Artificial neural networks to predict 3D spinal posture in reaching and lifting activities; Applications in biomechanical models

Gholipour, A.; Arjmand, Navid

doi:10.1016/j.jbiomech.2016.07.008

Cited by 41 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ANN have been used in various applications in the field of ergonomics (Brindisi & Concilio, 2008;Gholipour & Arjmand, 2016;Lerspalungsanti, Albers, Ott, & Düser, 2015). An ANN model has been applied to predict the automobile seat comfort (Quigley, Southall, Freer, Moody, & Porter, 2001).…”

mentioning

confidence: 99%

Predicting aircraft seat comfort using an artificial neural network

Zhao

Miller³

et al. 2018

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

Aircraft seat pitch is one of the most important factors affecting passengers ability to sit comfortably for a longer time on the plane. The purpose of this study was to illustrate the association between different seat pitches and overall comfort index, and seat‐interface pressure variables as well as try to predict aircraft seat comfort. Through an experimental study, 11 subjects (age, 26.3 ± 1.6; height, 169.8 ± 8.5; body mass, 65.1 ± 15.6) rated five different seat pitch settings (55 examples, 11 participants and five scenarios). Descriptive statistics, together with one‐way analysis of variance were used to determine which of the metrics could be used to distinguish the overall comfort index. The results show that overall comfort index was statistically significant (p < 0.05) between different seat pitches, but there was no statistically significant difference (p > 0.05) in interface pressure variables. In addition, a multilayer feed forward neural network with one hidden layer was proposed with the help of Matlab Neural Network Toolbox. The model explained 99% of the variance in overall comfort index with the root mean square error (RMSE) of 0.12551. The remainder of the total data was used for validation purposes; the correlation is r = 0.775, p < 0.01, and the RMSE is 1.21031. That suggests this model has a significant relationship between the actual and predicted overall comfort index.

show abstract

mentioning

confidence: 99%

Predicting aircraft seat comfort using an artificial neural network

Zhao

Miller³

et al. 2018

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

show abstract

“…These two devices are known for their accuracy and reliability on measurements of kinematic variables, but they are difficult to introduce in a workplace setting [11,22,[33][34][35]. Continuous monitoring of a working site could be obtained through the adoption of wearable motion capture systems that are suitable for outdoor motion analysis [2,4,9,10,17,[36][37][38][39]. Wearable devices, like inertial measurement units (IMUs), represent the most suitable technologic solution for gathering reliable measurements of kinematic parameters and performing motion analysis in a real manufacturing scenario.…”

Section: Introductionmentioning

confidence: 99%

“…Estimating biomechanical risks in MMH tasks through IMUs [4,37,39] allows for the design of setups that are not bulky and that suitable for each working activity. In 2016, Gholipour and colleagues assessed spinal posture during lifting tasks through three inertial sensors placed on pelvis and trunk segments [38]. In 2017, Yan and colleagues designed a small setup to analyze the working postures of construction workers in real time [4].…”

Section: Introductionmentioning

confidence: 99%

“…The machine learning algorithm allows for an automatic recognition of dangerous situations in several fields, such as rehabilitation and ergonomics [44][45][46][47][48][49], as well as the improvement of the adaptability of prosthetic lower limbs, as in a study by study Sun et al [50]. Thus, hazard lifting and fall risk could be immediately identified, thus increasing the safety on working places [1,38]. In 2019, Antwi-Afari and colleagues evaluated working activity recognition through four supervised machine-learning classifiers that were fed with wearable insole pressure data [51].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Measuring Biomechanical Risk in Lifting Load Tasks Through Wearable System and Machine-Learning Approach

Conforti

Mileti

Prete

et al. 2020

Sensors

View full text Add to dashboard Cite

Ergonomics evaluation through measurements of biomechanical parameters in real time has a great potential in reducing non-fatal occupational injuries, such as work-related musculoskeletal disorders. Assuming a correct posture guarantees the avoidance of high stress on the back and on the lower extremities, while an incorrect posture increases spinal stress. Here, we propose a solution for the recognition of postural patterns through wearable sensors and machine-learning algorithms fed with kinematic data. Twenty-six healthy subjects equipped with eight wireless inertial measurement units (IMUs) performed manual material handling tasks, such as lifting and releasing small loads, with two postural patterns: correctly and incorrectly. Measurements of kinematic parameters, such as the range of motion of lower limb and lumbosacral joints, along with the displacement of the trunk with respect to the pelvis, were estimated from IMU measurements through a biomechanical model. Statistical differences were found for all kinematic parameters between the correct and the incorrect postures (p < 0.01). Moreover, with the weight increase of load in the lifting task, changes in hip and trunk kinematics were observed (p < 0.01). To automatically identify the two postures, a supervised machine-learning algorithm, a support vector machine, was trained, and an accuracy of 99.4% (specificity of 100%) was reached by using the measurements of all kinematic parameters as features. Meanwhile, an accuracy of 76.9% (specificity of 76.9%) was reached by using the measurements of kinematic parameters related to the trunk body segment.

show abstract

“…Various researchers have employed methods which include experimental, statistical, and analytical approach in posture prediction of human with various degrees of freedom [3][4][5][6][7][8][9][10][11][12][13] for modeling. Inverse dynamics [3] and image processing tools [4] are also used by various researchers to predict posture and optimization using GA [9][10][11], ANN [15], MOO [16][17][18][19][20][21][22][23] to attain the posture prediction of human.…”

Section: Introductionmentioning

confidence: 99%

Posture prediction and optimization for a manual assembly operation involving lifting of weights

Rout

Dash

Dhupal

2020

Int. J. Simul. Multidisci. Des. Optim.

View full text Add to dashboard Cite

The present work combines ergonomics with the posture prediction in the assembly process to avoid musculoskeletal issues of human operator. For improved productivity the operator should be in a better work environment and in sound health. The purpose of this paper is to provide a different perspective to avoid ergonomic risk factors in manual assembly. Here, a human is modeled as 20-DOF as modeled in robotic analysis and simulated in a virtual environment. In the present study, two objective cost functions i.e. joint discomfort function and energy expenditure function have been employed for evaluating the optimized posture. For posture prediction, a combined multi-objective optimization (MOO) method is used and the objective cost functions are minimized i.e. less joint discomfort and less energy in MOO method required to do the manual assembly operation and consequently, the results are compared and finally the movements are tested using REBA technique.

show abstract

Artificial neural networks to predict 3D spinal posture in reaching and lifting activities; Applications in biomechanical models

Cited by 41 publications

References 23 publications

Predicting aircraft seat comfort using an artificial neural network

Predicting aircraft seat comfort using an artificial neural network

Measuring Biomechanical Risk in Lifting Load Tasks Through Wearable System and Machine-Learning Approach

Posture prediction and optimization for a manual assembly operation involving lifting of weights

Contact Info

Product

Resources

About