CN114841492A - Traditional village protection value evaluation method - Google Patents
Traditional village protection value evaluation method Download PDFInfo
- Publication number
- CN114841492A CN114841492A CN202210205318.8A CN202210205318A CN114841492A CN 114841492 A CN114841492 A CN 114841492A CN 202210205318 A CN202210205318 A CN 202210205318A CN 114841492 A CN114841492 A CN 114841492A
- Authority
- CN
- China
- Prior art keywords
- village
- traditional
- data
- evaluation
- random forest
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 52
- 238000007637 random forest analysis Methods 0.000 claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000013479 data entry Methods 0.000 claims abstract description 4
- 238000003066 decision tree Methods 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 15
- 239000000463 material Substances 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 9
- 238000010801 machine learning Methods 0.000 description 8
- 238000013210 evaluation model Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000019771 cognition Effects 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000007418 data mining Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an evaluation method of traditional village protection value, which comprises the following steps: s1: acquiring traditional village survey data; s2: performing data entry and data preprocessing operation on the traditional village survey data to obtain traditional village data; s3: classifying the traditional village data by using a random forest algorithm to obtain a classification result; s4: and outputting the classification result as an evaluation result. The traditional village protection value evaluation method provided by the invention can solve the technical problem that subjective judgment consciousness of different experts, understanding of the background in the research field and different recognition angles have certain influence on rating evaluation.
Description
Technical Field
The invention relates to the technical field of village value evaluation, in particular to a traditional village protection value evaluation method.
Background
The traditional village has certain historical, cultural, scientific, artistic, social and economic values. The traditional village is a precious cultural heritage and a non-renewable precious resource in China, not only preserves original ecological space settlement, but also preserves non-material culture, and bears the essence of Chinese traditional culture.
Since the 80 s of the last century, the traditional village protection work in China began gradually, and 5 batches of 'the famous village of Chinese historical culture' have been selected in the last decade. At present, 6819 traditional villages with important protection value in China cover 309 city grade cities in China. However, the number of traditional villages in China is huge, the selected traditional villages still do not account for two thousandths of the total amount, and a plurality of traditional villages with typical characteristics do not report 'China historical culture famous villages'. The value evaluation and evaluation system of the traditional village plays an important role in evaluating the traditional cultural traditional village in China and has an extremely important significance in inheritance of the traditional village in China. The traditional village has diversity, comprehensiveness and complexity, and the evaluation relates to multiple disciplines and fields, such as: applied disciplines such as architecture, planning, tourism, history, homeland, and the like, so the evaluation of the traditional village is collectively evaluated by experts in multiple fields. The current traditional village rating is evaluated based on expert scores, and for the research on the traditional village rating evaluation, a plurality of scholars obtain certain achievements in the traditional village rating evaluation field, and mainly research evaluation indexes, evaluation methods, value evaluation and the like. Machine learning is a very effective method for data analysis and pattern discovery, and is to use the existing data experience to continuously learn, summarize the rules and predict the attributes of unknown data. At present, the traditional village intelligent assessment model is researched less, huge achievements are obtained in all fields through machine learning, and the machine learning method is utilized to achieve intelligent assessment of the traditional village.
Disclosure of Invention
The invention aims to provide an evaluation method of the traditional village protection value, which can solve the technical problem that subjective judgment consciousness of different experts and understanding and cognition angle difference of the background of the research field have certain influence on the grading of the traditional village rating evaluation.
The technical scheme for solving the technical problems is as follows:
the invention provides an evaluation method of traditional village protection value, which comprises the following steps:
s1: acquiring traditional village survey data;
s2: performing data entry and data preprocessing operation on the traditional village survey data to obtain traditional village data;
s3: classifying the traditional village data by using a random forest algorithm to obtain a classification result;
s4: and outputting the classification result as an evaluation result.
Optionally, in step S1, the conventional village survey data at least includes the following characteristic indexes:
village profile, village surroundings, site selection pattern, traditional architecture and non-material cultural heritage.
Optionally, the village profile comprises the following sub-characteristic indicators: village floor area, household register population, topographic features, main nationality and cultural relic protection unit grade;
the village surrounding environment comprises the following sub-characteristic indexes: natural environment and scenic spots;
the site selection pattern comprises the following sub-characteristic indexes: village constellations and village features;
the traditional building comprises the following sub-characteristic indexes: the earliest construction age and type of building; and
the non-material cultural heritage comprises the following sub-characteristic indexes: family, leaderboard, and others.
Optionally, in step S2, the data preprocessing operation includes:
preliminarily screening the traditional village survey data into usable data and unusable data;
extracting traditional village data in the available data;
and assigning the sub-characteristic indexes of the characteristic indexes in the traditional village data.
Optionally, in the step S3, the random forest algorithm includes:
a1: taking the traditional village data as a sample set;
a2: extracting a plurality of samples from the sample set by a Boostrap resampling method, wherein the plurality of samples form a sampling set;
a3: training a target decision tree model with the sample set;
a4: randomly selecting a part of characteristics from all sample characteristics on the nodes of the target decision tree model;
a5: taking the optimal feature in the partial features as a left sub-tree and a right sub-tree of the target decision tree;
a6: and repeating the steps A1-A5 until the repetition times are equal to the preset iteration times, and outputting the category with the most optimal characteristics as a final category.
Optionally, the random forest algorithm model is:
wherein H (x) represents a classification result, Y represents a classification type, and T represents the number of decision trees in the random forest; i () is an indicative function, upsilon t Are random variables subject to independent distribution; x represents the eigenvalue and t represents the number of decision trees in the random forest.
The invention has the following beneficial effects:
through the technical scheme, namely the traditional village protection value evaluation method provided by the invention, the technical problem that subjective judgment consciousness of different experts, understanding of the background in the research field and difference of the cognition angle can have certain influence on rating evaluation can be solved, so that the weight setting is effectively prevented from being subjectively interfered, the traditional village value evaluation is more fair and fair, and the inheritance of cultural heritage and non-renewable resources in China is further effectively ensured.
Drawings
Fig. 1 is a flowchart of a conventional method for evaluating the protection value of a village according to the present invention;
fig. 2 is a flow chart of the random forest algorithm provided by the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Example 1
The technical scheme for solving the technical problems is as follows:
the invention provides an evaluation method of traditional village protection value, which comprises the following steps:
s1: acquiring traditional village survey data;
s2: performing data entry and data preprocessing operation on the traditional village survey data to obtain traditional village data;
s3: classifying the traditional village data by using a random forest algorithm to obtain a classification result;
s4: and outputting the classification result as an evaluation result.
Optionally, in step S1, the conventional village survey data at least includes the following characteristic indexes:
village profile, village surroundings, site selection pattern, traditional architecture and non-material cultural heritage.
Optionally, the village profile comprises the following sub-characteristic indicators: village floor area, household register population, topographic features, main nationality and cultural relic protection unit grade;
the village surrounding environment includes the following sub-characteristic indicators: natural environment and scenic spots;
the site selection pattern comprises the following sub-characteristic indexes: village constellations and village features;
the traditional building comprises the following sub-characteristic indexes: the earliest construction age and type of building; and the non-material cultural heritage comprises the following sub-characteristic indexes: family, leaderboard, and others.
Optionally, in step S2, the data preprocessing operation includes:
preliminarily screening the traditional village survey data into usable data and unusable data;
extracting traditional village data in the available data;
and assigning the sub-characteristic indexes of the characteristic indexes in the traditional village data.
Optionally, in the step S3, the random forest algorithm includes:
a1: taking the traditional village data as a sample set;
a2: extracting a plurality of samples from the sample set by a Boostrap resampling method, and forming a sampling set by the plurality of samples;
a3: training a target decision tree model with the sample set;
a4: randomly selecting a part of characteristics from all sample characteristics on the nodes of the target decision tree model;
a5: taking the optimal feature in the partial features as a left sub-tree and a right sub-tree of the target decision tree;
a6: and repeating the steps A1-A5 until the repetition times are equal to the preset iteration times, and outputting the category with the most optimal characteristics as a final category.
Optionally, the random forest algorithm model is:
wherein H (x) represents a classification result, Y represents a classification type, and T represents the number of decision trees in the random forest; i () is an indicative function, upsilon t Are random variables subject to independent distribution; x represents a characteristic value, t represents a random forest medianThe number of policy trees.
Example 2
At present, the affirmation of traditional village is reviewed with "traditional village evaluation affirmation index system (trial implementation)" as the basis, and this index system mainly assesses the affirmation from traditional building, village site selection and pattern, three leading direction of village non-material culture, and wherein every aassessment direction can be decomposed into a plurality of sub-index in proper order, and its index dimension includes: traditional village geographic information, belonged region, nationality, village formation time, ethnic group, terrain and landform, historical environment, historical figures, traditional buildings and the like. Taking the fifth batch of traditional village survey recommendation table as a reference, the evaluation system of the traditional village is evaluated from 5 evaluation directions such as village outline, village surrounding environment, site selection pattern, traditional architecture and non-material cultural heritage (see table 1), wherein each evaluation defense line has respective sub-indexes (see tables 2, 3, 4, 5 and 6). By analyzing the fifth batch of traditional village survey recommendation table, the invention excavates the following representative traditional village evaluation indexes.
TABLE 1 Key indices for traditional villages
Serial number | Evaluating the direction of the index | Index (I) |
1 | Village overview | Protective unit grade of village geographic information, nationality and cultural relics |
2 | Village surroundings | Natural ringScene, scenic spots, historical relics and ancient sites |
3 | Site selection pattern | Village site selection pattern and |
4 | Traditional building | Constructional features |
5 | Cultural heritage of non-material | Environment type, distribution, quantity |
(1) Village general evaluation index; basic information of the village is described. The quantitative indicators include village floor area, household register population, topographic features, main nationality and cultural relic protection unit grade, which are detailed in table 2.
TABLE 2 quantitative index table for village profile evaluation
Serial number | Index decomposition | Dictionary entry |
1 | Village floor area | More than 5 hectare, 3-5 hectare, 1-3 hectare, 0-1 hectare |
2 | Household registration population | 1000 or less, 1001 to 2000, 2000 or more |
3 | Topographic features | Mountain, plain, hilly and |
4 | Major nationality | Chinese and minority nationality |
5 | Cultural relic protection unit grade | National, provincial, county levels |
(2) Village ambient environment index; the harmonious symbiotic relationship between villages and the surrounding environment is mainly described, and the main indexes comprise: natural environment, scenic spots, detailed in table 3.
TABLE 3 quantitative index table for evaluation of village surroundings
Serial number | Index decomposition | Dictionary entry |
1 | Natural environment(s) | Mountain river system, geological landform and vegetationQuilt animal |
2 | Scenic spots | Level of interest, category, environment |
(3) Selecting an index of site pattern; the factors of cultural value, scientific value, historical environment and the like of village site selection are mainly described, including indexes of village pattern, village landscape and the like, and the detailed description is shown in table 4.
TABLE 4 quantitative index table for village site selection pattern evaluation
Serial number | Index decomposition | Dictionary entry |
1 | Village pattern | Conventional public space, water system and road network |
2 | Village landscape | Ancient river course, ancient tree, ancient well and village wall |
(4) Traditional building indexes; the existing valuable traditional dwellings, historical buildings and historical relics in villages are described, and the quantitative indexes are detailed in table 5.
TABLE 5 quantitative index table for evaluating traditional village buildings
Serial number | Index decomposition | Dictionary entry |
1 | Earliest construction age | Before the Ming dynasty, the Qing dynasty, the Ministry and the Jian nation till 1980 |
2 | Kind of building | Folk house, temple hall, temple, book hall, memorial archway, special building and homestead |
(5) Village non-material cultural heritage; the characteristics of cultural and non-material cultural heritage in the village are described in detail in table 6.
TABLE 6 quantitative index table for evaluation of non-material cultural heritage in village
And establishing the indexes into a structured data set to provide effective indexes for an intelligent evaluation model.
The random forest machine learning method is widely applied to the construction of data mining and rating judging systems in various fields. In addition, the traditional village evaluation method is limited by exponential dimensions, weight setting and complex linear relations in data, and the subjective judgment consciousness of different experts, understanding of the background in the research field and difference of the cognition angle have certain influence on rating evaluation. The classification evaluation system based on machine learning can effectively avoid subjective interference on weight setting. The machine learning method can realize the nonlinear statistics and fitting of the relation between the sample feature set and the classification result through the learning of the sample. Therefore, the invention adopts a random forest algorithm, and combines the classification results of a plurality of decision trees to obtain the final classification result, so that the classification result of the model is obviously improved, and the random forest can well solve the problem that a single classifier is easy to be over-fitted.
The random forest is a forest { h (x, v) composed of T classification trees which are extracted from samples by using a bostrap resampling method and established by using K samples t ) And T is 1,2, …, T. Wherein upsilon is t The method is a random variable subject to independent distribution, T represents the number of decision trees in a random forest, and each decision tree classifier determines an optimal classification result in a voting mode. The specific calculation formula is as follows:
wherein H (x) represents a classification result, Y represents a classification type, and T represents the number of decision trees in the random forest; i () is an indicative function, upsilon t Are random variables subject to independent distribution; x represents the eigenvalue and t represents the number of decision trees in the random forest.
Design and implementation of evaluation models
Data preprocessing:
the currently acquired data is 465 pieces of conventional village application table data, and the input of the 465 pieces of data selected as the conventional village is 370 pieces of data which are not successfully selected as the conventional village. According to earlier stage research, an important index characteristic value is extracted in 52 dimensions. Index numbers are expressed, such as village formation times: the number 3 is used for the Qing dynasty, the number 4 is used for the Ming dynasty, and the number 5 is used for the past generation; landform feature mountain 4, hill 2, plain 3. The representation method of the non-material cultural heritage of village is similar to the generation age of village, such as entertainment acrobatics is represented by numeral 1, the traditional skills are represented by numeral 2, and the traditional music is represented by numeral 3. If the other information is positive, it is represented by 1, and if the other information is negative, it is represented by 0. The data tables after the processing are shown in tables 7 and 8.
Table 7 processed conventional village application table data 1
Table 8 processed conventional village application table data 1
Model of traditional village protection based on random forest:
aiming at the requirements of research based on the traditional village protection value classification system, the 'cultural + ecological' pattern indexes (historical culture spatial pattern, geographic information, ecological civilization, historical culture, village activation and traditional village matching indexes and the like) are integrated into the traditional village protection value classification system, and the key indexes of the traditional village classification are combed. According to the traditional village evaluation result of an expert, the machine learning and data mining intelligent algorithm is used for learning the evaluation experience of the expert in the related field, the decision process of the expert is simulated, and the intelligent evaluation model of the traditional village protection evaluation system is realized. Many indexes are needed in the traditional village evaluation process, the indexes comprise qualitative indexes and quantitative indexes, an evaluation system is established by using a method for solving a classification problem, and grading is realized according to evaluation conditions. And establishing an intelligent evaluation model of the traditional village by using an algorithm of machine learning and data mining. Random forests have good processing capability on high-dimensional data sets, and overfitting can be effectively avoided. And an intelligent traditional village evaluation model is built by utilizing an improved random forest. The method comprises the steps that traditional village original data are extracted through samples and selected through characteristics, index samples are input into N decision trees of a random forest to be classified, a voting mechanism of the random forest votes all classification voting results, and a final evaluation result is given.
Experiment of
1) Constructing a traditional village classification random forest algorithm model
At present, a conventional village data set has 465 conventional village application table data in total, 95 tags selected for the conventional village are 1, 370 tags of the conventional data which are not successfully selected are 0. The data set is as follows 8: a scale of 2 into a training data set and a test data set. The experiment is to realize a random forest model by using a python language, and the experimental result shows that the classification precision reaches 82%.
2) Parameter adjustment optimization of model by grid search
The grid search is to grid the variable region, traverse all grid points, solve the objective function value meeting the constraint function in order to improve the generalization ability of the model, and adjust the parameters of the model by the network search technology to achieve the purpose of optimizing the model. Here we construct random forests of 120, 200, 300, 500 trees by adjusting the value of the parameter n _ estimaors. The best result is that when a random forest of 200 trees is built, the accuracy is 82%.
3) Importance of evaluation index by using random forest
It can thus be seen that the first place of residence is the most important feature, the importance of which is in the second and third place of age and household, respectively. This indicates that the building index has the greatest impact on the evaluation of traditional villages. The influence of the index on the traditional village selection can be shown according to table 9.
TABLE 9 influence of the indices on the traditional village selection
The invention has the following beneficial effects:
through the technical scheme, namely the traditional village protection value evaluation method provided by the invention, the technical problem that subjective judgment consciousness of different experts, understanding of the background in the research field and difference of the cognition angle can have certain influence on rating evaluation can be solved by adopting the random forest algorithm, so that the weight setting is effectively prevented from being subjectively interfered, the traditional village value evaluation is more fair and fair, and the inheritance of cultural heritage and non-renewable resources in China is further effectively ensured.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (6)
1. A traditional village protection value evaluation method is characterized by comprising the following steps:
s1: acquiring traditional village survey data;
s2: performing data entry and data preprocessing operation on the traditional village survey data to obtain traditional village data;
s3: classifying the traditional village data by using a random forest algorithm to obtain a classification result;
s4: and outputting the classification result as an evaluation result.
2. The method according to claim 1, wherein in step S1, the conventional village survey data at least includes the following characteristic indexes:
village profile, village surroundings, site selection pattern, traditional architecture and non-material cultural heritage.
3. The method of assessing the value of protection in a conventional village of claim 2,
the village profile includes the following sub-characteristic indicators: village floor area, household register population, topographic features, main nationality and cultural relic protection unit grade;
the village surrounding environment comprises the following sub-characteristic indexes: natural environment and scenic spots;
the site selection pattern comprises the following sub-characteristic indexes: village constellations and village features;
the traditional building comprises the following sub-characteristic indexes: the earliest construction age and type of building; and the non-material cultural heritage comprises the following sub-characteristic indexes: family and leaderboard.
4. The method for assessing the protection value of a conventional village according to claim 1, wherein in said step S2, said data preprocessing operation comprises:
preliminarily screening the traditional village survey data into usable data and unusable data;
extracting traditional village data in the available data;
and assigning the sub-characteristic indexes of the characteristic indexes in the traditional village data.
5. The method for evaluating the protection value of a conventional village according to claim 1, wherein in said step S3, said random forest algorithm comprises:
a1: taking the traditional village data as a sample set;
a2: extracting a plurality of samples from the sample set by a Boostrap resampling method, and forming a sampling set by the plurality of samples;
a3: training a target decision tree model with the sample set;
a4: randomly selecting a part of characteristics from all sample characteristics on the nodes of the target decision tree model;
a5: taking the optimal feature in the partial features as a left sub-tree and a right sub-tree of the target decision tree;
a6: and repeating the steps A1-A5 until the repetition times are equal to the preset iteration times, and outputting the category with the most optimal characteristics as a final category.
6. The method of assessing the value of protection of a traditional village of claim 1 or 5, wherein said random forest algorithm model is:
wherein H (x) represents a classification result, Y represents a classification type, and T represents the number of decision trees in the random forest; i () is an indicative function, upsilon t Are random variables subject to independent distribution; x represents the eigenvalue and t represents the number of decision trees in the random forest.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210205318.8A CN114841492A (en) | 2022-03-02 | 2022-03-02 | Traditional village protection value evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210205318.8A CN114841492A (en) | 2022-03-02 | 2022-03-02 | Traditional village protection value evaluation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114841492A true CN114841492A (en) | 2022-08-02 |
Family
ID=82562355
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210205318.8A Pending CN114841492A (en) | 2022-03-02 | 2022-03-02 | Traditional village protection value evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114841492A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115392875A (en) * | 2022-08-31 | 2022-11-25 | 广州市城市规划设计有限公司 | Traditional residential protective data system and data processing method |
CN116976692A (en) * | 2023-07-12 | 2023-10-31 | 北京大学 | Traditional village classification partition protection control method based on adaptive circulation path |
-
2022
- 2022-03-02 CN CN202210205318.8A patent/CN114841492A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115392875A (en) * | 2022-08-31 | 2022-11-25 | 广州市城市规划设计有限公司 | Traditional residential protective data system and data processing method |
CN115392875B (en) * | 2022-08-31 | 2024-02-27 | 广州市城市规划设计有限公司 | Traditional folk house protection data system and data processing method |
CN116976692A (en) * | 2023-07-12 | 2023-10-31 | 北京大学 | Traditional village classification partition protection control method based on adaptive circulation path |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112700045B (en) | Intelligent site selection system based on land reserve implementation monitoring model | |
CN114841492A (en) | Traditional village protection value evaluation method | |
CN107230113A (en) | A kind of house property appraisal procedure of multi-model fusion | |
CN105931116A (en) | Automated credit scoring system and method based on depth learning mechanism | |
CN106295874A (en) | Traffic flow parameter Forecasting Methodology based on deep belief network | |
Duinker | Criteria and indicators of sustainable forest management in Canada: progress and problems in integrating science and politics at the local level | |
CN104809522B (en) | A kind of comprehensive energy prediction technique | |
CN102646164A (en) | Land use change modeling method and system implemented in combination with spatial filtering | |
Huang et al. | Research on urban modern architectural art based on artificial intelligence and GIS image recognition system | |
CN107392164A (en) | A kind of Expression analysis method based on the estimation of Facial action unit intensity | |
Inyang et al. | Fuzzy clustering of students' data repository for at-risks students identification and monitoring | |
CN115099450A (en) | Family carbon emission monitoring and accounting platform based on fusion model | |
Liu et al. | Measurement and analysis of regional flood disaster resilience based on a support vector regression model refined by the selfish herd optimizer with elite opposition-based learning | |
Zhang et al. | Support vector machine weather prediction technology based on the improved quantum optimization algorithm | |
Elayidom et al. | A generalized data mining framework for placement chance prediction problems | |
CN108073978A (en) | A kind of constructive method of the ultra-deep learning model of artificial intelligence | |
Oladipo et al. | An Improved Particle Swarm Optimization and Adaptive Neuro‐Fuzzy Inference System for Predicting the Energy Consumption of University Residence | |
Sugianto et al. | K-Means Algorithm For Clustering Poverty Data in Bangka Belitung Island Province | |
Wang et al. | A fuzzy intelligent system for land consolidation–a case study in Shunde, China | |
CN109992592B (en) | College poverty and poverty identification method based on flow data of campus consumption card | |
Zhang et al. | Estimating the outdoor environment of workers’ villages in East China using machine learning | |
CN111428861A (en) | Manufacturing enterprise overseas investment site selection decision method based on multi-scale multi-dimensional proximity | |
CN108073985A (en) | A kind of importing ultra-deep study method for voice recognition of artificial intelligence | |
Oladipo et al. | Analysis of the impact of clustering techniques and parameters on evolutionary-based hybrid models for forecasting electricity consumption | |
CN111401683B (en) | Method and device for measuring tradition of ancient villages |
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 |