Delay propagation data examples simulated by LinTim software
delayAth
Delay propagation data generated on the Athens metro network by LinTim software
delayGoe
Delay propagation data generated on the Goettingen bus system by LinTim software
Public transportation network datasets are generated by LinTim software (Integrated Optimization in Public Transportation; https://www.lintim.net/index.php?go=data&lang=en).
delayAth
Delay data on the Athens metro network. Propagation simulation under consideration of secruity distances and fixed-waiting time delay management. 'data.frame' with 510 observations (10 sequential time pictures for delay spreading pattern from 51 stations) of 53 variables (k0
true source, time
, delays at 51 stations).
delayGoe
Delay data on the directed Goettingen bus system. Progation simulation under consideration of secruity distances and fixed-waiting time delay management. 'data.frame' with 2570 observations (10 sequential time pictures for delay spreading pattern from 257 stations) of 259 variables (k0
true source, time
, delays at 257 stations).
Manitz, J., J. Harbering, M. Schmidt, T. Kneib, and A. Schoebel (2017): Source Estimation for Propagation Processes on Complex Networks with an Application to Delays in Public Transportation Systems. Journal of Royal Statistical Society C (Applied Statistics), 66: 521-536.
Jonas Harbering
if (FALSE) { # compute effective distance data(ptnAth) athnet <- igraph::as_adjacency_matrix(ptnAth, sparse=FALSE) p <- athnet/rowSums(athnet) eff <- eff_dist(p) # apply source estimation if (requireNamespace("aplyr", quietly = TRUE)) { data(delayAth) res <- alply(.data=delayAth[,-c(1:2)], .margins=1, .fun=origin_edm, distance=eff, silent=TRUE, .progress='text') perfAth <- ldply(Map(performance, x = res, start = as.list(delayAth$k0), list(graph = ptnAth))) } } if (FALSE) { # compute effective distance data(ptnGoe) goenet <- igraph::as_adjacency_matrix(ptnGoe, sparse=FALSE) p <- goenet/rowSums(goenet) eff <- eff_dist(p) # apply source estimation if (requireNamespace("aplyr", quietly = TRUE)) { data(delayGoe) res <- alply(.data=delayGoe[,-c(1:2)], .margins=1, .fun=origin_edm, distance=eff, silent=TRUE, .progress='text') perfGoe <- ldply(Map(performance, x = res, start = as.list(delayGoe$k0), list(graph = ptnGoe))) } }