Abstract
Epilepsy is a neurological disorder and it is growing day by day. Electroencephalogram (EEG) signals are used to diagnose this brain related disorder. These signals are recorded from patient and classified as epileptic and normal EEG signals. Many machine learning and other techniques are used for performing this classification. Convolutional neural network is widely used for identification of these signals. Lots of improvement is done in machine learning techniques and its performance. At the same time these machine learning models are getting more and more complex. It is very difficult to understand their operations and how they arrive at particular decision. They are becoming black boxes. Because of this it is difficult to adopt them in medical domain. In epilepsy detection the results are very sensitive. Explainable Artificial Intelligence (XAI) is a growing field which provides new methods that explains and interprets the results produced by machine learning models. This paper provides review of neural network based epileptic seizure detection methods. It also gives an overview of various XAI methods which are helpful in interpreting the decisions of machine learning models. These methods can be used with neural network-based epilepsy detection system. XAI methods describe why particular signal is classified as epileptic or non-epileptic. They highlight the features which are important in making decisions. These methods help medical practitioners to trust the decision made by machine learning models and to accept these models and their results in medical domain such as epilepsy detection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.