Write your message

Search published articles


Body Mass Index Classification based on Facial Features Using Machine Learning Algorithms for Utilizing in Telemedicine
Mahsa Heidari, Farshid Babapour Mofrad, Hamed Shah-Hosseini,
Volume 10, Issue 1 (7-2022)
Abstract
Objectives: Given the benefits of controlling Body mass index (BMI) on the quality of life, BMI classification based on facial features can be used for developing telemedicine systems and eliminate the limitations of existing measuring tools especially for paralyzed people, that enable physicians to help people online when faced with situations like the COVID-19 pandemic.
Methods: In this study, new features and some previous-work features were extracted from face photos of white, black and Asian people, ages 18 to 81, with normal and overweight BMI. Faces were evaluated in three different steps. First, all faces were considered as one group. Second, they were divided into elliptical, round and square shape groups and third, they were separated based on gender. Then for each step, the performances of Random Forest (RF) and Support Vector Machine (SVM) were evaluated with all of the facial features and with selected features based on Pearson correlation coefficient. Matlab R2015b was used for implementation.
Results: The results revealed that features with higher correlation improved the accuracy of both algorithms. RF best performance using highly correlated features for 97 women and 92 men was in women and square-face groups (91.75% and 87.30% respectively), and SVM best performance was in women group (94.84%), square-face and round-face groups (84.12% and 84% respectively).
Conclusion: Accuracy of BMI classification based on facial features can be improved by categorizing faces into shapes and gender, and selecting appropriate features. The findings can be used for performance enhancement of telemedicine applications, especially for helping the differently-abled.

Evaluation of Muscle Activity when using the Passive Assistive Arm
Abdollah Vahedi, Iman Dianat,
Volume 12, Issue 1 (4-2024)
Abstract
Objectives: Despite the increasing trend of automation and mechanization in the industry, many workers are exposed to high physical workloads, repetitive motions, and unusual body postures. In this regard, assistive technology (AT) is a relatively new and practical solution. This study was conducted to design an assistive arm according to ergonomic principles and investigate its effect on the electrical activity of shoulder muscles.
Methods: This research was fundamental in its approach, using an experimental intervention method. The investigated samples included students studying in the Tabriz University of Medical Sciences, Faculty of Health in 2021, of which 12 participated in the study, half of whom were female and half were male. A prototype of a passive assistive arm was first designed. The electrical activity of muscles was then evaluated at two work heights and two tasks in a simulated workstation with and without the use of an assist arm. The data were analyzed at a significance level of 0.05 using SPSS26 software.
Results: The designed assistive arm reduced the electrical activity of the muscles in the tested heights and tasks, and among the six investigated muscles, the activity of the trapezius and anterior deltoid muscles decreased the most.
Conclusion: According to the results, the designed assistive arm reduces the electrical activity of the shoulder muscles and differentially affects different tasks and work heights. The results generally indicate that the use of an assistive arm can be an effective intervention for overhead tasks.

Page 1 from 1     

© 2025 CC BY-NC 4.0 | Iranian Journal of Ergonomics

Designed & Developed by : Yektaweb |