• Home
  • Search
  • Human Posture Detection Using Image Augmentation and Hyperparameter-Optimized Transfer Learning Algorithms
  • Open Access IconOpen Access
  • Cite Icon44
  • https://doi.org/10.3390/app121910156Copy DOI Icon

Human Posture Detection Using Image Augmentation and Hyperparameter-Optimized Transfer Learning Algorithms

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

With the advancement in pose estimation techniques, human posture detection recently received considerable attention in many applications, including ergonomics and healthcare. When using neural network models, overfitting and poor performance are prevalent issues. Recently, convolutional neural networks (CNNs) were successfully used for human posture recognition from human images due to their superior multiscale high-level visual representations over hand-engineering low-level characteristics. However, calculating millions of parameters in a deep CNN requires a significant number of annotated examples, which prohibits many deep CNNs such as AlexNet and VGG16 from being used on issues with minimal training data. We propose a new three-phase model for decision support that integrates CNN transfer learning, image data augmentation, and hyperparameter optimization (HPO) to address this problem. The model is used as part of a new decision support framework for the optimization of hyperparameters for AlexNet, VGG16, CNN, and multilayer perceptron (MLP) models for accomplishing optimal classification results. The AlexNet and VGG16 transfer learning algorithms with HPO are used for human posture detection, while CNN and Multilayer Perceptron (MLP) were used as standard classifiers for contrast. The HPO methods are essential for machine learning and deep learning algorithms because they directly influence the behaviors of training algorithms and have a major impact on the performance of machine learning and deep learning models. We used an image data augmentation technique to increase the number of images to be used for model training to reduce model overfitting and improve classification performance using the AlexNet, VGG16, CNN, and MLP models. The optimal combination of hyperparameters was found for the four models using a random-based search strategy. The MPII human posture datasets were used to test the proposed approach. The proposed models achieved an accuracy of 91.2% using AlexNet, 90.2% using VGG16, 87.5% using CNN, and 89.9% using MLP. The study is the first HPO study executed on the MPII human pose dataset.

Loading PDF

Similar Papers
  • Research Article
  • Citations1

Convolutional and hybrid neural network for cluster membership

  • Jun 04, 2024
  • Chinese Journal of Physics
  • Yasuhiro Hashimoto +1
  • Research Article
  • Citations59

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

  • Apr 18, 2023
  • Atmospheric Pollution Research
  • Mohammad Ehteram +3
  • Research Article
  • Citations25

Optimization of horizontal axis wind turbine performance with the dimpled blades by using CNN and MLP models

  • Mar 21, 2023
  • Ocean Engineering
  • Ahmad Abbaskhah +3
  • Research Article
  • Citations8

Hybrid convolutional neural networks-support vector machine classifier with dropout for Javanese character recognition

  • Apr 01, 2023
  • TELKOMNIKA (Telecommunication Computing Electronics and Control)
  • Diyah Utami Kusumaning Putri +2
  • Research Article
  • Citations3

Comparative Analysis of MLP, CNN, and RNN Models in Automatic Speech Recognition: Dissecting Performance Metric

  • Jan 08, 2024
  • Buletin Ilmiah Sarjana Teknik Elektro
  • Abraham K S Lenson +1
  • PDF
  • Research Article
  • Citations25

Medicine Expenditure Prediction via a Variance- Based Generative Adversarial Network

  • Jan 01, 2020
  • IEEE Access
  • Shruti Kaushik +4
  • Peer Review Report

Editor's evaluation: Development and evaluation of a live birth prediction model for evaluating human blastocysts from a retrospective study

  • Dec 12, 2022
  • Larisa V Suturina
  • Peer Review Report

Decision letter: Development and evaluation of a live birth prediction model for evaluating human blastocysts from a retrospective study

  • Dec 12, 2022
  • Larisa V Suturina +1
  • PDF
  • Research Article
  • Citations20

Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network

  • Apr 09, 2020
  • Sensors (Basel, Switzerland)
  • Jie Li +3
  • Research Article
  • Citations20

Prediction of the fruit development stage of sweet pepper (Capsicum annum var. annuum) by an ensemble model of convolutional and multilayer perceptron

  • Sep 04, 2021
  • Biosystems Engineering
  • Taewon Moon +2
  • Research Article
  • Citations4

Impact of Data Augmentation Techniques on the Implementation of a Combination Model of Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) for the Detection of Diseases in Rice Plants

  • Apr 08, 2023
  • Journal of Scientific Research, Education, and Technology (JSRET)
  • Mohamad Firdaus +2
  • Research Article

Levering machine learning to distinguish between optimal and suboptimal basketball shooting forms

  • Jan 01, 2025
  • Journal of Emerging Investigators
  • Hrishikesh Deosthali +1
  • Research Article
  • Citations3

Modeling ring current proton distribution using MLP, CNN, LSTM, and transformer networks

  • Oct 01, 2025
  • Frontiers in Astronomy and Space Sciences
  • Jinxing Li +8
  • Conference Article
  • Citations5

A Convolutional Neural Network Based Classification Approach for Breast Cancer Detection

  • Apr 11, 2023
  • Md Harun Or Rashid +5
  • Addendum
  • Citations3

RETRACTED: DL-SCA: An deep learning based approach for intra-class CutMix data augmentation

  • Jan 15, 2024
  • Physical Communication
  • Weiguang Liu
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.