Publications by authors named "Mudasir Jamil"
Article Synopsis
- This study investigates the classification of epileptic EEG signals using multiple pretrained convolutional neural networks (CNNs) such as AlexNet, GoogLeNet, MobileNetV2, ResNet-18, and SqueezeNet, emphasizing the use of time-frequency representations.
- It employs various algorithms like continuous wavelet transform (CWT) and empirical mode decomposition (EMD) to convert EEG data into 2D scalograms, assessing factors such as the impact of noise, optimizers, learning rates, and model configurations.
- Results indicate that the optimal combination of MobileNetV2, CWT, and the Adam optimizer with specific parameters leads to high performance metrics in classifying epilepsy EEG data, demonstrating the effectiveness of deep learning models in this
Due to the rapid spread of COVID-19 and its induced death worldwide, it is imperative to develop a reliable tool for the early detection of this disease. Chest X-ray is currently accepted to be one of the reliable means for such a detection purpose. However, most of the available methods utilize large training data, and there is a need for improvement in the detection accuracy due to the limited boundary segment of the acquired images for symptom identifications.
View Article and Find Full Text PDF