| Titre : | Deep Learning For EEG Signals Analysis While Listening To Quran |
| Auteurs : | Rofeida Khamar, Auteur ; Djouher Akrour, Directeur de thèse |
| Type de document : | Monographie imprimée |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2023 |
| Format : | 1 vol. (69 p.) / couv. ill. en coul / 30 cm |
| Langues: | Anglais |
| Langues originales: | Anglais |
| Mots-clés: | Electroencephalogram (EEG), Brain-Computer Interface, classification,Machine Learning, Deep Learning, EEG Signal. |
| Résumé : |
This study aims to develop an accurate and objective method for classifying EEG signals recorded during Quran listening. The research question addressed is whether EEG signals can be effectively utilized to classify the response of individuals while listening to Quran recitation. The findings demonstrate the feasibility of utilizing EEG signals for classification and provide insights into the performance of SVM and CNN models in this context. The study contributes to the development of an objective method for detecting and classifying responses to Quran recitation using EEG signals and suggests potential future research directions. |
| Sommaire : |
1 Brain Computer Interface.......3 1.1Introduction.........3 1.2Brain computer interface (BCI).........3 1.2.1History and evolution of BCI.........4 1.2.2Application of BCI........4 1.2.3Components of a BCI.......5 1.2.4Types of BCI..............7 1.2.4.1 Invasive...............7 1.2.4.2 Semi-Invasive..........7 1.2.4.3 NON-Invasive...........8 1.3Brain signal acquisition....8 1.3.1Brain structure..........9 1.3.2Electroencephalography (EEG).....12 1.3.2.1Principle and functioning of EEG...............12 1.3.2.2 The Rhythms...........13 1.3.2.3 ChannelsofEEG.........14 1.3.2.4 10-20 System..........15 1.4Brain image techniques.....16 1.4.1Event-Related Potentials........18 1.4.2Steady-StateEvokedPotentials....18 1.5Conclusion.............19 2 Sentiment analysis using EEG (Literature review).......20 2.1Introduction............20 2.2Sentimentanalysis.......20 2.2.1Emotions..............21 2.2.2The Importance of using EEG in the classification of emotions.........22 2.3Auditory stimulus for sentimentanalysis..............23 2.4Related Works...............23 2.4.1EEG-Based Emotion Recognition while Listening to Quran Recitation Compared with Relaxing Music Using Arousal-Valence Model[58].........24 2.4.2Emotion Detection among Muslims and Non-Muslims While Listeningto Quran Recitation Using EEG[59]...................25 2.4.3Analyzing Brainwaves While Listening To Quranic Recitation ComparedWith Listening To Music Based on EEG Signals[60]...................25 2.4.4TheEffectofTemporalEEGSignalsWhileListeningtoQuranRecitation[61]..........26 2.4.5EffectsOfQuranListeningAndMusicOnElectroencephalogramBrainWaves[62].......27 2.5Conclusion.....29 3Methodology......30 3.1Introduction.............30 3.2Preprocessing............30 3.2.1Downsampling...........31 3.2.2Temporal Filtering.....31 3.2.3Temporal filtering application...........32 3.2.4Spatial Filtering............33 3.2.5Source Localisation..........36 3.3Artifacts removal and Preprocessing methods.......37 3.3.1Regression Methods.........37 3.3.2Blind Source Separation Methods...........37 3.3.3Wavelet Transform.............38 3.3.4Filtering Methods.............38 3.4Feature Extraction..............39 3.4.1Amplitude Features............40 3.4.2Band power Features...........40 3.4.3Power Spectral Density Features........40 3.5Feature Extraction Methods...............42 3.5.1Principal Component Analysis...........42 3.5.2Autoregressive Mode...........42 3.5.3Fast Fourier Transform........43 3.5.4Wavelet Transform.............43 3.5.5Common Spatial Pattern........44 3.6Classification......44 3.7Conclusion..........45 4Machine and Deep Learning for EEG.......46 4.1Introduction.............46 4.2Machine Learning Overview.........46 4.3Machine Learning for EEG-Based Sentiment Analysis..........47 4.3.1Support Vector Machine SVM........47 4.3.2Linear discriminant analysis LDA......48 4.3.3Principal Component Analysis PCA......48 4.3.4KNN K-Nearset Neighbours..........49 4.3.5Naive Bayes............49 4.4Deep Learning for EEG-Based Sentiment Analysis...........50 4.4.1Convolutional Neural Networks CNN.....50 4.4.2Artificial Neural Networks ANN........50 4.4.3Long Short-Term Memory (LSTM)............52 4.5Comparison of machine and deep-learning techniques.........52 4.6Hybrid approaches.......52 4.7Conclusion.......53 5Experimental Implementation and Result..........54 5.1Introduction..............54 5.2Languages and FrameWorks..54 5.3Experimental setup........55 5.3.1Data Collection.........55 5.3.2Preprocessing...........56 5.3.3Feature Extraction .....57 5.4Classification.......58 5.4.1SVM model implementation and tuning......58 5.4.2CNN model implementation and tuning......59 5.5Result and Analysis........61 5.5.1SVM model results........61 5.5.2CNN model results........63 5.6Discussion........64 5.6.1Comparison of SVM and CNN model performance......64 5.6.2Comparison of The Three Datasets.......65 5.7Limitations and future directions........66 5.8Conclusion......67 Conclusion.........68 Bibliography.......69 |
| Type de document : | Mémoire master |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/793 | Mémoire master | bibliothèque sciences exactes | Consultable |
