“…There exists a great number of studies employing neural network methods as estimators and predictors to various problems of civil engineering (Flood and Kartam, 1994; Hung and Jan, 1999; Adeli, 2001; Panakkat and Adeli, 2009; Graf et al, 2010; Graf et al, 2012; Osornio‐Rios et al, 2012; Ghodrati Amiri et al, 2012) and particularly transportation engineering, including work‐zone capacity and delay estimation (Jiang and Adeli, 2003, 2004a; Karim and Adeli, 2003; Hooshdar and Adeli, 2004; Ghosh‐Dastidar and Adeli, 2006); short‐term traffic flow forecasting (Jiang and Adeli, 2005; Vlahogianni et al, 2008; Stathopoulos et al, 2008; Boto‐Giralda et al, 2010); incident detection (Adeli and Karim, 2000; Adeli and Samant, 2000; Samant and Adeli, 2001; Karim and Adeli, 2002a; Ghosh‐Dastidar and Adeli, 2003); pave performance (Mei et al, 2004; Bianchini and Bandini, 2010); zonal trip distribution modeling (Tillema et al, 2006); and road safety (Pande and Abdel‐Aty, 2008). Specifically, in a series of works on traffic pattern estimation (Treiber et al, 2010; Treiber et al, 2011) and classification, the time‐series characteristics of input flow measures are deeply analyzed employing various methods for time‐frequency representation.…”