CN107958274A - A kind of structural fire protection safety index computational methods based on big data sorting algorithm - Google Patents
A kind of structural fire protection safety index computational methods based on big data sorting algorithm Download PDFInfo
- Publication number
- CN107958274A CN107958274A CN201711361455.6A CN201711361455A CN107958274A CN 107958274 A CN107958274 A CN 107958274A CN 201711361455 A CN201711361455 A CN 201711361455A CN 107958274 A CN107958274 A CN 107958274A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- mtd
- data
- building
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The present invention relates to security against fire big data analysis platform technology field, especially a kind of structural fire protection safety index computational methods based on big data sorting algorithm, its method and step is：Step 1：Data markers and packet；Step 2：Build SVM classifier；Step 3：Train classification models；Step 4：Application model prediction result.Beneficial effect of the present invention：The present invention combines newest data mining theories implementation, using the safety index computation model of SVM support vector machines structure standardization, and shift to an earlier date the basis using historical data as model construction, under the support of modern computer arithmetic speed, quick, science, standard, objective result of calculation can be reached.
Description
Technical field
It is especially a kind of to be based on big data sorting algorithm the present invention relates to security against fire big data analysis platform technology field
Structural fire protection safety index computational methods.
Background technology
With the fast development of social economy in recent years, new situation that fire-fighting work faces, new problem are on the increase, fire-fighting peace
Holotype gesture is still severe, and regional fire hazard protrudes, and generally still in fire-prone, multiple phase, is brought to fire-fighting work
Stern challenge and test.In order to investigate structural fire protection security risk, structural fire protection security risk, various regions administration of the prevention and control portion are reduced
Door increases the security against fire detection for building, and fire protection refers to management of fire safety department or testing agency pair
Specify building fire protection facility to carry out complete detection, and quantify to record a series of inspection behaviors of each fire fighting device state.It is based on
The quantized data that fire protection is formed, specify the security against fire index of building to calculate, to determine whether the building belongs to
Excessive risk is built, and fire chief department determines that emphasis fire hazard takes precautions against target with this, strengthens the management of excessive risk building, so that
Reduce the occurrence probability of fire-fighting accident.
Since fire protection record data volume is huge, data relationship is complicated, and structural fire protection safety index, which calculates, to be needed to expend
A large amount of manpowers, and evaluation result is often limited to experience level of adjuster etc., cause evaluation result unstable etc..
Therefore, it is necessary to propose a kind of structural fire protection safety index meter based on big data sorting algorithm for the above problem
Calculation method.
The content of the invention
The present invention seeks to overcome deficiency of the prior art, there is provided a kind of building based on big data sorting algorithm
Security against fire index calculation method, by common sorting algorithm in data mining, the result based on some original grouped datas
Data study is carried out, so that the big data disaggregated model of structural fire protection safety index calculating is established, it is more scientific, fast, exactly
Carry out structural fire protection safety index evaluation.
In order to solve the above-mentioned technical problem, the present invention is to be achieved through the following technical solutions：
A kind of structural fire protection safety index computational methods based on big data sorting algorithm, its method and step are：Step 1：
Data markers and packet；Step 2：Build SVM classifier；Step 3：Train classification models；Step 4：Application model prediction knot
Fruit.
Preferably, data markers further comprise with packet：(1) it is according to different by all fire protection project datas
System classification；(2) scoring rate of all items is calculated according to the tabulation in step (1), statistics.Scoring rate calculation formula is：
(3) by all 21 project scoring rates being calculated in step (2) be combined into one 21 dimension vector x=[a1,
A2 ..., a21], which is all detection scoring events for representing a solitary building, calculates the detection score feelings of all buildings
Condition vector, forms entirety data set X={ xn, n ∈ R }；(4) with historical building risk index result of calculation to all data set X
In data classify into line label, all excessive risks building is labeled as 1, and non-excessive risk building is labeled as -1；And by annotation results
Taken out at random in all data sets afterwards 60% data combination composing training data set Strain=(xn, yn) | xn ∈ X, yn ∈
{ -1,1 }, n=1,2,3 ... } wherein xn is the scoring rate vector of n-th of building, and yn is the Risk Results of corresponding n-th of building,
Remaining 40% as test data set Stest={ (xm, ym) | xm ∈ X, ym ∈ { -1,1 }, m=1,2,3 ... } wherein xm is m
The scoring rate vector of a building, ym are the safety index result of calculation of corresponding m-th of building.Training dataset is used to train SVM
Disaggregated model, obtains the model parameter under corresponding data collection, and test data set is used to examine under this parameter level to being not involved in
The predictablity rate of trained data, so that the generalization ability (being interpreted as the predictive ability to unknown data) of analysis model.
Preferably, wherein structure SVM classifier further includes：(1) set given training set as (x1, y1), (x2,
Y2) ..., (xn, yn) } wherein xi ∈ Rn are input vector, yi ∈ { -1,1 } are output vector, it is assumed that the training set can be by one
Hyperplane WX+b=0 linear partitions, problem, which is converted into ask, optimizes hyperplane problem：
(2), can be by a mapping function (claiming kernel function in SVM), by low-dimensional in the case of Nonlinear separability
Input space Rn is mapped to the feature space H of higher-dimension, makes linear separability.Then optimization problem is converted into
(3) solving formula (2) optimization function is：
From formula (2), minimization problem can be drawn, select suitable function K () and C to determine SVM classifier；
(4) RBF Radial basis kernel functions, i.e. K (X are selectedi, Xj)=exp (- γ | | Xi-Xj||)2, then the optimization problem of grader finally turn
Turn to select permeability of the parameter to (C, γ).
Preferably, wherein train classification models further include：
(1) it is scope with 1≤C≤1000 and 0≤γ≤100, builds the parameter of all C and γ compositions in value range
It is right；
(2) take parameter to (C, γ) as the SVM classifier initial parameter value based on RBF kernel functions, training data successively
Vector set Strain and test data vector set Stest, remembers that the accuracy rate predicted under this disaggregated model test data set is
pt；
(3) test set accuracy rate is directed to, C values and γ value parameters different in test SVM algorithm are adjusted with computer program
It is right, accuracy rate pt is reached the accuracy rate p0 of pre-provisioning request, and keep records of the model parameter under this accuracy rate p0 to (C0,
γ0), i.e., this parameter is to the model parameter for required svm classifier model.
Preferably, wherein application model prediction result further includes：(1) building score of the structure without mark result
Rate data vector x '.(construction method refers to the Step1-Step3 in step 1)；
(2) model parameter (C0, the γ of training gained in step 3 are used0) svm classifier prediction is carried out to x ', exported
As a result y ' ∈ { -1,1 }；(3) y ' is required building safety index result of calculation.
Beneficial effect of the present invention：The present invention combines newest data mining theories implementation, using SVM support vector machines
The safety index computation model of standardization, and the basis using historical data as model construction in advance are built, in modern computer
Under the support of arithmetic speed, quick, science, standard, objective result of calculation can be reached.
It is described further below with reference to the technique effect of design of the attached drawing to the present invention, concrete structure and generation, with
It is fully understood from the purpose of the present invention, feature and effect.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention.
Embodiment
The embodiment of the present invention is described in detail below in conjunction with attached drawing, but the present invention can be defined by the claims
Implement with the multitude of different ways of covering.
As shown in Figure 1, a kind of structural fire protection safety index computational methods based on big data sorting algorithm, its method and step
For：Step 1：Data markers and packet；
(such as：Fire supply system, gas extinguishing system, temperature sense system etc.) and important level (be to one
Different subitems in system are classified, overall to be divided into three-level to fire-fighting system operation influence size according to project, are respectively：It is larger
Influence project, General Influence project, smaller influence project) it is grouped classification.Specific tabulation is as follows：
Step 2：Build SVM classifier；Step 3：Train classification models；Step 4：Application model prediction result.
Further, data markers further comprise with packet：(1) by all fire protection project datas according to different
System classification；(2) scoring rate of all items is calculated according to the tabulation in step (1), statistics.Scoring rate calculation formula
For：
(3) by all 21 project scoring rates being calculated in step (2) be combined into one 21 dimension vector x=[a1,
A2 ..., a21], which is all detection scoring events for representing a solitary building, calculates the detection score feelings of all buildings
Condition vector, forms entirety data set X={ xn, n ∈ R }；(4) with historical building risk index result of calculation to all data set X
In data classify into line label, all excessive risks building is labeled as 1, and non-excessive risk building is labeled as -1；And by annotation results
Taken out at random in all data sets afterwards 60% data combination composing training data set Strain=(xn, yn) | xn ∈ X, yn ∈
{ -1,1 }, n=1,2,3 ... } wherein xn is the scoring rate vector of n-th of building, and yn is the Risk Results of corresponding n-th of building,
Remaining 40% as test data set Stest={ (xm, ym) | xm ∈ X, ym ∈ { -1,1 }, m=1,2,3 ... } wherein xm is m
The scoring rate vector of a building, ym are the safety index result of calculation of corresponding m-th of building.Training dataset is used to train SVM
Disaggregated model, obtains the model parameter under corresponding data collection, and test data set is used to examine under this parameter level to being not involved in
The predictablity rate of trained data, so that the generalization ability (being interpreted as the predictive ability to unknown data) of analysis model.
Wherein structure SVM classifier further includes：(1) set given training set as (x1, y1), (x2, y2) ...,
(xn, yn) } wherein xi ∈ Rn are input vector, yi ∈ { -1,1 } are output vector, it is assumed that the training set can be by a hyperplane
WX+b=0 linear partitions, problem, which is converted into ask, optimizes hyperplane problem：
(2), can be by a mapping function (claiming kernel function in SVM), by low-dimensional in the case of Nonlinear separability
Input space Rn is mapped to the feature space H of higher-dimension, makes linear separability.Then optimization problem is converted into
(3) solving formula (2) optimization function is：
From formula (2), minimization problem can be drawn, select suitable function K () and C to determine SVM classifier；
(4) RBF Radial basis kernel functions, i.e. K (X are selectedi, Xj)=exp (- γ | | Xi-Xj||)2, then the optimization problem of grader finally turn
Turn to select permeability of the parameter to (C, γ).
Wherein train classification models further include：
(1) it is scope with 1≤C≤1000 and 0≤γ≤100, builds the parameter of all C and γ compositions in value range
It is right；
(2) take parameter to (C, γ) as the SVM classifier initial parameter value based on RBF kernel functions, training data successively
Vector set Strain and test data vector set Stest, remembers that the accuracy rate predicted under this disaggregated model test data set is
pt；
(3) test set accuracy rate is directed to, C values and γ value parameters different in test SVM algorithm are adjusted with computer program
It is right, accuracy rate pt is reached the accuracy rate p0 of pre-provisioning request, and keep records of the model parameter under this accuracy rate p0 to (C0,
γ0), i.e., this parameter is to the model parameter for required svm classifier model.
Wherein application model prediction result further includes：(1) building scoring rate data of the structure without mark result
Vector x '.(construction method refers to the Step1-Step3 in step 1)；
(2) model parameter (C0, the γ of training gained in step 3 are used0) svm classifier prediction is carried out to x ', exported
As a result y ' ∈ { -1,1 }；(3) y ' is required building safety index result of calculation.
Beneficial effect of the present invention：The present invention combines newest data mining theories implementation, using SVM support vector machines
The safety index computation model of standardization, and the basis using historical data as model construction in advance are built, in modern computer
Under the support of arithmetic speed, quick, science, standard, objective result of calculation can be reached.
Wherein, big data sorting algorithm is referred to based on support vector machines, neutral net etc., to find out in database
One group of data object common feature and the algorithm of different classes is divided into according to classification mode.The purpose is to by dividing
Class model, by the maps data items in database into some given classification.
In machine learning, support vector machines (SVM, goes back support vector network) is the prison related with relevant learning algorithm
Learning model is superintended and directed, data, recognition mode, for classification and regression analysis can be analyzed.Give one group of training sample, each mark
To belong to two classes, a SVM training algorithm establishes a model, distributes new example as a kind of or other classes, becomes
Non- probability binary linearity classification.
Preferred embodiment of the invention described in detail above.It should be appreciated that those of ordinary skill in the art without
Need creative work to conceive according to the present invention and make many modifications and variations.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical solution, all should be in the protection domain being defined in the patent claims.
Claims (5)
- A kind of 1. structural fire protection safety index computational methods based on big data sorting algorithm, it is characterised in that：Its method and step For：Step 1：Data markers and packet；Step 2：Build SVM classifier；Step 3：Train classification models；Step 4：Application model prediction result.
- 2. a kind of structural fire protection safety index computational methods based on big data sorting algorithm as claimed in claim 1, it is special Sign is：Data markers further comprise with packet：(1) by all fire protection project datas according to different system classifications；(2) scoring rate of all items is calculated according to the tabulation in step (1), statistics, scoring rate calculation formula is：(3) by all 21 project scoring rates being calculated in step (3) be combined into one 21 dimension vector x=[a1, A2 ..., a21], which is all detection scoring events for representing a solitary building, calculates the detection score feelings of all buildings Condition vector, forms entirety data set X={ xn, n ∈ R }；(4) classified with historical building risk index result of calculation to the data in all data set X into line label, all excessive risks Building is labeled as 1, and non-excessive risk building is labeled as -1；And 60% data that will be taken out at random in all data sets after annotation results It is n-th to combine composing training data set Strain={ (xn, yn) | xn ∈ X, yn ∈ { -1,1 }, n=1,2,3 ... } wherein xn The scoring rate vector of building, yn are the Risk Results of corresponding n-th of building, remaining is 40% as test data set Stest= { (xm, ym) | xm ∈ X, ym ∈ { -1,1 }, m=1,2,3 ... } wherein xm is the scoring rate vector of m-th of building, and ym is corresponding the The safety index result of calculation of m building；Training dataset is used to train svm classifier model, obtains the mould under corresponding data collection Shape parameter, test data set are used to examine to the predictablity rate for being not involved in trained data under this parameter level, so that point Analyse the generalization ability of model.
- 3. a kind of structural fire protection safety index computational methods based on big data sorting algorithm as claimed in claim 1, it is special Sign is：Wherein structure SVM classifier further includes：(1) it is input vector to set given training set as { (x1, y1), (x2, y2) ..., (xn, yn) } wherein xi ∈ Rn, yi ∈ { -1,1 } is output vector, it is assumed that the training set can be by a hyperplane WX+b=0 linear partition, and problem, which is converted into, asks optimal Change hyperplane problem：<mrow> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>min</mi> <mi>&Phi;</mi> <mrow> <mo>(</mo> <mi>W</mi> <mo>,</mo> <mi>&xi;</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mn>2</mn> </mfrac> <mo>|</mo> <mo>|</mo> <mi>W</mi> <mo>|</mo> <msup> <mo>|</mo> <mn>2</mn> </msup> <mo>+</mo> <mi>c</mi> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>&xi;</mi> <mi>i</mi> </msub> <mo>,</mo> <mi>c</mi> <mo>&GreaterEqual;</mo> <mn>0</mn> <mo>,</mo> <mrow> <mo>(</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>...</mn> <mo>,</mo> <mi>n</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>s</mi> <mo>.</mo> <mi>t</mi> </mrow> </mtd> <mtd> <mrow> <msub> <mi>y</mi> <mi>i</mi> </msub> <mo>&lsqb;</mo> <mrow> <mo>(</mo> <mi>W</mi> <mo>&CenterDot;</mo> <msub> <mi>X</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>+</mo> <mi>b</mi> <mo>&rsqb;</mo> <mo>&GreaterEqual;</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>&xi;</mi> <mi>i</mi> </msub> <mo>,</mo> <msub> <mi>&xi;</mi> <mi>i</mi> </msub> <mo>&GreaterEqual;</mo> <mn>0</mn> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>(2), can be by a mapping function (claiming kernel function in SVM), by the input of low-dimensional in the case of Nonlinear separability Space Rn is mapped to the feature space H of higher-dimension, makes linear separability, then optimization problem is converted into<mrow> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <munder> <mi>min</mi> <mi>a</mi> </munder> <mfrac> <mn>1</mn> <mn>2</mn> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>y</mi> <mi>i</mi> </msub> <msub> <mi>y</mi> <mi>j</mi> </msub> <msub> <mi>a</mi> <mi>i</mi> </msub> <msub> <mi>a</mi> <mi>j</mi> </msub> <mi>K</mi> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>,</mo> <msub> <mi>X</mi> <mi>j</mi> </msub> <mo>)</mo> </mrow> <mo>-</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>a</mi> <mi>i</mi> </msub> <mo>,</mo> <mrow> <mo>(</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>...</mn> <mo>,</mo> <mi>n</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>s</mi> <mo>.</mo> <mi>t</mi> <mo>.</mo> </mrow> </mtd> <mtd> <mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>y</mi> <mi>i</mi> </msub> <msub> <mi>a</mi> <mi>i</mi> </msub> <mo>=</mo> <mn>0</mn> <mo>,</mo> <mn>0</mn> <mo>&le;</mo> <msub> <mi>a</mi> <mi>i</mi> </msub> <mo>&le;</mo> <mi>C</mi> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>2</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>(3) solving formula (2) optimization function is：<mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>X</mi> <mo>)</mo> </mrow> <mo>=</mo> <mi>s</mi> <mi>i</mi> <mi>g</mi> <mi>n</mi> <mo>&lsqb;</mo> <msubsup> <mi>&Sigma;</mi> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </msubsup> <msub> <mi>y</mi> <mi>i</mi> </msub> <msub> <mi>a</mi> <mi>i</mi> </msub> <mi>K</mi> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>,</mo> <msub> <mi>X</mi> <mi>j</mi> </msub> <mo>)</mo> </mrow> <mo>+</mo> <msup> <mi>b</mi> <mo>*</mo> </msup> <mo>&rsqb;</mo> </mrow>From formula (2), minimization problem can be drawn, select suitable function K () and C to determine SVM classifier；(4) RBF Radial basis kernel functions, i.e. K (X are selectedi, Xj)=exp (- γ | | Xi-Xj||)2, then the optimization problem of grader is most Select permeability of the parameter to (C, γ) is converted into eventually.
- 4. a kind of structural fire protection safety index computational methods based on big data sorting algorithm as claimed in claim 1, it is special Sign is：Wherein train classification models further include：(1) it is scope with 1≤C≤1000 and 0≤γ≤100, builds the parameter pair of all C and γ compositions in value range；(2) take parameter to (C, γ) as the SVM classifier initial parameter value based on RBF kernel functions, training data vector successively Collect Strain and test data vector set Stest, remember under this disaggregated model to be pt to the accuracy rate of test data set prediction；(3) test set accuracy rate is directed to, C values and γ value parameters pair different in test SVM algorithm are adjusted with computer program, is made Accuracy rate pt reaches the accuracy rate p0 of pre-provisioning request, and keeps records of the model parameter under this accuracy rate p0 to (C0, γ0), I.e. this parameter is to the model parameter for required svm classifier model.
- 5. a kind of structural fire protection safety index computational methods based on big data sorting algorithm as claimed in claim 1, it is special Sign is：Wherein application model prediction result further includes：(1) building scoring rate data vector x ' of the structure without mark result；(2) model parameter (C0, the γ of training gained in step 3 are used0) svm classifier prediction is carried out to x ', obtain output result y’∈{-1,1}；(3) y ' is required building safety index result of calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711361455.6A CN107958274A (en) | 2017-12-18 | 2017-12-18 | A kind of structural fire protection safety index computational methods based on big data sorting algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711361455.6A CN107958274A (en) | 2017-12-18 | 2017-12-18 | A kind of structural fire protection safety index computational methods based on big data sorting algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107958274A true CN107958274A (en) | 2018-04-24 |
Family
ID=61959017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711361455.6A Pending CN107958274A (en) | 2017-12-18 | 2017-12-18 | A kind of structural fire protection safety index computational methods based on big data sorting algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958274A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389795A (en) * | 2018-09-05 | 2019-02-26 | 深圳市中电数通智慧安全科技股份有限公司 | Dynamic Fire risk assessment method, device, server and storage medium |
| CN110163251A (en) * | 2019-04-15 | 2019-08-23 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of Optimum Identification Method of fire hazard rating, device and terminal device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105806400A (en) * | 2016-02-29 | 2016-07-27 | 北斗导航位置服务（北京）有限公司 | Intelligent method and system for monitoring hydrant's safety state |
| CN106295685A (en) * | 2016-08-01 | 2017-01-04 | 浙江大学 | The large blast furnace failure modes algorithm of the transductive SVM improved and application |
| CN106897792A (en) * | 2017-01-10 | 2017-06-27 | 广东广业开元科技有限公司 | A kind of structural fire protection risk class Forecasting Methodology and system |
-
2017
- 2017-12-18 CN CN201711361455.6A patent/CN107958274A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105806400A (en) * | 2016-02-29 | 2016-07-27 | 北斗导航位置服务（北京）有限公司 | Intelligent method and system for monitoring hydrant's safety state |
| CN106295685A (en) * | 2016-08-01 | 2017-01-04 | 浙江大学 | The large blast furnace failure modes algorithm of the transductive SVM improved and application |
| CN106897792A (en) * | 2017-01-10 | 2017-06-27 | 广东广业开元科技有限公司 | A kind of structural fire protection risk class Forecasting Methodology and system |
Non-Patent Citations (2)
| Title |
|---|
| 王飞等: "基于SVM的建筑施工项目安全风险评价", 《辽宁工程技术大学学报（自然科学版）》 * |
| 胡月: "建筑施工现场危险源风险等级评价研究", 《万方数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389795A (en) * | 2018-09-05 | 2019-02-26 | 深圳市中电数通智慧安全科技股份有限公司 | Dynamic Fire risk assessment method, device, server and storage medium |
| CN110163251A (en) * | 2019-04-15 | 2019-08-23 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of Optimum Identification Method of fire hazard rating, device and terminal device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Failure mode and effects analysis using D numbers and grey relational projection method | |
| Su et al. | Smart performance-based design for building fire safety: Prediction of smoke motion via AI | |
| Xu et al. | A genetic programming model for real-time crash prediction on freeways | |
| Li et al. | Forecasting short-term electricity consumption using the adaptive grey-based approach—An Asian case | |
| CN110390465A (en) | Air control analysis and processing method, device and the computer equipment of business datum | |
| TWI608367B (en) | Text readability measuring system and method thereof | |
| Wang et al. | Incident tree model and incident tree analysis method for quantified risk assessment: an in-depth accident study in traffic operation | |
| Do et al. | A neuro-fuzzy approach in the classification of students' academic performance | |
| CN108900546A (en) | The method and apparatus of time series Network anomaly detection based on LSTM | |
| CN103440368B (en) | A kind of multi-model dynamic soft measuring modeling method | |
| Hajian et al. | New automated power quality recognition system for online/offline monitoring | |
| CN106897792A (en) | A kind of structural fire protection risk class Forecasting Methodology and system | |
| Zhang et al. | Risk early warning safety model for sports events based on back propagation neural network machine learning | |
| CN110225055A (en) | A kind of network flow abnormal detecting method and system based on KNN semi-supervised learning model | |
| CN108266219A (en) | Mine ventilation system resistive-switching single fault source diagnostic method based on air quantity feature | |
| CN113704410B (en) | Mood wave detection method and device, electronic equipment and storage medium | |
| Niu et al. | Optimization of support vector machine power load forecasting model based on data mining and Lyapunov exponents | |
| WO2022062193A1 (en) | Individual credit assessment and explanation method and apparatus based on time sequence attribution analysis, and device and storage medium | |
| CN106647650A (en) | Distributed industrial process monitoring method based variable weighting PCA (Principal Component Analysis) model | |
| Sang et al. | Incremental attribute reduction approaches for ordered data with time-evolving objects | |
| US11593648B2 (en) | Methods and systems for detection and isolation of bias in predictive models | |
| CN107958274A (en) | A kind of structural fire protection safety index computational methods based on big data sorting algorithm | |
| Kamran et al. | Decision support system for the prediction of mine fire levels in underground coal mining using machine learning approaches | |
| KR102054500B1 (en) | Method for providing design drawing | |
| Wen et al. | An APPSO–SVM approach building the monitoring model of dam safety |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180424 |
|
| RJ01 | Rejection of invention patent application after publication |