Wearable Smart Clothing Platform For Massive ECG Data Analysis

As the population is getting progressively older, the higher quality of health and medical care is now expected in countries with significant aging problems. According to a recent statistical analysis, two million deaths are caused by heart and cerebrovascular diseases every year in China. Wireless and sensor technologies facilitating noninvasive sensors integrated into clothing can enhance disease prevention.By combining cloud technology with smart clothing, the measured personal physiological data can establish a health database to promote telemedicine and medical service. The goal of this study is using wireless sensor technologies to develop smart clothes service platform for healthy monitoring. Our platform consists of smart clothes, sensor node, gateway server and health cloud. The smart clothes have fabric electrodes to detect ECG signal. The sensor node improves the accuracy of QRS complexes detection by morphology analysis and reduces power consumption by the "Lazy transmission" functionality. Gateway server provides a reconfigurable software architecture using Finite State Machine (RFSM) for abnormal ECG detection to support on-line updating. Most normal ECG can be filtered out and the abnormal ECG will be further analyzed in the health cloud.Three experiments are conducted to evaluate the platform performance. The results show that the signal to noise value of the smart clothes exceeds 37dB which is within "very good signal" interval. The average of QRS sensitivity and positive prediction is above 99.5%. The "Lazy transmission" is reduced by nearly 500 times power consumption in best-case analysis. We also got 26.8 speedup by CUDA compared to regular server performanceIt is demonstrated that our platform can be helpful for long-term monitoring of elders’ cardiovascular status with high accuracy, simplicity and future expandability.