Mostrar el registro sencillo del ítem

Generalized Models for the Classification of Abnormal Movements in Daily Life and its Applicability to Epilepsy Convulsion Recognition

dc.contributor.authorVillar J.R.
dc.contributor.authorVergara P.
dc.contributor.authorMenéndez M.
dc.contributor.authorDe La Cal E.
dc.contributor.authorGonzález V.M.
dc.contributor.authorSedano J.
dc.date.accessioned2020-09-02T22:30:25Z
dc.date.available2020-09-02T22:30:25Z
dc.date.issued2016
dc.identifier10.1142/S0129065716500374
dc.identifier.citation26, 6, -
dc.identifier.issn01290657
dc.identifier.urihttps://hdl.handle.net/20.500.12728/6577
dc.descriptionThe identification and the modeling of epilepsy convulsions during everyday life using wearable devices would enhance patient anamnesis and monitoring. The psychology of the epilepsy patient penalizes the use of user-driven modeling, which means that the probability of identifying convulsions is driven through generalized models. Focusing on clonic convulsions, this pre-clinical study proposes a method for generating a type of model that can evaluate the generalization capabilities. A realistic experimentation with healthy participants is performed, each with a single 3D accelerometer placed on the most affected wrist. Unlike similar studies reported in the literature, this proposal makes use of 5 × 2 cross-validation scheme, in order to evaluate the generalization capabilities of the models. Event-based error measurements are proposed instead of classification-error measurements, to evaluate the generalization capabilities of the model, and Fuzzy Systems are proposed as the generalization modeling technique. Using this method, the experimentation compares the most common solutions in the literature, such as Support Vector Machines, k-Nearest Neighbors, Decision Trees and Fuzzy Systems. The event-based error measurement system records the results, penalizing those models that raise false alarms. The results showed the good generalization capabilities of Fuzzy Systems. © 2016 World Scientific Publishing Company.
dc.language.isoen
dc.publisherWorld Scientific Publishing Co. Pte Ltd
dc.subjectdaily living
dc.subjectEpilepsy convulsions recognition
dc.subjectfuzzy rule-based classifiers
dc.subjectDecision trees
dc.subjectErrors
dc.subjectFuzzy inference
dc.subjectFuzzy systems
dc.subjectClassification errors
dc.subjectDaily living
dc.subjectEpilepsy convulsions recognition
dc.subjectError measurements
dc.subjectFuzzy rule-based classifier
dc.subjectGeneralization capability
dc.subjectGeneralized models
dc.subjectModeling technique
dc.subjectNeurology
dc.subjectaccelerometry
dc.subjectadult
dc.subjectclassification
dc.subjectdaily life activity
dc.subjectDyskinesias
dc.subjectepilepsy
dc.subjectfemale
dc.subjectfuzzy logic
dc.subjecthuman
dc.subjectmale
dc.subjectmiddle aged
dc.subjectpathophysiology
dc.subjectprocedures
dc.subjectSeizures
dc.subjectsensitivity and specificity
dc.subjectsupport vector machine
dc.subjectvalidation study
dc.subjectyoung adult
dc.subjectAccelerometry
dc.subjectActivities of Daily Living
dc.subjectAdult
dc.subjectDyskinesias
dc.subjectEpilepsy
dc.subjectFemale
dc.subjectFuzzy Logic
dc.subjectHumans
dc.subjectMale
dc.subjectMiddle Aged
dc.subjectSeizures
dc.subjectSensitivity and Specificity
dc.subjectSupport Vector Machine
dc.subjectYoung Adult
dc.titleGeneralized Models for the Classification of Abnormal Movements in Daily Life and its Applicability to Epilepsy Convulsion Recognition
dc.typeArticle


Ficheros en el ítem

Thumbnail
Nombre:
item_2-s2.0-84976577783.pdf
Tamaño:
3.477Kb
Formato:
PDF
Ver/

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem