LDTW result

[NiuWenYu12138]

When I use the ldtw method to calculate the distance between two time series of different lengths, the result obtained is the same as the result calculated with dtw (the parameter max_length is not greater than the sum of the lengths of the two time series)

[rtavenar]

Hi @NiuWenYu12138

In fact, if the length of the DTW path is smaller than the max_length you set, then LDTW and DTW will indeed return the same result. LDTW is just a way to avoid pathologically long paths in the DTW optimization. Some quick explanation is provided here, if it may help.

[NiuWenYu12138]

Hi @NiuWenYu12138

In fact, if the length of the DTW path is smaller than the max_length you set, then LDTW and DTW will indeed return the same result. LDTW is just a way to avoid pathologically long paths in the DTW optimization. Some quick explanation is provided here, if it may help.

Thanks for your answer! I have tested some other data,When I set the value of Max_length to be smaller than the DTW path, the result is still consistent with the result calculated by DTW.By the way,now my data is two-dimensional.

[rtavenar]

Could you please provide an example of this behavior ?