Figure 4 | Scientific Reports

Figure 4

From: Using dynamic time warping self-organizing maps to characterize diurnal patterns in environmental exposures

Figure 4

Visual comparison of the trained weights resulting from one iteration of the Euclidean training rule vs. the DTW training rule applied to a randomly selected observation from the 24-h outdoor temperature time series. Input data refers to the standard time series, trained weights refer to the weights after the iteration, and BMU weights refer to the weights at the previous iteration.

Back to article page