The index file was then modified in accordance with Table 2, so that the first segment reflects the complete journey segment, with the in-segment stop considered as part of the movement time.
A simple representation for the classification problem at hand is to have one gene for each journey segment, with the set of possible alleles for each gene corresponding to all the possible station-station journey pairs (along with alleles for unknown segments and in-segment stops).
The next step was to examine each day in turn and divide it up into individual journey segments.
Although it was shown above that the initial extraction algorithm creates additional spurious journey segments compared to the filtering extraction algorithm, it should always be possible to combine these to obtain the correct segments.
These improvements meant that it became practical to manually examine the entire dataset and make corrections where the index showed problems, which were typically manifested as unexpected '(unknown)' segments, or single journey segments being assigned a specific identity despite the train almost certainly moving to/from/within the depot or sidings at the time.
The sequence-based algorithm builds up plausible sequences of individual journey segments and is a good fit for validation of other algorithms, as it has a lower likelihood of assigning incorrect identities and illustrates all possible options rather than only the best match.
The results obtained in this paper in a case study of a metro system suggest that the most promising approach for this problem is to check the cumulative distance of several consecutive journey segments against a set of reference station-to-station distances, along with additional dataset-specific rules defined for pre-processing and post-processing of the data.
Furthermore, all bus journeys are segmented into links between subsequent bus stops, since the bus stop sequences and the location of each bus stop are available, and the segments between every two bus stops are useful for bus traffic analysis.
During a passenger journey, each route segment, each start and end station, and each interchange, are all given an equal weight.
Or, blindfolded, you set out on a journey in five segments with different themes: you can remove the blindfold at any point, but that's where the journey ends.
I figured that I could greatly reduce the high cost of long-distance airfare by splitting up my journey into short segments, which I would travel predominantly by train, bus, or budget airlines.
