifier is a support vector machine.
In a second aspect of the present invention, a magnetic storm prediction method based on multi-modal characterization learning is applied to the magnetic storm prediction apparatus based on multi-modal characterization learning in the first aspect of the present invention, and the magnetic storm prediction method includes the following steps:
inputting satellite magnetic measurement data and solar high-energy particle data through an input module;
extracting a first feature of the satellite magnetic measurement data through a first feature extraction module;
extracting second characteristics of the solar high-energy particle data through a second characteristic extraction module;
extracting geomagnetic discrimination characteristics according to the first characteristics and the second characteristics through a multi-mode deep learning module;
and classifying according to the geomagnetic distinguishing characteristics through a classifier to obtain a geomagnetic index.
According to a second aspect of the invention, the multimodal deep learning module is a bi-directional auto-encoder.
According to the second aspect of the present invention, the extracting the geomagnetic discrimination feature according to the first feature and the second feature further includes:
inputting the first feature and the second feature to train the bidirectional automatic encoder until the bidirectional automatic encoder converges;
and removing the decoder of the bidirectional automatic encoder, and taking the characteristics output by the encoder of the bidirectional automatic encoder as the geomagnetic distinguishing characteristics.
According to a second aspect of the invention, the classifier is a support vector machine.
According to the second aspect of the present invention, the extracting the first feature of the satellite magnetic measurement data by the first feature extraction module specifically includes the following steps:
simultaneously extracting spatial features and time features of a fast-forwarding video segment obtained by satellite magnetic measurement data sampling through a plurality of feature encoders;
inputting the spatial features and the temporal features into a fusion network formed by a discrimination sensor and a generation sensor to obtain geomagnetic features; wherein the discrimination perceptron perceives subtle differences in the intensity of motion of the geomagnetic lines between adjacent video frames by performing a classification of the sampling intervals; the generating perceptron is reconstructed by the difference values to reduce the details of the motion of the original magnetic wire.
According to the second aspect of the present invention, the extracting of the second feature of the solar energetic particle data by the second feature extraction module includes the steps of:
inputting the solar high-energy particle data to a coding module of the second feature extraction module, and processing the solar high-energy particle data through a plurality of coding sublayers; wherein in the coding sublayer, the input data sequentially passes through a first multi-head self-attention structure and a first full-connection forward network processing;
inputting the output of the coding module into a decoding module of the second feature extraction module, processing the output of the coding module through a plurality of decoding sublayers, and processing through a final linear transformation layer and a softmax function layer to obtain the second feature; wherein in the decoding sublayer, the input data is processed sequentially through a masked multi-headed self-attention structure, a second multi-headed self-attention structure, and a second fully-connected forward network.
In a third aspect of the present invention, a storage medium stores executable instructions that can be executed by a computer to cause the computer to perform a method for predicting a magnetic storm based on a self-attention deformation network according to the first aspect of the present invention.
The scheme at least has the following beneficial effects: the redundancy between the two modes is eliminated by utilizing the complementarity between the first characteristic of the satellite magnetic measurement data and the second characteristic of the solar high-energy particle data, so that better geomagnetic discrimination characteristic representation is learned, the accuracy of the geomagnetic index obtained by classifying the classifier is improved, and the magnetic storm prediction effect is further improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart of a magnetic storm prediction method based on multi-modal characterization learning according to an embodiment of the present invention;
FIG. 2 is a block diagram of a magnetic storm prediction device based on multi-modal characterization learning according to an embodiment of the present invention;
fig. 3 is a block diagram of the multimodal deep learning module of fig. 2.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
Referring to fig. 2, an embodiment of the present invention provides a magnetic storm prediction apparatus based on multi-modal characterization learning, including:
the input module 10 is used for inputting satellite magnetic measurement data and solar high-energy particle data;
the first feature extraction module 20 is used for extracting first features of the satellite magnetic measurement data;
the second feature extraction module 30 is configured to extract a second feature of the solar high-energy particle data;
the multi-mode deep learning module 40 is used for extracting geomagnetic discriminant features according to the first features and the second features; and
and the classifier 50 is used for obtaining the geomagnetic index according to the geomagnetic distinguishing characteristic classification.
In this embodiment, since the first feature extraction module 20 and the second feature extraction module 30 are both neural network results; referring to fig. 3, in the multi-modal deep learning module 40, the hidden layer 21 of the first feature extraction module 20 and the hidden layer 31 of the second feature extraction module 30 are further connected in series, and a restricted boltzmann machine of an upper layer is constructed above the hidden layer 21 of the first feature extraction module 20 and the hidden layer 31 of the second feature extraction module 30 connected in series. The stacked constrained boltzmann machine will be expanded to a multi-modal deep learning module 40 and learn a shared representation of the two modalities from the input first and second features at a feature sharing layer 41, and finally the weights can be fine-tuned using unsupervised back propagation algorithms.
By utilizing the complementarity between the two modes of the first characteristic of the satellite magnetic measurement data and the second characteristic of the solar high-energy particle data, the redundancy between the two modes is eliminated, so that better geomagnetic discrimination characteristic representation is learned, the accuracy of the geomagnetic index obtained by classifying by the classifier 50 is improved, and the magnetic storm prediction effect is further improved.
In particular, the multimodal deep learning module 40 is a bi-directional auto-encoder architecture.
Specifically, the classifier 50 is a support vector machine. The support vector machine may be implemented using MATLAB. Extreme and estimated standard deviations are used in the support vector machine and functional level fusion is used as a benchmark for modal fusion. And the geomagnetic distinguishing feature obtained by processing the first feature and the second feature is used as the input of the support vector machine.
Referring to fig. 1, an embodiment of the method of the present invention provides a magnetic storm prediction method based on multi-modal characterization learning, and a magnetic storm prediction apparatus based on multi-modal characterization learning in the above apparatus embodiment is applied, where the magnetic storm prediction method includes the following steps:
s100, inputting satellite magnetic measurement data and solar high-energy particle data through an input module 10;
step S200, extracting a first feature of the satellite magnetic measurement data through a first feature extraction module 20;
step S300, extracting a second feature of the solar high-energy particle data through a second feature extraction module 30;
step S400, extracting geomagnetic discriminant features according to the first features and the second features through the multi-mode deep learning module 40;
step S500, classifying according to the geomagnetic discrimination characteristics by the classifier 50 to obtain a geomagnetic index.
In this embodiment, by using the complementarity between the two modes, i.e., the first feature of the satellite magnetic measurement data and the second feature of the solar high-energy particle data, the redundancy between the two modes is eliminated, so that a better geomagnetic discrimination feature representation is learned, the accuracy of the geomagnetic index obtained by classifying by the classifier 50 is improved, and the magnetic storm prediction effect is further improved.
Certainly, it should be noted that, since the historical satellite magnetic measurement data is the magnetic storm which is observed visually, the future magnetic storm can be easily inferred through the historical satellite magnetic measurement data; and the solar high-energy particle data are factors directly influencing the magnetic storm, so the two are adopted for feature extraction to carry out multi-modal characterization learning in the invention. Besides two modal forms of the first feature of the satellite magnetic measurement data and the second feature of the solar high-energy particle data, other factors influencing the occurrence of the magnetic storm can be adopted to further extract the features to obtain feature representation of more modes, so that the multi-mode deep learning module 40 can learn better geomagnetic judgment feature representation according to the multiple mode features, and the magnetic storm prediction effect can be further improved.
Referring to fig. 3, in particular, in step S400, the multi-modal deep learning module 40 is a bi-directional auto-encoder. The hidden layer 21 of the first feature extraction module 20 and the hidden layer 31 of the second feature extraction module 30 are further connected in series, and a restricted boltzmann machine of an upper layer is constructed above the hidden layer 21 of the first feature extraction module 20 and the hidden layer 31 of the second feature extraction module 30 connected in series. The stacked constrained boltzmann machine will be unfolded into a bidirectional autoencoder structure and a shared representation of both modalities is learned from the input first and second features at a feature sharing layer 41 in the bidirectional autoencoder structure, and finally the weights can be fine-tuned for the bidirectional autoencoder using unsupervised back-propagation algorithms.
Further, for step S400, extracting the geomagnetic discrimination feature according to the first feature and the second feature further includes the following steps:
inputting the first characteristic and the second characteristic to train the bidirectional automatic encoder until the bidirectional automatic encoder converges;
and removing the decoder of the bidirectional automatic encoder, and taking the characteristics output by the encoder of the bidirectional automatic encoder as the geomagnetic judgment characteristics.
Specifically, the classifier 50 is a support vector machine. The support vector machine may be implemented using MATLAB. Extreme and estimated standard deviations are used in the support vector machine and functional level fusion is used as a benchmark for modal fusion. And the geomagnetic distinguishing feature obtained by processing the first feature and the second feature is used as the input of the support vector machine.
Further, the step S200 of extracting the first feature of the satellite magnetic measurement data by the first feature extraction module 20 specifically includes the following steps:
simultaneously extracting spatial features and time features of a fast-forwarding video segment obtained by satellite magnetic measurement data sampling through a plurality of feature encoders; converting satellite magnetic measurement data into a geomagnetic intensity graph, converting a plurality of geomagnetic intensity graphs into a video streaming geomagnetic intensity video according to a time sequence, and sampling the geomagnetic intensity video at different sampling intervals to obtain a plurality of different fast forward video segments;
inputting the spatial features and the temporal features into a fusion network formed by a discrimination sensor and a generation sensor to obtain geomagnetic features; wherein the discrimination sensor senses a subtle difference in the intensity of motion of the geomagnetic line between adjacent video frames by performing classification of the sampling interval; the generation perceptron is reconstructed by the difference values to reduce the details of the motion of the local magnetic wire.
Semantic preservation is realized through the distinguishing perceptron and the generating perceptron, which means that the encoded time semantics can be transferred to a downstream single-input multi-output classification task as much as possible. Through self-supervision space-time representation learning, the time resolution characteristics of the video and the inner space are captured, so that accurate extraction of geomagnetic features from geomagnetic intensity videos is facilitated, and further improvement of geomagnetic index prediction effects is facilitated.
Further, for the step S300, the extracting, by the second feature extraction module 30, the second feature of the solar high-energy particle data includes the following steps:
inputting the solar high-energy particle data to the coding module of the second feature extraction module 30, so that the solar high-energy particle data is processed by a plurality of coding sublayers; in the coding sublayer, the input data sequentially passes through a first multi-head self-attention structure and a first full-connection forward network for processing;
inputting the output of the coding module to the decoding module of the second feature extraction module 30, so that the output of the coding module is processed by a plurality of decoding sublayers, and then processed by a final linear transformation layer and a softmax function layer to obtain a second feature; in the decoding sublayer, the input data is processed by the mask multi-head self-attention structure, the second multi-head self-attention structure and the second full-connection forward network in sequence.
Parallel calculation is realized through a plurality of coding sublayers and a plurality of decoding sublayers, so that the calculation efficiency is improved; the calculation complexity required for calculating the real-time satellite magnetic measurement data and the association between the solar high-energy particle data and the geomagnetic index at the future moment is not increased along with the increase of the data distance, so that the calculation complexity is reduced; each head of the multi-headed self-attention structure can perform different tasks, making the model more interpretable.
In another embodiment of the present invention, a storage medium is provided, which stores executable instructions that can be executed by a computer to cause the computer to perform a method for predicting a magnetic storm based on a self-attention deformed network according to an embodiment of the method of the present invention.
Examples of storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
The above is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiments, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means.
Claims (10)
1. Magnetic storm prediction device based on multi-modal characterization learning, characterized by comprising:
the input module is used for inputting satellite magnetic measurement data and solar high-energy particle data;
the first feature extraction module is used for extracting first features of the satellite magnetic measurement data;
the second characteristic extraction module is used for extracting second characteristics of the solar energetic particle data;
the multi-mode deep learning module is used for extracting geomagnetic discriminant features according to the first features and the second features; and
and the classifier is used for classifying according to the geomagnetic distinguishing characteristics to obtain the geomagnetic index.
2. The apparatus of claim 1, wherein the multi-modal deep learning module is a bi-directional auto-encoder.
3. The magnetic storm prediction device based on multi-modal characterization learning according to claim 1, wherein the classifier is a support vector machine.
4. The magnetic storm prediction method based on multi-modal characterization learning is characterized in that the magnetic storm prediction device based on multi-modal characterization learning of claim 1 is applied, and the magnetic storm prediction method comprises the following steps:
inputting satellite magnetic measurement data and solar high-energy particle data through an input module;
extracting a first feature of the satellite magnetic measurement data through a first feature extraction module;
extracting second characteristics of the solar high-energy particle data through a second characteristic extraction module;
extracting geomagnetic discrimination characteristics according to the first characteristics and the second characteristics through a multi-mode deep learning module;
and classifying according to the geomagnetic distinguishing characteristics through a classifier to obtain a geomagnetic index.
5. The method of claim 4, wherein the multi-modal deep learning module is a bi-directional auto-encoder.
6. The method of claim 5, wherein the extracting geomagnetic discriminant features from the first and second features further comprises:
inputting the first feature and the second feature to train the bidirectional automatic encoder until the bidirectional automatic encoder converges;
and removing the decoder of the bidirectional automatic encoder, and taking the characteristics output by the encoder of the bidirectional automatic encoder as the geomagnetic distinguishing characteristics.
7. The method of claim 4, wherein the classifier is a support vector machine.
8. The method for predicting the magnetic storm based on the multi-modal characterization learning according to claim 4, wherein the extracting the first feature of the satellite magnetic survey data by the first feature extraction module specifically comprises the following steps:
simultaneously extracting spatial features and time features of a fast-forwarding video segment obtained by satellite magnetic measurement data sampling through a plurality of feature encoders;
inputting the spatial features and the temporal features into a fusion network formed by a discrimination sensor and a generation sensor to obtain geomagnetic features; wherein the discrimination perceptron perceives subtle differences in the intensity of motion of the geomagnetic lines between adjacent video frames by performing a classification of the sampling intervals; the generating perceptron is reconstructed by the difference values to reduce the details of the motion of the original magnetic wire.
9. The method of claim 4, wherein the extracting the second feature of the solar energetic particle data by the second feature extraction module comprises the following steps:
inputting the solar high-energy particle data to a coding module of the second feature extraction module, and processing the solar high-energy particle data through a plurality of coding sublayers; wherein in the coding sublayer, the input data sequentially passes through a first multi-head self-attention structure and a first full-connection forward network processing;
inputting the output of the coding module into a decoding module of the second feature extraction module, processing the output of the coding module through a plurality of decoding sublayers, and processing through a final linear transformation layer and a softmax function layer to obtain the second feature; wherein in the decoding sublayer, the input data is processed sequentially through a masked multi-headed self-attention structure, a second multi-headed self-attention structure, and a second fully-connected forward network.
10. A storage medium storing executable instructions that are executable by a computer to cause the computer to perform the method for predicting a magnetic storm based on a self-attention deformation network according to any one of claims 4 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010839412.XA CN112069717A (en) | 2020-08-19 | 2020-08-19 | Magnetic storm prediction method and device based on multi-mode representation learning and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010839412.XA CN112069717A (en) | 2020-08-19 | 2020-08-19 | Magnetic storm prediction method and device based on multi-mode representation learning and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112069717A true CN112069717A (en) | 2020-12-11 |
Family
ID=73661379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010839412.XA Pending CN112069717A (en) | 2020-08-19 | 2020-08-19 | Magnetic storm prediction method and device based on multi-mode representation learning and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112069717A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113627285A (en) * | 2021-07-26 | 2021-11-09 | 长沙理工大学 | Video forensics method, system, and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101726758A (en) * | 2009-12-11 | 2010-06-09 | 中国科学院地质与地球物理研究所 | Geomagnetic field disturbance real-time analysis forecasting system |
| CN107679580A (en) * | 2017-10-21 | 2018-02-09 | 桂林电子科技大学 | A kind of isomery shift image feeling polarities analysis method based on the potential association of multi-modal depth |
| CN108108849A (en) * | 2017-12-31 | 2018-06-01 | 厦门大学 | A kind of microblog emotional Forecasting Methodology based on Weakly supervised multi-modal deep learning |
| CN109376857A (en) * | 2018-09-03 | 2019-02-22 | 上海交通大学 | A kind of multi-modal depth internet startup disk method of fusion structure and attribute information |
| CN110472242A (en) * | 2019-08-05 | 2019-11-19 | 腾讯科技（深圳）有限公司 | A kind of text handling method, device and computer readable storage medium |
| CN110717599A (en) * | 2019-09-29 | 2020-01-21 | 清华大学 | Dissociation characterization learning method and device integrating multiple modes |
| CN111079753A (en) * | 2019-12-20 | 2020-04-28 | 长沙千视通智能科技有限公司 | License plate recognition method and device based on deep learning and big data combination |
| CN111275130A (en) * | 2020-02-18 | 2020-06-12 | 上海交通大学 | Deep learning prediction method, system, medium and device based on multiple modes |
-
2020
- 2020-08-19 CN CN202010839412.XA patent/CN112069717A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101726758A (en) * | 2009-12-11 | 2010-06-09 | 中国科学院地质与地球物理研究所 | Geomagnetic field disturbance real-time analysis forecasting system |
| CN107679580A (en) * | 2017-10-21 | 2018-02-09 | 桂林电子科技大学 | A kind of isomery shift image feeling polarities analysis method based on the potential association of multi-modal depth |
| CN108108849A (en) * | 2017-12-31 | 2018-06-01 | 厦门大学 | A kind of microblog emotional Forecasting Methodology based on Weakly supervised multi-modal deep learning |
| CN109376857A (en) * | 2018-09-03 | 2019-02-22 | 上海交通大学 | A kind of multi-modal depth internet startup disk method of fusion structure and attribute information |
| CN110472242A (en) * | 2019-08-05 | 2019-11-19 | 腾讯科技（深圳）有限公司 | A kind of text handling method, device and computer readable storage medium |
| CN110717599A (en) * | 2019-09-29 | 2020-01-21 | 清华大学 | Dissociation characterization learning method and device integrating multiple modes |
| CN111079753A (en) * | 2019-12-20 | 2020-04-28 | 长沙千视通智能科技有限公司 | License plate recognition method and device based on deep learning and big data combination |
| CN111275130A (en) * | 2020-02-18 | 2020-06-12 | 上海交通大学 | Deep learning prediction method, system, medium and device based on multiple modes |
Non-Patent Citations (1)
| Title |
|---|
| 何正义等: "基于集成深度学习的时间序列预测模型", 山东大学学报( 工学版), vol. 46, no. 6, pages 40 - 47 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113627285A (en) * | 2021-07-26 | 2021-11-09 | 长沙理工大学 | Video forensics method, system, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909046B (en) | Time-series abnormality detection method and device, electronic equipment and storage medium | |
| CN113435253B (en) | Multi-source image combined urban area ground surface coverage classification method | |
| CN113468978B (en) | Fine granularity car body color classification method, device and equipment based on deep learning | |
| CN115688035A (en) | Time sequence power data anomaly detection method based on self-supervision learning | |
| EP3965071A2 (en) | Method and apparatus for pose identification | |
| CN113838135B (en) | Pose estimation method, system and medium based on LSTM double-flow convolutional neural network | |
| CN112033406B (en) | Navigation method, device and storage medium based on lightweight network | |
| US20230222781A1 (en) | Method and apparatus with object recognition | |
| Rayhan et al. | AIST: An interpretable attention-based deep learning model for crime prediction | |
| CN116203971A (en) | Unmanned obstacle avoidance method for generating countering network collaborative prediction | |
| CN112069717A (en) | Magnetic storm prediction method and device based on multi-mode representation learning and storage medium | |
| CN115792913A (en) | Radar echo extrapolation method and system based on time-space network | |
| Zhang et al. | Efficient object detection method based on aerial optical sensors for remote sensing | |
| CN117314965A (en) | Space-time fusion multi-target tracking method, device, equipment and medium | |
| Yu et al. | A Deep Domain‐Adversarial Transfer Fault Diagnosis Method for Rolling Bearing Based on Ensemble Empirical Mode Decomposition | |
| CN116777068A (en) | Causal transducer-based networked data prediction method | |
| CN112052986A (en) | Magnetic storm prediction method and device based on self-supervision learning and storage medium | |
| US11776319B2 (en) | Methods and systems to predict activity in a sequence of images | |
| CN115169431A (en) | Thunderstorm identification method and system | |
| Zhao et al. | Car‐following trajectory data imputation with adversarial convolutional neural network | |
| CN110650130B (en) | Industrial control intrusion detection method based on multi-classification GoogLeNet-LSTM model | |
| Wang et al. | Short‐Term Traffic Prediction considering Spatial‐Temporal Characteristics of Freeway Flow | |
| Ziyabari et al. | Short-term solar irradiance forecasting based on self-attentive transformers | |
| CN112016245A (en) | Magnetic storm prediction method and device based on self-attention deformation network and storage medium | |
| CN111507410A (en) | Construction method of rolling capsule layer and classification method and device of multi-view images |
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 |