Epilepsy is a central nervous system (neurological) disorder in which brain activity becomes abnormal, causing seizures or periods of unusual behaviour, sensations, and sometimes loss of awareness. Seizure symptoms can vary widely. Some people with epilepsy simply stare blankly for a few seconds during a seizure, while others repeatedly twitch their arms or legs. Having a single seizure doesn't mean you have epilepsy. At least two unprovoked seizures are generally required for an epilepsy diagnosis. In the case of seizure patients, they always require a caretaker along with them. The caretaker could be either the parents in case of children or could also be other people. The caretakers face a lot of stress it is not possible to know when would the seizure occur. This stress affects the caretakers in the long run. So we had built a device which could detect a seizure while it is happening and alert the caretaker immediately
We hope to construct a wearable wrist band which will record sEMG signals and Accelerometry with the help of sensors such as EMG Muscle Sensor Module and a triaxial accelerometer embedded into the band. Using this information, we shall predict epileptic seizures and notify the caregiver in case a seizure actually occurs with the help of an Android application. The application will notify the caregiver such as a parent that an episode is taking place and also the exact location of the patient on Google maps. The solution also consists of a continuous low power heart rate monitoring system by Motion Capturing System (IMUs). The band will also consist of an audio module, which shall provide instructions on how to deliver first aid to the patient, for nearby people to help, in case the caregiver is far away. The application will also feature a database where the patient history can be uploaded for medical use including sleep time cycle. It will also include First Aid instructions to be followed during the seizure such as turning of the head to prevent choking, as well as the location of the nearest hospitals, in case of an emergency. We obtained dataset from Patients Data from Health Centre inside campus, which will be used to train the necessary Machine Learning/Deep Learning model. The model will predict the seizures activity by using the real-time data collected from sensors and will use that as test data to classify the activity as seizures or not. The IoT based alarming system will then inform the caretakers via Android application about the activity with certain other information as detailed earlier.
- Kasina Jyothi Swaroop, Parth Khanna, Suddunuri Sandeep, Sreyans Bohara