Subclinical ketosis is an important and common disease in early lactating dairy cows, associated with economic losses because of decreased milk production, decreased reproductive performance and increased risk of additional periparturient diseases. Subclinical ketosis is defined by increased blood concentrations of ketone bodies in the absence of clinical signs of ketosis. The gold standard for subclinical ketosis is the measurement of BHBA (β- hydroxybutyrate) in serum or plasma. Available on-site blood tests detect the disease with high accuracy, but are expensive and labor-intensive on a herd level. Introducing easier procedures for detecting the disease in practice, or at least reducing the number of animals which have to be blood-tested, by identifying animals at risk, are desired. Our approach is based on the SMARTBOW system, an ear-tag equipped with a 3D accelerometer, which records lying, standing, rumination and activity behavior. Blood samples for the measurement of BHBA were used as gold standard. We propose a new measure called MITOD (Minimal Total Distance), which aims to flexibly compare time series and compensate for possible alignment errors. This distance measure was incorporated in a machine learning approach and it's classification quality was compared with state of the art methods on our data to infer the health status of the considered animals. Our approach shows promising results for detecting subclinical ketosis and for classifying time series in general. This work has been supported by the COMET-K2 Center of the Linz Center of Mechatronics (LCM) funded by the Austrian federal government and the federal state of Upper Austria. Animal health data were collected in the agriProKnow project funded by the Austrian Research Promotion Agency (FFG, project# 848610).

1.
T. F.
Duffield
,
Vet. Clin. North Am. Food Anim. Pract
16
,
231
253
(
2000
).
2.
A.
Hayirli
,
S. J.
Bertics
and
R. R.
Grummer
,
Journal of Dairy Science
85
,
2180
2191
(
2002
).
3.
R. R.
Grummer
,
D. G.
Mashek
and
A.
Hayirli
,
Veterinary Clinics of North America: Food Animal Practice
20
,
447
470
(
2004
).
4.
R. R.
Grummer
,
The Veterinary Journal
176
,
10
20
(
2008
).
5.
Iwersen
,
M.
,
U.
Falkenberg
,
R.
voigtsberger
,
D.
Forderung
and
W.
Heuwieser
,
Journal of Dairy Science
92
,
2618
2624
(
2009
).
6.
L.
Andersson
,
Vet. Clin. North Am. Food Anim. Pract
4
,
233
251
(
1988
).
7.
E.
Rollin
,
R. D.
Berghaus
,
P.
Rapnicki
,
S. M.
Godden
, and
M. W.
Overton
,
Journal of Dairy Science
93
,
978
987
(
2010
).
8.
T.
Geishauser
,
K.
Leslie
and
T.
Duffield
,
Veterinary Clinics of North America: Food Animal Practice
16
,
255
265
(
2000
).
9.
J. A. A.
McArt
,
D. V.
Nydam
, and
G. R.
Oetzel
,
Journal of Dairy Science
95
,
2505
2512
. (
2012
).
10.
V. S.
Suthar
,
J.
Canelas-Raposo
,
A.
Deniz
, and
W.
Heuwieser
,
Journal of Dairy Science
96
,
2925
2938
(
2013
).
11.
T.
Geishauser
,
K.
Leslie
,
D.
Kelton
and
T.
Duffield
,
Journal of Dairy Science
81
,
438
443
(
1998
).
12.
G. R.
Oetzel
,
Veterinary Clinics of North America: Food Animal Practice
20
,
651
674
(
2004
).
13.
S.
Leblanc
,
J Reprod Dev
56
,
29
35
(
2010
).
14.
M.
Iwersen
,
D.
Klein-Jöbstl
,
M.
Pichler
,
L.
Roland
,
B.
Fidlschuster
,
I.
Schwendenwein
, and
M.
Drillich
,
Journal of Dairy Science
96
,
7719
7730
(
2013
).
15.
V.
Schweinzer
,
E.
Gusterer
,
P.
Kanz
,
S.
Krieger
,
D.
Süss
,
L.
Lidauer
and
M.
Drillich
,
Theriogenology
130
,
19
25
(
2019
).
16.
A.
Stone
, “
Precision dairy farming technology solutions for detecting dairy cow disease to improve dairy cow well-being
”, Ph.D. thesis,
University of Kentucky
,
2017
.
17.
E. I.
Kaufman
, “
Monitoring transition dairy cow behaviour for the detection of subclinical ketosis
”, Ph.D. thesis.
Department of animal and poultry Science
,
2015
.
18.
Manning
C
,
P.
Raghavan
and
H.
Schutze
. (
2008
).
Introduction to Information Retrieval
,
Cambridge University Press
. pp
292
297
.
19.
T.
Cover
and
P.
Hart
,
IEEE transactions on information theory
13
,
21
27
(
1967
).
20.
A.
Bagnall
,
J.
Lines
,
A.
Bostrom
,
J.
Large
and
E.
Keogh
,
Data Mining and Knowledge Discovery
31
,
606
660
(
2017
).
This content is only available via PDF.
You do not currently have access to this content.