www-ai.cs.tu-dortmund.de/de/PERSONAL/MORIK/papers/pdf/Communication_efficient_learning_of_traffic_flow_in_a_network_of_wireless_presence_sensors.pdf
counts sent to neighboring nodes for learning
...
...
n1(j)
n2(j)
nc(j)
j
j j
D(j) j
x1(j)
x2(j)
x3(j)
y(j)1 . . . p 1 p
q1,low = 1
q1,high = 2
. . .
Fig. 1: Distributed Learning of Local Models
Let each [...] recording from time step s, obser- vations xi(j) = [vs+i−1(j), . . . , vs+i−2+p(j)] are windows of measurements and labels yi = d(vs+i−2+p+r(j)) are discretized measurements r time steps ahead.
For every node [...] Dublin, where the focus is on the prediction of future traffic flow at junctions throughout the city.
2 Related Work
Distributed algorithms mostly focus on horizontally partitioned data, whereas our data …