Recognition of motion patterns using accelerometers for ataxic gait assessment

Dostál, Otto; Procházka, Aleš; Vyšata, Oldřich; Ťupa, Ondřej; Cejnar, Pavel; Vališ, Martin

doi:10.1007/s00521-020-05103-2

Cited by 28 publications

(37 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3(a) for the spine2 location of the accelerometric sensor are much better separated then those obtained from data recorded by accelerometers at the right foot position that are presented in Fig. 3(b), which corresponds with the study [8].…”

Section: B Feature Extraction and Classificationmentioning

confidence: 59%

“…Sensors placed in the upper part of the body are therefore more sensitive to separation of normal and ataxic gait. The classification accuracy for sensors located on the left/right foot of about 77% increased to more than 98% for sensors located on the head, spine or shoulders [8]. These results allow the replacement of the complex set of accelerometric sensors by the one wearable sensor in the selected position only.…”

Section: Discussionmentioning

confidence: 82%

“…Accelerometric signals recorded during the gait allow the detection of motion patterns that are important for recognition of movement disorders. Figure 1 presents the principle of simultaneous data acquisition by the Perception neuron system [8], [26], [43] that uses 31 sensor units located at different parts of the body. This system enables the simultaneous recording of accelerometric data at different body positions with a given sampling frequency.…”

Section: A Data Acquisitionmentioning

confidence: 99%

“…G AIT assessment and the study of motion disorders [1]- [5] have a wide range of applications in early diagnostics in neurology [6]- [8], physical therapy, rehabilitation, and physical activity analysis. The ataxic gait monitoring of patients with the multiple sclerosis forms a very important problem in this area.…”

Section: Introductionmentioning

confidence: 99%

“…The present analysis is based on three-axis accelerometric data of 16 ataxic patients and 19 healthy controls. All of the datasets were acquired by a system of sensors located at different positions [8] of the body, using a full-body motion capture device (Perception Neuron [26]) to simultaneously record accelerometric data [27] during the gait. Figure 1 presents an example of some possible locations for accelerometers used for data acquisition.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring

Procházka

Dostál

Cejnar

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Ataxic gait monitoring and assessment of neurological disorders belong to important multidisciplinary areas that are supported by digital signal processing methods and machine learning tools. This paper presents the possibility of using accelerometric data to optimise deep learning convolutional neural network systems to distinguish between ataxic and normal gait. The experimental dataset includes 860 signal segments of 16 ataxic patients and 19 individuals from the control set with the mean age of 38.6 and 39.6 years, respectively. The proposed methodology is based upon the analysis of frequency components of accelerometric signals simultaneously recorded at specific body positions with a sampling frequency of 60 Hz. The deep learning system uses all of the frequency components in a range of 0, 30 Hz. Our classification results are compared with those obtained by standard methods, which include the support vector machine, Bayesian methods, and the two-layer neural network with features estimated as the relative power in selected frequency bands. Our results show that the appropriate selection of sensor positions can increase the accuracy from 81.2% for the foot position to 91.7% for the spine position. Combining the input data and the deep learning methodology with five layers increased the accuracy to 95.8%. Our methodology suggests that artificial intelligence methods and deep learning are efficient methods in the assessment of motion disorders and they have a wide range of further applications.

show abstract

Section: B Feature Extraction and Classificationmentioning

confidence: 59%

Section: Discussionmentioning

confidence: 82%

Section: A Data Acquisitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring

Procházka

Dostál

Cejnar

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

Improving Accuracy of Ataxic Gait Monitoring Using SVM and ANN

Sandhya¹,

Vikash²,

Surrya³

et al. 2022

ICT Systems and Sustainability

View full text Add to dashboard Cite

Discrimination of cycling patterns using accelerometric data and deep learning techniques

Procházka

Charvátová

Vyšata

et al. 2020

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

The monitoring of physical activities and recognition of motion disorders belong to important diagnostical tools in neurology and rehabilitation. The goal of the present paper is in the contribution to this topic by (i) analysis of accelerometric signals recorded by wearable sensors located at specific body positions and by (ii) implementation of deep learning methods to classify signal features. This paper uses the general methodology to analysis of accelerometric signals acquired during cycling at different routes followed by the global positioning system (GPS). The experimental dataset includes 850 observations that were recorded by a mobile device in the spine area (L3 verterbra) for cycling routes with the different slope. The proposed methodology includes the use of deep learning convolutional neural networks with five layers applied to signal values transformed into the frequency domain without A. Procházka ( )

show abstract

Recognition of motion patterns using accelerometers for ataxic gait assessment

Cited by 28 publications

References 41 publications

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring

Improving Accuracy of Ataxic Gait Monitoring Using SVM and ANN

Discrimination of cycling patterns using accelerometric data and deep learning techniques

Contact Info

Product

Resources

About