Asset Details
Do you wish to reserve the book?
An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier
Do you wish to request the book?
An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier
2024
Overview
Seizures are defined as short occurrences of unusual elevated brain electrical activity that can result in a variety of symptoms and actions where Seizures are the main sign of epilepsy. Due to the unexpected character of seizures and the individual variances in symptoms, examining individuals who are experiencing epileptic seizures could pose some difficulties. Recent researches have very low accuracies in epileptic seizure detection so in order to solve these above issues a detection model is developed that helps the health care sector. In this research, an improved deep dual adaptive CNN-HMM classifier is developed to detect the epileptic seizures automatically with focal and non-focal epileptic EEG signals. The inputs are collected from the four datasets and preprocessing is performed for converting unstructured data into structured data. The preprocessed signal is divided into five separate sub-bands and subjected to wavelet decomposition to decrease noise. The Human learning optimization (HLO) algorithm is proposed to perform the electrode selection process to identify the best electrode and also helps to reduce the overfitting problem. Once the signals are decided optimally, the features extraction takes place through three steps such as TQWT, Hjorth and statistical features are preferred for analyzing the EEG signals to derive the deep analysis of the data. The seizure detection is done using the deep dual adaptive CNN-HMM classifier, which helps in the efficient detection of epileptic seizure. The accuracy, sensitivity, specificity, precision and f-measure of the deep dual adaptive CNN-HMM classifier's outputs are evaluated. For dataset 1, attains 99.46%, 98.48%, 99.46%, 99.90%, and 99.58% with TP, 98.13%, 98.46%, 97.56%, 99.88%, and 99.56% with tenfold. For dataset 2, attains 94.53%, 92.37%, 99.94%, 93.11% and 93.60% with TP, 90.84%, 91.17%, 90.27%, 93.09% and 93.58% with tenfold. Similarly, for dataset 3 attains 94.48%, 94.62%, 96.82%, 95.41%, and 96.40% with TP, 94.54%, 94.68%, 96.87%, 95.46% and 96.45% with tenfold. For dataset 4, attains 99.13%, 98.72%, 98.00%, 96.73% and 97.72% with TP, 99.28%, 99.32%, 99.22%, 98.85% and 98.92% with tenfold, which is more efficient than other existing methods.
Publisher
Springer US,Springer Nature B.V
