Kohonen Neural Network Investigation of the Effects of the Visual, Proprioceptive and Vestibular Systems to Balance in Young Healthy Adult Subjects

Ojie, Oseikhuemen Davis; Saatchi, Reza

doi:10.3390/healthcare9091219

Cited by 7 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous methods are available for assessing balance ability, and among them, the CTSIB evaluates balance performance based on sensory interaction and the time allocated for performing tasks under different sensory conditions. In recent years, research has progressed towards employing instrumented tests that quantitatively evaluate balance using the center of pressure (CoP) variables measured and calculated with a force plate during CTSIB assessments [ 25 , 26 , 27 ]. For instance, a study examined the stance postural control of ambulant children with cerebral palsy, utilizing CoP-derived variables such as velocity, range, and area to compare them with typically developing children [ 28 ].…”

Section: Discussionmentioning

confidence: 99%

Development and Application of a Stability Index Estimation Algorithm Based on Machine Learning for Elderly Balance Ability Diagnosis in Daily Life

Seo

Kim

et al. 2023

Bioengineering

View full text Add to dashboard Cite

Background: The stability index estimation algorithm was derived and applied to develop and implement a balance ability diagnosis system that can be used in daily life. Methods: The system integrated an approach based on sensory function interaction, called the clinical test of sensory interaction with balance. A capacitance and resistance sensing type force mat was fabricated, and a stability index prediction algorithm was developed and applied using the center of pressure variables. The stability index prediction algorithm derived a center of pressure variable for 103 elderly people by Nintendo Wii Balance Board to predict the stability index of the balance system (Biodex SD), and the accuracy of this approach was confirmed. Results: As a result of testing with the test set, the linear regression model confirmed that the r-value ranged between 0.943 and 0.983. To confirm the similarity between the WBB and the flexible force mat, each measured center of pressure value was inputted and calculated in the developed regression model, and the result of the correlation coefficient validation confirmed an r-value of 0.96. Conclusion: The system developed in this study will be applicable to daily life in the home in the form of a floor mat.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and Application of a Stability Index Estimation Algorithm Based on Machine Learning for Elderly Balance Ability Diagnosis in Daily Life

Seo

Kim

et al. 2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…The higher the recall, the more effective the clustering and hence the greater the separation. With the analysis limited to nonempty clusters, the lowest amount of purity is obtained when all the samples converged to one cluster (Ojie & Saatchi, 2021). Similarly, the lowest precision is obtained when all the data samples are present in a single cluster.…”

Section: Clustering Performance Evaluationmentioning

confidence: 99%

“…functionality towards maintaining balance(Ojie & Saatchi, 2021). For example, information of visual cues are provided by the visual system(Assländer et al, 2015); information of the position and movement of the limbs and trunk are provided by the proprioceptive system(Proske & Gandevia, 2012); information of the acceleration of the head and spatial orientation are provided by the vestibular system(Zalewski, 2015).To examine these systems, clinicians commonly use a standstill balance test called the modified clinical test of sensory interaction and balance (mCTSIB)Cohen et al, 2019).…”

mentioning

confidence: 99%

“…The lowest recall is obtained when only one sample is present in the cluster i.e., the recall varies with the number of clusters (Ojie & Saatchi, 2021). In the case of two clusters and equal number of samples, the lowest attainable value for purity, recall and precision is 0.5 respectively(Ojie & Saatchi, 2021). The formulae for these measures are stated in Equations (8.2) to(8.5).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Computerised accelerometric machine learning techniques and statistical developments for human balance analysis

Ojie¹

View full text Add to dashboard Cite

Balance maintenance is crucial to participating in the activities of daily life. Balance is often considered as the ability to maintain the centre of mass (COM) position within the base of support. Primarily, to maintain balance, reliance is placed on the balance related sensory systems i.e., the visual, proprioceptive and vestibular. Several factors can affect a person’s balance such as neurological diseases, ageing, medication and obesity etc. To gain insight into the balance operations, studies rely on statistical and machine learning techniques. Statistical techniques are used for inferencing while machine learning techniques proved effective for interpretation. The focus of this study was on the issues encountered in human balance analysis such as the quantification of balance by relevant features, the relationships between COM and ground projected body sway, the performance of various sensory systems in balance analysis, and their relationships between the directions of body sway (i.e., mediolateral (ML) and anteriorposterior (AP)). A portable wireless accelerometry device was developed, balance analysis methods based on the inverted pendulum were devised and evaluated for their accuracy and reliability against a setup designed to allow manual balance measurements. Balance data were collected from 23 healthy adult subjects with the mean (standard deviation) of the age, height and weight: 24.5 (4.0) years, 173.6 (6.8) cm, and 72.7 (9.9) kg respectively. The accelerometry device was attached to the subjects at the approximate position of the illac crest, while they performed 30 seconds trials of the four conditions associated with a standard balance test called the modified Clinical Test of Sensory Interaction and Balance (mCTSIB). These required standing on a hard (ground) surface with the eyes open, standing on hard surface with the eyes closed, standing on a compliant surface (sponge, 10 cm thick) with the eyes open and standing on a compliant surface with the eyes closed. Statistical and machine learning techniques such as t-test, Wilcoxon signed-rank test, the Mann-Whitney U test, Analysis of variance (ANOVA), Kruskal-Wallis test, Friedman test, correlation analysis, linear regression, Bland and Altman analysis, principal component analysis (PCA), K-means clustering, and Kohonen neural network (KNN) were employed for interpreting the measurements. The findings showed close agreement between the developed balance analysis methods and the related measurements from the manual setup for balance analysis. The COM was observed to be responsible for differing amount of sway across the subjects and could affect both the angle and ground projected sway. The AP direction was more sensitive to sway than the ML direction. The subjects were observed to depend more on their proprioceptive system to control balance. The proprioceptive system was observed to have a greater impact in controlling the AP velocity of the subjects as compared to their visual system. The proprioceptive system had no impact on the ML velocity. The visual system was responsible for the control of the ML velocity and for reducing the acceleration in both directions. It was concluded that for comparison of postural sway information, subjects with closely related COM positions should be compared, comparison should be carried out in respect to the base of their support. The sway normalisation by dividing with COM position should be performed to reduce the obscuring effect of the COM. Enhancement of the proprioceptive system should be carried out to reduce the AP velocity while enhancement of the visual system should be used to reduce the ML sway and acceleration in ML and AP directions. The velocity in the AP direction should be used to examine the performance of the proprioceptive system while the ML velocity and acceleration should be used for the visual system. The vestibular system characterised sway more in the AP direction, and hence, the AP direction should be used to examine its performance in balance.

show abstract

Automated Bayesian operational modal analysis of the long-span bridge using machine-learning algorithms

Mao

Wang

et al. 2023

Engineering Structures

View full text Add to dashboard Cite

Kohonen Neural Network Investigation of the Effects of the Visual, Proprioceptive and Vestibular Systems to Balance in Young Healthy Adult Subjects

Cited by 7 publications

References 38 publications

Development and Application of a Stability Index Estimation Algorithm Based on Machine Learning for Elderly Balance Ability Diagnosis in Daily Life

Development and Application of a Stability Index Estimation Algorithm Based on Machine Learning for Elderly Balance Ability Diagnosis in Daily Life

Computerised accelerometric machine learning techniques and statistical developments for human balance analysis

Automated Bayesian operational modal analysis of the long-span bridge using machine-learning algorithms

Contact Info

Product

Resources

About