Dataset Information

Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance.

ABSTRACT: The distinction between subject-dependent and subject-independent performance is ubiquitous in the human activity recognition (HAR) literature. We assess whether HAR models really do achieve better subject-dependent performance than subject-independent performance, whether a model trained with data from many users achieves better subject-independent performance than one trained with data from a single person, and whether one trained with data from a single specific target user performs better for that user than one trained with data from many. To those ends, we compare four popular machine learning algorithms' subject-dependent and subject-independent performances across eight datasets using three different personalisation-generalisation approaches, which we term person-independent models (PIMs), person-specific models (PSMs), and ensembles of PSMs (EPSMs). We further consider three different ways to construct such an ensemble: unweighted, ? -weighted, and baseline-feature-weighted. Our analysis shows that PSMs outperform PIMs by 43.5% in terms of their subject-dependent performances, whereas PIMs outperform PSMs by 55.9% and ? -weighted EPSMs-the best-performing EPSM type-by 16.4% in terms of the subject-independent performance.

SUBMITTER: Scheurer S

PROVIDER: S-EPMC7374316 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance.

Scheurer Sebastian S Tedesco Salvatore S O'Flynn Brendan B Brown Kenneth N KN

Sensors (Basel, Switzerland) 20200629 13

The distinction between subject-dependent and subject-independent performance is ubiquitous in the human activity recognition (HAR) literature. We assess whether HAR models really do achieve better subject-dependent performance than subject-independent performance, whether a model trained with data from many users achieves better subject-independent performance than one trained with data from a single person, and whether one trained with data from a single specific target user performs better fo ...[more]

PMID: 32610614

Similar Datasets

Project description:Subject-specific musculoskeletal modeling can be applied to study musculoskeletal disorders, allowing inclusion of personalized anatomy and properties. Independent of the tools used for model creation, there are unavoidable uncertainties associated with parameter identification, whose effect on model predictions is still not fully understood. The aim of the present study was to analyze the sensitivity of subject-specific model predictions (i.e., joint angles, joint moments, muscle and joint contact forces) during walking to the uncertainties in the identification of body landmark positions, maximum muscle tension and musculotendon geometry. To this aim, we created an MRI-based musculoskeletal model of the lower limbs, defined as a 7-segment, 10-degree-of-freedom articulated linkage, actuated by 84 musculotendon units. We then performed a Monte-Carlo probabilistic analysis perturbing model parameters according to their uncertainty, and solving a typical inverse dynamics and static optimization problem using 500 models that included the different sets of perturbed variable values. Model creation and gait simulations were performed by using freely available software that we developed to standardize the process of model creation, integrate with OpenSim and create probabilistic simulations of movement. The uncertainties in input variables had a moderate effect on model predictions, as muscle and joint contact forces showed maximum standard deviation of 0.3 times body-weight and maximum range of 2.1 times body-weight. In addition, the output variables significantly correlated with few input variables (up to 7 out of 312) across the gait cycle, including the geometry definition of larger muscles and the maximum muscle tension in limited gait portions. Although we found subject-specific models not markedly sensitive to parameter identification, researchers should be aware of the model precision in relation to the intended application. In fact, force predictions could be affected by an uncertainty in the same order of magnitude of its value, although this condition has low probability to occur.

Project description:Finite element (FE) models have been widely used to investigate knee joint biomechanics. Most of these models have been developed to study adult knees, neglecting pediatric populations. In this study, an atlas-based approach was employed to develop subject-specific FE models of the knee for eight typically developing pediatric individuals. Initially, validation simulations were performed at four passive tibiofemoral joint (TFJ) flexion angles, and the resulting TFJ and patellofemoral joint (PFJ) kinematics were compared to corresponding patient-matched measurements derived from magnetic resonance imaging (MRI). A neuromusculoskeletal-(NMSK)-FE pipeline was then used to simulate knee biomechanics during stance phase of walking gait for each participant to evaluate model simulation of a common motor task. Validation simulations demonstrated minimal error and strong correlations between FE-predicted and MRI-measured TFJ and PFJ kinematics (ensemble average of root mean square errors < 5 mm for translations and < 4.1° for rotations). The FE-predicted kinematics were strongly correlated with published reports (ensemble average of Pearson's correlation coefficients (ρ) > 0.9 for translations and ρ > 0.8 for rotations), except for TFJ mediolateral translation and abduction/adduction rotation. For walking gait, NMSK-FE model-predicted knee kinematics, contact areas, and contact pressures were consistent with experimental reports from literature. The strong agreement between model predictions and experimental reports underscores the capability of sequentially linked NMSK-FE models to accurately predict pediatric knee kinematics, as well as complex contact pressure distributions across the TFJ articulations. These models hold promise as effective tools for parametric analyses, population-based clinical studies, and enhancing our understanding of various pediatric knee injury mechanisms. They also support intervention design and prediction of surgical outcomes in pediatric populations.

Dataset Information

Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance.

Publications

Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets