Adaptive regression model for synthesizing anthropometric population data

Brolin, Erik; Högberg, Dan; Hanson, Lars; Örtengren, Roland

doi:10.1016/j.ergon.2017.03.008

Cited by 10 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The selection of the manikin family in the verification could have been done differently. It is possible to create digital manikins that would represent the anthropometrics of the physical human performing the tests (Brolin et al, 2017). However, in creating HIRC simulations, a process that considers the variety of all humans is suggested, and in this process the characteristics of the future user of the workstation are not always known.…”

Section: Methods Discussionmentioning

confidence: 99%

Verification of manikin motions in human-industrial robot collaborative simulations

Ore¹,

Castro²,

Hanson³

et al. 2022

IJDH

View full text Add to dashboard Cite

Stefan Gustafsson is a software developer at Industrial Path Solutions. He has a BSc in Mathematics from Gothenburg University. He works on the IPS software as developer and overall release manager, recently focussing his development efforts on adding virtual reality support to the program. His interests include large-scale software development and the C++ programming language, as well as computer graphics.

show abstract

Section: Methods Discussionmentioning

confidence: 99%

Verification of manikin motions in human-industrial robot collaborative simulations

Ore¹,

Castro²,

Hanson³

et al. 2022

IJDH

View full text Add to dashboard Cite

show abstract

“…Therefore, the values for the allowable or "expert" error [30] for each measurement are defined in the standard ISO:7250 [33,34]. Based on the public databases, several works propose linear regression models for the estimation of measurements [35][36][37] and other body characteristics such as skeletal muscle mass [38]. We extend these analyses by focusing specifically on using self-estimated height and weight as input as well as on using the statistical body models.…”

Section: Related Workmentioning

confidence: 99%

Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement

Bartol

Bojanic

Petković

et al. 2022

Sensors

View full text Add to dashboard Cite

We propose a linear regression model for the estimation of human body measurements. The input to the model only consists of the information that a person can self-estimate, such as height and weight. We evaluate our model against the state-of-the-art approaches for body measurement from point clouds and images, demonstrate the comparable performance with the best methods, and even outperform several deep learning models on public datasets. The simplicity of the proposed regression model makes it perfectly suitable as a baseline in addition to the convenience for applications such as the virtual try-on. To improve the repeatability of the results of our baseline and the competing methods, we provide guidelines toward standardized body measurement estimation.

show abstract

“…Utilizing existing anthropometric databases, such as ANSUR [37], users can be virtually fit to a product to assess how well they are spatially accommodated [40]. Statistical modeling can be performed to infer missing data, model correlation between human parameters, and extend the usefulness of the data in practice [41][42][43]. Often, anthropometric data is accompanied by demographic data, which allows modeling for specific user populations, assuming the demographics of the target population are known [44].…”

Section: Modeling Variability With Existing Human Datamentioning

confidence: 99%

Virtual Modeling of User Populations and Formative Design Parameters

Knisely

Vaughn-Cooke

2020

Systems

View full text Add to dashboard Cite

Human variability related to physical, cognitive, socio-demographic, and other factors can contribute to large differences in human performance. Quantifying population heterogeneity can be useful for designers wishing to evaluate design parameters such that a system design is robust to this variability. Comprehensively integrating human variability in the design process poses many challenges, such as limited access to a statistically representative population and limited data collection resources. This paper discusses two virtual population modeling approaches intended to be performed prior to in-person design validation studies to minimize these challenges by: (1) targeting recruitment of representative population strata and (2) reducing the candidate design parameters being validated in the target population. The first approach suggests the use of digital human models, virtual representations of humans that can simulate system interaction to eliminate candidate design parameters. The second approach suggests the use of existing human databases to identify relevant human characteristics for representative recruitment strata in subsequent studies. Two case studies are presented to demonstrate each approach, and the benefits and limitations of each are discussed. This paper demonstrates the benefit of modeling prior to conducting in-person human performance studies to minimize resource burden, which has significant implications on early design stages.

show abstract

Adaptive regression model for synthesizing anthropometric population data

Cited by 10 publications

References 7 publications

Verification of manikin motions in human-industrial robot collaborative simulations

Verification of manikin motions in human-industrial robot collaborative simulations

Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement

Virtual Modeling of User Populations and Formative Design Parameters

Contact Info

Product

Resources

About