| Description: | The task is to classify the psuedo-acoustic series produced by an
insects wingbeat.
The time series represent the change in amplitude of a infra-red light
as is occluded by the wings of flying mosquito.
The database contains wav recordings from the same optical sensor inserted
in-turn into six insectary boxes containing only one mosquito species of both sexes.
As the mosquitoes fly randomly through the sensor their wingbeat partially occludes
the light from the transmitter to the receiver. The light fluctuation recorded follows
the rhythm of the wingbeat. Recordings are sampled at 6,000Hz.
Original data can be found here:
(Link Here)
Original paper:
Potamitis I, Rigakis I. Large aperture optoelectronic devices to record and
time-stamp insects wingbeats. IEEE Sensors Journal. 2016 Jun 1;16(15):6053-61.
Correspondence should be addressed to Ilyas Potamitis:
potamitis@staff.teicrete.gr
Instances: 279,566
Time series length: 3750
Classes:
0 Ae. aegypti (85553)
1 Ae. albopictus (20231)
2 An. arabiensis (19297)
3 An. gambiae (49471)
4 Cu. pipiens (30415)
5 Cu. quinquefasciatus (74599)
default train test split created through a random partition. There is a multivariate version
of this data in the archive called MosquitoWingbeat |
