大数据：助力航空业数字化转型.pdf

1、KeynotePresentationBig Data:Powering Digital Transformation in AviationPAGE|2Big Data:Isnt it Dead?Big Data,3+VsVolume:The sheer amount of data being generated.Velocity:The speed at which data is generated and processed.Variety:The diverse formats and types of data (structured,unstructured,etc.).Giv

2、en this definition,Big Data is alive.However,it underwent a transformationVolume:Expensive trend:“collect and think later”.Drove cost and complexity in processing.Velocity:A lack of differentiation between data and information.Variety:Underestimated efforts on data transformation(ETL)to adapt to exi

3、sting algorithms and frameworks.Learning.(i)Processing data is not for free,(ii)storage is not for free business case killer.PAGE|3Paradigm ChangesParadigm Change 1Paradigm Change 2Paradigm Change 3Output first,collection second.Self generated data input data.IT Security(end2end)Big Data Hype Contri

4、bution-Sophisticated and robust tool chain.-Examples Single turn(45min):3.5GB of video streams,70 events/key attributes describing the turn.At 1000 movements a day this leads to 3.5TB.EQ Lights:20.000 assets per airport,1 message per second per asset each at 1kb Yearly 63TB.-Maybe not“big data”for t

5、he known hyperscalers,but still challenging for many installations.PAGE|4The New Challenges(In Aviation)Collaboration&Probabilistic Values(AI,ML,CV)Use CasesPredictiveMaintenanceRemote MarshallingDynamicHolding PosIncursion DetectionCrossing MonitoringCollaboration:became a mantra,but moving slow Re

6、asonsTechnically:The diverse formats and types of data(structured,unstructured,etc.).Operationally:Siloed areas of responsibilities,even different organizations Commercially:contractual/competition issue,thin business cases,beneficiary different from investor.High Impact use cases require collaborat