Rosales Licet, Skubic Marjorie, Heise David, Devaney Michael J, Schaumburg Mark
Department of Electrical and Computer Engineering, University of Missouri, Columbia, MO 65211, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:2383-7. doi: 10.1109/EMBC.2012.6346443.
Encouraged by previous performance of a hydraulic bed sensor, this work presents a new hydraulic transducer configuration which improves the system's ability to capture a heartbeat signal from four subjects with different body weight and height, gender, age and cardiac history. It also proposes a new approach for detecting the occurrence of heartbeats from ballistocardiogram (BCG) signals through the use of the k-means clustering algorithm, based on finding the location of the J-peaks. Preliminary testing showed that the new transducer arrangement was able to capture the occurrence of heartbeats for all the participants, and the clustering approach achieved correct heartbeat detection ranging from 98.6 to 100% for three of them. Some considerations are discussed regarding adjustments that can be done in order to increase the correct detection of heartbeats for the participant whose percentage of correct detection ranged from 71.0 to 92.5%.
受液压床传感器先前性能的鼓舞，这项工作提出了一种新的液压传感器配置，该配置提高了系统从四名体重、身高、性别、年龄和心脏病史不同的受试者身上捕捉心跳信号的能力。它还提出了一种新方法，通过使用k均值聚类算法，基于找到J波峰的位置，从心冲击图（BCG）信号中检测心跳的发生。初步测试表明，新的传感器布置能够捕捉到所有参与者的心跳情况，对于其中三名参与者，聚类方法实现的正确心跳检测率在98.6%至100%之间。对于正确检测率在71.0%至92.5%之间的参与者，讨论了为提高心跳正确检测率可进行的一些调整。
