Multi-Facet Design of Interactive Systems through Visual Languages

Thisarticlepresentsamethodtopredictthemedicalresourcesrequiredtobedispatchedafterlarge-scale disasterstosatisfythedemand.Thehistoricaldataofpastincidents(earthquakes,floods)regardingthe numberofvictimsrequestedemergencymedicalservicesandhospitalisation,simulationtools,webservices andmachinelearningtechniqueshavebeencombined.Theauthorsadoptedatwofoldapproach:a)use ofwebservicesandsimulationtoolstopredictthepotentialnumberofvictimsandb)useofhistorical dataandself-trainedalgorithmsto“learn”fromthesedataandproviderelativepredictions.Comparing actualandpredictedvictimsneededhospitalisationshowedthat theproposedmodelscanpredict the medicalresourcesrequiredtobedispatchedwithacceptableerrors.Theresultsarepromotingtheuseof electronicplatformsabletocoordinateanemergencymedicalresponsesincetheseplatformscancollect bigheterogeneousdatasetsnecessarytooptimisetheperformanceofthesuggestedalgorithms. KEywORDS Deep Learning, Earthquake, Flood, Historical Data, Linear Regression Models, Medical Resources Prediction, NLP