The images to the right shows a random sample of some of the time series in the archive. The datasets come from diverse fields, including finance, medicine, biometrics, chemistry, astronomy, robotics, networking and industry. 

These datasets cover the complete spectrum of stationary/ non-stationary, noisy/ smooth, cyclical/ non-cyclical, symmetric/ asymmetric etc.

The data, together with an index describing the source of each sequence and other details, is freely available by emailing eamonn@cs.ucr.edu

If you use the data in a publication, please acknowledge the source...

Keogh, E. (2006). The UCR Time Series Data Mining Archive
[http://www.cs.ucr.edu/~eamonn/TSDMA/index.html]. Riverside CA. University of California - Computer Science & Engineering Department

... and send us a pointer to the paper.

Name Size
sunspot.dat  2899x1 
attas.dat  1024x2 
leleccum  4320x1 
greatlakes  984x5 
synthetic.dat  100001x10 
random_walk.dat  65536x1 
koski_ecg.dat  44002x1 
eeg.dat  512x22
burst.dat   9382x1 
network.dat  18000x1
infrasound_beamd.dat   8192x1 
buoy_sensor.dat  13991x4 
soiltemp.dat  2304x1
earthquake.dat  4096x1 
speech.dat  1020x1
standardandpoor500.dat  17610x2
wool.dat  310x9 
balloon.dat  2001x2 
wind.dat  6574x15
ballbeam.dat  1000x2 
tongue.dat  50x14 
foetal_ecg.dat  2500x9 
robot_arm.dat  1024x2
flutter.dat  1024x2
glassfurnace.dat  1247x9
powerplant.dat  2400x1
evaporator.dat  6305x6  
phdata.dat  2001x3 
dryer2.dat  867x6
winding.dat  2500x7
cstr.dat  7500x3
steamgen.dat  9600x4 
ocean.dat  4096x1
tide.dat  8746x1
chaotic.dat  1800x1 
water.dat  2191x3 
tickwise.dat  279113x1
shuttle.dat  1000x6 
pgt50_cdc15.dat  990x24 
pgt50_alpha.dat  990x18 
ERP_data  31x6400 
EEG_heart_rate.dat  7200x2 
power_data.dat  35040x1 
spot_exrates.dat  2567x12 
darwin.dat  1400x
and many more datasets!!!