1 Recognition of Smartphone User Activity：From A Cyclical Perspective Chunmin Mi 1 , Runjie Xu 1 , Ching-Torng Lin 2 and RunYu Meng 3,4 1 Nanjing University of Aeronautics and Astronautics, College of Economics and Management, Nanjing, 210016 China 2 Da-yeh University, Department of IT, Changhua, 5159 Taiwan 3 University of Science and Technology of China, Anhui, 230026 China 4 Yunnan Observatories of the Chinese Academy of Sciences, Kunming, 650011 China ABSTRACT Smartphones have become an important tool for people's daily lives, which brings higher security requirements in high-risk application areas, for example, mobile payment. Although the combination of physical password, fingerprint and facial recognition have improved the security to a certain extent, there still exists a high risk of being decrepted. This paper attempts an algorithm which is more suitable for studying human partial periodic activity, namely Prophet algorithm. This algorithm has strong robustness for missing data and trend change, and can deal with outliers well. The experimental results on the UniMiB SHAR DATA show that the user simply needs to do 5 cycles of specified actions to realize the prediction of the next time series. The Error analysis of cross validation was applied to 4 different indicators, and the Mean Squared Error of the optimal result "Jumping" behavior was only 8.20%. With these appealing features, The main contribution of this paper is to propose a smart phone user identification system based on behavioral activity cycle, which can be replicated in other behavioral studies. Another outstanding feature of such a system is the capability of fitting models using small data set by exploiting behavioral characteristics derived from periodicity and thus reducing dependence on sensor scanning frequency, therefore the system balances among energy consumption, data quantity and fitting accuracy. Key Words: periodic motion,time series prediction, activity recognition, prophet algorithms 1. INTRODUCTION Everything has two sides, the vigorous development of smartphone industry has brought a brand new area of user-friendly applications, (such as mobile transfer, e-mail, mobile payment, smart home, etc.) [1][2] , and leaves personal information more exposed to leakage risks. Research shows that attackers can detect the position of screen click on smartphones based on acceleration sensors and gyroscopes, get letters, numbers or sliding gestures on the screen, and crack the PIN password, or even extract a password from the residual oil on a smartphone screen [3][4][5] . There are also studies showing that mobile phone theft and other criminal incidents occur every year in various countries, and continue to grow. The loss of these smart devices will not only cause the consumption of property of the owners, but also cause the leakage of privacy data inside the mobile phone [6][7] . Therefore, a non-active user authentication mechanism is very necessary, which makes biometrics become a popular research field [8][9][10][11] . At present, biometric research has achieved relatively high accuracy, but it is still difficult to be applied in mobile devices, which mainly results from dependence on hardware, and high sensitivity of physiological mechanisms to some environmental factors. For example, facial recognition requires that the sensing device must be correctly aligned with the face, while speech recognition has more stringent environmental requirements for background noise. Some scholars have proposed a activity recognition model based on mobile acceleration sensor [12][13][14] , which can operate normally without other hardware devices, and its authentication mode is transparent, persistent, making it much more difficult to imitate. For example, Sitova etc. studied the physical characteristics of 100 subjects who tapped or held their mobile phones while sitting or walking to achieve behavioral recognition, while also considering energy consumption [15] . They carry out surveys on the effects of activity identification (authentication, BKG, and energy consumption on friendship) from multiple perspectives. These are truly important innovations that can be commercialized and universally embraced in the future.