Comparing the Performance of Different Classifiers for Posture Detection - Archive ouverte HAL
Communication Dans Un Congrès Année : 2021

Comparing the Performance of Different Classifiers for Posture Detection

Sagar Suresh Kumar
  • Fonction : Auteur
Kia Dashtipour
  • Fonction : Auteur
Jawad Ahmad
  • Fonction : Auteur
Khaled Assaleh
  • Fonction : Auteur
Kamran Arshad
  • Fonction : Auteur
Muhammad Ali Imran
  • Fonction : Auteur
Qammer Abbai
  • Fonction : Auteur
Wasim Ahmad
  • Fonction : Auteur

Résumé

Human Posture Classification(HPC) is used in many fields such as as human computer interfacing, security surveillance, rehabilitation, remote monitoring, and so on. This paper compares the performance of different classifiers in the detection of 3 postures, sitting, standing, and lying down, which was recorded using Microsoft Kinect cameras. The Machine Learning classifiers used included the Support Vector Classifier, Naive Bayes, Logistic Regression, K-Nearest Neighbours, and Random Forests. The Deep Learning ones included the standard Multi-Layer Perceptron, Convolutional Neural Networks(CNN), and Long Short Term Memory Networks(LSTM). It was observed that Deep Learning methods outperformed the former and that the one-dimensional CNN performed the best with an accuracy of 93.45%.
Fichier principal
Vignette du fichier
Body_Detection_BodyNet_Sagar (2).pdf (170.78 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03381753 , version 1 (17-10-2021)

Identifiants

  • HAL Id : hal-03381753 , version 1

Citer

Sagar Suresh Kumar, Kia Dashtipour, Mandar Gogate, Jawad Ahmad, Khaled Assaleh, et al.. Comparing the Performance of Different Classifiers for Posture Detection. EAI, Oct 2021, Glasgow, France. ⟨hal-03381753⟩
68 Consultations
254 Téléchargements

Partager

More