Cloud-Assisted Speech and Face Recognition Framework for Health Monitoring

Abstract

The increasing demand for the remote monitoring of patients combined with the promising potential of cloud computing has enabled the design and development of a number of cloud-based systems and services for healthcare. The cloud computing, in combination with the popularity of smart handheld devices, has inspired healthcare professionals to remotely monitor patients' health while the patient is at home. To this end, this paper proposes a cloud-assisted speech and face recognition framework for elderly health monitoring, where handheld devices or video cameras collect speech along with face images and deliver to the cloud server for possible analysis and classification. In the framework, a patient's state such as pain, tensed, and so forth is recognized from his or her speech and face images. The patient state recognition system extracts local features from speech, and texture descriptors from face images. Then it classifies using support vector machines. The recognized state is later sent to the remote care center, healthcare professionals and providers for necessary services in order to provide seamless health monitoring. Experiments have been performed to validate the approach and to evaluate the suitability of this framework in terms of accuracy and time requirements. The results demonstrate the effectiveness of the proposed approach with regards to face and speech processing.