资源描述
Developing a Visualization Tool for Spider Web-Building Algorithms模擬蜘蛛結網之演算法設計及視覺化工具開發指導教授：尹邦嚴 陳怡孜 陳瑩哲 沈扇綸 郭怡君 6/30/20241OPlab,IM,NTUOutlineI.IntroductionlAbstractlMotivationII.Literature reviewlArtificial IntelligencelRelated spider papersIII.Spider web-building algorithm designIV.Visualization tool prototype of the modellInternal factorslExternal factorsV.Conclusion and future work6/30/20242OPlab,IM,NTUI.Introduction1/2lAbstractSequential behavior of spider web-building modelInternal factors of the spider web-building modelExternal factors of the spider web-building modelImplementation of visualization tool 6/30/20243OPlab,IM,NTUI.Introduction2/2lMotivationFigure 1.The motivation of the model6/30/20244OPlab,IM,NTUOutlineI.IntroductionlAbstractlMotivationII.Literature reviewlArtificial IntelligencelRelated spider papersIII.Spider web-building algorithm designIV.Visualization tool prototype of the modellInternal factorslExternal factorsV.Conclusion and future work6/30/20245OPlab,IM,NTUII.Literature review1/3lArtificial Intelligence Swarm intelligenceGeese migratine fly in a “V”formationBees and wag-tail danceAnt colony optimization(ACO)Solve discrete optimization problems(Dorigo,1992)Particle swarm optimization(PSO)A optimization for representing sociocognition of human and artificial agents tool(Kennedy and Eberhart,1995)6/30/20246OPlab,IM,NTUII.Literature review2/3lRelated spider papersInfluence of the genes on the web(Kirnk,1996)Wind,Temperature,and Humidity(Vollrath,1997)Prey size(Vollrath,1998)The pattern of the capture spiral(李蔡彥and林翰儂,2004)6/30/20247OPlab,IM,NTUII.Literature review3/3lRelated spider artificial intelligenceThe pattern of the capture spiral(李蔡彥and林翰儂,2004)Figure.2 Capture spiral patternFigure.3 Different capture spiral pattern6/30/20248OPlab,IM,NTUOutlineI.IntroductionlAbstractlMotivationII.Literature reviewlArtificial IntelligencelRelated spider papersIII.Spider web-building algorithm designIV.Visualization tool prototype of the modellInternal factorslExternal factorsV.Conclusion and future work6/30/20249OPlab,IM,NTUIII.Spider web-building algorithm model design 1/8Figure.4 The factor-analysis tree of web-building.6/30/202410OPlab,IM,NTUIII.Spider web-building algorithm model design2/8Figure.5 The rule-analysis tree of web-building.Auxiliary spiral(AS)Capture spiral(CS)Figure.6 The real spider web.Influence of the genes on the web(Kirnk,1996)6/30/202411OPlab,IM,NTUIII.Spider web-building algorithm model design3/8RadiiGene 1：Control the number of radii()and base angle().Gene 2：Control the difference of the angle()from the north to the first radii.Gene 3：Control the difference of the angle()between the other radii.Figure.7 The relation between radii and gene 6/30/202412OPlab,IM,NTUIII.Spider web-building algorithm model design4/8Frame The distance(HF)between hub and frame is the length of the radii(RL)subtract the length which is control by Gene 4().HF=RL-Because of the effects of the gravity,the distance between hub and downward frame is longer than the others distance.RLHFFigure.8 The relation between frame and gene 6/30/202413OPlab,IM,NTUIII.Spider web-building algorithm model design5/8ASThe effects of the interactions between Gene 5()and Gene 6()control the intersection points of the AS and radii,resulting in a clockwise spiral(AS).Figure.9 The relation between AS and gene 6/30/202414OPlab,IM,NTUIII.Spider web-building algorithm model design6/8CSAlong the AS,a spider creates an anticlockwise spiral(CS).The intersection points of the CS and radii are effected by Gene 7().Figure.10 The relation between CS and gene 6/30/202415OPlab,IM,NTUIII.Spider web-building algorithm model design7/8CS reverseUsing reverse to fill the remaining space of web,which is uncovered with CS.Figure.11 The relation between radii and gene 6/30/202416OPlab,IM,NTUIII.Spider web-building algorithm model design8/8Figure.12 Sequential behavior of spider web-building.lExperiments6/30/202417OPlab,IM,NTUOutlineI.IntroductionlAbstractlMotivationII.Literature reviewlArtificial IntelligencelRelated spider papersIII.Spider web-building algorithm designIV.Visualization tool prototype of the modellInternal factorslExternal factorsV.Conclusion and future work6/30/202418OPlab,IM,NTUIV.Visualization tool prototype of the model1/23lInternal factorsExplanation of the rulesExperiments lModel simulationlVerificationlExternal factorsExplanation of the rulesExperiments lModel simulationlVerification6/30/202419OPlab,IM,NTUIV.Spider web-building algorithm model design2/12lInternal factorsFigure.6 The internal factor-analysis tree of web-building6/30/202420OPlab,IM,NTUIV.Visualization tool prototype of the model3/23lInternal factorsBody size()Larger spiders would build larger websWeight()Heavier spiders with the same size of their body would build larger websGland silk()Larger gland silk with the same size of their body build larger webs,interaction6/30/202421OPlab,IM,NTUIV.Visualization tool prototype of the model3/23Figure.13(a)minimize,Figure.13(b)Maximize,minimize,lBody size()experiments lModel simulationlVerification6/30/202422OPlab,IM,NTUFigure.14(a)minimize,Figure.14(b)Maximize,minimize,IV.Visualization tool prototype of the model4/23lWeight()experiments lModel simulationlVerification6/30/202423OPlab,IM,NTUIV.Visualization tool prototype of the model5/23lGland silk()experiments lModel simulationlVerification Figure.15(b)Maximize,minimize,Figure.15(a)minimize,6/30/202424OPlab,IM,NTUIV.Visualization tool prototype of the model6/23Figure.16(b)Maximize,l,interaction experiments experiments lModel simulationlVerificationFigure.16(a)minimize,6/30/202425OPlab,IM,NTUIV.Visualization tool prototype of the model1/23lInternal factorsExplanation of the rulesExperiments lModel simulationlVerificationlExternal factorsExplanation of the rulesExperiments lModel simulationlVerification6/30/202426OPlab,IM,NTUIV.Visualization tool prototype of the model7/23Figure.17 The external factor analysis tree of web-buildinglExternal factorsClimateSurrounding environmentsPrey size6/30/202427OPlab,IM,NTUIV.Visualization tool prototype of the model8/23lClimateWindAffect meshAffect the length and the number of radiusTemperature Affect mesh Affect the frequency of CS reverseHumidityAffect mesh Affect the viscosity of CS6/30/202428OPlab,IM,NTUIV.Visualization tool prototype of the model9/23lWind()experimentsModel simulationAdjusting the control value of Gene to create new mesh.Figure.18 Wind influence in mesh6/30/202429OPlab,IM,NTUIV.Visualization tool prototype of the model10/23：0m/s ：25：45%：1m/s ：25 ：45%Verification-wind Bias:16.33%Bias:17.33%Figure.19(a)Wind effect meshFigure.19(b)Wind effect mesh6/30/202430OPlab,IM,NTUlTemperature()experimentsModel simulationAdjusting the control value of Gene to create new mesh.IV.Visualization tool prototype of the model11/23Figure.20 Temperature influence in mesh6/30/202431OPlab,IM,NTUIV.Visualization tool prototype of the model12/23：24 ：0m/s ：55%：12 ：0m/s：55%Verification-temperature Figure.21(a)Temperature effect meshFigure.21(b)Temperature effect meshBias:0.60%Bias:1.67%6/30/202432OPlab,IM,NTUlHumidity()experimentsModel simulationAdjusting the control value of Gene to create new mesh.IV.Visualization tool prototype of the model13/23Figure.22 Humidity influence in mesh6/30/202433OPlab,IM,NTUVerification-humidityIV.Visualization tool prototype of the model14/23 ：70%：0m/s ：24 ：20%：0m/s ：24 Figure.23(a)Humidity effect meshFigure.23(b)Humidity effect meshBias:0.87%Bias:0.16%6/30/202434OPlab,IM,NTUlSurrounding environmentsTo affect the area of the webThe goal of web-building is to maximizeIV.Visualization tool prototype of the model15/236/30/202435OPlab,IM,NTUIV.Visualization tool prototype of the model16/23Figure.24(a)Available space relatively smalllSurrounding environmentsexperiments lModel simulationlVerificationFigure.24(a)Available space relatively big6/30/202436OPlab,IM,NTUIV.Visualization tool prototype of the model17/23lPrey sizeAffect meshApplying the past experiences for catching difference sizes of prey to adjust the mesh of the next web-building6/30/202437OPlab,IM,NTUIV.Visualization tool prototype of the model18/23lPrey sizeexperiments lModel simulationThe major concept is that using animals learning to simulate the real worldlVerification6/30/202438OPlab,IM,NTUIV.Visualization tool prototype of the model19/23Figure.25(a)The first dayFigure.25(b)The second dayVerification6/30/202439OPlab,IM,NTUIV.Visualization tool prototype of the model20/23VerificationFigure.25(c)The third dayFigure.25(d)The fourth day6/30/202440OPlab,IM,NTUIV.Visualization tool prototype of the model21/23Summary6/30/202441OPlab,IM,NTUOutlineI.IntroductionlAbstractlMotivationII.Literature reviewlArtificial IntelligencelRelated spider papersIII.Spider web-building algorithm designIV.Visualization tool prototype of the modellInternal factorslExternal factorsV.Conclusion and future work6/30/202442OPlab,IM,NTUV.Conclusion and future work1/2lSuccess in simulation the sequential behavior of spider web-buildinglThe proposed model was verified by comparing with numerical experiment of biologists lUnobserved behavior of spiders could be successfully predicted6/30/202443OPlab,IM,NTUV.Conclusion and future work2/2lLong term learning lSimulating the behavior of spider to repair the weblDesigning social spider web-building modellApplying spider web-building algorithms to optimization problems 6/30/202444OPlab,IM,NTUAcknowledgementslWe thank our adviser PhD Peng-Yeng Yin.lWe thank NSC to provide our budget.Project name:模擬蜘蛛結網之演算法設計及視覺化工具開發Project number:94-2815-C-260-014-E Adviser:尹邦嚴Name:陳怡孜 6/30/202445OPlab,IM,NTU QA?6/30/202446OPlab,IM,NTUThank you!6/30/202447OPlab,IM,NTU
展开阅读全文