An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors

Dogs and cats tend to show their conditions and desires through their behaviors. In companion animal behavior recognition, behavior data obtained by attaching a wearable device or sensor to a dog’s body are mostly used. However, differences occur in the output values of the sensor when the dog moves...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hye-Jin Lee, Sun-Young Ihm, So-Hyun Park, Young-Ho Park
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/62b75da753794be2b0119ae084edaf3d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:62b75da753794be2b0119ae084edaf3d
record_format dspace
spelling oai:doaj.org-article:62b75da753794be2b0119ae084edaf3d2021-11-25T16:43:21ZAn Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors10.3390/app1122110502076-3417https://doaj.org/article/62b75da753794be2b0119ae084edaf3d2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/11050https://doaj.org/toc/2076-3417Dogs and cats tend to show their conditions and desires through their behaviors. In companion animal behavior recognition, behavior data obtained by attaching a wearable device or sensor to a dog’s body are mostly used. However, differences occur in the output values of the sensor when the dog moves violently. A tightly coupled RGB time tensor network (TRT-Net) is proposed that minimizes the loss of spatiotemporal information by reflecting the three components (x-, y-, and z-axes) of the skeleton sequences in the corresponding three channels (red, green, and blue) for the behavioral classification of dogs. This paper introduces the YouTube-C7B dataset consisting of dog behaviors in various environments. Based on a method that visualizes the Conv-layer filters in analyzable feature maps, we add reliability to the results derived by the model. We can identify the joint parts, i.e., those represented as rows of input images showing behaviors, learned by the proposed model mainly for making decisions. Finally, the performance of the proposed method is compared to those of the LSTM, GRU, and RNN models. The experimental results demonstrate that the proposed TRT-Net method classifies dog behaviors more effectively, with improved accuracy and F1 scores of 7.9% and 7.3% over conventional models.Hye-Jin LeeSun-Young IhmSo-Hyun ParkYoung-Ho ParkMDPI AGarticleartificial intelligencedog behaviorsmulti class classificationtensor fusionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 11050, p 11050 (2021)
institution DOAJ
collection DOAJ
language EN
topic artificial intelligence
dog behaviors
multi class classification
tensor fusion
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle artificial intelligence
dog behaviors
multi class classification
tensor fusion
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Hye-Jin Lee
Sun-Young Ihm
So-Hyun Park
Young-Ho Park
An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors
description Dogs and cats tend to show their conditions and desires through their behaviors. In companion animal behavior recognition, behavior data obtained by attaching a wearable device or sensor to a dog’s body are mostly used. However, differences occur in the output values of the sensor when the dog moves violently. A tightly coupled RGB time tensor network (TRT-Net) is proposed that minimizes the loss of spatiotemporal information by reflecting the three components (x-, y-, and z-axes) of the skeleton sequences in the corresponding three channels (red, green, and blue) for the behavioral classification of dogs. This paper introduces the YouTube-C7B dataset consisting of dog behaviors in various environments. Based on a method that visualizes the Conv-layer filters in analyzable feature maps, we add reliability to the results derived by the model. We can identify the joint parts, i.e., those represented as rows of input images showing behaviors, learned by the proposed model mainly for making decisions. Finally, the performance of the proposed method is compared to those of the LSTM, GRU, and RNN models. The experimental results demonstrate that the proposed TRT-Net method classifies dog behaviors more effectively, with improved accuracy and F1 scores of 7.9% and 7.3% over conventional models.
format article
author Hye-Jin Lee
Sun-Young Ihm
So-Hyun Park
Young-Ho Park
author_facet Hye-Jin Lee
Sun-Young Ihm
So-Hyun Park
Young-Ho Park
author_sort Hye-Jin Lee
title An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors
title_short An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors
title_full An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors
title_fullStr An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors
title_full_unstemmed An Analytic Method for Improving the Reliability of Models Based on a Histogram for Prediction of Companion Dogs’ Behaviors
title_sort analytic method for improving the reliability of models based on a histogram for prediction of companion dogs’ behaviors
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/62b75da753794be2b0119ae084edaf3d
work_keys_str_mv AT hyejinlee ananalyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT sunyoungihm ananalyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT sohyunpark ananalyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT younghopark ananalyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT hyejinlee analyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT sunyoungihm analyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT sohyunpark analyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
AT younghopark analyticmethodforimprovingthereliabilityofmodelsbasedonahistogramforpredictionofcompaniondogsbehaviors
_version_ 1718413021385064448