Freezing-of-Gait detection using temporal, spatial, and physiological features with a support-vector-machine classifier

Tahafchi, Parisa; Molina, Rene; Roper, Jaimie A.; Sowalsky, Kristen; Hass, Chris J.; Gündüz, Ayşegül; Okun, Michael S.; Judy, Jack W.

doi:10.1109/embc.2017.8037455

Cited by 32 publications

(28 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A support vector machine (SVM) with radial basis function (RBF) kernel was chosen as the classification method. This classifier has shown good results among previous publications of FOG detection [21,22,24,25,33]. Fourteen subjects (20%) were selected randomly as the test set, and the other 57 subjects (80%) were selected for the training set.…”

Section: Machine-learning Algorithmsmentioning

confidence: 96%

“…More recently, several forms of supervised learning approaches were used to automatically detect FOG. These include support vector machines (SVM) [21][22][23][24][25], boosting ensembles [26,27], and trees [25,27]. Machine-learning (ML) classifiers make it possible to combine multiple features from different axes and sensors and to provide information in a predefined window length.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Wearable Sensors and Machine Learning to Automatically Detect Freezing of Gait during a FOG-Provoking Test

Reches

Dagan

Herman

et al. 2020

Sensors

View full text Add to dashboard Cite

Freezing of gait (FOG) is a debilitating motor phenomenon that is common among individuals with advanced Parkinson’s disease. Objective and sensitive measures are needed to better quantify FOG. The present work addresses this need by leveraging wearable devices and machine-learning methods to develop and evaluate automated detection of FOG and quantification of its severity. Seventy-one subjects with FOG completed a FOG-provoking test while wearing three wearable sensors (lower back and each ankle). Subjects were videotaped before (OFF state) and after (ON state) they took their antiparkinsonian medications. Annotations of the videos provided the “ground-truth” for FOG detection. A leave-one-patient-out validation process with a training set of 57 subjects resulted in 84.1% sensitivity, 83.4% specificity, and 85.0% accuracy for FOG detection. Similar results were seen in an independent test set (data from 14 other subjects). Two derived outcomes, percent time frozen and number of FOG episodes, were associated with self-report of FOG. Bother derived-metrics were higher in the OFF state than in the ON state and in the most challenging level of the FOG-provoking test, compared to the least challenging level. These results suggest that this automated machine-learning approach can objectively assess FOG and that its outcomes are responsive to therapeutic interventions.

show abstract

Section: Machine-learning Algorithmsmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Using Wearable Sensors and Machine Learning to Automatically Detect Freezing of Gait during a FOG-Provoking Test

Reches

Dagan

Herman

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Related fields are gait cycle classification [16]- [19], reinforcement learning from human feedback [20]- [27], or inverse learning methods [28]- [41]. Differing from gait cycle classification methods [16]- [19], this paper does not aim to identify a human's individual gait but to generalize the classification of a physiological gait using data from multiple humans. Further, we infer the physiology of the gait from data and use the gathered knowledge for feedback control.…”

Section: Related Workmentioning

confidence: 99%

Using Human Ratings for Feedback Control: A Supervised Learning Approach With Application to Rehabilitation Robotics

et al. 2020

View full text Add to dashboard Cite

This paper presents a method for tailoring a parametric controller based on human ratings. The method leverages supervised learning concepts in order to train a reward model from data. It is applied to a gait rehabilitation robot with the goal of teaching the robot how to walk patients physiologically. In this context, the reward model judges the physiology of the gait cycle (instead of therapists) using sensor measurements provided by the robot and the automatic feedback controller chooses the input settings of the robot so as to maximize the reward. The key advantage of the proposed method is that only a few input adaptations are necessary to achieve a physiological gait cycle. Experiments with non-disabled subjects show that the proposed method permits the incorporation of human expertise into a control law and to automatically walk patients physiologically.

show abstract

“…Executing three classifier increment the multifaceted nature of framework. The examination in [17] characterized another arrangement of highlights to improve execution of past strategies for FOG identification. Spatial and transient highlights of the walk with vitality and physiological highlights (EMG) result in an increasingly strong grouping answer for recognizing solidifying scenes.…”

Section: Related Workmentioning

confidence: 99%

Design and Application of a Smart Diagnostic System for Parkinson’s Patients using Machine Learning

Channa¹,

Baqai²,

Ceylan³

2019

IJACSA

View full text Add to dashboard Cite

For analysis of Parkinson illness gait disabilities detection is essential. The only motivation behind this examination is to equitably and consequently differentiate among sound subjects and the one who is forbearing the Parkinson, utilizing IOT based indicative framework. In this examination absolute, 16 distinctive force sensors being attached with the shoes of subjects which documented the Multisignal Vertical Ground Reaction Force (VGRF). Overall sensors signals utilizing 1024 window estimate around the raw signals, utilizing the Packet wavelet change (PWT) five diverse characteristics that includes entropy, energy, variance, standard deviation and waveform length were derived and support vector machine (SVM) is to recognize Parkinson patients and healthy subjects. SVM is trained on 85% of the dataset and tested on 15% dataset. Preparation accomplice relies upon 93 patients with idiopathic PD (mean age: 66.3 years; 63% men and 37% ladies), and 73 healthy controls (mean age: 66.3 years; 55% men and 45% ladies). IOT framework included all 16 sensors, from which 8 compel sensors were appended to left side foot of subject and the rest of the 8 on the right side foot. The outcomes demonstrate that fifth sensor worn on a Medial part of the dorsum of right foot highlighted by R5 gives 90.3% accuracy. Henceforth this examination gives the knowledge to utilize single wearable force sensor. Hence, this examination deduce that a solitary sensor might help in differentiation amongst Parkinson and healthy subjects.

show abstract

Freezing-of-Gait detection using temporal, spatial, and physiological features with a support-vector-machine classifier

Cited by 32 publications

References 10 publications

Using Wearable Sensors and Machine Learning to Automatically Detect Freezing of Gait during a FOG-Provoking Test

Using Wearable Sensors and Machine Learning to Automatically Detect Freezing of Gait during a FOG-Provoking Test

Using Human Ratings for Feedback Control: A Supervised Learning Approach With Application to Rehabilitation Robotics

Design and Application of a Smart Diagnostic System for Parkinson’s Patients using Machine Learning

Contact Info

Product

Resources

About