نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه مهندسی برق، واحد مشهد، دانشگاه آزاد اسلامی، مشهد، ایران.
2 گروه مهندسی کامپیوتر، واحد مشهد، دانشگاه آزاد اسلامی، مشهد، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
In recent years, quantum machine learning (QML) algorithms have been considered to detect different brain states through EEG signals. Emotion recognition using EEG signals plays a key role in human-computer interaction and emotional computing. This study uses the DEAP (A Database for Emotion Analysis Using Physiological Signals) dataset consisting of 32 channels of EEG signals obtained from 32 participants while watching 40 one-minute music videos. The proposed model based on hierarchical QML includes phases of EEG signal pre-processing using surface Laplacian, preparation of EEG signal as a quantum state, feature extraction using quantum wavelet packet transform (QWPT) and wavelet packet energy entropy (WPEE) and three layers quantum neural network (QNN) classifier. The results show that the proposed model can distinguish two categories of emotional states of valence and arousal states with 94.71 and 97.62 accuracy percentages, respectively. The results show the significant success of the proposed model in detecting different emotional states.
کلیدواژهها [English]