Detection and Assessment of Abnormal Circadian Rhythm by Analyzing Rest/Activity Cycle
There is an increasing proportion of diseases occur due to unhealthy lifestyle.These diseases are called lifestyle diseases.Cancer is one of them and main cause of death at Taiwan in 2012.Therefore,it is important to help people to be aware of unhealthy lifestyles as early as possible.In this research,we focus on two kinds of unhealthy lifestyles,disruption of sleep-wake cycle and lack of physical activity.Such lifestyles tend to cause the disorder of circadian rhythm which leads to diseases and even accelerating tumor growth.According to the literature,rest/activity cycle is highly correlated with circadian function.The objective of this research is to design a system that automatically detects and assesses abnormal circadian rhythm by analyzing rest/activity cycle.In this system,the wrist accelerometer is used to record movement intensity continuously and signal magnitude area(SMA)of tri-axis acceleration is accumulated every minute.Totally six rhythm features are extracted from 24-h SMA time series data by cosinor analysis.Cosinor analysis is performed to fit a best-fitting cosine function using least squares method and period is set to 24 hours.Then,support vector data description(SVDD)is applied to generate a hyper-sphere boundary which encloses feature vectors of normal circadian rhythm.The outliers of SVDD boundary will be detected as abnormal situations.When abnormal situations are detected,the system is able to alerts caregivers or doctors and then deviation degree of outlier is used to represent the current health alert level.As a result,the proposed system is able to help modern people to maintain healthy lifestyles more easily and to perceive abnormal health condition as early as possible.
Circadian Rhythm Cosinor Analysis SVDD Accelerometer Health Assessment
Li-Ren Hou Kuan-Ling Huang Shu-Fan Lee Chun-Feng Liao Chia-Hui Chen Li-Chen Fu
Department of Computer Science & Information Engineering,College of Medicine National Taiwan Univers Department of Information Engineering & Computer Science Feng Chia University Taichung,Taiwan 40724 Department of Nursing,College of Medicine National Taiwan University Taipei,Taiwan 10617
国际会议
The 2014 ICME International Conference on Complex Medical Engineering (CME2014)ICME复合医学工程国际会议
台北
英文
285-290,143
2014-06-26（万方平台首次上网日期，不代表论文的发表时间）