Design of inception with deep convolutional neural network based fall detection and classification model

Falling is the most serious health problem for elderly population resulting in serious injuries, if not treated quickly. As the world population gets increased, the number of serious falls and succeeding financial burdens rise accordingly. It is important to detect falls timely to initiate appropriate medical responses to decrease considerable physical, social, and financial losses. Earlier detection of fall events can helps to provide timely medical services and reduce severe injuries. Different techniques have been developed for fall detection process among elderly population. Recently, the development of Internet of Things (IoT) and artificial intelligence (AI) technologies involving deep learning (DL) and machine learning (ML) approaches can be employed in the field of healthcare for automating the diagnosis procedure of diseased and abnormal cases. This study designs a new Inception with deep convolutional neural network-based fall detection and classification (INDCNN-FDC) model. The presented INDCNN-FDC model intends to categorize the events into two class labels namely fall and not fall. To accomplish this, the INDCNN-FDC model carries out two stages of data pre-processing: Gaussian filter (GF) based image sharpening and Guided Filter (GIF) based image smoothing. In addition, the presented INDCNN-FDC model applies deep transfer learning-based Inception v3 model for generating a helpful group of feature vectors. Finally, DCNN approach receives the feature vectors as input and performs fall detection process. The experimental validation of the INDCNN-FDC approach is performed on benchmark dataset. The comparative study reported the supremacy of the INDCNN-FDC model over state-of-the-art.