Cover Image

An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems

Q1

Saved in:
Bibliographic Details
Main Author: Tran, Duc-Nghia
Other Authors: Nguyen, Tu N.
Format: Article
Language:English
Published: IEEE Sensors Journal 2021
Subjects:
monitoring
cow
acceleration
sensor
Online Access:https://ieeexplore.ieee.org/document/9319861
https://dlib.phenikaa-uni.edu.vn/handle/PNK/1736
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-1736
record_format dspace
spelling oai:localhost:PNK-17362022-08-17T05:54:41Z An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems Tran, Duc-Nghia Nguyen, Tu N. Phung, Cong Phi Khanh Tran, Duc-Tan monitoring cow acceleration sensor Q1 Cow behavior recognition systems support the assessment of cows’ condition by providing their behavior information. Accelerometers are particularly suited for a non-invasive solution for the development of these monitoring systems. They are cheap and simple in setting up and providing high-performance recognition when using machine learning algorithms. The activity complexity of animals brings challenges in real context applications because different behaviors may have similar acceleration data. The reason is that they contain similar gestures, for example, feeding and standing. In our previous work, we proposed a cows’ behavior classifier based on leg-mounted acceleration data. The distinguishing of similar behaviors, such as feeding and standing, is limited by the data. This study presents a new efficient cow behavior recognition system based on combining leg-mounted and collar-mounted accelerometers. Significantly, the acceleration data from these two sensors were synchronized. Therefore, we can substantially expand the amount of information for classification purposes. Our approach identifies four cow behaviors: walking, feeding, lying, and standing. Random Forest algorithm with our extracted features (root mean square, standard deviation, and mean) and 16-second data window (a sample/second) offer excellent performance when identifying all concerning behaviors: feeding (0.914 accuracy, 0.884 sensitivity, 0.956 positive predictive value), lying (0.998, 0.996, 1), standing (0.88, 0.928, 0.842), and walking (0.998, 0.996, 0.998). These performances are better than other existing works, especially in our experiments with free-grazing cows. 2021-06-14T06:54:19Z 2021-06-14T06:54:19Z 2021 Article Working Paper https://ieeexplore.ieee.org/document/9319861 https://dlib.phenikaa-uni.edu.vn/handle/PNK/1736 10.1109/JSEN.2021.3051194 en IEEE Sensors Journal
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic monitoring
cow
acceleration
sensor
spellingShingle monitoring
cow
acceleration
sensor
Tran, Duc-Nghia
An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems
description Q1
author2 Nguyen, Tu N.
author_facet Nguyen, Tu N.
Tran, Duc-Nghia
format Article
author Tran, Duc-Nghia
author_sort Tran, Duc-Nghia
title An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems
title_short An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems
title_full An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems
title_fullStr An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems
title_full_unstemmed An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems
title_sort iot-based design using accelerometers in animal behavior recognition systems
publisher IEEE Sensors Journal
publishDate 2021
url https://ieeexplore.ieee.org/document/9319861
https://dlib.phenikaa-uni.edu.vn/handle/PNK/1736
_version_ 1751856295133052928
score 8.891053

Similar Items