يُعدّ موضوع واجهة الدماغ والحاسوب BCI (Brain Computer Interface) وخاصةً أنظمة التعرف على الإشارات الدماغية باستخدام التعلم العميق بعد توصيف هذه الإشارات عن طريق مخطط كهربائية الدماغ EEG (Electroencephalography) من المواضيع البحثية الهامة التي تثير اهتمام الكثير من الباحثين في الوقت الراهن, وتعد الشبكات العصبونية الالتفافية CNN (Convolutional Neural Nets) من أهم مصنفات التعلم العميق المستخدمة في عملية التعرف هذه، إلا أنه لم يتم بعد تحديد بارامترات هذا المصنف بشكل دقيق بحيث يعطي أعلى نسبة تعرف ممكنة وبأقل زمن تدريب وزمن تعرف ممكن.
يقترح هذا البحث نظام تعرف على إشارات EEG باستخدام شبكة CNN مع دراسة تأثير تغيير بارامترات هذه الشبكة على نسبة التعرف وزمني التدريب والتعرف على الإشارات الدماغية, وبالنتيجة تم الحصول بواسطة نظام التعرف المقترح على نسبة تعرف 76.38 %, وانقاص زمن تدريب المصنف (3 seconds) باستخدام النمط المكاني المشترك CSP (Common Spatial Pattern) في عملية المعالجة المسبقة لقاعدة البيانات IV2b, كما تم الوصول لنسبة تعرف 76.533 % من خلال إضافة طبقة للمصنف المقترح.
Brain Computer Interface (BCI), especially systems for recognizing brain signals using deep learning after characterizing these signals as EEG (Electroencephalography), is one of the important research topics that arouse the interest of many researchers currently. Convolutional Neural Nets (CNN) is one of the most important deep learning classifiers used in this recognition process, but the parameters of this classifier have not yet been precisely defined so that it gives the highest recognition rate and the lowest possible training and recognition time.
This research proposes a system for recognizing EEG signals using the CNN network, while studying the effect of changing the parameters of this network on the recognition rate, training time, and recognition time of brain signals, as a result the proposed recognition system was achieved 76.38 % recognition rate, And the reduction of classifier training time (3 seconds) by using Common Spatial Pattern (CSP) in the preprocessing of IV2b dataset, and a recognition rate of 76.533% was reached by adding a layer to the proposed classifier.
References used
O. Trifonova, P. Lokhov, metabolic Profiling ofHuman Blood. Biomeditsinskaya Khimiya, Vol. 60, No. 3.pp. 281-294, 2014.
C.SWEENEY, E. ENNIS, M. MULVENNA, R. BOND, S. O'NEILL.How Machine Learning Classification Accuracy Changes in a Happiness Dataset with Different Demographic Groups. Computers, VOL.11, NO.5, 2022.
M. CONGEDO, L. KORCZOWSKI, A. DELORME AND F. LOPES DA SILVA. Spatio-temporal common pattern: A companion method for ERP analysis in the time domain. Journal of Neuroscience Methods, Vol. 267, pp. 74-88, 2016.
] H. MEISHERI, N. RAMRAO, S. MITRA, Multiclass Common Spatial Pattern for EEGbased BrainComputer Interface with Adaptive Learning Classifier. arXiv: abs/1802.09046, 2018.
Due to the popularity of intelligent dialogue assistant services, speech emotion recognition has become more and more important. In the communication between humans and machines, emotion recognition and emotion analysis can enhance the interaction be
The application of this research was implemented at the laboratories of
Food Science Department, Agriculture College, Damascus University in order
to investigate the effect of different ratios of added oil upon the rheological,
chemical and microb
Speech denoising is a field of engineering that studies techniques used to recover the
original signal from the noisy signal corrupted with different types of noise, such as
broadband noise and narrowband noise, and other types present in environme
Transformer models fine-tuned with a sequence labeling objective have become the dominant choice for named entity recognition tasks. However, a self-attention mechanism with unconstrained length can fail to fully capture local dependencies, particula
Abstract We study learning named entity recognizers in the presence of missing entity annotations. We approach this setting as tagging with latent variables and propose a novel loss, the Expected Entity Ratio, to learn models in the presence of syste