Data not found

An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction

Country : Malaysia
Department : Universiti Sains Malaysia, Malaysia
Project Title : An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction
Researcher : Lai , Kee Huong
Keyword : QA1 Mathematics (General)
Year End : 2016
Identifier : http://eprints.usm.my/31881/1/LAI_KEE_HUONG_24%28NN%29.pdf , Lai , Kee Huong (2016) An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction. PhD thesis, Universiti Sains Malaysia.
Relation : http://eprints.usm.my/31881/
Abstract / Description :

Epilepsi merupakan suatu penyakit neurologi yang sangat lazim dan ditakuti orang ramai. Banyak kajian telah dibuat untuk membangunkan pengelas automatik yang dapat memberikan ketepatan yang lebih tinggi. Pengelas automatik ini dapat membantu doktor dalam mengenali pelbagai segmen isyarat electroencephalography (EEG) yang berbeza. Dalam kerja penyelidikan ini, suatu model rangkaian neural wavelet (RNW) telah dicadangkan bagi tujuan pengesanan dan ramalan serangan epilepsi. Arkitektur dan kon�gurasi RNW dapat ditambah baik menggunakan pendekatan metaheuristik. Khususnya, algoritma carian harmoni (CH) digunakan dan diterapkan dalam proses pembelajaran RNW. Tesis ini mengandungi tiga sumbangan utama. Pertama, algoritma CH digunakan dalam proses pemilihan �tur. Firstly, the HS algorithm is used in the feature selection stage. The HS algorithm, which is originally used for optimization problems involving real numbers, is modi�ed and employed in the task of feature selection, which involves binary values. Epilepsy is a very common and much-feared neurological disorder. Much research has been done in developing better automated classi�ers with higher accuracy that can help clinicians identify the di�erent segments of electroencephalography (EEG) signals. In this research work, an enhanced wavelet neural network (WNN) model is proposed for the purpose of epileptic seizure detection and prediction. The architecture and con�guration of WNNs can be further enhanced using metaheuristic strategies. Speci�cally, the harmony search (HS) algorithm is employed and incorporated in the learning of WNNs. The contribution of this thesis is threefold. Firstly, the HS algorithm is used in the feature selection stage. The HS algorithm, which is originally used for optimization problems involving real numbers, is modi�ed and employed in the task of feature selection, which involves binary values.

References

Lai , Kee Huong. (2016). An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction.  Malaysia: Universiti Sains Malaysia, Malaysia.
Lai , Kee Huong. 2016. "An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction".  Malaysia: Universiti Sains Malaysia, Malaysia.
Lai , Kee Huong. "An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction."  Malaysia: Universiti Sains Malaysia, Malaysia, 2016. Print.
Lai , Kee Huong. An Enhanced Wavelet Neural Network Model For Epileptic Seizure Detection And Prediction. Malaysia: Universiti Sains Malaysia, Malaysia; 2016.

Export

Share