A Comparative Study on Machine Learning Models for Predicting the Behavior of Pet
- 30 September 2024
- journal article
- Published by Korean Institute of Information Technology in The Journal of Korean Institute of Information Technology
- Vol. 22 (9) , 35-41
Abstract
저자의 기존 연구에서는 라벨링 된 4가지의 반려동물 행동 데이터를 통해 3가지 모델을 활용한 행동 예측 결과를 선보였다. 본 연구에서는 기존보다 더 많은 행동 데이터를 라벨링 하고 모델도 다양화 할 수 있음을 선보인다. 이에 따라 본 연구에서 활용하는 행동 데이터는 총 16가지이며, 모델은 총 8가지이다. 연구결과, RF(Random Forest), GBM(Gradient Boosting Machine), KNN(K-nearest neighbor) 순으로 정확도가 높음을 알 수 있었다. 본 연구결과를 통해 기계학습 기반의 분류 모델을 활용한 반려동물의 행동 예측의 가능성을 시사하며, 더 나아가 추후에는 질환 예측도 할 수 있을 것으로 기대한다.Keywords
Funding Information
- Ministry of Science and ICT, South Korea
- Korea Industrial Technology Association (SOS1379)
This publication has 12 references indexed in Scilit:
- A Study on the Artificial Intelligence-based Wearable Sensor Data Pet Behavior AnalysisThe Journal of Korean Institute of Information Technology, 2023
- A Study on the Development of Wearable Products Applied to PetTech Service Using IoT and AI TechnologyJOURNAL OF THE KOREAN SOCIETY DESIGN CULTURE, 2020
- People counting based on head detection combining Adaboost and CNN in crowded surveillance environmentNeurocomputing, 2016
- An Approach of Semantic Web Service Classification Based on Naive Bayes2016
- A Study of Intelligent Recommendation System based on Naive Bayes Text Classification and Collaborative FilteringJournal of Information Management, 2010
- Random ForestsMachine Learning, 2001
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- Ensemble Methods in Machine Learning2000
- Support-vector networksMachine Learning, 1995
- Some methods of speeding up the convergence of iteration methodsUSSR Computational Mathematics and Mathematical Physics, 1964