Due to the COVID-19 pandemic, wearing a mask is mandatory in public spaces, as properly wearing a mask offers a maximum preventive effect against viral transmission. Body temperature has also become an important consideration in determining whether an individual is healthy. In this work, we design a real-time deep learning model to meet current demand to detect the mask-wearing position and head temperature of a person before he or she enters a public space. In this experiment, we use a deep learning object detection method to create a mask position and head temperature detector using a popular onestage object detection, RetinaNet. We build two modules for the RetinaNet model to detect three categories of mask-wearing positions and the temperature of the head. We implement an RGB camera and thermal camera to generate input images and capture a person's temperature respectively. The output of these experiments is a live video that carries accurate information about whether a person is wearing a mask properly and what his or her head temperature is. Our model is light and fast, achieving a confidence score of 81.31% for the prediction object and a prediction speed below 0.1s/image.

Alzheimer's disease (AD) is a major public health priority. Hippocampus is one of the most affected areas of the brain and is easily accessible as a biomarker using MRI images in machine learning for diagnosing AD. In machine learning, using entire MRI image slices showed lower accuracy for AD classification. We present the select slices method by landmarks on the hippocampus region in MRI images. This study aims to see which views of MRI images have higher accuracy for AD classification. Then, to get the value of three views and categories, we used multiclass classification with the publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset using Resnet50 and LeNet. The models were used in a total dataset of 4,500 MRI slices in three views and categories. Our study demonstrated that the selecting slices performed better than using entire slices in MRI images for AD classification. Our method improves the accuracy of machine learning, and the coronal view showed higher accuracy. This method played a significant role in improving the accuracy of machine learning performance. The results for the coronal view were similar to the medical experts usually used to diagnose AD. We also found that LeNet models became the potential model for AD classification.

Anomalies are a set of samples that do not follow the normal behavior of the majority of data. In an industrial dataset, anomalies appear in a very small number of samples. Currently, deep learning-based models have achieved important advances in image anomaly detection. However, with general models, real-world application data consisting of non-ideal images, also known as poison images, become a challenge. When the work environment is not conducive to consistently acquiring a good or ideal sample, an additional adaptive learning model is needed. In this work, we design a potential methodology to tackle poison or non-ideal images that commonly appear in industrial production lines by enhancing the existing training data. We propose Hierarchical Image Transformation and Multi-level Features (HIT-MiLF) modules for an anomaly detection network to adapt to perturbances from novelties in testing images. This approach provides a hierarchical process for image transformation during pre-processing and explores the most efficient layer of extracted features from a CNN backbone. The model generates new transformations of training samples that simulate the non-ideal condition and learn the normality in high-dimensional features before applying a Gaussian mixture model to detect the anomalies from new data that it has never seen before. Our experimental results show that hierarchical transformation and multi-level feature exploration improve the baseline performance on industrial metal datasets.