Show simple item record

dc.contributor.authorJayawardena, MDVAG
dc.contributor.authorKarunasekara, PPCR
dc.contributor.authorSirisena, YVND
dc.date.accessioned2023-06-23T03:34:49Z
dc.date.available2023-06-23T03:34:49Z
dc.date.issued2022-09
dc.identifier.urihttp://ir.kdu.ac.lk/handle/345/6369
dc.description.abstractAbstract: Freezing of Gait (FoG) is a common incapacitating complication in Parkinson’s patients, which will temporarily hinder the forward progression and will prevent them from re-initiating their normal gait. This can lead to potentially fatal falls and severely affect the quality of life of the patient. Due to characteristic changes in their gait, FoG can be identified by using wearable sensors such as pressure sensors, Inertial Measurement Units (IMU), and Electroencephalogram (EEG) electrodes. Classification models that run on machine learning algorithms have been frequently used. Prediction of FoG would be highly useful for the patients since this identifies the changes in their gait preceding the event and the patient can be notified. This will allow them to overcome FoG. This systematic review identifies the best sensors, sensor placements, predictive algorithms, and the limitations of the existing prediction systems. Out of all the methods reviewed, combinations of plantar pressure sensors placed on the insoles and IMUs placed on the shank produced the highest accuracies with a specificity of 91.6%. The best algorithm was identified as Convolutional Neural Networks.en_US
dc.language.isoenen_US
dc.subjectFreezing of Gaiten_US
dc.subjectPredictionen_US
dc.subjectMachine learningen_US
dc.subjectWearable sensorsen_US
dc.titlePredicting the Freezing of Gait in Parkinson’s patients based on Machine Learning and Wearable Sensors: A reviewen_US
dc.typeArticle Full Texten_US
dc.identifier.facultyFaculty of Engineeringen_US
dc.identifier.journal15th International Research Conference, KDUen_US
dc.identifier.pgnos10en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record