PMID- 34066410
OWN - NLM
STAT- MEDLINE
DCOM- 20210604
LR  - 20210605
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 21
IP  - 9
DP  - 2021 May 6
TI  - Pig Weight and Body Size Estimation Using a Multiple Output Regression 
      Convolutional Neural Network: A Fast and Fully Automatic Method.
LID - 10.3390/s21093218 [doi]
LID - 3218
AB  - Pig weight and body size are important indicators for producers. Due to the 
      increasing scale of pig farms, it is increasingly difficult for farmers to 
      quickly and automatically obtain pig weight and body size. Due to this problem, 
      we focused on a multiple output regression convolutional neural network (CNN) to 
      estimate pig weight and body size. DenseNet201, ResNet152 V2, Xception and 
      MobileNet V2 were modified into multiple output regression CNNs and trained on 
      modeling data. By comparing the estimated performance of each model on test data, 
      modified Xception was selected as the optimal estimation model. Based on pig 
      height, body shape, and contour, the mean absolute error (MAE) of the model to 
      estimate body weight (BW), shoulder width (SW), shoulder height (SH), hip width 
      (HW), hip width (HH), and body length (BL) were 1.16 kg, 0.33 cm, 1.23 cm, 0.38 
      cm, 0.66 cm, and 0.75 cm, respectively. The coefficient of determination (R(2)) 
      value between the estimated and measured results was in the range of 
      0.9879-0.9973. Combined with the LabVIEW software development platform, this 
      method can estimate pig weight and body size accurately, quickly, and 
      automatically. This work contributes to the automatic management of pig farms.
FAU - Zhang, Jianlong
AU  - Zhang J
AUID- ORCID: 0000-0001-9930-2639
AD  - College of Water Resources & Civil Engineering, China Agricultural University, 
      Beijing 100083, China.
AD  - Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry 
      of Agriculture and Rural Affairs, Beijing 100083, China.
FAU - Zhuang, Yanrong
AU  - Zhuang Y
AD  - College of Water Resources & Civil Engineering, China Agricultural University, 
      Beijing 100083, China.
AD  - Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry 
      of Agriculture and Rural Affairs, Beijing 100083, China.
FAU - Ji, Hengyi
AU  - Ji H
AD  - College of Water Resources & Civil Engineering, China Agricultural University, 
      Beijing 100083, China.
AD  - Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry 
      of Agriculture and Rural Affairs, Beijing 100083, China.
FAU - Teng, Guanghui
AU  - Teng G
AD  - College of Water Resources & Civil Engineering, China Agricultural University, 
      Beijing 100083, China.
AD  - Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry 
      of Agriculture and Rural Affairs, Beijing 100083, China.
AD  - Beijing Engineering Research Center on Animal Healthy Environment, Beijing 
      100083, China.
LA  - eng
GR  - 2016YFD0700204/the National Key Research and Development Program of China/
PT  - Journal Article
DEP - 20210506
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - Animals
MH  - Body Height
MH  - Body Weight
MH  - *Deep Learning
MH  - Humans
MH  - Neural Networks, Computer
MH  - Research Design
MH  - Swine
PMC - PMC8124602
OTO - NOTNLM
OT  - body size
OT  - convolutional neural network
OT  - deep learning
OT  - estimation
OT  - pig weight
COIS- The authors declare no conflict of interest.
EDAT- 2021/06/03 06:00
MHDA- 2021/06/05 06:00
PMCR- 2021/05/06
CRDT- 2021/06/02 01:16
PHST- 2021/03/01 00:00 [received]
PHST- 2021/04/23 00:00 [revised]
PHST- 2021/04/27 00:00 [accepted]
PHST- 2021/06/02 01:16 [entrez]
PHST- 2021/06/03 06:00 [pubmed]
PHST- 2021/06/05 06:00 [medline]
PHST- 2021/05/06 00:00 [pmc-release]
AID - s21093218 [pii]
AID - sensors-21-03218 [pii]
AID - 10.3390/s21093218 [doi]
PST - epublish
SO  - Sensors (Basel). 2021 May 6;21(9):3218. doi: 10.3390/s21093218.