no code implementations • 26 Dec 2021 • Ismail Shahin, Ali Bou Nassif, Nawel Nemmour, Ashraf Elnagar, Adi Alhudhaif, Kemal Polat
The test results of the aforementioned hybrid models demonstrated that the proposed HMM-DNN leveraged the verification performance in emotional and stressful environments.
no code implementations • 26 Dec 2021 • Ismail Shahin, Noor Hindawi, Ali Bou Nassif, Adi Alhudhaif, Kemal Polat
Using the Arabic Emirati-accented corpus, our results demonstrate that the proposed work yields average emotion recognition accuracy of 89. 3% compared to 84. 7%, 82. 2%, 69. 8%, 69. 2%, 53. 8%, 42. 6%, and 31. 9% based on CapsNet, CNN, support vector machine, multi-layer perceptron, k-nearest neighbor, radial basis function, and naive Bayes, respectively.
no code implementations • 11 Nov 2020 • Umut Özkaya, Şaban Öztürk, Serkan Budak, Farid Melgani, Kemal Polat
Unlike the pre-trained Convolutional Neural Networks (CNN) trained with the transfer learning method, the CSVM model is trained as a scratch.