Zaheer, Muhammad Asad - Výsledky hledání - Digitální repozitář

host :: přihlásit Digitální repozitář
		Hledej		Nový záznam		Nápověda		O repozitáři

Hlavní stránka > Výsledky hledání: Zaheer, Muhammad Asad

Hledej:

Tipy pro vyhledávaní :: Rozšířené hledání

Hledej ve sbírkách:

Seřadit podle:	Zobrazit výsledky:	Výstupní formát:

	Electroencephalogram (EEG) and machine learning based classification of depression: unveiling hidden patterns for early detection Jurkechová, Adriana ; Malik, Aamir Saeed (oponent) ; Zaheer, Muhammad Asad (vedoucí práce) This work deals with the pre-processing EEG signals, extraction of the features and classifying depressed patients and healthy control group. For classification, 5 different machine learning models were considered and evaluated. Findings confirm results from prior research and show the importance of a large, diverse dataset. This work utilises a public dataset. Úplný záznam
	Electroencephalogram (EEG) and machine learning-based classification of various stages of mental stress Lapčíková, Tereza ; Malik, Aamir Saeed (oponent) ; Zaheer, Muhammad Asad (vedoucí práce) This thesis deals with the recognition of various stress stages experienced by patients from electroencephalogram (EEG). Various Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) models classifying EEG into three classes – not stressed, moderate stressed, and very stressed were created. The process of implementing such a classifier consisted of data preparation, extraction, and finally, classification. This solution also implements augmentation of data. The highest accuracy achieved in this thesis was of 90 % using the SVM model. The best LSTM model was a three-layer LSTM and achieved classification accuracy of 70 %. Úplný záznam
	EEG Classification Model for Emotion Detection Using Python Vengerová, Veronika ; Zaheer, Muhammad Asad (oponent) ; Jawed, Soyiba (vedoucí práce) This thesis deals with the task of recognizing emotions from electroencephalogram (EEG). Two models were trained for binary classification of emotions, where one classifies neutral emotion or fear and the other classifies happiness or sadness. During the work on this thesis many different architectures were tried, and the best result was obtained using a model with two branches of CNN-LSTM connected before the output layer. The resulting accuracy was 87.309% for sad-happy classification and 84.865% for neutral-fear emotion. Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.

Digitální repozitář :: :: :: ::
Powered by v1.1.2
Spravuje

Tato stránka je dostupná také v následujících jazycích:
Česky English