A Model to Predict The Live Bodyweight of Livestock Using Back-propagation Algorithm

TELKOMNIKA, Vol.16, No.4, August 2018, pp. 1667~1672
ISSN: 1693-6930, accredited First Grade by Kemenristekdikti, Decree No: 21/E/KPT/2018
DOI: 10.12928/TELKOMNIKA.v16i4.6716  1667
Received July 3, 2017; Revised June 12, 2018; Accepted June 23, 2018
A Model to Predict The Live Bodyweight of Livestock
Using Back-propagation Algorithm
Inggih Permana*
1
, Ria agustina
2
, Endah Purnamasari
3
, Febi Nur Salisah
4
1,2,4
Department of Information Systems, Faculty of Science and Technology, Universitas Islam Negeri
Sultan Syarif Kasim (UIN SUSKA) Riau 28293, Pekanbaru, Riau, Indonesia
3
Department of Animal Sciences, Faculty of Agriculture and Animal Sciences, Universitas Islam Negeri
Sultan Syarif Kasim (UIN SUSKA) Riau 28293, Pekanbaru, Riau, Indonesia
*Corresponding author, e-mail: inggihpermana@uin-suska.ac.id
1
, ria.agustina@student.uin-suska.ac.id
2
,
endah.purnama.sari@uin-suska.ac.id
3
, febinursalisah@uin-suska.ac.id
4
Abstract
Cattle is the most popular livestock in Indonesia. Assessments of the live bodyweight of cattle
can be conducted through weighing or predicting. Weighing is an accurate method, but it is not efficient
due to the prices of scales that most traditional farmers cannot afford. Prediction is a more affordable
technique however occurrences of error remains high. To deal with this issue this research has created a
model predicting the live bodyweight of cattle through Back-Propagation algorithm. There are four
morphometric variables examined in this study: (1) body length; (2) withers height; (3) chest girth; and (4)
hip width. Based on comparative results with conventional prediction methods, Schoorl Indonesia and
Schoorl Denmark, showed that the method offered has a lower error. Rate of error is 60.54% lower than
Schoorl Denmark and 53.95% lower than Schoorl Indonesia.
Keywords: Back-propagation, Cattle, Live bodyweight, Morphometric characteristic, Prediction
Copyright © 2018 Universitas Ahmad Dahlan. All rights reserved.
1. Introduction
In Indonesia the Bali cattle contributes to the development of livestock industries [1].
Millions of Indonesian families consider Bali cattle the most suitable indigenous cattle breed for
the low-input, high stress production system still practiced [2]. Accounting for 25% of cattle
population [3], Bali cattle have been used for meat production in small scale units. These cattle
are considered being among the most important livestock in the populated regions of
Indonesia [4].
The determination of live bodyweight is necessary to: (1) calculate feed requirements;
(2) know animal growth; (3) market livestock products; (4) estimate of the animal's cash value;
(5) conduct studies such as field experiments; and (6) make an estimation of dressed carcass
weight [5]. The live bodyweight of cattle can be determined by weighing them using a scale.
However, large capacity scales for cows and bulls are only available in certain locations such as
traditional livestock markets or slaughter houses. Possession of this cattle scale among cattle
breeders/producers is not common because of its unaffordable price, its impractical size and
heavy weight which makes its use in the field inconvenient. The digital version is much smaller
in size but its dependence on electricity makes it impractical. Hence it is necessary to create
another method for estimating the live bodyweight of livestock [6].
Prediction is another technique which can estimate the live bodyweight of livestock.
This technique is cheaper but error is frequent. This is confirmed because the Schoorl formula,
employed as one method used, can only be applied on livestock whose live weight is 300
kilograms or over [7]. In addition, traditional farmers estimate the live weight of livestock based
on visual cues alone [8].
To deal with the mentioned issues, this study created a model for predicting the live
bodyweight of livestock using an Artificial Neural Network of Back-Propagation algorithm. The
Back-Propagation algorithm has been chosen because studies have shown that this algorithm is
better than the conventional prediction method [9-11]. In addition, this algorithm has also been
successful in accomplishing many prediction related cases such as (1) human health issues
[12-15]; (2) financial issues [16,17]; and (3) plant disease [18].

 ISSN: 1693-6930
TELKOMNIKA Vol. 16, No. 4, August 2018: 1667-1672
1668
This study used physical morphometries as variables to estimate the live bodyweight of
cattle. The variables included four morphometries of cattle known as (1) body length; (2) withers
height; (3) chest girth; and (4) hip width. Body length and hip width were chosen since both of
them have high correlation coefficient regarding the live bodyweight of cattle [19]. The same
characteristic is also showed by withers height and chest girth in that the two variables can
estimate live bodyweight of cattle [20].
2. Back-Propagation Algorithm
Back-Propagation algorithm is a multi-layered Artificial Neural Network training method
comprising 3 phases [21]: (1) feed forward pattern of input training; (2) calculation and Back-
Propagation of respective error; and (3) adjustments of weights. This algorithm can be
implemented on the associative pattern, classification of compressed data pattern, robotic
control and function of approximation [22]. Algorithm 1 is Back-Propagation which has one
hidden layer.
Algorithm 1. Pseudo-code of Back-Propagation algorithm
while (iter < MaxIter and err > max_err) do
for (i = 0 to (sum_of_data-1)) do
{feedforward phase}
for (j = 1 to (sum_of_hidden_nds–1)) do
z_in[j] = 0
for (k = 0 to (Sum_of_Attrib-1)) do
z_in[j] ← z_in[j] + x[i,k]*v[k,j]
endfor
z[j] ← activation_function(z_in[j])
endfor
for (j = 0 to (sum_of_output_nds–1)) do
y_in[j] ← 0
for (k = 0 to (sum_of_hidden_nds–1)) do
y_in[j] ← y_in[j] + z[k]*w[k,j]
endfor
y[j] ← activation_func(y_in[j])
endfor
{back-propagation phase}
for (j = 0 to (sum_of_output_nds-1)) do
s[j] ← (target[j] –
y[j])*activation_function_derivative(y_in[j])
for (k = 0 to (sum_of_hidden_nds-1)) do
delta_w[k,j] ← a*s[j]*z[k]
{weight_adjustment}
w[k,j] ← w[k,j] + delta_w[k,j]
endfor
endfor
for (j = 1 to (hidden_nd_func-1)) do
q_in[j] ← 0
for (k = 0 to (sum_of_outpt_nds-1)) do
q_in[j] ← s_in[j] + s[k]*w[j,k]
endfor
q[j] ← q_in[j] *
activation_function_derivative(z_in[j])
endfor
for (j = 1 to (sum_of_hidden_nds-1)) do
for (k = 0 to (Sum_of_Attrib - 1)) do
delta_v[k,j] ← a*q[j]*x[k]
{weight_adjustment}
v[k,j] ← v[k,j] + delta_v[k,j]
endfor
endfor
endfor
err ← calculate_err(x,v,w)
iter ← iter + 1
endwhile
3. Research Method
3.1. Data Collection
Data collection was conducted between September 19, 2016 and October 4, 2016 in
Pekanbaru City, Riau Province, Indonesia. Variables were observed in the cattle are the live
body weight and four morphometric variables (body length, withers height, chest girth, and hip
width). Tools were used in the data collection were a digital scale, a measuring tape, and a
measuring stick. The digital scale was used to measure the live bodyweight of cattle. The
measuring tape was used to find out body length, chest girth and hip width. The measuring stick
was used to quantify withers height. The data was collected from 96 livestock comprising 40
cows and 56 bulls.
3.2. Data Normalization
Data normalization was carried out using Min-Max Normalization method before the
data were entered the process of Back-Propagation training. This method equalizes range of
values among attributes from 0 to 1. Min-Max Normalization formula can be seen in the
Formula 1.
(1)

TELKOMNIKA ISSN: 1693-6930 
A Model to Predict The Live Bodyweight of Livestock Using… (Inggih Permana)
1669
In Formula 1, Xnormij is the value resulting from the normalization at i-th observation at
j-th variable, Xij is the original value from i-th observation at j-th variable, Nminj is the minimum
value of observations at the j-th variable and Nmaxj is the maximum value of observations at j-th
variable.
3.3. Architecture of Back-Propagation to Predict The Live Bodyweight
The live bodyweight prediction model was devised by utilizing Artificial Neural Network
method of Back-Propagation. The inputs from the Back-propagation are the morphometric
characteristics (body length, withers height, chest girth, and hip width) of cattle whereas the
target of the Back-Propagation method is live bodyweight of cattle. The output derived from the
Back-Propagation model is the prediction of the live bodyweight of the livestock.
The architecture of Back-Propagation that was used can be seen in Figure 1. As can be
seen in the figure, in the input layer there are 5 nodes, of which four of these are assigned for
morphometric characteristics and one node for bias. The figure also shows one hidden layer
with two nodes besides one node for bias. Output layer indicates one node storing estimates of
live bodyweight in the form of normalized values. Activation function that is used in the hidden
layer and output layer is binary sigmoid. This Back-propagation architecture was made in simple
fashion to maintain a low complexity which allows easy implementation on devices that only
have low specifications.
X0
x1
x2
Z0
Z1
Z2
V12
V01
V11
V22
V21
V02
y
w01
w11
w21
x3
x4
V32
V31
V41
V42
Bias
Body
length
Chest
girth
Withers
height
Hip
width
Zin1
Zin2
Sigmoid(Zin1)
Sigmoid(Zin2)
Bias
Yin Sigmoid(Yin)
Figure 1. Back-Propagation architecture
In Figure 1, Xi is i-th input value, Y is the output value, Zj is j-th hidden value, Vij is the weight
value of Xi to Zj and Wj1 is the weight value of Zj to Y.
3.4. Denormalization
The output produced by Back-Propagation is the prediction of normalized live
bodyweight of livestock. Therefore, to get the actual range of live body weight of cattle
denormalization is required. Denormalization can be seen in Formula 2. In Formula 2, Xij is the
denormalized value of i-th observation at j-th variable, Xnormij is the value got from
normalization in i-th observation at j-th variable, Nmaxj is the maximum value of observations at
j-th variable and Nminj is the minimum value of observations at j-th variable.
( ) (2)

 ISSN: 1693-6930
1670
3.5. Experimental Setup for Back-Propagation
The collected data were divided into two parts namely training data (70%) and testing
data (30%). The training data comprises 68 cattle consisting of 28 cows and 40 bulls. The
testing data comprises 28 cattle consisting of 12 cows and 16 bulls. Training data are used to
create a prediction model using Back-Propagation method whereas testing data are used for
assessment of model performance. Parameters values were used in the process of making the
prediction model using Back-Propagation method can be seen in Table 1. Upon conducting
trials, the best performance was selected.
Table 1. Parameters of experiments
No. Parameter Value
1 Learning rate (ἀ) 0.025, 0.05, 0.075, ..., 0.975
2 Activation functions Sigmoid biner
3 Sum of iteration 1000
4 Maximum error 0.001
Performance of the model obtained from the results in backprogpagation training was
measured using root means square error (RMSE). The RMSE formula can be seen in
Formula 3. In Formula 3, Xi is the actual live bodyweight of a livestock resulting from i-th
observation using digital scale, Yi is the live bodyweight resulting from i-th observation using
Back-Propagation prediction model and n is the number of livestock.
√
∑
(3)
Having got the best model from Back-propagation training, the performance of the
model is compared with the conventional methods for the prediction of the live bodyweight of
cattle, Danish Schoorl method and the Schoorl Indonesia method. The comparison is performed
to determine whether the model offered better than previous methods. The formula of Schoorl
Denmark can be seen in Formula 4 whereas the formula of Schoorl Indonesia can be observed
in Formula 5.
(4)
(5)
In Formula 4 and Formula 5, LB is the live bodyweight and CG is chest girth of livestock.
4. Results and Analysis
Algorithm 2 is the best model of Back-Propagation training results. On the algorithm,
BL is body length, CG is chest girth, HW is hip width, and WH is withers height. Figure 2 is the
comparison of performance between prediction model of Schoorl Denmark, Schoorl Indonesia
and Back-propagation. The figure showed that the Back-propagation is the best model
because it has the smallest error. In the training data, the Back-propagation model produced
RMSE value 58.84% smaller than the Schoorl Denmark method and 52.13% smaller than the
Schoorl Indonesia method. Likewise, in the testing data, the Back-propagation model produced
RMSE 60.54% smaller than the method of Schoorl Denmark and 53.95% smaller than then
method of Schoorl Indonesia.
Figure 3 is the comparison of performance of model produced between cows and bulls.
The figure shows that RMSE the bulls are lower than the cows. This means the model offered
has better accuracy in bulls than cows. This may occur because the number of bulls data on
training data is more 42.85% than female cows. Thus, Back-Propagation is more recognize
pattern of the live bodyweight of bulls. In the training data, the values of RMSE of the bulls

TELKOMNIKA ISSN: 1693-6930 
A Model to Predict The Live Bodyweight of Livestock Using… (Inggih Permana)
1671
31.36% smaller than those found in cows. In the meantime, in the testing data, the values of
RMSE of the bulls 57.39% smaller than those found among the cows.
Algorithm 2. The live bodyweight prediction model for cattle
{Data Normalization}
BL ← (PB-62)/(154-62}
CG ← (LD-85)/(162-85)
HW ← (LP-7)/(24-7)
WH ← (TP-79)/(115-79}
{prediction using results of back-propagation model}
z_in1 ← 0.2897 + BL*0.3213 + CG*0.6324 + HW*0.9027 + WH*0.2153
z_in2 ← -3.4008 + BL*1.2271 + CG*1.4046 + HW*0.2281 + WH*2.1792
z1 ← sigmoid(z_in1)
z2 ← sigmoid(z_in2)
y_in1 ← -2.3538 + z1*0.5829 + z2*4.3933
y1 ← sigmoid(y_in1)
{denormalization of y1}
y1 ← y1*(286-69)+69 {y1 is the prediction result of live bodyweight of livestock}
Figure 2. Comparisons of RMSE between Schoorl Denmark, Schoorl Indonesia and Back-
Propagation
Figure 3. Comparisons of RMSE of proposed model between bulls and cows
5. Conclusion
This study developed new model to predict the live bodyweight of livestock using Back-
propagation. The proposed model has a better accuracy than method of Schoorl Denmark and
method of Schoorl Indonesia because RMSE of the model lower than the both methods.
The results in this study also showed that cows are more difficult to predict than bulls using the
proposed model. It can be seen from the comparison of RMSE of the live bodyweight
Schoorl Denmark Schoorl Indonesia Back-Propagation
Training Data 73,06 62,82 30,07
Testing Data 77,92 66,78 30,75
0
10
20
30
40
50
60
70
80
90
100
RMSE
Cow Bull
Training Data 36,23 24,87
Testing Data 42,15 17,96
0
10
20
30
40
50
60
70
80
90
100
RMSE

 ISSN: 1693-6930
1672
estimation, cows higher than bulls. Therefore, in future studies, the ability of this model should
be improved thus it can estimate the live bodyweight of cows with better accuracy.
This research has been successfully made a model to estimate the live bodyweight for
cattle. Though Indonesia has several livestock that have been cultivated by the community,
such us goat, sheep, and buffalo. Hence, in further studies, researches could be applied for the
others livestock.
References
[1] Purwantara B, Noor RR, Andersson G, Martinez HR. Banteng and Bali Cattle in Indonesia: Status and
Forecasts. Reproduction in Domestic Animals. 2012; 47(s1): 2–6.
[2] Martojo H. Indigenous Bali Cattle: The Best Suited Cattle Breed for Sustainable Small Farming in
Indonesia. In: Chang HL, Huang YC. Editors. The Relationship Between Indigenous Animals and
Humans in APEC Region. Taiwan: Chinese Society of Animal Sciences; 2003: 21–36.
[3] Lisson S, MacLeod N, McDonald C, Corfield J, Pengelly B, Wirajaswadi L, Rahman R, Bahar S,
Padjung R, Razak N, Puspadi K, Dahlanuddin, Sutaryono Y, Saenong S, Panjaitan T, Hadiawati L,
Ash A, Brennan L. A participatory, Farming Systems Approach to Improving Bali Cattle Production in
The Smallholder Crop–Livestock Systems of Eastern Indonesia. Agricultural Systems. 2010; 103(7):
486–497.
[4] Mohamad K, Olsson, Andersson M, Purwantara G, van Tol B, Martinez HR, Colenbrander H, Lenstra
JB. The Origin of Indonesian Cattle and Conservation Genetics of the Bali Cattle Breed. Reproduction
in Domestic Animals. 2012; 47(s1): 18–20.
[5] Payne WJA. An introduction to Animal Husbandry in The Tropics. Fourth Edition. Harlow: Longman
Scientific & Technical. 1990.
[6] Hadini HA, Badaruddin R. Pendugaan Bobot Hidup Kerbau Menggunakan Ukuran Dimensi Tubuh
sebagai Dasar Penentuan Harga di Pulau Kabaena. Jurnal Ilmu dan Teknologi Peternakan Tropis.
2016; 3(2): 16-20.
[7] Badriyah N. Kesesuaian Rumus Schoorl Terhadap Bobot Badan Sapi Peranakan Ongole (P.O).
Jurnal Ilmu Eksata. 2014; 2(2): 99-103.
[8] Riffiandi N, Priyanto R, Nuraini H. Prediction of Live Weight in PO and Pesisir Cattle Using Digital
Image Analysis. Jurnal Ilmu Produksi dan Teknologi Hasil Peternakan. 2015; 3(3):153-156.
[9] Comrie AC. Comparing Neural Networks and Regression Models for Ozone Forecasting. Journal of
the Air & Waste Management Association. 1997; 47(6): 653-663.
[10] Nguyen N, Cripps A. Predicting housing value: A comparison of multiple regression analysis and
artificial neural networks. Journal of Real Estate Research. 2001; 22(3): 313-336.
[11] Parsons TD, Rizzo AA, Buckwalter JG. Backpropagation and Regression: Comparative Utility for
Neuropsychologists. Journal of Clinical and Experimental Neuropsychology. 2004; 26(1): 95-104.
[12] Aggarwal Y, Karan BM, Das BN, Aggarwal T, Sinha RK. Backpropagation ANN-Based Prediction of
Exertional Heat Illness. Journal of Medical Systems. 2007; 31(6): 547-550.
[13] Azmi MSBM, Cob ZC. Breast Cancer Prediction Based on Backpropagation Algorithm. 2010 IEEE
Student Conference on Research and Development (SCOReD). Kuala Lumpur. 2010; 164-168.
[14] Gupta V, Sagale KS. Implementation of Classification System for Brain Cancer Using
Backpropagation Network and MRI. In Engineering (NUiCONE). 2012 Nirma University International
Conference on Engineering (NUiCONE). Ahmedabad. 2012; 1-4.
[15] Malik BA, Naqash A, Bhat GM. Backpropagation Artificial Neural Network for Determination of
Glucose Concentration from Near-Infrared Spectra. 2016 International Conference on Advances in
Computing, Communications and Informatics (ICACCI). Jaipur. 2016; 2688-2691.
[16] Hassan AKI, Abraham A. Modeling Consumer Loan Default Prediction Using Neural Netware. 2013
International Conference on Computing, Electrical and Electronic Engineering (ICCEEE). Khartoum.
2013; 239-243.
[17] Ramadhani I, Rismala R. Prediction of Multi Currency Exchange Rates Using Correlation Analysis and
Backpropagation. 2016 International Conference on ICT For Smart Society (ICISS). Surabaya. 2016;
63-68.
[18] Wang H, Li G, Ma Z, Li X. Image Recognition of Plant Diseases Based on Backpropagation Networks.
2012 5th International Congress on Image and Signal Processing. Chongqing. 2012; 894-900.
[19] Prabowo S, Rusman, Panjono. Carcass Weight Predictor Variables of Live Simmental Crossbreed
Ongole Bulls. Bulletin Peternakan. 2012; 36(2): 95-102.
[20] Francis J, Sibanda S, Hermansen JE, kristensen K. Estimating Body Weight of Cattle Using Linear
Body Measurements. Zimbabwe Veterinary Journal. 2002; 33(1): 15-21.
[21] Fausett L. Fundamentals of Neural Networks: Architectures, Algorithms and Applications. Prentice-
Hall, New Jersey, USA. 1994.
[22] Wythoff BJ. Backpropagation Neural Networks: A Tutorial. Chemometrics and Intelligent Laboratory
Systems. 1993; 18(2): 115-155.

A Model to Predict The Live Bodyweight of Livestock Using Back-propagation Algorithm

More Related Content

More from TELKOMNIKA JOURNAL (20)

Recently uploaded (20)

A Model to Predict The Live Bodyweight of Livestock Using Back-propagation Algorithm