CN106485327B - Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition - Google Patents
Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition Download PDFInfo
- Publication number
- CN106485327B CN106485327B CN201610815386.0A CN201610815386A CN106485327B CN 106485327 B CN106485327 B CN 106485327B CN 201610815386 A CN201610815386 A CN 201610815386A CN 106485327 B CN106485327 B CN 106485327B
- Authority
- CN
- China
- Prior art keywords
- individual
- evacuation
- crowd
- knowledge
- tramples
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 231100001261 hazardous Toxicity 0.000 title claims abstract description 13
- 230000009467 reduction Effects 0.000 claims abstract description 40
- 230000007246 mechanism Effects 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 32
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 8
- 238000012502 risk assessment Methods 0.000 claims description 8
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000000694 effects Effects 0.000 claims 1
- 238000011160 research Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 206010034912 Phobia Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 208000019899 phobic disease Diseases 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000002341 toxic gas Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 101000642661 Homo sapiens Serine-threonine kinase receptor-associated protein Proteins 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 102100035934 Serine-threonine kinase receptor-associated protein Human genes 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004138 cluster model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011438 discrete method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000505 pernicious effect Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000192 social effect Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to the Methods of Knowledge Discovering Based that crowd under a kind of hazardous condition tramples behavior evolution, the following steps are included: 1) extraction crowd tramples scenario factors feature, it is emulated in colony intelligence crowd evacuation model, it obtains trampling evolved behavior feature during evacuation, constructs the domain object set of domain space layer；2) scenario factors feature is trampled to the crowd and tramples evolved behavior feature progress rough set attribute sliding-model control；3) that establishes " condition-decision " two-dimensional signal mode tramples evolution mechanism knowledge expression, and carries out Reduction of Knowledge to the evolution mechanism knowledge expression of trampling；4) evolved behavior feature is trampled according to generates meta-rule library；5) the meta-rule library and evacuation example are loaded, the abstraction rule library for trampling evolution is generated.Compared with prior art, the present invention passes through classical rough set theory, and realization crowd tramples the automatic Knowledge Discovery of behavior evolution mechanism, and the crowd of solution tramples the lack of knowledge of evolution mechanism.
Description
Technical field
The present invention relates to crowds to trample precautionary technology field, drills more particularly, to crowd's behavior of trampling under a kind of hazardous condition
The Methods of Knowledge Discovering Based of change.
Background technique
Currently, trampling the analysis of accident for crowd and prevention is still in infancy.Occur during crowd evacuation
Trample may be that " rumour-fear " mode individually occurs, it is also possible to which as burst fire-disaster, (fire, earthquake, explosion, poison gas are let out
Leakage etc. accidents) secondary disaster, with " disaster-fear " Mode Coupling occur.
Existing crowd evacuation model is mostly the research focused in terms of crowd movement learns with dynamics, and main description crowd dredges
Dissipate behavior, and analyze building evacuation element (stairs port and passageway for fire apparatus minimum widith etc.) and crowd's traffic capacity and evacuate when
Between relationship, provide building several contingency management strategies for trampling of prevention crowd and suggestion.Most existing models not yet system
The condition and evolution mechanism of generation are trampled in research, are only examined as the typical unstable phenomenon in existing evacuation model using trampling
Consider.
Existing crowd evacuation research conclusion is analyzed it can be found that being in the elementary step for the research for trampling evolution mechanism,
The problems such as there are still knowledge experience dependence and lack of knowledge.For trampling Precautions, rest on the prediction scheme pipe based on experience more
The reason stage, for the real-time control problem trampled, mostly dependent on the tissue experience of emergency evacuation floor manager personnel and crowd
Degree of cooperation.There is an urgent need to use scientific method, analysis crowd tramples origin mechanism, and announcement crowd tramples Evolution.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide a kind of hazardous condition servants
Group tramples the Methods of Knowledge Discovering Based of behavior evolution, only relies only on practical domain record data itself, tight using rough set theory
Comb logic, the automatic knowledge for calculating and finding crowd and trample behavior evolution.
The purpose of the present invention can be achieved through the following technical solutions:
Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition, comprising the following steps:
1) extraction crowd tramples scenario factors feature, is emulated, was evacuated in colony intelligence crowd evacuation model
Evolved behavior feature is trampled in journey, constructs the domain object set of domain space layer, the evolved behavior feature of trampling includes stepping on
Step on probability；
2) scenario factors feature is trampled to the crowd and trampled at evolved behavior feature progress rough set attribute discretization
Reason；
3) scenario factors feature is trampled as the conditional attribute of domain object, with phase using the crowd after the sliding-model control
Decision attribute of the evolved behavior feature as domain object is trampled described in answering, and establishes " condition-decision " two-dimensional signal mode
Evolution mechanism knowledge expression is trampled, and Reduction of Knowledge is carried out to the evolution mechanism knowledge expression of trampling；
4) evolved behavior feature is trampled according to generates meta-rule library；
5) the meta-rule library and evacuation example are loaded, the abstraction rule library for trampling evolution is generated.
It includes evacuating individual physiologic factor, social factor, behavioural characteristic and environment that the crowd, which tramples scenario factors feature,
Feature, the individual physiologic factor of the evacuation includes age, gender, disability degree, agility and weight, and the social factor includes
Strange degree, the behavioural characteristic include panic degree, and the environmental characteristic includes disaster factors and space constraint.
The fear degree is mapped as of evacuation individual according to Helbing, D. fear " psychology-behavior " volatility model
Body diameter, the solution procedure of the individual diameter specifically:
fiw={ Ai exp[(ri-diw)/Bi]+kg(ri-diw)}niw-γg(ri-diw)vitiw (3)
In formula, miIt is the quality of i-th of evacuation individual,It is the ideal velocity of i-th of evacuation individual,It is i-th of evacuation
The direction initialization of individual, viIt is the actual speed of i-th of evacuation individual, τiIt is the characteristic time of i-th of evacuation individual, when t is
Between, fijIt is the interaction force evacuated between individual i and evacuation individual j, fiwIt is the phase interaction evacuated between individual i and boundary
Firmly, Ai、BiFor constant, dcijIt is mass centre's distance of two evacuations individual, dijThe distance between two evacuation individuals, nijBe by
Evacuate the standard vector that individual j is directed toward i, tijIt is nijTangential direction,It is the phasor difference of t moment speed, kg
(dij-dcij) indicate mass force,Indicate that t moment force of sliding friction, k and γ are to determine evacuation individual i and j
Between interaction blocking effect parameter, diwIt is evacuation individual the distance between i and boundary, niwRefer to vertical direction,
tiwRefer to tangential direction, riIt is the individual diameter of i-th of evacuation individual, viFor the individual speed of i-th of evacuation individual, g (x) is
One function collides if evacuating individual, g (x)=0, otherwise g (x)=x.
The individual speed that the disaster factors are mapped as the evacuation individual after panic propagate is expressed, specifically:
Definition rule θ are as follows:
In formula, μDAFor the subordinating degree function of casualty loss degree DA,DAmaxFor maximum casualty loss degree,
For risk assessment intensity I0Subordinating degree function,ImaxIntensity is assessed for greateset risk, subscript t is hdisSequence
Number, s is the serial number of i value, and i is risk assessment intensity I0On coordinate value, n be i maximum value, rstIt is in fuzzy relation matrix
Element, using inference formula:
DA=I0θR (5)
By risk assessment intensity I0It is assigned on control point in the method that information is distributed, finally finds out calamity source index
hdisValue, R is fuzzy relation matrix；
Calculate individual speed of each evacuation individual after panic propagate:
hdis=f (ρ) (6)
In formula, ρ is density of stream of people, and f () indicates calamity source index hdisWith density of stream of people ρ institute linear relationship function, DL
=NAP/WALA=ρ AP, DLIt is the evacuation individual amount of unit area in horizontal plane, N is the total number of persons in the walking stream of people, AP
For the horizontal projected area of single people, WAFor the width of the stream of people, LAFor the length of the stream of people, viFor the individual speed of i-th of evacuation individual
Degree.
The crowd tramples scenario factors feature and is divided into qualitative features and quantitative characteristic, when executing step 2), for qualitative
Feature is directly mapped as rough set Category Attributes；For quantitative characteristic, it is first mapped as rough set connection attribute, so
Heuristic SOM self-organizing clustering model is used afterwards, and automatic sliding-model control is carried out to rough set connection attribute, rough set is continuous
Attribute value is converted into the distinguishable mathematic sign of rough set matrix.
The Reduction of Knowledge is included the domain space dimensionality reduction reduction carried out using full distance dimensionality reduction model and used coarse
Collect the attribute reduction and Value reduction of theoretical reduction and the progress of core computation model.
Reduction of Knowledge is carried out with rough set theory specifically:
It is domain object set, U={ x for knowledge system S=(U, A), U1,x2,…,xn, element x thereiniFor opinion
Object in domain, n are object sum, and A is the attribute set of non-empty, and A=C ∪ D, C are conditional attribute set, and D is decision attribute
Collection, and C ∩ D=φ, calculate the differentiation matrix M of the knowledge systemDS(C):
Element m in discrimination matrixijIt is to discriminate between object xiAnd xjAll conditions attribute set；
Define Boolean function fDSIt is as follows:
Wherein, Boolean variableCorresponding to m conditional attribute a1,...,am,Symbol ∨ table
Show operation of extracting, symbol ∧ indicates conjunction operation；
The decision matrix M of calculation knowledge system SDS(C):
Element in decision matrixIt is to discriminate between object xiAnd xjAll conditions attribute set；
Define decision function fDRDSIt is as follows:
Here
Compared with prior art, the invention has the following advantages that
Building crowd tramples the rough set Knowledge Discovery Model of evolution mechanism, and crowd is trampled to the Knowledge Discovery of evolution
It is converted into rough set decision rule and automatically generates problem.
The feature extraction of scenario factors and the research of discretization are trampled for crowd, are based on Self-organizing Maps (SOM) network
Heuristic automatic cluster model, extraction crowd tramples key scene element and evolved behavior feature, and discrete turns to rough set
The conditional attribute and decision attribute of domain object, the two-dimensional signal table that crowd tramples evolution knowledge is contained in building, with succinct and complete
Standby mode proposes the knowledge-representation system that crowd tramples evolution mechanism.It is automatically generated and is known by rough set matrix computation model
Know the meta-rule of expression, trample situational examples during load crowd evacuation, the strict reduction of meta-rule can be become into tool
There is the abstraction rule of realistic background meaning, forms Explicit Knowledge.The consistency and completeness of above-mentioned each method, simultaneously for system-computed
It was found that crowd, which tramples the valuable knowledge that evolved behavior is contained, provides scientific basis, become innovative point of the invention.
Detailed description of the invention
Fig. 1 is the principle of the present invention schematic diagram.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
As shown in Figure 1, the present embodiment provides the Methods of Knowledge Discovering Based that crowd under a kind of hazardous condition tramples behavior evolution, packet
Include following steps:
Step 1: the crowd of extraction tramples scenario factors feature, is emulated, dredged in colony intelligence crowd evacuation model
Evolved behavior feature is trampled during dissipating, constructs the domain object set of domain space layer, and trampling evolved behavior feature includes stepping on
Step on probability.
It includes evacuating individual physiologic factor, social factor, behavioural characteristic and environment that the crowd, which tramples scenario factors feature,
Feature, the individual physiologic factor of the evacuation includes age, gender, disability degree, agility and weight etc., the social factor packet
Strange degree is included, the behavioural characteristic includes panic degree, and the environmental characteristic includes disaster factors and space constraint.
In the present invention, the fear degree is mapped as evacuating according to Helbing, D. fear " psychology-behavior " volatility model
The individual diameter of individual measures its panic degree from the individual tensity (Psychological phobia) of evacuation and velocity variations, by panic journey
Degree is mapped as the diameter of evacuation individual, establishes panic quantitative model.
The solution procedure of the individual diameter specifically:
fiw={ Ai exp[(ri-diw)/Bi]+kg(ri-diw)}niw-γg(ri-diw)vitiw (3)
In formula, miIt is the quality of i-th of evacuation individual,It is the ideal velocity of i-th of evacuation individual,It is thin i-th
Dissipate the direction initialization of individual, viIt is the actual speed of i-th of evacuation individual, τiIt is the characteristic time of i-th of evacuation individual, when t is
Between, fijIt is the interaction force evacuated between individual i and evacuation individual j, fiwIt is the phase interaction evacuated between individual i and boundary
Firmly, Ai、BiFor constant, dcijIt is mass centre's distance of two evacuations individual, dijThe distance between two evacuation individuals, nijBe by
Evacuate the standard vector that individual j is directed toward i, tijIt is nijTangential direction,It is the phasor difference of t moment speed, kg
(dij-dcij) indicate mass force,Indicate that t moment force of sliding friction, k and γ are to determine evacuation individual i and j
Between interaction blocking effect parameter, diwIt is evacuation individual the distance between i and boundary, niwRefer to vertical direction,
tiwRefer to tangential direction, riIt is the individual diameter of i-th of evacuation individual, viFor the individual speed of i-th of evacuation individual, g (x) is
One function collides if evacuating individual, g (x)=0, otherwise g (x)=x.
The model data that the typical disasters such as fire and toxic gas leakage are exported from hazard model library extracts disaster to evacuation
Key influence factor；Relevant building space structure data is evacuated in export from building model library, extracts space about
Beam (such as exit width and wall locations) is to the key influence factor of evacuation.Using disaster factors and space constraint as environment spy
Sign, and according to qualitative and quantitatively classify.Disaster is the trigger condition that crowd panic is propagated, and disaster factors are mapped to fear
In propagation model, disaster factors influence the speed of evacuation individual.
In the present invention, the individual speed that the disaster factors are mapped as the evacuation individual after panic propagate is expressed,
Specifically:
Definition rule θ are as follows:
In formula, μDAFor the subordinating degree function of casualty loss degree DA,DAmaxFor maximum casualty loss degree,
For risk assessment intensity I0Subordinating degree function,ImaxIntensity is assessed for greateset risk, subscript t is hdisSequence
Number, s is the serial number of i value, and i is risk assessment intensity I0On coordinate value, n be i maximum value, rstIt is in fuzzy relation matrix
Element, using inference formula:
DA=I0θR (5)
By risk assessment intensity I0It is assigned on control point in the method that information is distributed, finally finds out calamity source index
hdisValue, R is fuzzy relation matrix；
Calculate individual speed of each evacuation individual after panic propagate:
hdis=f (ρ) (6)
In formula, ρ is density of stream of people, and f () indicates calamity source index hdisWith density of stream of people ρ institute linear relationship function, DL
=NAP/WALA=ρ AP, DLIt is the evacuation individual amount of unit area in horizontal plane, N is the total number of persons in the walking stream of people, AP
For the horizontal projected area of single people, WAFor the width of the stream of people, LAFor the length of the stream of people, viFor the individual speed of i-th of evacuation individual
Degree.
It is carried out at rough set attribute discretization Step 2: trampling scenario factors feature to crowd and trampling evolved behavior feature
Reason carries out discretization using evacuation feature of the characteristic attribute discretization algorithm based on SOM self-organized mapping network to extraction, and
Carry out quantization and dependent linearity mapping.
The crowd tramples scenario factors feature and is divided into qualitative features and quantitative characteristic, when executing step 2), for qualitative
Feature (such as gender) is directly mapped as rough set Category Attributes (such as 1 and 0)；For quantitative characteristic (such as age, fear
Spend and trample probability etc.), it is first mapped as rough set connection attribute, then uses heuristic SOM self-organizing clustering model, it is right
Rough set connection attribute carries out automatic sliding-model control, converts the distinguishable number of rough set matrix for rough set continuous property
Symbol (such as 1,2 ... etc.).
Step 3: trampling scenario factors feature as the condition category of domain object using the crowd after the sliding-model control
Property, using the corresponding evolved behavior feature of trampling as the decision attribute of domain object, establish " condition-decision " two dimension letter
Breath mode tramples evolution mechanism knowledge expression, and carries out Reduction of Knowledge to the evolution mechanism knowledge expression of trampling.
In terms of trampling evolution knowledge representation and reduction method research, the attribute discretization of scenario factors is trampled based on crowd
Expression analyzes scenario factors (such as people using rough set theory Knowledge Representation Model (domain, attribute, attribute value, information function)
Group's quantity, movement speed and panic degree etc.) relationship and variation characteristic between attribute, formed knowledge-representation system attribute and
Attribute value.
U={ x1,x2,x3···xn} (8)
Wherein, U is domain set, and each element x in set, x indicates that crowd evacuation result (is dredged containing crowd in this patent
Dissipate each characteristic value) single record.
Using physiology, society, psychology and the environmental characteristic in scenario factors as the conditional attribute a of rough set domain objecti, with
The decision attribute D that probability is rough set domain object of trampling in colony intelligence evacuation model simulation result proposes that " condition-is certainly
The information function expression formula of plan " two-dimensional signal table schema forms the knowledge representation for trampling evolution mechanism, can indicate are as follows:
C={ a1,a2,a3···an} (9)
Wherein, C is conditional attribute, settable a1For age, a2For gender, a3For disability degree, a4For agility, a5For body
Weight, a6For the individual diameter mapped by panic degree, a7For the individual speed mapped by disaster factors.D is decision kind set.
In terms of Reduction of Knowledge, under conditions of keeping domain object set classification capacity constant, using full distance dimensionality reduction mould
Type merges domain object, carries out dimensionality reduction reduction to domain space, simplifies subsequent domain space and calculates.With rough set theory reduction
(Reduct) and core (Core) computation model, the redundant attributes of deletion domain object carry out attribute reduction and Value reduction, with
Evolution knowledge is trampled in simplification.If Q is independent, and Q ∈ C, if having
IND (Q)=IND (C) (10)
Then Q is a reduction of equivalence relation family C, and all collection that can not save relationship are combined into the core of equivalence relation family C in C,
Remember Core (C).There are multiple reduction, the set of all reduction of C is indicated with Red (C).
In the present invention, Reduction of Knowledge includes the dimensionality reduction reduction of domain space and utilization carried out using full distance dimensionality reduction model
The attribute reduction and Value reduction that rough set theory reduction and core computation model carry out.
Step 4: trampling the rough set Knowledge Discovery of evolution mechanism.Member rule are generated according to the evolved behavior feature of trampling
Then library loads the meta-rule library and evacuation example, generates the abstraction rule library for trampling evolution.
Using classical Skowron matrix computational approach, rough set matrix computation model is constructed；For knowledge system S=(U,
A, V, f), U is domain, xiFor the object in domain, U={ x1,x2,…,xn}.A is the attribute set of non-empty, and A=C ∪ D, C are
Conditional attribute, D are decision attributes, and C ∩ D=φ.V indicates attribute value, and f is information function.For system S, condition is only considered
Attribute forms the information system about conditional attribute C.Number of objects in the differentiation matrix DM of the system, order and domain
Related, as n × n rank is denoted as MDS(C):
Element m in discrimination matrixijIt is to discriminate between object xiAnd xjAll conditions attribute set.For variable j, i's
Range is defined as 1≤j≤i≤n, obtains lower triangular matrix, but as variable j=i, i.e. MDS(C), diagonal entry is obtained,
And object oneself comparison result is empty set φ certainly.So comparing to reduce n times, here to j, the range of i is defined are as follows: 1
≤ j < i≤n, reduces the computation complexity of original definition.
Introduce a Boolean function fDS, referred to as resolution function is as follows:
Wherein, Boolean variableCorresponding to m conditional attribute a1,...,am,Symbol ∨ table
Show operation of extracting, symbol ∧ indicates conjunction operation；
The decision matrix of calculation knowledge system S, order is related with the number of objects in domain, as n × n rank, is denoted as
MDS(C):
With to above-mentioned matrix calculating discovery, it is this definition only reflect decision attribute values it is identical other than object compare
Situation, without the description for conflict object (inconsistent).Conditional attribute value is identical and conflict pair that decision attribute values are different
The matrix value of elephant remains as empty set, this can not just reflect the presence of conflict phenomenon, can not more reflect the degree problem of conflict.For
This, has carried out the matrix to improve definition, has eliminated limitation.
Element in decision matrixIt is to discriminate between object xiAnd xjAll conditions attribute set.
Define decision function fDRDSIt is as follows:
Here
The purpose of rough set theory research is to simplify calculating, reduces computation complexity, optimization algorithm structure, more effectively
Solve engineering problem.In summary research achievement carries out MAWD dimensionality reduction meter to domain space in data preprocessing phase
It calculates；For connection attribute, cluster calculation is carried out using the SOM network method based on modified IMDV；For quantitative attributes or
The qualitative attribute of variation little (i.e. value is relatively fixed), uses direct-discrete method here.
In this way, the optimization achievement of links above is integrated into organic whole, the MS- of overall performance improvement is just obtained
VPRS Knowledge Discovery Model.How IMSRS model is applied in engineering and medical domain by chapters and sections afterwards if will study
It is enterprise customer and medical researchers' solving practical problems, also from Knowledge Discovery and decision support in dry typical diagnostic case
Aspect, validity and versatility to the model carry out engineering verification.
Rough set matrix computation model produces the meta-rule of attribute nucleus collection, and is input to meta-rule library；Meta-rule can table
It is shown as:
Rule 1:
if a3=0 and a4=0 and a7=1.then d=0
Rule 2:
if a3=1 and a4=0 and a7=1.then d=1
Rule 3:
if a3=0 and a4=1 and a7=0.then d=1
Rule 4:
if a3=1 and a4=0 and a7=1.then d=2
Meta-rule is loaded, using the reversible process analytic method of attribute discretization, by domain object properties and tramples feelings
Scape element forms invertible mapping；Domain characteristics of objects value is reloaded, the mathematic sign (such as gender attribute value is 0) of discretization is also
Original becomes evacuation scenario factors (such as gender is male)；In the regular generating portion for trampling evolution, example is evacuated into load, it will be coarse
It is extensive as the abstraction rule towards specific evacuation example to collect meta-rule, formation has the abstraction rule library of practical guided significance,
Form Explicit Knowledge.Such as rule 1, under disaster serious conditions, non-disability, overweight women old man, when not generating Psychological phobia
The probability trampled is 0.
With a case verification above method of Hongqiao in Shanghai transport hub.
The first step passes through extraction Shanghai Hongqiao Integrative Transport Hub construction example data, analysis and extraction environmental characteristic, mould
The real conditions at the scene of drawing up, are emulated.Total number of persons N=2109 people (can according to the calculating of State Statistics Bureau's population ratio data
Obtain 723 people of man, 686 people of woman, 131 people of 348 people of children, 221 people of old man and physical disabilities).
Second step extracts 4 record composition domain set U, and U={ x from entire emulation1,x2,x3,x4}。a1For year
Age, a2For gender, a3For disability degree, a4For agility, a5For weight, a6For the individual diameter mapped by panic degree, a7For
The individual speed mapped by disaster factors, C={ a1,a2,a3,a4,a5,a6,a7}.Wherein, old man 2, children 1, in youth
Year is 0；Male is 1, and female 0；Disability is 1, and non-disability is 0；Agile is 2, and movement generally 1, handicapped is 0；It is overweight
It is 2, it is 1 lower than normal type, normal type 0；Fear is 2, and it is normally 0 that anxiety, which is 1,；Disaster scenarios it is seriously 1, disaster
Situation is not seriously 0, as shown in table 1.
Table 1
| U | a1 | a2 | a3 | a4 | a5 | a6 | a7 | D |
| x1 | 2 | 0 | 0 | 0 | 2 | 0 | 1 | 0 |
| x2 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 |
| x3 | 0 | 1 | 0 | 1 | 0 | 2 | 0 | 1 |
| x4 | 1 | 1 | 1 | 0 | 1 | 2 | 1 | 2 |
Third step finds out differentiation matrix, resolution function and decision function.
According to formula (11), differentiation matrix is obtained:
Resolution function are as follows:
fDS=(a1∨a2∨a3∨a5∨a6)(a1∨a2∨a4∨a5∨a6∨a7)(a2∨a3∨a4∨a6∨a7)(a1∨a2
∨a3∨a5∨a6)(a1∨a2∨a5∨a6)(a1∨a3∨a4∨a5∨a7)
=a1a2a4a5a7
According to formula (14), discrimination matrix is obtained:
Obtain decision function:
fDRDS=(a1∨a2∨a3∨a5∨a6)(a1∨a2∨a4∨a5∨a6∨a7)(a2∨a3∨a4∨a6∨a7)(a1∨
a2∨a5∨a6)(a1∨a3∨a4∨a5∨a7)
=a3a4a7
After reduction as shown in table 2.
Table 2
| U | a3 | a4 | a7 | D |
| x1 | 0 | 0 | 1 | 0 |
| x2 | 1 | 0 | 1 | 1 |
| x3 | 0 | 1 | 0 | 1 |
| x4 | 1 | 0 | 1 | 2 |
According to meta-rule, the element value in decision kind set D (D is the probability trampled, in the range of 0-1) is found out
For；Again by abstraction rule, decision attribute is translated as Explicit Knowledge, d1=0 be the probability trampled is 0, d2=1 is hair
The raw probability trampled is 0.1, d3=1 be the probability trampled is 0.1, d4=2 be the probability trampled be 0.2.
The present invention proposes that crowd tramples the Methods of Knowledge Discovering Based of evolution mechanism, and scenario factors and people are evacuated under hazardous condition
Group tramples extraction correlated characteristic element in evolved behavior, is calculated with existing rule base, obtains decision attribute values, to prevent
Pernicious accident of trampling provides scientific basis and theories integration, has important theoretical value and social effect.
Claims (5)
1. crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition, which comprises the following steps:
1) extraction crowd tramples scenario factors feature, is emulated in colony intelligence crowd evacuation model, during obtaining evacuation
Evolved behavior feature is trampled, constructs the domain object set of domain space layer, the evolved behavior feature of trampling includes trampling generally
Rate；
2) scenario factors feature is trampled to the crowd and tramples evolved behavior feature progress rough set attribute sliding-model control；
3) scenario factors feature is trampled as the conditional attribute of domain object, with corresponding using the crowd after the sliding-model control
The decision attribute that evolved behavior feature is trampled as domain object, " condition-decision " the two-dimensional signal mode of foundation are trampled
Evolution mechanism knowledge expression, and Reduction of Knowledge is carried out to the evolution mechanism knowledge expression of trampling；
4) evolved behavior feature is trampled according to generates meta-rule library；
5) the meta-rule library and evacuation example are loaded, the abstraction rule library for trampling evolution is generated；
It includes evacuating individual physiologic factor, social factor, behavioural characteristic and environmental characteristic that the crowd, which tramples scenario factors feature,
The individual physiologic factor of the evacuation includes age, gender, disability degree, agility and weight, and the social factor includes strange
Degree, the behavioural characteristic include panic degree, and the environmental characteristic includes disaster factors and space constraint；
For the fear degree according to Helbing, the individual that D. fear " psychology-behavior " volatility model is mapped as evacuation individual is straight
Diameter, the solution procedure of the individual diameter specifically:
fiw={ Ai exp[(ri-diw)/Bi]+kg(ri-diw)}niw-γg(ri-diw)vitiw (3)
In formula, miIt is the quality of i-th of evacuation individual,It is the ideal velocity of i-th of evacuation individual,It is i-th of evacuation individual
Direction initialization, viIt is the actual speed of i-th of evacuation individual, τiIt is the characteristic time of i-th of evacuation individual, t is time, fij
It is the interaction force evacuated between individual i and evacuation individual j, fiwIt is the interaction force evacuated between individual i and boundary,
Ai、BiFor constant, dcijIt is mass centre's distance of two evacuations individual, dijThe distance between two evacuation individuals, nijIt is a by evacuating
Body j is directed toward the standard vector of i, tijIt is nijTangential direction,It is the phasor difference of t moment speed, kg (dij-dcij)
Indicate mass force,Indicate that t moment force of sliding friction, k and γ are mutual between decision evacuation individual i and j
The parameter of the blocking effect of effect, diwIt is evacuation individual the distance between i and boundary, niwRefer to vertical direction, tiwRefer to tangential
Direction, riIt is the individual diameter of i-th of evacuation individual, viFor the individual speed of i-th of evacuation individual, g (x) is a function, such as
Fruit evacuation individual collides, g (x)=0, otherwise g (x)=x.
2. crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under hazardous condition according to claim 1, which is characterized in that
The individual speed that the disaster factors are mapped as the evacuation individual after panic propagate is expressed, specifically:
Definition rule θ are as follows:
In formula, μDAFor the subordinating degree function of casualty loss degree DA,DAmaxFor maximum casualty loss degree,For wind
Danger assessment intensity I0Subordinating degree function,ImaxIntensity is assessed for greateset risk, subscript t is hdisSequence number, s
It is the serial number of i value, i is risk assessment intensity I0On coordinate value, n be i maximum value, rstIt is the member in fuzzy relation matrix
Element, using inference formula:
DA=I0θR (5)
By risk assessment intensity I0It is assigned on control point in the method that information is distributed, finally finds out calamity source index hdis's
Value, R is fuzzy relation matrix；
Calculate individual speed of each evacuation individual after panic propagate:
hdis=f (ρ) (6)
In formula, ρ is density of stream of people, and f () indicates calamity source index hdisWith density of stream of people ρ institute linear relationship function, DL=
NAP/WALA=ρ AP, DLIt is the evacuation individual amount of unit area in horizontal plane, N is the total number of persons in the walking stream of people, APFor
The horizontal projected area of single people, WAFor the width of the stream of people, LAFor the length of the stream of people, viFor the individual speed of i-th of evacuation individual
Degree.
3. crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under hazardous condition according to claim 1, which is characterized in that
The crowd tramples scenario factors feature and is divided into qualitative features and quantitative characteristic, when executing step 2), for qualitative features, directly
It is mapped as rough set Category Attributes；For quantitative characteristic, it is first mapped as rough set connection attribute, then using inspiration
Formula SOM self-organizing clustering model carries out automatic sliding-model control to rough set connection attribute, rough set continuous property is converted
For the distinguishable mathematic sign of rough set matrix.
4. crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under hazardous condition according to claim 1, which is characterized in that
The Reduction of Knowledge is included the domain space dimensionality reduction reduction carried out using full distance dimensionality reduction model and uses rough set theory about
The attribute reduction and Value reduction that letter and core computation model carry out.
5. crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under hazardous condition according to claim 4, which is characterized in that
Reduction of Knowledge is carried out with rough set theory specifically:
It is domain object set, U={ x for knowledge system S=(U, A), U1,x2,…,xn, element x thereiniFor in domain
Object, n be object sum, A be non-empty attribute set, A=C ∪ D, C are conditional attribute set, and D is decision kind set, and
C ∩ D=φ, calculates the differentiation matrix M of the knowledge systemDS(C):
Element m in discrimination matrixijIt is to discriminate between object xiAnd xjAll conditions attribute set；
Define Boolean function fDSIt is as follows:
Wherein, Boolean variableCorresponding to m conditional attribute a1,...,am,Symbol ∨ indicates analysis
Operation is taken, symbol ∧ indicates conjunction operation；
The decision matrix M of calculation knowledge system SDS(C):
Element in decision matrixIt is to discriminate between object xiAnd xjAll conditions attribute set；
Define decision function fDRDSIt is as follows:
Here
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610815386.0A CN106485327B (en) | 2016-09-08 | 2016-09-08 | Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610815386.0A CN106485327B (en) | 2016-09-08 | 2016-09-08 | Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106485327A CN106485327A (en) | 2017-03-08 |
| CN106485327B true CN106485327B (en) | 2019-04-02 |
Family
ID=58273723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610815386.0A Active CN106485327B (en) | 2016-09-08 | 2016-09-08 | Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106485327B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330147B (en) * | 2017-05-26 | 2020-04-24 | 北京交通大学 | Simulation method and system for emergency evacuation of personnel in subway station |
| CN107665282B (en) * | 2017-10-11 | 2021-06-25 | 山东师范大学 | Crowd evacuation simulation method and system based on heterogeneous emotional infection model |
| CN108256152B (en) * | 2017-12-19 | 2021-05-11 | 同济大学 | T-shaped intersection evacuation simulation method based on crowd evacuation macro model |
| CN108256155B (en) * | 2017-12-20 | 2021-03-26 | 同济大学 | Passenger getting-off point selection method for T-junction passenger car |
| CN110555216B (en) * | 2018-05-30 | 2022-12-13 | 郑州大学 | Crowd crowding scene simulation method and system |
| CN109542949B (en) * | 2018-11-07 | 2022-04-12 | 太原理工大学 | Formal vector-based decision information system knowledge acquisition method |
| CN109871582A (en) * | 2019-01-11 | 2019-06-11 | 山东师范大学 | Knowledge based engineering crowd evacuation emulation method, system and medium in foreign environment |
| CN111080080B (en) * | 2019-11-25 | 2023-05-26 | 桂林理工大学南宁分校 | Village geological disaster risk prediction method and system |
| CN116415047B (en) * | 2023-06-09 | 2023-08-18 | 湖南师范大学 | Resource screening method and system based on national image resource recommendation |
| CN118230260B (en) * | 2024-05-27 | 2024-07-30 | 山东科技大学 | Method for quantifying and early warning analysis of trampling risk of high-density crowd at subway platform |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760484A (en) * | 2016-02-17 | 2016-07-13 | 中国科学院上海高等研究院 | Crowd treading pre-warning method and system and server with system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100004975A1 (en) * | 2008-07-03 | 2010-01-07 | Scott White | System and method for leveraging proximity data in a web-based socially-enabled knowledge networking environment |
-
2016
- 2016-09-08 CN CN201610815386.0A patent/CN106485327B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760484A (en) * | 2016-02-17 | 2016-07-13 | 中国科学院上海高等研究院 | Crowd treading pre-warning method and system and server with system |
Non-Patent Citations (1)
| Title |
|---|
| 建筑火灾人员疏散行为及优化研究;杨立兵;《中国博士学位论文全文数据库工程科技Ⅱ辑》;20140315(第3期);第29-87页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106485327A (en) | 2017-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485327B (en) | Crowd tramples the Methods of Knowledge Discovering Based of behavior evolution under a kind of hazardous condition | |
| Zhang et al. | Strategies to utilize the positive emotional contagion optimally in crowd evacuation | |
| Yu et al. | A distance-based group decision-making methodology for multi-person multi-criteria emergency decision support | |
| Ashraf et al. | Emergency decision support modeling for COVID‐19 based on spherical fuzzy information | |
| Wang et al. | Studies on a multidimensional public opinion network model and its topic detection algorithm | |
| Wu et al. | Modeling crowd evacuation via behavioral heterogeneity-based social force model | |
| Mei et al. | Purpose Driven Disputation Modeling, Analysis and Resolution Based on DIKWP Graphs | |
| Wang et al. | Risk of Large‐Scale Evacuation Based on the Effectiveness of Rescue Strategies Under Different Crowd Densities | |
| CN106096115B (en) | A kind of crowd evacuation emulation method based on self-organizing sand ionization formula | |
| Borah et al. | Examining the correlation between the weather conditions and COVID-19 pandemic in India: a mathematical evidence | |
| CN110472226A (en) | A kind of network security situation prediction method and device of knowledge based map | |
| Shi et al. | Determination of effective management strategies for scenic area emergencies using association rule mining | |
| Liu et al. | A new evacuation accessibility analysis approach based on spatial information | |
| Choudhury et al. | Evaluating the preparedness of indian states against COVID‐19 pandemic risk: A fuzzy multi‐criteria decision‐making approach | |
| CN109800881A (en) | A kind of causality determination method based on Bayesian network | |
| CN110472225A (en) | The railway accident analysis of causes method of word-based extension LDA | |
| Mesiarová-Zemánková et al. | Bonferroni mean with weighted interaction | |
| Kefan et al. | Analysis of crowd stampede risk mechanism: A systems thinking perspective | |
| Li et al. | Rapid risk assessment of emergency evacuation based on deep learning | |
| Zhao et al. | Dynamic crowd accident-risk assessment based on internal energy and information entropy for large-scale crowd flow considering covid-19 epidemic | |
| Li et al. | Fire propagation-driven dynamic intelligent evacuation model in multifloor hybrid buildings | |
| Schröder | Multivariate methods for life safety analysis in case of fire | |
| Li et al. | Dynamic risk assessment of emergency evacuation in large public buildings: A case study | |
| Huang et al. | Quantum Sequential Sampler: a dynamical model for human probability reasoning and judgments | |
| Bej et al. | Time-Series prediction for the epidemic trends of COVID-19 using Conditional Generative adversarial Networks Regression on country-wise case studies |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |