The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
젖소 행동 모니터링은 젖소 복지의 현재 상태를 이해하고 질병 및 발정의 조기 발견과 같은 목초지 관리를 위한 효과적인 계획 전략을 개발하는 데 중요합니다. 가장 강력하고 비용 효율적인 방법 중 하나는 소에 부착된 관성 센서의 시계열 데이터를 분석하는 신경망 기반 모니터링 시스템입니다. 이 방법의 경우 신경망 모델 개발에 있어서 교육 데이터의 질과 양을 향상시키는 것이 중요한 과제이며, 이를 위해서는 다양한 현실적 조건을 포괄할 수 있는 데이터를 수집하고 이에 라벨을 부여해야 합니다. 결과적으로 데이터 수집 비용이 상당히 높습니다. 본 연구에서는 교육 데이터 수집 과정에서 발생하는 두 가지 주요 품질 문제를 해결하기 위한 데이터 증대 방법을 제안합니다. 하나는 티칭 데이터 수집의 어려움과 무작위성이고, 다른 하나는 실제 작동 중 센서 위치가 변경된다는 점입니다. 제안된 방법은 측정된 가속도 데이터로부터 칼라형 센서 장치의 다양한 회전 상태를 계산적으로 에뮬레이션할 수 있습니다. 또한 덜 자주 발생하는 작업에 대한 데이터를 생성합니다. 검증 결과, 장단기 기억(LSTM) 네트워크를 통한 학습 기반 98가지 주요 행동(먹기, 걷기, 마시기, 반추, 휴식)에 대해 평균 60.48% 이상의 정확도로 상당히 높은 추정 성능을 보여주었다. 최소 2.52%로 부족했던 데이터 보강을 하지 않은 추정 성능과 비교하면 다양한 행위에 대한 인식률이 37.05~30pt 향상되었다. 또한 다양한 회전 간격의 비교를 조사하고 정확도 성능 분석을 바탕으로 XNUMX도 간격을 선택했습니다. 결론적으로, 제안된 데이터 확장 방법은 신경망 모델을 통한 젖소 행동 추정의 정확도를 향상시킬 수 있다. 또한, 머신러닝을 위한 교육 데이터 수집 비용을 대폭 절감하는 데 기여하고 새로운 연구의 기회를 많이 열어줍니다.
Chao LI
Tokyo Institute of Technology
Korkut Kaan TOKGOZ
Tokyo Institute of Technology
Ayuka OKUMURA
Shinshu University
Jim BARTELS
Tokyo Institute of Technology
Kazuhiro TODA
Information Services International-Dentsu, Ltd.
Hiroaki MATSUSHIMA
Information Services International-Dentsu, Ltd.
Takumi OHASHI
Tokyo Institute of Technology
Ken-ichi TAKEDA
Shinshu University
Hiroyuki ITO
Tokyo Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Chao LI, Korkut Kaan TOKGOZ, Ayuka OKUMURA, Jim BARTELS, Kazuhiro TODA, Hiroaki MATSUSHIMA, Takumi OHASHI, Ken-ichi TAKEDA, Hiroyuki ITO, "A Data Augmentation Method for Cow Behavior Estimation Systems Using 3-Axis Acceleration Data and Neural Network Technology" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 4, pp. 655-663, April 2022, doi: 10.1587/transfun.2021SMP0003.
Abstract: Cow behavior monitoring is critical for understanding the current state of cow welfare and developing an effective planning strategy for pasture management, such as early detection of disease and estrus. One of the most powerful and cost-effective methods is a neural-network-based monitoring system that analyzes time series data from inertial sensors attached to cows. For this method, a significant challenge is to improve the quality and quantity of teaching data in the development of neural network models, which requires us to collect data that can cover various realistic conditions and assign labels to them. As a result, the cost of data collection is significantly high. This work proposes a data augmentation method to solve two major quality problems in the collection process of teaching data. One is the difficulty and randomicity of teaching data acquisition and the other is the sensor position changes during actual operation. The proposed method can computationally emulate different rotating states of the collar-type sensor device from the measured acceleration data. Furthermore, it generates data for actions that occur less frequently. The verification results showed significantly higher estimation performance with an average accuracy of over 98% for five main behaviors (feeding, walking, drinking, rumination, and resting) based on learning with long short-term memory (LSTM) network. Compared with the estimation performance without data augmentation, which was insufficient with a minimum of 60.48%, the recognition rate was improved by 2.52-37.05pt for various behaviors. In addition, comparison of different rotation intervals was investigated and a 30-degree increment was selected based on the accuracy performances analysis. In conclusion, the proposed data expansion method can improve the accuracy in cow behavior estimation by a neural network model. Moreover, it contributes to a significant reduction of the teaching data collection cost for machine learning and opens many opportunities for new research.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021SMP0003/_p
부
@ARTICLE{e105-a_4_655,
author={Chao LI, Korkut Kaan TOKGOZ, Ayuka OKUMURA, Jim BARTELS, Kazuhiro TODA, Hiroaki MATSUSHIMA, Takumi OHASHI, Ken-ichi TAKEDA, Hiroyuki ITO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Data Augmentation Method for Cow Behavior Estimation Systems Using 3-Axis Acceleration Data and Neural Network Technology},
year={2022},
volume={E105-A},
number={4},
pages={655-663},
abstract={Cow behavior monitoring is critical for understanding the current state of cow welfare and developing an effective planning strategy for pasture management, such as early detection of disease and estrus. One of the most powerful and cost-effective methods is a neural-network-based monitoring system that analyzes time series data from inertial sensors attached to cows. For this method, a significant challenge is to improve the quality and quantity of teaching data in the development of neural network models, which requires us to collect data that can cover various realistic conditions and assign labels to them. As a result, the cost of data collection is significantly high. This work proposes a data augmentation method to solve two major quality problems in the collection process of teaching data. One is the difficulty and randomicity of teaching data acquisition and the other is the sensor position changes during actual operation. The proposed method can computationally emulate different rotating states of the collar-type sensor device from the measured acceleration data. Furthermore, it generates data for actions that occur less frequently. The verification results showed significantly higher estimation performance with an average accuracy of over 98% for five main behaviors (feeding, walking, drinking, rumination, and resting) based on learning with long short-term memory (LSTM) network. Compared with the estimation performance without data augmentation, which was insufficient with a minimum of 60.48%, the recognition rate was improved by 2.52-37.05pt for various behaviors. In addition, comparison of different rotation intervals was investigated and a 30-degree increment was selected based on the accuracy performances analysis. In conclusion, the proposed data expansion method can improve the accuracy in cow behavior estimation by a neural network model. Moreover, it contributes to a significant reduction of the teaching data collection cost for machine learning and opens many opportunities for new research.},
keywords={},
doi={10.1587/transfun.2021SMP0003},
ISSN={1745-1337},
month={April},}
부
TY - JOUR
TI - A Data Augmentation Method for Cow Behavior Estimation Systems Using 3-Axis Acceleration Data and Neural Network Technology
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 655
EP - 663
AU - Chao LI
AU - Korkut Kaan TOKGOZ
AU - Ayuka OKUMURA
AU - Jim BARTELS
AU - Kazuhiro TODA
AU - Hiroaki MATSUSHIMA
AU - Takumi OHASHI
AU - Ken-ichi TAKEDA
AU - Hiroyuki ITO
PY - 2022
DO - 10.1587/transfun.2021SMP0003
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2022
AB - Cow behavior monitoring is critical for understanding the current state of cow welfare and developing an effective planning strategy for pasture management, such as early detection of disease and estrus. One of the most powerful and cost-effective methods is a neural-network-based monitoring system that analyzes time series data from inertial sensors attached to cows. For this method, a significant challenge is to improve the quality and quantity of teaching data in the development of neural network models, which requires us to collect data that can cover various realistic conditions and assign labels to them. As a result, the cost of data collection is significantly high. This work proposes a data augmentation method to solve two major quality problems in the collection process of teaching data. One is the difficulty and randomicity of teaching data acquisition and the other is the sensor position changes during actual operation. The proposed method can computationally emulate different rotating states of the collar-type sensor device from the measured acceleration data. Furthermore, it generates data for actions that occur less frequently. The verification results showed significantly higher estimation performance with an average accuracy of over 98% for five main behaviors (feeding, walking, drinking, rumination, and resting) based on learning with long short-term memory (LSTM) network. Compared with the estimation performance without data augmentation, which was insufficient with a minimum of 60.48%, the recognition rate was improved by 2.52-37.05pt for various behaviors. In addition, comparison of different rotation intervals was investigated and a 30-degree increment was selected based on the accuracy performances analysis. In conclusion, the proposed data expansion method can improve the accuracy in cow behavior estimation by a neural network model. Moreover, it contributes to a significant reduction of the teaching data collection cost for machine learning and opens many opportunities for new research.
ER -