Academia.eduAcademia.edu

Figure 2 – uploaded by mokhtar mohammadi

See full PDFdownloadDownload figure
Fig. 2. The plot of six channels electroencephalogram recording brair activity without seizure. After determining both mean and standard deviation value for each signal (normal and seizure) X» ,X , , and 6, ,6 the normalization operation of electroencephalogram data done using the following equations:

Figure 2 The plot of six channels electroencephalogram recording brair activity without seizure. After determining both mean and standard deviation value for each signal (normal and seizure) X» ,X , , and 6, ,6 the normalization operation of electroencephalogram data done using the following equations:

Related Figures (18)

Fig. 1. The flowchart of the proposed system.
Fig. 1. The flowchart of the proposed system.
Where N is the total number of measurement per raw, and, X is the mean. We have standard deviation values for normal and seizure data denoted by 6, and 6, , respectively.
Where N is the total number of measurement per raw, and, X is the mean. We have standard deviation values for normal and seizure data denoted by 6, and 6, , respectively.
Fig. 3. The plot of six channels electroencephalogram recording ot brain activity which has a seizure.
Fig. 3. The plot of six channels electroencephalogram recording ot brain activity which has a seizure.
Fig. 5. The plot of a normalized seizure data of six-channel electroencephalogram signals. Fig. 4. The plot of a normalized normal data of six-channel electroencephalogram signals.
Fig. 5. The plot of a normalized seizure data of six-channel electroencephalogram signals. Fig. 4. The plot of a normalized normal data of six-channel electroencephalogram signals.
There are popular and different types of EEG artifacts by applying various filter operations that can identify and removing them. The following points are the most significant soutces of artifacts.
There are popular and different types of EEG artifacts by applying various filter operations that can identify and removing them. The following points are the most significant soutces of artifacts.
Fig. 6. The plot of a filtered normal electroencephalogram data witt Butterworth low-pass filter.
Fig. 6. The plot of a filtered normal electroencephalogram data witt Butterworth low-pass filter.
Fig. 8. The plot of a filtered normal electroencephalogram data with a notch filter. Fig. 7. The plot of a filtered normal electroencephalogram data with Butterworth high-pass filter.
Fig. 8. The plot of a filtered normal electroencephalogram data with a notch filter. Fig. 7. The plot of a filtered normal electroencephalogram data with Butterworth high-pass filter.
Fig. 9. The plot of a filtered seizure electroencephalogram data with Butterworth low-pass filter. Deep learning is a part of machine learning allows multi- ayered computational models (multiple hidden layers) to learn data representations with various abstraction levels. Higher ayers of representation amplify elements of the input fot classification processes that are essential for discrimination and eliminate irrelevant features. The data representation earning is a collection of techniques allowing a machine to be fed with raw data and to learn the representations
Fig. 9. The plot of a filtered seizure electroencephalogram data with Butterworth low-pass filter. Deep learning is a part of machine learning allows multi- ayered computational models (multiple hidden layers) to learn data representations with various abstraction levels. Higher ayers of representation amplify elements of the input fot classification processes that are essential for discrimination and eliminate irrelevant features. The data representation earning is a collection of techniques allowing a machine to be fed with raw data and to learn the representations
Fig. 10. The plot of a filtered seizure electroencephalogram data with Butterworth high-pass filter.
Fig. 10. The plot of a filtered seizure electroencephalogram data with Butterworth high-pass filter.
-ig. 13. The plot a single channel of electroencephalogram (EEG seizure signal after computing average of six EEG channels. -ig. 12. The plot a single channel of electroencephalogram (EEG) normal signal after computing average of six EEG channels.
-ig. 13. The plot a single channel of electroencephalogram (EEG seizure signal after computing average of six EEG channels. -ig. 12. The plot a single channel of electroencephalogram (EEG) normal signal after computing average of six EEG channels.
Fig. 11. The plot of a filtered seizure electroencephalogram data witt a notch filter.
Fig. 11. The plot of a filtered seizure electroencephalogram data witt a notch filter.
automatically which is required for detection [29]. Deep learning method has dramatically improved object detections
automatically which is required for detection [29]. Deep learning method has dramatically improved object detections
Fig. 14. The detail of schematic architecture of the long- and short- term memory block [35]. We use the LSTM network for this work. It works best on time-series with short- and long-term dependencies [24]. Each block of this network has three gates (input, forget, and output); every block output is connected again to the block input [30]. The LSTM cell has the input layer X,, output layer, the cell input state C; , the cell output state C,, and the previous cell output state C,_, . The LSTM has the gated structure can deal with long-term dependencies to allow useful information to pass through the LSTM network ot ability to control a memory cell. The LSTM cell has three gates, including an input gate, a forgotten gate, and an output gate. The output gate is needed to read out the entries from the cell. The input gate is required to decide when to read data into the cell. We need a mechanism to reset the contents
Fig. 14. The detail of schematic architecture of the long- and short- term memory block [35]. We use the LSTM network for this work. It works best on time-series with short- and long-term dependencies [24]. Each block of this network has three gates (input, forget, and output); every block output is connected again to the block input [30]. The LSTM cell has the input layer X,, output layer, the cell input state C; , the cell output state C,, and the previous cell output state C,_, . The LSTM has the gated structure can deal with long-term dependencies to allow useful information to pass through the LSTM network ot ability to control a memory cell. The LSTM cell has three gates, including an input gate, a forgotten gate, and an output gate. The output gate is needed to read out the entries from the cell. The input gate is required to decide when to read data into the cell. We need a mechanism to reset the contents
Fig. 15. Overall seizure detection system schematic diagram describes the proposed entire system: (y) is the output of long- and short-term memory layer; (h) stand for units of time distributed layer; (p) represents the probability distribution produced by Softmax. n [he best characteristic of the LSTM is the retaining information for an extended period and makes the LSTM the strongest nominee for handling long-term EEG signals. Then, the output of the LSTM layer entered as an input into the time distributed layer (dense). Finally, the dense layer output is used as an input to the Softmax layer to classify the incoming data at the output.
Fig. 15. Overall seizure detection system schematic diagram describes the proposed entire system: (y) is the output of long- and short-term memory layer; (h) stand for units of time distributed layer; (p) represents the probability distribution produced by Softmax. n [he best characteristic of the LSTM is the retaining information for an extended period and makes the LSTM the strongest nominee for handling long-term EEG signals. Then, the output of the LSTM layer entered as an input into the time distributed layer (dense). Finally, the dense layer output is used as an input to the Softmax layer to classify the incoming data at the output.
CV: Cross-validation
CV: Cross-validation
Fig. 16. The plot of showing the result of the proposed system accuracy using 5-fold cross-validation approach. TABLE 1: Result of our proposed model with the 5-Fold CV that determines the classification accuracy
Fig. 16. The plot of showing the result of the proposed system accuracy using 5-fold cross-validation approach. TABLE 1: Result of our proposed model with the 5-Fold CV that determines the classification accuracy
TABLE 2: The comparison of the state-of-the-art techniques with our proposed method used 10-fold CV to select performances of the model with 2s length for each epoch (512 samples). They earned above 97.74% of accuracy.
TABLE 2: The comparison of the state-of-the-art techniques with our proposed method used 10-fold CV to select performances of the model with 2s length for each epoch (512 samples). They earned above 97.74% of accuracy.
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved