1. Wearable online freezing of gait detection and cueing systemJan Slemenšek, Jelka Geršak, Božidar Bratina, Vesna M. Van Midden, Zvezdan Pirtošek, Riko Šafarič, 2024, izvirni znanstveni članek Opis: This paper presents a real-time wearable system designed to assist Parkinson’s disease patients experiencing freezing of gait episodes. The system utilizes advanced machine learning models, including convolutional and recurrent neural networks, enhanced with past sample data preprocessing to achieve high accuracy, efficiency, and robustness. By continuously monitoring gait patterns, the system provides timely interventions, improving mobility and reducing the impact of freezing episodes. This paper explores the implementation of a CNN+RNN+PS machine learning model on a microcontroller-based device. The device operates at a real-time processing rate of 40 Hz and is deployed in practical settings to provide ‘on demand’ vibratory stimulation to patients. This paper examines the system’s ability to operate with minimal latency, achieving an average detection delay of just 261 milliseconds and a freezing of gait detection accuracy of 95.1%. While patients received on-demand stimulation, the system’s effectiveness was assessed by decreasing the average duration of freezing of gait episodes by 45%. These preliminarily results underscore the potential of personalized, real-time feedback systems in enhancing the quality of life and rehabilitation outcomes for patients with movement disorders.
Ključne besede: Parkinson’s disease, freezing of gait, machine learning, real-time systems, wearable devices, on-demand stimulation
Objavljeno v DKUM: 31.01.2025; Ogledov: 0; Prenosov: 4
 Celotno besedilo (6,29 MB) |
2. Brain dynamics underlying preserved cycling ability in patients with Parkinson’s disease and freezing of gaitTeja Ličen, Martin Rakuša, Nicolaas I. Bohnen, Paolo Manganotti, Uroš Marušič, 2022, pregledni znanstveni članek Opis: Parkinson’s disease (PD) is generally associated with abnormally increased beta band oscillations in the cortico-basal ganglia loop during walking. PD patients with freezing of gait (FOG) exhibit a more distinct, prolonged narrow band of beta oscillations that are locked to the initiation of movement at ∼18 Hz. Upon initiation of cycling movements, this oscillation has been reported to be weaker and rather brief in duration. Due to the suppression of the overall beta band power during cycling and its continuous nature of the movement, cycling is considered to be less demanding for cortical networks compared to walking, including reduced need for sensorimotor processing, and thus unimpaired continuous cycling motion. Furthermore, cycling has been considered one of the most efficient non-pharmacological therapies with an influence on the subthalamic nucleus (STN) beta rhythms implicative of the deep brain stimulation effects. In the current review, we provide an overview of the currently available studies and discuss the underlying mechanism of preserved cycling ability in relation to the FOG in PD patients. The mechanisms are presented in detail using a graphical scheme comparing cortical oscillations during walking and cycling in PD.
Ključne besede: gait, freezing of gait, Parkinson's disease, cycling, cortical oscillations, beta band
Objavljeno v DKUM: 04.12.2024; Ogledov: 0; Prenosov: 4
 Povezava na celotno besedilo
Gradivo ima več datotek! Več... |
3. Human gait activity recognition machine learning methodsJan Slemenšek, Iztok Fister, Jelka Geršak, Božidar Bratina, Vesna M. Van Midden, Zvezdan Pirtošek, Riko Šafarič, 2023, izvirni znanstveni članek Ključne besede: human gait, activity recognition, wearable, machine learning, convolutional neural network, recurrent neural network, attention mechanism
Objavljeno v DKUM: 10.04.2024; Ogledov: 274; Prenosov: 22
Celotno besedilo (5,11 MB)
Gradivo ima več datotek! Več... |
4. The dynamics of human gaitMatjaž Perc, 2005, izvirni znanstveni članek Opis: We analyse the dynamics of human gait with simple nonlinear time series analysis methods that are appropriate for undergraduate courses. We show that short continuous recordings of the human locomotory apparatus possess properties typical of deterministic chaotic systems. To facilitate interest and enable the reproduction of presented results, as well as to promote applications of nonlinear time series analysis to other experimental systems, we provide user-friendly programs for each implemented method. Thus, we provide new insights into the dynamics of human locomotion, and make an effort to ease the inclusion of nonlinear time series analysis methods into the curriculum at an early stage of the educational process.
Ključne besede: dynamic systems, chaotic systems, nonlinear dynamics, human gait, human locomotion
Objavljeno v DKUM: 01.06.2012; Ogledov: 2149; Prenosov: 80
Povezava na celotno besedilo |
