Instrumentation & Measurement Magazine 23-6 - 33

Table 2 - Locomotion Scoring - within and between observer agreement [7]
Locomotion
Score

Within Observer Agreement,
% (95% confidence interval)

Between Observer Agreement,
% (95% confidence interval)

1

72.5 (64.4 - 80.6)

63.9 (60.3 - 67.6)

2

63.9 (56.9 - 70.9)

58.9 (55.9 - 61.6)

3

60.0 (51.7 - 68.2)

53.1 (49.6 - 56.5)

4

74.5 (67.2 - 81.9)

62.1 (58.6 - 65.5)

5

75.6 (60.2 - 91.9)

38.7 (30.5 - 46.9)

Existing Automated Solutions
The idea to measure lameness automatically is a recent concept, and currently there are very few commercial systems
available. The StepMetrix system developed by Bou-Matic generates scores based on the captured ground reaction
forces produced by an array of single axis load cells as the
animal walks over a platform. The system is permanently installed in the return lane of a milking shed. The platform has
two parallel platform segments, one for left side legs and one
for right side legs. The software compares previous records of
the cow's gait such as force, location and duration to the current signals detected. The score is displayed to the farmer who
decides whether to act and examine the cow further or let her
keep walking. The system supposedly averages over 85%
accuracy in detecting lameness in individual cattle [8]. The
disadvantage of this system is that it only detects lameness in
the hind limbs, and it requires reference data from each cow
before it can compare differences. Consequently, all of the animals need to walk over the system at least once when they are
healthy before lameness detection can occur. The system has a
high specificity rate, but the sensitivity rate is low, ranging between 20-35 %. This means that many lameness cases are not
being detected, which lowers the farmers' confidence in the
system [9].
The GAITWISE system was developed in Belgium [10].
It uses a pressure-sensitive walkway incorporated into a
platform to monitor the cow's gait using variables in four
dimensions (two spatial, one temporal and one force). The
recorded data is analyzed against ten basic gait kinematic variables with the use of MATLAB, with these variables being:
stride length, stride time, stance time, step overlap, abduction,
asymmetry in step width, step length, step time, stance time
and force. The system operates fully automatically and in real
time and has 84% accuracy in correctly classifying lame cattle
[10]. An important discovery made by this study was that out
of all the gait variables used to decide if a cow was lame, four
variables contributed the most to the correct classification. The
variables were asymmetry in step length, asymmetry in stance
time, asymmetry in step time, and asymmetry in step width.
The four variables showed a strong correlation for detecting
lameness.
A London-based research team has developed an automated early lameness detection system for dairy cattle [11].
The system uses five force plates to analyze the gait of a cow.
September 2020	

Over a two-year period, the team collected over 500,000 foot
strikes from dairy cows exiting the milking shed. Of interest
is that only 13.4% of the foot strikes (67,000) could be used to
extract data from. This was found to be the case when using a
platform to measure ground reaction forces; if the cow were
not walking with a constant speed, then the data collected
would be invalid. The StepMetrix and GAITWISE system also
mentioned this finding. The results of the study found there
was no single discriminatory feature when identifying lameness [11]. Using advanced statistical techniques, it was found
that vertical forces were not as closely related to identifying
lameness as stride variables. This result is surprising considering that when a cow shows signs of lameness, it tries to shift its
weight distribution from the affected leg to ease the pain. Similar results were found with multiple variables contributing to
lameness detection [12]. They also found that stride variables
showed a higher correlation than vertical forces alone, and that
compared with lame cows, healthy cows had shorter stride durations (1.26 ± 0.03 s vs. 1.48 ± 0.05 s), longer strides (139.5 ± 2.1
cm vs. 130.0 ± 3.2 cm) and walked faster (1.11 ± 0.03 m/s vs.
0.90 ± 0.05 m/s) [12].

Project Goals
The major goal of this project is to calculate and determine the
variables of significance in detecting lameness in order to build
an accurate classification model to identify lame and healthy
cattle. We present the design of a ground reaction force-based
platform using an array of load cells to capture the three main
kinematic parameters associated with detecting lameness:
force, position and duration. From the three parameters, gait
variables can be found, such as stride length, to analyze differences in each hoof of individual cattle. The hypothesis that
a lame cow will produce a distinct signal signature that will be
distinguishable from a healthy cow first needs to be tested. The
significance of the variables will determine the role in which
they are applied to statistical models.
The designed platform is not intended to replace the current walkover weighing (WoW) scales, so it must be able to
find the total cow weight in addition to lameness related variables. The test data is to be captured from a farm without any
intervention to the natural flow of the cows leaving the milking shed. The system needs to provide numerical information
to assess acute daily changes in the front and hind limbs to
monitor the health and wellbeing of dairy cattle, and ideally

IEEE Instrumentation & Measurement Magazine	33



Instrumentation & Measurement Magazine 23-6

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 23-6

No label
Instrumentation & Measurement Magazine 23-6 - Cover1
Instrumentation & Measurement Magazine 23-6 - No label
Instrumentation & Measurement Magazine 23-6 - 2
Instrumentation & Measurement Magazine 23-6 - 3
Instrumentation & Measurement Magazine 23-6 - 4
Instrumentation & Measurement Magazine 23-6 - 5
Instrumentation & Measurement Magazine 23-6 - 6
Instrumentation & Measurement Magazine 23-6 - 7
Instrumentation & Measurement Magazine 23-6 - 8
Instrumentation & Measurement Magazine 23-6 - 9
Instrumentation & Measurement Magazine 23-6 - 10
Instrumentation & Measurement Magazine 23-6 - 11
Instrumentation & Measurement Magazine 23-6 - 12
Instrumentation & Measurement Magazine 23-6 - 13
Instrumentation & Measurement Magazine 23-6 - 14
Instrumentation & Measurement Magazine 23-6 - 15
Instrumentation & Measurement Magazine 23-6 - 16
Instrumentation & Measurement Magazine 23-6 - 17
Instrumentation & Measurement Magazine 23-6 - 18
Instrumentation & Measurement Magazine 23-6 - 19
Instrumentation & Measurement Magazine 23-6 - 20
Instrumentation & Measurement Magazine 23-6 - 21
Instrumentation & Measurement Magazine 23-6 - 22
Instrumentation & Measurement Magazine 23-6 - 23
Instrumentation & Measurement Magazine 23-6 - 24
Instrumentation & Measurement Magazine 23-6 - 25
Instrumentation & Measurement Magazine 23-6 - 26
Instrumentation & Measurement Magazine 23-6 - 27
Instrumentation & Measurement Magazine 23-6 - 28
Instrumentation & Measurement Magazine 23-6 - 29
Instrumentation & Measurement Magazine 23-6 - 30
Instrumentation & Measurement Magazine 23-6 - 31
Instrumentation & Measurement Magazine 23-6 - 32
Instrumentation & Measurement Magazine 23-6 - 33
Instrumentation & Measurement Magazine 23-6 - 34
Instrumentation & Measurement Magazine 23-6 - 35
Instrumentation & Measurement Magazine 23-6 - 36
Instrumentation & Measurement Magazine 23-6 - 37
Instrumentation & Measurement Magazine 23-6 - 38
Instrumentation & Measurement Magazine 23-6 - 39
Instrumentation & Measurement Magazine 23-6 - 40
Instrumentation & Measurement Magazine 23-6 - 41
Instrumentation & Measurement Magazine 23-6 - 42
Instrumentation & Measurement Magazine 23-6 - 43
Instrumentation & Measurement Magazine 23-6 - 44
Instrumentation & Measurement Magazine 23-6 - 45
Instrumentation & Measurement Magazine 23-6 - 46
Instrumentation & Measurement Magazine 23-6 - 47
https://www.nxtbook.com/allen/iamm/26-1
https://www.nxtbook.com/allen/iamm/25-9
https://www.nxtbook.com/allen/iamm/25-8
https://www.nxtbook.com/allen/iamm/25-7
https://www.nxtbook.com/allen/iamm/25-6
https://www.nxtbook.com/allen/iamm/25-5
https://www.nxtbook.com/allen/iamm/25-4
https://www.nxtbook.com/allen/iamm/25-3
https://www.nxtbook.com/allen/iamm/instrumentation-measurement-magazine-25-2
https://www.nxtbook.com/allen/iamm/25-1
https://www.nxtbook.com/allen/iamm/24-9
https://www.nxtbook.com/allen/iamm/24-7
https://www.nxtbook.com/allen/iamm/24-8
https://www.nxtbook.com/allen/iamm/24-6
https://www.nxtbook.com/allen/iamm/24-5
https://www.nxtbook.com/allen/iamm/24-4
https://www.nxtbook.com/allen/iamm/24-3
https://www.nxtbook.com/allen/iamm/24-2
https://www.nxtbook.com/allen/iamm/24-1
https://www.nxtbook.com/allen/iamm/23-9
https://www.nxtbook.com/allen/iamm/23-8
https://www.nxtbook.com/allen/iamm/23-6
https://www.nxtbook.com/allen/iamm/23-5
https://www.nxtbook.com/allen/iamm/23-2
https://www.nxtbook.com/allen/iamm/23-3
https://www.nxtbook.com/allen/iamm/23-4
https://www.nxtbookmedia.com