3) Cluster C – strong evening peak
The time-series data plots in cluster C have displayed a
very strong evening peak on weekdays. However the evening
peak pattern was not observed on weekends. Examining into
the composition of cluster C, we found that it is made up of
MRT stations situated in commercial and industrial areas. A
preliminary explanation for the weekday evening peak could
be that the passengers were leaving their workplace to return
back home. Another interesting observation is that the
weekday evening passenger volume of commercial and
industrial area (cluster C) was higher than weekday evening
passenger volume of residential area (cluster A and B). This
might be due to more train stations serving residential areas
than commercial and industrial areas.
Train stations in cluster D were experiencing moderately
high passenger volume entering the stations in the morning.
The morning peak pattern was again not observed on
weekends. Examining into the composition of cluster D, we
found that it is made up of LRT stations situated in residential
areas. This could give us a preliminary explanation for the
weekday morning peak where the passengers living in
residential areas were traveling to work on weekday morning.
The morning peak in cluster D also generally had a relatively
lower passenger volume compared to the passenger volume in
cluster B. This could be due to lesser residents in the
residential areas served by stations in cluster D, or the
residents could have a better alternative mode of transport (i.e.
public bus or private cars).
5) Cluster E – moderate morning peak/ strong evening
peak
The time-series data plots in cluster E have displayed a