Light-weight MobileNet for Fast Detection of COVID-19

The machine learning models based on Convolutional Neural Networks (CNNs) can be effectively used for detection and recognition of objects, such as Corona Virus Disease 19 (COVID-19). In particular, the MobileNet Single Shot multi-box Detector (SSD) have recently been proposed model object detection. However, there are still some challenges deployment architectures embedded devices, due to limited computational power. Another problem is that accuracy associated may decreased, depending number concerned parameters layers. This paper proposes a light-weight (LMN) architecture improve model, with small layers lower computation time, compared existing models. By experimentation, we show LMN COVID-19 virus. achieve 98% file size 27.8 Mbits by replacing standard CNN separable convolutional