A Comparison among Different Strategies to Detect Potential Unstable Behaviors in Postural Sway

Andò, B.; Baglio, S.; Graziani, S.; Marletta, Vincenzo; Dibilio, Valeria; Mostile, Giovanni; Zappia, Mario

doi:10.3390/s22197106

Cited by 6 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the time domain approach has provided good performance, to better characterize the postural dynamics frequency content of inertial dynamics has been also investigated [23], [24]. In [25] a comparison among different approaches to detect potential postural instability with a wearable inertial system, is provided. In this study threshold-based algorithms and Neuro-Fuzzy models, both processing time-based features or Discrete-Wavelet-Transform based features, have been compared.…”

Section: A Advancement As Respect the State Of The Artmentioning

confidence: 99%

“…The methodology investigated through this work aims to classify among the following four different postural dynamics: ST, AP, ML and UNST. The first step accomplished towards the achievement of this task was dedicated to estimate the time evolution of the Antero-Posterior and Medio-Lateral displacement (DAP and DML) [25], [33], from the three…”

Section: The Postural Sway Classification Strategymentioning

confidence: 99%

“…Main features considered in this work are summarized in Table I [21]. Such quantities have been selected among others available in the literature, based on: (i) the criterion of easy implementation on embedded systems [25]; (ii) the study presented in [34] to assess the reliability associated to the use of different features, which demonstrated that Maximum Antero-Posterior and Medio-Lateral Displacements, the Confidence Ellipse Area and the Root Mean Square Displacement are the most convenient features.…”

Section: A the Adopted Set Of Featuresmentioning

confidence: 99%

See 2 more Smart Citations

A Neuro-Fuzzy-Based Sensing Approach for the Classification of Emulated Postural Instability

Andò,

Baglio,

Marletta

et al. 2023

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

Technology helps to assess the daily living of frail people and may have a strategic role to detect and prevent falls. In this paper, the task of classifying different classes of postural sway behaviors has been addressed by developing a Neuro-Fuzzy inference approach that is robust against noise. The proposed approach classifies four different postural behaviors namely Stable Standing, Antero-Posterior, Medio-Lateral and Unstable. The strategy exploits data generated by a wearable sensor node, to be positioned on the user chest. A dedicated experimental set-up has been realized to emulate the postural dynamics and generate the dataset. Two novel indices to assess the robustness of the system have been proposed. The first index is a measure of residuals between the predicted and the expected postural status, which equally weights estimations with respect to expected classes. The second metric is a reliability index, which allows for assessing the degree of trust of each estimation performed by the Neuro-Fuzzy inference. Results obtained demonstrate the suitability of the proposed methodology, showing a capability of almost 100% to correctly classify patterns among different allowed classes, with reliability indexes of 97.56% and 98.50% for the training and test patterns, respectively. Also, robustness of the Neuro-Fuzzy classification algorithm against noisy data has been demonstrated.

show abstract

Section: A Advancement As Respect the State Of The Artmentioning

confidence: 99%

Section: The Postural Sway Classification Strategymentioning

confidence: 99%