09-09-2017, 09:23 AM
In many biomedical approaches to signal processing, the source signals are noisy and some have kurtosis near zero. These sources of noise increase the difficulty of analyzing the EEG and obtaining clinical information. To eliminate these artifacts a method based on the no-noise method of Donoho is used. The Wavelet Stationary Transformation (SWT) has recently been used to eliminate the noise of damaged EEG signals.
Statistical analysis of electrical recordings of brain activity by an electroencephalogram is an important problem in neuroscience. Brain signals have several origins that lead to the complexity of their identification. Therefore, the elimination of noise is of the first necessity to facilitate the interpretation of data and representation and to recover the signal that perfectly matches a functioning of the brain. A common problem faced during the clinical record of the EEG signal are eye blinking and eye ball movement producing eye artifacts. It has been known for quite some time that the EEG alpha rhythm, which is the main resting rhythm of the brain in adults while awake, is directly influenced by visual stimuli. Auditory and mental arithmetic tasks with closed eyes lead to strong alpha waves, which are suppressed when the eyes are opened. This EEG property has been ineffectively used over a long period of time to detect blinking and eye movements. The slow threshold response, lack of detection of rapid eye blinks and lack of an effective noise technique forced researchers to study the frequency characteristics of the EEG as well.
The model is based on discrete wavelet (DWT) and adaptive noise cancellation (ANC). A particularly novel feature of the new model is the use of DWTs to construct an OA reference signal, using the three lowest EEG waveform coefficients. The results show that the new model demonstrates improved performance over the recovery of true EEG signals and also has better tracking performance. The model is also applied and evaluated with data recorded in the EUFP Project 7 - Online Predictive Tools for Mental Illness Intervention (OPTIMI). The results show that the proposed model is effective in eliminating OAs and meets the requirements of portable systems used for patient monitoring as characterized by the OPTIMI project. Thereafter, artifact removal signals are received to identify the brain condition and then extract the characteristic. such as the mean, the median, and wavelet-based characteristics are extracted from the signal. The extracted features are sorted using SVM classifier.
Statistical analysis of electrical recordings of brain activity by an electroencephalogram is an important problem in neuroscience. Brain signals have several origins that lead to the complexity of their identification. Therefore, the elimination of noise is of the first necessity to facilitate the interpretation of data and representation and to recover the signal that perfectly matches a functioning of the brain. A common problem faced during the clinical record of the EEG signal are eye blinking and eye ball movement producing eye artifacts. It has been known for quite some time that the EEG alpha rhythm, which is the main resting rhythm of the brain in adults while awake, is directly influenced by visual stimuli. Auditory and mental arithmetic tasks with closed eyes lead to strong alpha waves, which are suppressed when the eyes are opened. This EEG property has been ineffectively used over a long period of time to detect blinking and eye movements. The slow threshold response, lack of detection of rapid eye blinks and lack of an effective noise technique forced researchers to study the frequency characteristics of the EEG as well.
The model is based on discrete wavelet (DWT) and adaptive noise cancellation (ANC). A particularly novel feature of the new model is the use of DWTs to construct an OA reference signal, using the three lowest EEG waveform coefficients. The results show that the new model demonstrates improved performance over the recovery of true EEG signals and also has better tracking performance. The model is also applied and evaluated with data recorded in the EUFP Project 7 - Online Predictive Tools for Mental Illness Intervention (OPTIMI). The results show that the proposed model is effective in eliminating OAs and meets the requirements of portable systems used for patient monitoring as characterized by the OPTIMI project. Thereafter, artifact removal signals are received to identify the brain condition and then extract the characteristic. such as the mean, the median, and wavelet-based characteristics are extracted from the signal. The extracted features are sorted using SVM classifier.