Cloud-based health monitoring framework using smart sensors and smartphone

Advances in wearable biomedical sensors, smartphones, wireless communications, and cloud computing technologies offer promising techniques for the implementation of cloud-based mobile health monitoring system, especially for chronic disease monitoring, prevention, and treatment. Such systems are capable of monitoring chronic diseases such as epileptic seizures and heart attacks. In this chapter, we present a cloud-based chronic health monitoring framework composed of wearable devices, to acquire the biomedical signals such as electrocardiogram (ECG) and electroencephalogram (EEG), and a smartphone at the patient side to process the data received from the wearable sensors. In this framework, patient’s biomedical signals are continuously collected using body sensors and sent to a smartphone. To enhance the system resources utilization, the signals are acquired by using the event-driven A/D converters and then delivered to a remote healthcare cloud. Currently, health informatics represents an important area to improve healthcare efficiency by optimizing the acquisition, storage, and the retrieval of crucial patient’s health information. In this context, there is a lot of motivation about the improvement of machine learning techniques which play a crucial role in health monitoring. The intelligent system uses machine learning methods to create a warning system in an emergency case and generate alarms. The approach is original and has a potential to be integrated in modern health informatics. In this chapter, we concentrate on two different biomedical signals (ECG and EEG) to monitor chronic diseases using wearable sensors and smartphone. Then this chapter will be concluded by demonstrating the application of heart failure detection using ECG and epileptic seizure detection using EEG. The results demonstrate that the devised event-driven solution realizes a computationally efficient automatic detection of chronic disorders while achieving comparable classification accuracy.