CN115619605A - Traditional residential environment quality evaluation method based on semantic information - Google Patents
Traditional residential environment quality evaluation method based on semantic information Download PDFInfo
- Publication number
- CN115619605A CN115619605A CN202210988129.2A CN202210988129A CN115619605A CN 115619605 A CN115619605 A CN 115619605A CN 202210988129 A CN202210988129 A CN 202210988129A CN 115619605 A CN115619605 A CN 115619605A
- Authority
- CN
- China
- Prior art keywords
- environment
- traditional
- carrying
- data
- environmental
- 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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention discloses a traditional resident house environment quality evaluation method based on semantic information, which comprises the steps of firstly carrying out environment data acquisition on a traditional resident house building through a mobile terminal and carrying out data transmission to a cloud server to preprocess original data; then calculating semantic information of each sampling point by combining multi-source information, then carrying out K-medoids clustering based on the semantic information to obtain pollution source distribution and pollution propagation trend conditions under the whole traditional residential environment, and carrying out region division and visual output; and finally, carrying out environment evaluation on the collected traditional residential environment by a fuzzy comprehensive evaluation method according to the self-adaptive adjustment environment parameter weight of each divided region. In the traditional residential environment quality evaluation process, the method can be used for carrying out high-quality acquisition on the environment data, is low in cost and high in accuracy, and can be used for carrying out reasonable evaluation on the traditional residential environment quality so as to be optimized and processed by a decision maker.
Description
Technical Field
The invention belongs to the field of environmental quality monitoring, and particularly relates to a traditional residential environmental quality evaluation method based on semantic information.
Background
At present, in the aspect of environmental monitoring of traditional residences, a fixed sensor-based mode is generally adopted to collect environmental data of the traditional residences. However, the indoor environment is complicated and changeable, the traditional local-style dwelling houses have uneven distribution of environmental parameters, the acquisition range of the fixed sensor is limited, and the whole building is difficult to monitor comprehensively. In addition, the evaluation of the quality of the traditional residential environment is mostly limited to a single environmental factor, and a traditional residential environment evaluation system based on a plurality of environmental factors is lacked.
Disclosure of Invention
The invention provides a traditional residential environment quality assessment method based on semantic information, and aims to solve the problems that in the traditional residential environment monitoring process, the cost for building an environment monitoring system is high, the monitoring precision is low, assessment is inaccurate and the like.
The invention adopts the following technical scheme for solving the technical problems: a traditional folk house environment quality evaluation method based on semantic information is characterized by comprising the following steps:
(1) Obtaining and processing multi-source environment information;
the method comprises the following steps of multi-source environment information obtaining and processing stages:
(1.1) carrying a collection end by utilizing a mobile carrier to collect environmental data of the traditional residential building environment to obtain an environmental data set
The collected multi-source data are transmitted to a cloud server, gaussian smoothing filtering is carried out on the original data to process accidental factor interference, and then Kalman filtering is carried out on the data to obtain reliable environment parameter data;
(2) Fine-grained region division based on semantic information;
the area division stage comprises the following specific steps:
(2.1) solving psi = f (X, gamma) for semantic tags according to environment prior physical structure information gamma and mobile carrier positioning information X, and endowing each sample data with the semantic tags
(2.2) carrying out K-medoids clustering on the processed data, which specifically comprises the following steps: performing conditional ordering on the sampling point information under each semantic information to obtain sampling points c where the maximum value and the minimum value of each pollutant are located, and clustering by taking the sampling points c as initial clustering centers; calculating the distance between each sample and the clustering center under different semantic environments, and performing category division; iteration is carried out repeatedly by taking the central point as a new clustering center;
(2.3) performing area fine-grained division L = { L } on the traditional residential environment according to the environmental pollutant information clustering result and the house physical structure 1 ,L 2 ,...L n }；
(2.4) performing spatial heat map visual output on the processed multi-source data to obtain the pollution source distribution and the pollution propagation trend condition in the whole traditional residential environment;
(3) An environment evaluation method based on fuzzy comprehensive evaluation;
the environment evaluation stage comprises the following specific steps:
(3.1) fuzzifying the collected traditional residential environment parameters, establishing a membership function of each environment parameter, and obtaining the membership of each environment parameter X in a fuzzy subset X, wherein the fuzzification is specifically as follows: extremely low, normal, high and high; similarly, establishing a fuzzy subset Y and a membership function for the environment evaluation set Y, and setting the environment evaluation standard as excellent, good, qualified, poor and extremely bad;
(3.2) integrating the membership degree of each environmental parameter, and establishing a fuzzy control rule of the environmental parameters and an evaluation system
(3.3) weighting by adopting an improved analytic hierarchy process, wherein the improved analytic hierarchy process specifically comprises the following steps: firstly, establishing a hierarchical structure model; according to the previous fine-grained region division result L = { L = { (L) 1 ,L 2 ,...L n Comparing every two environmental factors with each other by the environmental semantic information to obtain a judgment matrix
Wherein q is ij ＞0,
The judgment matrix is self-adaptively adjusted according to different environmental semantics; calculating the maximum eigenvalue lambda and the corresponding eigenvalue weight vector W = { omega } on the basis of the judgment matrix 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 }；
(3.4) weighting W multiplied by R according to the obtained weight vector W and the established fuzzy control rule R to obtain a fuzzy comprehensive evaluation result B = { B = 1 ,B 2 ,B 3 ,B 4 ,B 5 And finally, carrying out environment judgment by using a maximum membership degree principle to obtain a final environment evaluation: b = max (B).
As a further improvement of the invention: the specific form of the original multi-source data collected in the step (1.1) is as follows: temperature, humidity, carbon dioxide concentration, TVOC concentration, formaldehyde concentration, time, and location.
As a further improvement of the invention: in the step (3.1), the membership function model selects a trapezoidal function according to the traditional residential environment evaluation system
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
the invention can obtain the following advantages by adopting the technical means: by adopting the technical scheme, the mobile carrier is used for carrying the collector to traverse the environment, and multi-source environment information in the target environment is collected at the same time, so that non-fixed-point environment monitoring can be realized; removing gross errors and smoothing filtering of the multi-source information by using a data processing module, performing clustering division on original data by using a multi-feature self-adaptive clustering method for each multi-source information at the same time, and performing visual output for visual display; and then partitioning the whole environment, performing hierarchical analysis by combining clustering results and environment semantic information to determine the weight of each environment parameter, and performing comprehensive evaluation on the whole traditional dwelling environment by adopting fuzzy control, so that the target environment can be evaluated to the greatest extent, the environmental quality condition of the traditional dwelling can be reflected scientifically and reasonably, and data reference is provided for subsequent environmental improvement and regulation.
Drawings
FIG. 1 is a diagram of a monitoring system architecture;
FIG. 2 is a flow chart of a traditional residential environment quality assessment method based on semantic information
FIG. 3 is a flow chart of a fuzzy comprehensive decision algorithm;
FIG. 4 is a hierarchical analysis model of an environmental assessment problem.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention adopts a mode of carrying the collector by the mobile carrier to replace a mode of fixing the environment monitoring base station to improve the monitoring efficiency and the monitoring precision of environment monitoring. Meanwhile, the environmental quality evaluation problem of the complex indoor environment is solved by combining the environmental semantic information, the fuzzy comprehensive evaluation method and the improved hierarchical analysis method, the environmental quality condition of the traditional residences can be scientifically and reasonably reflected, and reference is provided for environmental regulation and modification.
The specific technical scheme is as follows: a traditional folk house environment quality evaluation method based on semantic information comprises the following steps:
step 1: the multi-source environment information acquisition and processing method specifically comprises the following steps:
1.1 this example utilizes the mobile carrier to carry on the collection end and carry on the environmental data acquisition to the traditional local-style dwelling houses building environment, obtains the environmental data set
The position information of the mobile carrier is resolved in real time through a combined positioning system. The carried sensor module mainly selects a temperature and humidity sensor, a carbon dioxide sensor, a TVOC sensor and a formaldehyde sensor according to the environmental characteristics;
1.2 transmit data and time and position data that environmental sensor gathered to high in the clouds server, integrate multisource data at high in the clouds server, and concrete form is: temperature, humidity, carbon dioxide concentration, TVOC concentration, formaldehyde concentration, time and position, performing Gaussian smoothing filtering on the original data to process accidental factor interference, and then performing Kalman filtering on the data to obtain reliable environmental parameter data.
And 2, step: based on the fine-grained region partitioning of the semantic information,
specifically comprises
2.1 carrying out multi-dimensional K-medoids clustering on the processed data, which specifically comprises the following steps: firstly, a semantic tag is solved by psi = f (X, gamma) according to environment prior physical structure information gamma and mobile carrier positioning information X, and each semantic tag is subjected to calculationSample data-to-semantic tag
2.2, performing condition sequencing on the sampling point information under each semantic information to obtain sampling points c where the maximum value and the minimum value of each pollutant are located, and clustering by taking the sampling points as initial clustering centers; calculating the distance between each sample and the clustering center under different semantic environments, and performing category division; repeatedly performing iteration by taking the central point as a new clustering center;
2.3 according to the clustering result of the environmental pollutant information and the physical structure of the house, carrying out regional fine granularity division on the traditional residential environment, wherein L is = { L = { L } 1 ,L 2 ,...L n }；
2.4, performing spatial heat map visual output on the processed multi-source data to obtain the pollution source distribution and the pollution propagation trend condition under the whole traditional residential environment;
step 3, based on the environmental assessment method of fuzzy comprehensive evaluation,
the method comprises the following specific steps:
and 3.1, fuzzifying the collected traditional residential environment parameters, and establishing a membership function of each environment parameter to obtain the membership of each environment parameter X in the fuzzy subset X. The method specifically comprises the following steps: very low (NB), low (NS), normal (ZO), high (PS), very high (PB); similarly, a fuzzy subset Y and a membership function are established for the environment evaluation set Y, and environment evaluation criteria are set as excellent (VS), good (S), qualified (M), poor (L) and extremely poor (VL). An affiliation function model selects a trapezoidal function according to a traditional residential environment evaluation system
3.2 synthesize the membership degree of each environmental parameter, and establish the fuzzy control rule of the environmental parameter and the evaluation system
3.3 by modified analytic hierarchy ProcessThe weight is given, and the improved analytic hierarchy process specifically comprises the following steps: firstly, establishing a hierarchical structure model as shown in FIG. 4; according to the previous stage area division result and the environment semantic information, two pairs of comparison are carried out on each environment factor to obtain a judgment matrix
Wherein q is ij ＞0,
The judgment matrix is self-adaptively adjusted according to different environmental semantics; calculating the maximum eigenvalue lambda and the corresponding eigenvalue weight vector W = { omega } on the basis of the judgment matrix 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 }。
3.4 based on the weight vector W and the fuzzy control established weighting W multiplied by R by rule R to obtain fuzzy comprehensive evaluation result B = { B = { (B) } 1 ,B 2 ,B 3 ,B 4 ,B 5 And finally, carrying out environment judgment by using a maximum membership degree principle to obtain a final environment evaluation: b = max (B).
According to the invention, the mobile carrier is used for carrying the collector to traverse the environment, and multi-source environment information is collected, so that non-fixed-point environment monitoring can be realized, the efficiency is high and the effect is good; removing gross errors and smoothing filtering of the multi-source information by using a data processing module, performing clustering division on original data by using a multi-feature self-adaptive clustering method aiming at each multi-source information, performing visual output, and performing visual display; and then partitioning the whole environment, performing hierarchical analysis by combining clustering results and environment semantic information to determine the weight of each environment parameter, and performing comprehensive evaluation on the whole traditional dwelling environment by adopting fuzzy control, so that the target environment can be evaluated in the maximum degree, the environmental quality condition of the traditional dwelling can be reflected scientifically and reasonably, and data reference is provided for subsequent environmental improvement and regulation.
The above description is only one of the preferred embodiments of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made in accordance with the technical spirit of the present invention are within the scope of the present invention as claimed.
Claims (3)
1. A traditional folk house environment quality evaluation method based on semantic information is characterized by comprising the following steps:
(1) Obtaining and processing multi-source environment information;
(1.1) carrying a collection end by utilizing a mobile carrier to collect environmental data of the traditional residential building environment to obtain an environmental data set gamma; the collected multi-source data are transmitted to a cloud server, gaussian smoothing filtering is carried out on the original data to process accidental factor interference, and then Kalman filtering is carried out on the data to obtain reliable environment parameter data;
(2) Fine-grained region division based on semantic information;
the area division stage comprises the following specific steps:
(2.1) solving psi = f (X, gamma) for semantic tags according to environment prior physical structure information gamma and mobile carrier positioning information X, and endowing each sample data with the semantic tags
(2.2) carrying out K-medoids clustering on the processed data, which specifically comprises the following steps: performing conditional ordering on the sampling point information under each semantic information to obtain sampling points c where the maximum value and the minimum value of each pollutant are located, and clustering by taking the sampling points c as initial clustering centers; calculating the distance between each sample and the clustering center under different semantic environments, and performing classification; repeatedly iterating by taking the central point as a new clustering center;
(2.3) performing area fine-grained division L = { L } on the traditional residential environment according to the environmental pollutant information clustering result and the house physical structure 1 ,L 2 ,...L n }；
(2.4) carrying out spatial heat map visual output on the processed multi-source data to obtain pollution source distribution and pollution propagation trend conditions in the whole traditional residential environment;
(3) An environment evaluation method based on fuzzy comprehensive evaluation;
in the environment evaluation stage, the specific steps are as follows:
(3.1) fuzzifying the collected traditional residential environment parameters, establishing a membership function of each environment parameter, and obtaining the membership of each environment parameter X in a fuzzy subset X, wherein the fuzzification is specifically as follows: extremely low, normal, high and high; similarly, establishing a fuzzy subset Y and a membership function for the environment evaluation set Y, and setting the environment evaluation standard as excellent, good, qualified, poor and extremely poor;
(3.2) integrating the membership degree of each environmental parameter, and establishing a fuzzy control rule of the environmental parameters and an evaluation system
(3.3) weighting by adopting an improved analytic hierarchy process, wherein the improved analytic hierarchy process specifically comprises the following steps: firstly, establishing a hierarchical structure model; according to the previous fine-grained region division result L = { L = { (L) 1 ,L 2 ,...L n Comparing every two environmental factors with each other according to the environmental semantic information to obtain a judgment matrix
Wherein the content of the first and second substances,
the judgment matrix is self-adaptively adjusted according to different environmental semantics; calculating the maximum eigenvalue lambda and the corresponding eigenvalue weight vector W = { omega } on the basis of the judgment matrix 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 }；
(3.4) weighting W multiplied by R according to the obtained weight vector W and the established fuzzy control rule R to obtain a fuzzy comprehensive evaluation result B = { B = 1 ,B 2 ,B 3 ,B 4 ,B 5 And finally, carrying out environment judgment by using a maximum membership degree principle to obtain a final environment evaluation: b = max (B).
2. The traditional folk house environment quality assessment method based on semantic information as claimed in claim 1, wherein: the specific form of the original multi-source data collected in the step (1.1) is as follows: temperature, humidity, carbon dioxide concentration, TVOC concentration, formaldehyde concentration, time, and location.
3. The traditional folk house environment quality assessment method based on semantic information as claimed in claim 1, characterized in that: in the step (3.1), the membership function model selects a trapezoidal function according to a traditional residential environment evaluation system
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210988129.2A CN115619605A (en) | 2022-08-17 | 2022-08-17 | Traditional residential environment quality evaluation method based on semantic information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210988129.2A CN115619605A (en) | 2022-08-17 | 2022-08-17 | Traditional residential environment quality evaluation method based on semantic information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115619605A true CN115619605A (en) | 2023-01-17 |
Family
ID=84857332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210988129.2A Pending CN115619605A (en) | 2022-08-17 | 2022-08-17 | Traditional residential environment quality evaluation method based on semantic information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115619605A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116520718A (en) * | 2023-07-03 | 2023-08-01 | 深圳小米房产网络科技有限公司 | Intelligent home self-adaptive control method and device based on Internet of things technology |
-
2022
- 2022-08-17 CN CN202210988129.2A patent/CN115619605A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116520718A (en) * | 2023-07-03 | 2023-08-01 | 深圳小米房产网络科技有限公司 | Intelligent home self-adaptive control method and device based on Internet of things technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116186634B (en) | Intelligent management system for construction data of building engineering | |
| CN109461025B (en) | Electric energy substitution potential customer prediction method based on machine learning | |
| CN110705760A (en) | Photovoltaic power generation power prediction method based on deep belief network | |
| CN111654874A (en) | Wireless sensor network anomaly detection method | |
| Lee et al. | Using climate classification to evaluate building energy performance | |
| CN105701572B (en) | Photovoltaic short-term output prediction method based on improved Gaussian process regression | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN109327797A (en) | Mobile robot indoor locating system based on WiFi network signal | |
| CN116205310B (en) | Soil water content influence factor sensitive interval judging method based on interpretable integrated learning model | |
| CN104850867A (en) | Object identification method based on intuitive fuzzy c-means clustering | |
| CN111937016B (en) | City internal poverty-poor space measuring method and system based on street view picture and machine learning | |
| CN112183625A (en) | PM based on deep learning2.5High-precision time-space prediction method | |
| CN115619605A (en) | Traditional residential environment quality evaluation method based on semantic information | |
| CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
| CN112508437A (en) | Method for correcting time sequence similarity error of wind speed forecast in micro-climate environment | |
| CN116665001A (en) | Intelligent park multisource data dynamic monitoring and real-time analysis system and method | |
| CN115099511A (en) | Photovoltaic power probability estimation method and system based on optimized copula | |
| Omar et al. | Seasonal clustering forecasting technique for intelligent hourly solar irradiance systems | |
| CN116257792B (en) | Smart city carbon neutralization data analysis system | |
| CN108830405A (en) | Real-time electric power load prediction system and method based on multi objective Dynamic Matching | |
| KR102067110B1 (en) | Energy data processing apparatus and method with high accuracy for constructed building | |
| CN116822381A (en) | Marine temperature salt structure inversion method based on artificial intelligence | |
| CN116050592A (en) | Multi-dimensional photovoltaic power prediction method and system | |
| CN113177675B (en) | Air conditioner cooling load prediction method based on longicorn group algorithm optimization neural network | |
| CN115146742A (en) | Offshore wind farm unit grouping and flagship machine selection method suitable for farm group control |
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 |