Ali Douik

Recently, panic detection has become essential in security, healthcare, and human-computer interaction. Automatic panic detection (APD) systems are designed to monitor physiological signals and behavioral patterns in real-time to detect stress responses. APD is increasingly adopted across many sectors, including disaster preparedness, COVID-19, and terror attacks. Their integration with various applications reduces human efforts and saves costs. However, most studies rely on existing models with fewer new ones or techniques. This study proposes a vision-based panic detection model using MobileNet, ResNet, and convolutional neural network (CNN). The FER2013 dataset is used for the model training and testing. The results indicate that MobileNet is the most effective model for image-based panic detection across ten folds with an accuracy of 90%, recall of 96.9%, and mean accuracy of 0.032. MobileNet also showed a mean absolute error (MAE) between 0.02 and 0.04. This study has been to confirm MobileNet's suitability for image-based panic detection. The findings contribute to developing more reliable and accurate image-based panic detection systems in real-world applications. It offers valuable insights and lays the groundwork for future deep-leaning-based panic detection studies.

We propose a novel architecture, Transformer Dil-DenseUNet, designed to address the challenges of accurately segmenting stroke lesions in MRI images. Precise segmentation is essential for diagnosing and treating stroke patients, as it provides critical spatial insights into the affected brain regions and the extent of damage. Traditional manual segmentation is labor-intensive and error-prone, highlighting the need for automated solutions. Our Transformer Dil-DenseUNet combines DenseNet, dilated convolutions, and Transformer blocks, each contributing unique strengths to enhance segmentation accuracy. The DenseNet component captures fine-grained details and global features by leveraging dense connections, improving both precision and feature reuse. The dilated convolutional blocks, placed before each DenseNet module, expand the receptive field, capturing broader contextual information essential for accurate segmentation. Additionally, the Transformer blocks within our architecture address CNN limitations in capturing long-range dependencies by modeling complex spatial relationships through multi-head self-attention mechanisms. We assess our model’s performance on the Ischemic Stroke Lesion Segmentation Challenge 2015 (SISS 2015) and ISLES 2022 datasets. In the testing phase, the model achieves a Dice coefficient of 0.80 ± 0.30 on SISS 2015 and 0.81 ± 0.33 on ISLES 2022, surpassing the current state-of-the-art results on these datasets.