Survey of Mobile Phone Sensing

Today smartphone not only serves as the key computing and communication mobile device of c h o i c e ,b u ti ta l s oc o m e sw i t har i c hs e to f embedded s ensor s ,such a san a c c e l e rome t e r , digital compass, gyroscope, GPS, microphone, a n dc a m e r a .C o l l e c t i v e l y ,t h e s es e n s o r sa r e enabling new applications across a wide variety of doma ins ,such a s he a l thc a r e ,soc i a l ne t works [2], safety, environmental monitoring , and transportation [4, 5], and give rise to a new area of research called mobile phone sensing. Until recently mobile sensing research such as activity recognition, where people’s activity (e.g., walking, driving, sitting, talking) is classified and monitored, required specialized mobile d e v i c e s( e . g . ,t h eM o b i l eS e n s i n gP l a t f o r m [MSP]) to be fabricated . Mobile sensing appl i c a t ions had to be manua l l y downloaded, installed, and hand tuned for each device. User studies conducted to evaluate new mobile sensing applications and algorithms were small-scale because of the expense and complexity of doing experiments at scale. As a result the research, which was innovative, gained little momentum outside a small group of dedicated researchers. Although the potential of using mobile phones as a platform for sensing research has been discussed for a number of years now, in both industrial [8] and research communities [9, 10], there ha s be en l i t t l e or no adv anc ementin thef i e ld until recently. All that is changing because of a number of i m p o r t a n tt e c h n o l o g i c a la d v a n c e s .F i r s t ,t h e availability of cheap embedded sensors initially included in phones to drive the user experience (e.g., the accelerometer used to change the displ a y or i ent a t ion)i schang ingthel ands c ape of possible applications. Now phones can be prog r a m m e dt os u p p o r tn e wd i s r u p t i v es e n s i n g applications such as sharing the user’s real-time activity with friends on social networks such as Fa c ebook, ke epingt r a ck ofa pe r son’ sc a rbon footprint, or monitoring a user’s well being. Second, smartphones are open and programmable. In addition to sensing, phones come with computing and communication resources that offer a low barrier of entry for third-party programmers (e.g., undergraduates with little phone programminge xpe r i enc ea r e de v e lopingand shipping appl i c a t ions ) . Thi rd,impor t ant l y ,e a ch phone vendor now offers an app store allowing developers to deliver new applications to large populat i o n so fu s e r sa c r o s st h eg l o b e ,w h i c hi s transforming the deployment of new applications, and allowing the collection and analysis of data far beyond the scale of what was previously possible. Fourth, the mobile computing cloud enables developers to offload mobile services to back-end servers, providing unprecedented scale and additional resources for computing on collections of large-scale sensor data and supporting advanced features such as persuasive user feedback based on the analysis of big sensor data. The combination of these advances opens the door for new innovative research and will lead to the development of sensing applications that are likely to revolutionize a large number of existing b u s i n e s ss e c t o r sa n du l t i m a t e l ys i g n i f i c a n t l y i m p a c to u re v e r y d a yl i v e s .M a n yq u e s t i o n s remain to make this vision a reality. For example, how much intelligence can we push to the phone without jeopardizing the phone experience? What breakthroughs are needed in order to perform robust and accurate classification of activities and context out in the wild? How do we scale a sensing application from an individual to a target community or even the general population? How do we use these new forms of largescale application delivery systems (e.g., Apple AppStor e , Goog l e Ma rke t )to be s t dr i v e da t

Free download research paper