CN115545473A - LSTM-based intelligent prediction method for domestic garbage throwing trend - Google Patents
LSTM-based intelligent prediction method for domestic garbage throwing trend Download PDFInfo
- Publication number
- CN115545473A CN115545473A CN202211222533.5A CN202211222533A CN115545473A CN 115545473 A CN115545473 A CN 115545473A CN 202211222533 A CN202211222533 A CN 202211222533A CN 115545473 A CN115545473 A CN 115545473A
- Authority
- CN
- China
- Prior art keywords
- data
- lstm
- garbage
- model
- representing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000010606 normalization Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 12
- 210000004027 cell Anatomy 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims description 2
- 230000033764 rhythmic process Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims 1
- 238000004140 cleaning Methods 0.000 abstract description 2
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses an LSTM-based intelligent prediction method for domestic garbage throwing trend, which comprises the following steps of: step 1: acquiring data, acquiring the garbage throwing amount and throwing time of each time through intelligent garbage collection and transportation equipment, and acquiring national holiday information, climate information and temperature information in a crawler mode; step 2: data preprocessing, namely establishing a sequence data set for the acquired various types of data and carrying out normalization processing; and step 3: establishing a model, establishing an LSTM network prediction model for delivering the household garbage, and training the LSTM network prediction model by using historical data; and 4, step 4: model prediction, namely predicting the garbage throwing trend by using a model; and 5: and evaluating and analyzing the predicted result, and verifying the effectiveness of prediction. The invention predicts the garbage throwing rule in the future 24 hours by establishing the garbage throwing rule prediction model, thereby facilitating sanitation enterprises, sanitation departments, residential property and the like to arrange garbage collection and transportation operations in time by taking the model as reference and rapidly cleaning and transporting the garbage.
Description
Technical Field
The invention discloses an LSTM-based intelligent prediction method for a household garbage putting rule, which belongs to the field of garbage classification and is called a Long-Short Term Memory (Chinese name is a Long-Short Term Memory model recurrent neural network) by LSTM.
Background
With the rapid development of Chinese economy, the domestic garbage production amount in China is gradually increased, and according to the statistics of Chinese statistical yearbook in 2019 and 2020, the domestic garbage clearing and transporting amount in 2019 reaches 24,206.2 ten thousand tons, and the annual growth rate is 5%. At present, about 2/3 of large and medium cities in the whole country have the severe situation of 'refuse great wall'. This occurs for two main reasons: one is that the facilities are not arranged reasonably, and the other is that the sanitation operation is not timely. Therefore, the method can accurately predict the domestic garbage generation condition, is an important reference for the management department to plan the environmental sanitation construction, and has great help for promoting the green cycle low-carbon development and improving the life quality of residents.
In the past decades of exploration, many methods for predicting the yield of domestic garbage have been proposed, mainly including conventional models such as Multiple Linear Regression (MLR), autoregressive moving average (ARMA), gray system model (ANN), and artificial intelligence models such as artificial neural networks, etc.
The traditional model is simple and is mainly used for predicting the yield of the household garbage in a large range, and the artificial intelligence model is more used for predicting the yield of the household garbage in a small range. In the past, the garbage yield data is mostly collected manually, and most of the regional sanitation management and statistics departments count the garbage generation data in weeks or months, so that the prediction range of the prediction model is mostly in cities or provinces, and the time is in weeks or months or years.
In recent years, with the intelligent transformation of traditional garbage throwing facilities, the throwing data of the residential garbage throwing link can be recorded,
meanwhile, with the development of artificial intelligence technology, experts in the field use artificial intelligence technologies such as machine learning and deep learning to predict the domestic garbage yield for a period of time in the future, but the current prediction can only roughly predict the domestic garbage yield in a large area and cannot accurately predict the domestic garbage yield in time dimensions such as every day, week and month. On the basis, the invention innovatively provides a prediction method for the garbage throwing rule of the specific front-end garbage collection device, and the method can easily take the climate, temperature and holiday factors influencing the garbage yield into consideration, so that the short-term garbage yield prediction precision is improved.
Disclosure of Invention
In view of the above problems, the present invention aims to provide an intelligent prediction method for a household garbage throwing rule, which can realize accurate prediction of a garbage throwing rule of a specific collection device and provide a reliable judgment basis for the arrangement of a garbage collection, transportation, dispatching, collection and transportation facility system.
In order to realize the purpose, the technical scheme of the invention is as follows: an LSTM-based household garbage throwing rule intelligent prediction method can realize accurate prediction of 4 types of household garbage throwing trends, and comprises the following steps: step 1: acquiring data, acquiring the garbage throwing amount and throwing time of each time through intelligent garbage collection and transportation equipment, and acquiring national holiday information, climate information and temperature information in a crawler mode; and 2, step: data preprocessing, namely establishing a sequence data set for the acquired various types of data and carrying out normalization processing; and step 3: establishing a model, establishing an LSTM network prediction model for delivering the household garbage, and training the LSTM network prediction model by using historical data; and 4, step 4: model prediction, namely predicting the garbage throwing trend by using a model; and 5: and evaluating and analyzing the predicted result, and verifying the effectiveness of prediction.
Furthermore, in the step 1, the source of the collected data is divided into two ways, one way is that the intelligent garbage classification collecting and transporting equipment collects garbage data on site, and the garbage data comprises garbage putting amount data per hour and garbage putting frequency data per hour; and secondly, acquiring network public data including national holiday information, climate information and temperature information of the region by using a network crawler mode.
Furthermore, in step 2, the collected data needs to be preprocessed, the data collected by the intelligent collecting and transporting equipment is integrated, the garbage throwing weight and the garbage throwing frequency per hour are obtained, normalization is performed after abnormal data are eliminated, and a sequence data set is built. The numerical value of the input variable is limited between 0 and 1 by adopting a max-min normalization processing method, and the processing mode is as follows:
wherein X represents the value of the current variable, X min Represents the minimum value of the variable, X max Represents the maximum value of the variable, X norm Representing the result of the normalization process of the value X.
Further, in step 2, the normalization method of the climate data is to normalize the collected climate data conditions: sunny, cloudy, light rain, medium rain, heavy rain, light snow, medium snow, heavy snow and others are respectively corresponding to 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8 and 0.9 to 1, so that the numerical value is between [0,1 ].
Further, the holiday information data in the step 2 is divided into three types of working days, holidays and holidays according to the influence degree of the holidays on the life rhythm of residents, and the holiday judgment condition is that the holidays are more than or equal to three days, including spring festival, labor festival, afternoon festival, national day festival and date festival. And respectively corresponding the information data of working days, holidays and holidays to 0, 0.5 and 1.
Furthermore, in the step 2, the value of the input variable is limited to be between 0 and 1 by adopting a max-min normalization processing method for the temperature information data.
Further, in step 3, the input parameters of the LSTM neural network model are: the garbage delivery amount per hour, the garbage throwing times per hour, the temperature data of the hour, the climate data of the hour and the 5 parameters of the day, the holiday data of the day are normalized to obtain data, model parameters are input by an input layer and then are transmitted to an LSTM layer for LSTM network training, and the number of neurons in the LSTM layer is 128; the LSTM layer is transmitted to a Dropout layer for regularization treatment to prevent overfitting; and then transmitted to the full connection layer and the regression output layer.
Further, in step 3, the training method of the LSTM neural network model includes: dividing a training set and a testing set into a plurality of samples, wherein each sample consists of K +1 days, the previous K days are used as the input of a network, and the next day is used as a reference value of an evaluation model; and training the neural network by using the training set, evaluating the model, and repeatedly training to achieve optimal fitting.
Further, in the step 5, the Root Mean Square Error (RMSE) is used as a measure for the analysis and verification of the prediction result.
In conclusion, the invention has the following obvious advantages and beneficial effects:
by establishing the garbage throwing rule prediction model, the predicted garbage throwing rule in the future 24 hours can be used for facilitating garbage collection and transportation operations of sanitation enterprises, sanitation departments, residential property and the like to be arranged in time by taking the model as a reference, so that garbage can be rapidly cleared, the garbage overflow exposure and the situation of unmanned cleaning of self-generated peculiar smell can be reduced, and the effects of protecting the environment and beautifying the urban appearance can be achieved.
Drawings
The technical solutions of the present invention will be described in further detail below with reference to the accompanying drawings and examples, but it should be understood that these drawings are designed for illustrative purposes only and thus do not limit the scope of the present invention. Furthermore, unless otherwise indicated, the drawings are intended to be illustrative of the structural configurations described herein and are not necessarily drawn to scale.
Fig. 1 is a logic block diagram of a garbage throwing trend prediction method according to an embodiment of the present invention;
FIG. 2 is a logical block diagram of an LSTM prediction model provided by an embodiment of the present invention;
FIG. 3 is a comparison graph of predicted future spam delivery and actual delivery of a predicted data set provided by an example of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
The data adopted by the embodiment is derived from data collected by intelligent garbage collection equipment in a certain Beijing area and climate data disclosed by a national weather network, and garbage throwing data of the intelligent garbage collection equipment in the area for 2 months is collected, and fig. 1 is a logic block diagram of the garbage throwing trend prediction method provided by the embodiment of the invention.
In the actual prediction process, the original data matrix obtained in step 1
A matrix of size T x d, where d represents the dimension of the raw data (i.e., the type of raw data), and T represents the sequence length (i.e., the number of acquisitions of each type of raw data); the value range of t is (0,T)]Is an integer of (1). In this example, d is 5,T is 1440 for 60 days of raw data collected.
Original data matrix X k Is 5, respectively comprises: the garbage delivery amount per hour, the garbage throwing times per hour, the temperature data of the hour, the climate data of the hour and the holiday data of the day; the original data matrix has a sequence length of 1440 (i.e., 1440 different time points are used to collect the above 5-dimensional data), and an original data matrix X with a size of 1440 × 5 is formed k ；
In step 2, the collected data is normalized, and the values of input variables of the three types of data, namely the garbage delivery amount per hour, the garbage throwing times per hour and the temperature data per hour, are limited to be between 0 and 1 by adopting a max-min normalization processing method. The normalization processing mode of the holiday information data is that the working day is 0 and the holiday is 1; the normalization processing mode of the climate information data is that rain/snow/fog is 0, shade is 0.5, and clear is 1. The first 80% of the data were selected as the training set and the remaining 20% were selected as the test set.
In step 3, as shown in fig. 2, the LSTM prediction model logic block diagram provided by the embodiment of the present invention is obtained by inputting the normalized data matrix into the LSTM network, and extracting a future time sequence of the garbage input amount after passing through the input gate, the forgetting gate and the output gate of the LSTM network in sequence;
wherein, the formula of the input gate of the LSTM network is as follows:
the formula of the LSTM network forgetting gate is as follows:
the formula of the LSTM network output gate is:
and calculated by combining the following formula:
C t ＝f t ⊙C t-1 +i t ⊙C t
h t ＝O t ⊙tanh(C t )
in the formula i t Presentation input Gate, W i Representing the input Gate weight parameter matrix, b i Representing the input gate bias term, f t Indicating forgetting gate, W f Representing a forgetting gate weight parameter matrix, b f Indicating a forgetting gate bias term, O t Indicating output gate, W o Representing the output gate weight parameter matrix, b o Representing an output gate bias term; σ denotes sigmoid activation function,. Alpha.denotes element-by-element product,. H t-1 Representing the state of the hidden layer at a time prior to t,
representing the original data matrix X k The corresponding original data vector at time t, h t Representing the raw data at time t of the output,
time series feature vectors corresponding to the vectors; tan h is tan h activation function; c t Represents the state of the cells at the time t; c t-1 Represents the state of the cells at the time immediately before t; t represents the value time step of the time T; c t Representing a cell state vector at time t; w c Weights representing cell state vectors; b c A bias term representing a cell state vector.
And 5, evaluating and analyzing the predicted result, and verifying the effectiveness of prediction as shown in fig. 3.
When analyzing and verifying, the mean square error (RMSE) is used as a measuring standard.
The method for calculating the mean square error (RMSE) comprises the following steps:
where RMSE represents the root mean square error, n represents the number of sample data in the training data set, y k The real value of the garbage throwing amount is represented,
and (4) representing the predicted value of the garbage input amount. In this example, the RMSE value is 0.23.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that modifications and variations can be made without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. An LSTM-based intelligent prediction method for household garbage putting trend is characterized by comprising the following steps: step 1: acquiring data, acquiring the garbage throwing amount and throwing time of each time through intelligent garbage collection and transportation equipment, and acquiring national holiday information, climate information and temperature information in a crawler mode; step 2: data preprocessing, namely establishing a sequence data set for the acquired various types of data and carrying out normalization processing; and step 3: establishing a model, establishing an LSTM network prediction model for delivering the household garbage, and training the LSTM network prediction model by using historical data; and 4, step 4: model prediction, namely predicting the garbage throwing trend by using a model; and 5: and evaluating and analyzing the predicted result, and verifying the effectiveness of prediction.
2. The LSTM-based intelligent prediction method for domestic garbage putting trend as claimed in claim 1, wherein: in the step 1, the source ways of the collected data are divided into two ways, namely, the intelligent garbage classification collecting and transporting equipment collects garbage data on site, wherein the garbage data comprises garbage putting amount data per hour and garbage putting frequency data per hour; and secondly, acquiring network public data including national holiday information, climate information and temperature information of the region by using a network crawler mode.
3. The LSTM-based intelligent prediction method for domestic garbage putting trend as claimed in claim 1, wherein: in step 2, the normalization method of the climate data is to collect the conditions of the climate data: sunny, cloudy, light rain, medium rain, heavy rain, light snow, medium snow, heavy snow and others are respectively corresponding to 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8 and 0.9 to 1, so that the numerical value is between [0,1 ].
4. The LSTM-based intelligent prediction method for domestic garbage putting trend according to claim 1, characterized in that: and 2, dividing the holiday types into three types of working days, holidays and holidays according to the influence degree of the holidays on the life rhythm of residents in the step 2, wherein the holidays are judged to be holidays of more than or equal to three days including spring festival, labor festival, afternoon festival, national day festival and Dane festival, and the information data of the working days, the holidays and the holidays correspond to 0, 0.5 and 1 respectively.
5. The LSTM-based intelligent prediction method for domestic garbage putting trend as claimed in claim 1, wherein: the model parameters are input by the input layer and then transmitted to the LSTM layer for LSTM network training, and the number of the LSTM layer neurons is 128; the LSTM layer is transmitted to a Dropout layer for regularization; and then transmitted to the full connection layer and the regression output layer.
6. The LSTM-based intelligent prediction method for domestic garbage putting trend according to claim 1, characterized in that: the training method of the LSTM neural network model comprises the steps of dividing a training set and a testing set into a plurality of samples, wherein each sample consists of K +1 days, the previous K days are used as the input of the network, and the next day is used as the reference value of an evaluation model; and training the neural network by using the training set, evaluating the model, and repeatedly training to achieve optimal fitting.
7. The LSTM-based intelligent prediction method for domestic garbage putting trend as claimed in claim 1, wherein: the LSTM prediction model inputs the data matrix after normalization processing into the LSTM network, and extracts a future time sequence of the garbage input amount after sequentially passing through an input gate, a forgetting gate and an output gate of the LSTM network;
wherein, the formula of the input gate of the LSTM network is as follows:
the formula of the LSTM network forgetting gate is as follows:
the formula of the LSTM network output gate is:
and calculated by combining the following formula:
C t ＝f t ⊙C t-1 +i t ⊙C t
h t ＝O t ⊙tanh(C t )
in the formula i t Presentation input Gate, W i Representing the input Gate weight parameter matrix, b i Representing the input gate bias term, f t Indicating forgetting gate, W f Representing a forgetting gate weight parameter matrix, b f Indicating a forgetting gate bias term, O t Indicating output gate, W o Representing the output gate weight parameter matrix, b o Representing an output gate bias term; σ denotes a sigmoid activation function,. Alpha.denotes a product element by element, h t-1 Representing the hidden layer state at the time immediately before t,
representing the original data matrix X k The corresponding original data vector at time t, h t Representing the raw data at time t of the output,
time series characteristic vectors corresponding to the vectors; tan h is an activation function; c t Represents the state of the cells at the time t; c t-1 Cells representing the time immediately before tA state; t represents the value time step of the time T; c t Representing a cell state vector at time t; w c Weights representing cell state vectors; b c A bias term representing a cell state vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211222533.5A CN115545473A (en) | 2022-10-08 | 2022-10-08 | LSTM-based intelligent prediction method for domestic garbage throwing trend |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211222533.5A CN115545473A (en) | 2022-10-08 | 2022-10-08 | LSTM-based intelligent prediction method for domestic garbage throwing trend |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115545473A true CN115545473A (en) | 2022-12-30 |
Family
ID=84732054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211222533.5A Pending CN115545473A (en) | 2022-10-08 | 2022-10-08 | LSTM-based intelligent prediction method for domestic garbage throwing trend |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545473A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115983504A (en) * | 2023-03-18 | 2023-04-18 | 中环洁集团股份有限公司 | Road garbage point location prediction method, system, equipment and storage medium |
| CN115994625A (en) * | 2023-03-17 | 2023-04-21 | 中环洁集团股份有限公司 | Pavement garbage prediction method and system and intelligent terminal |
-
2022
- 2022-10-08 CN CN202211222533.5A patent/CN115545473A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115994625A (en) * | 2023-03-17 | 2023-04-21 | 中环洁集团股份有限公司 | Pavement garbage prediction method and system and intelligent terminal |
| CN115983504A (en) * | 2023-03-18 | 2023-04-18 | 中环洁集团股份有限公司 | Road garbage point location prediction method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| CN112949945B (en) | Wind power ultra-short-term prediction method for improving bidirectional long-term and short-term memory network | |
| CN110705743B (en) | New energy consumption electric quantity prediction method based on long-term and short-term memory neural network | |
| CN115545473A (en) | LSTM-based intelligent prediction method for domestic garbage throwing trend | |
| CN112116080A (en) | CNN-GRU water quality prediction method integrated with attention mechanism | |
| CN108388962B (en) | Wind power prediction system and method | |
| CN111105332A (en) | Highway intelligent pre-maintenance method and system based on artificial neural network | |
| CN106886846A (en) | A kind of bank outlets' excess reserve Forecasting Methodology that Recognition with Recurrent Neural Network is remembered based on shot and long term | |
| CN104036360B (en) | User data processing system and processing method based on magcard attendance behaviors | |
| CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
| CN109272364A (en) | Automatic Valuation Modelling modeling method | |
| Liu et al. | Heating load forecasting for combined heat and power plants via strand-based LSTM | |
| CN113537469B (en) | Urban water demand prediction method based on LSTM network and Attention mechanism | |
| CN113033081A (en) | Runoff simulation method and system based on SOM-BPNN model | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| CN112085108A (en) | Photovoltaic power station fault diagnosis algorithm based on automatic encoder and K-means clustering | |
| Wibawa et al. | Long Short-Term Memory to Predict Unique Visitors of an Electronic Journal | |
| CN114692981A (en) | Medium-and-long-term runoff forecasting method and system based on Seq2Seq model | |
| Zhang et al. | Spatiotemporal prediction of O3 concentration based on the KNN-Prophet-LSTM model | |
| Feng et al. | A dual-staged attention based conversion-gated long short term memory for multivariable time series prediction | |
| CN113570414A (en) | Electricity price prediction method for optimizing deep neural network based on improved Adam algorithm | |
| CN112132334A (en) | Method for predicting yield of urban domestic garbage | |
| CN116485075A (en) | FTS-based power grid load prediction method | |
| CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
| CN110852496A (en) | Natural gas load prediction method based on LSTM recurrent neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |