Automated epileptic seizure detection system based on a wearable prototype and cloud computing to assist people with epilepsy
Epilepsy is characterized by the recurrence of epileptic seizures that affect secondary physiological changes in the patient. This leads to a series of adverse events in the manifestation of convulsions in an uncontrolled environment and without medical help, resulting in risk to the patient, especi...
- Autores:
-
González Vargas, Andrés Mauricio
Escobar Cruz, Juan Nicolás
Solarte, Jhon
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2018
- Institución:
- Universidad Autónoma de Occidente
- Repositorio:
- RED: Repositorio Educativo Digital UAO
- Idioma:
- eng
- OAI Identifier:
- oai:red.uao.edu.co:10614/11414
- Acceso en línea:
- http://hdl.handle.net/10614/11414
- Palabra clave:
- Electrodiagnóstico
Arquitectura en la nube
Electrodiagnosis
Cloud computing architecture
Epileptic seizure detection
Wearable
Electromyography
Cloud computing
- Rights
- openAccess
- License
- Derechos Reservados - Universidad Autónoma de Occidente
| Summary: | Epilepsy is characterized by the recurrence of epileptic seizures that affect secondary physiological changes in the patient. This leads to a series of adverse events in the manifestation of convulsions in an uncontrolled environment and without medical help, resulting in risk to the patient, especially in people with refractory epilepsy where modern pharmacology is not able to control seizures. The traditional methods of detection based on wired hospital monitoring systems are not suitable for the detection of long-term monitoring in outdoors. For these reasons, this paper proposes a system that can detect generalized tonic-clonic seizures on patients to alert family members or medical personnel for prompt assistance, based on a wearable device (glove), a mobile application and a Support Vector Machine classifier deployed in a system based on cloud computing. In the proposed approach we use Accelerometry (ACC), Electromyography (ECG) as measurement signals for the development of the glove, a machine learning algorithm (SVM) is used to discriminate between simulated tonic-clonic seizures and non-seizure activities that may be confused with convulsions. In this paper, the high level architecture of the system and its implementation based on Cloud Computing are described. Considering the traditional methods of measurement, the detection system proposed in this paper could mean an alternative solution that allows a prompt response and assistance that could be lifesaving in many situations |
|---|