Smartphone-Based Lifelogging: An Investigation of Data Volume Generation Strength of Smartphone Sensors

The lifelogging enable people to digitally record information about their daily life events for a variety of purposes including human memory augmentation. However, the lifelogging systems have several challenges regarding capturing, managing, semantic analyses, indexing, and retrieval of error-prone and noisy data produced by the sensors. The ubiquitous nature and technological developments makes smartphone as de-facto lifelogging device. The smartphone integrates a rich set of sensors, which provide unique opportunities for capturing contents and contextual information into a comprehensive lifelog archive. However, the continuous use of sensors can generate large amount of data that could raise problems for smartphone-based lifelogging systems. In addition, insight understanding of smartphone sensors data generation strength is needed for effective smartphone-based lifelogging systems development. These estimations will also help in understanding of smartphone sensors capability of fulfilling lifelogging systems objectives. To fulfill objective of this paper, an Android based application namely Sensors dAta Volume Estimator (SAVE) is developed using a proposed architecture. The SAVE utilizes smartphone sensors to capture and estimate sensors data from different real world scenarios. The results indicated that smartphone sensors can generate significant amount of data that can create storage, retrieval, and battery power issues for smartphone-based lifelogging systems.

[1]  C. Walter Kryder's law. , 2005, Scientific American.

[2]  Shah Khusro,et al.  A SURVEY OF MOBILE PHONES CONTEXT-AWARENESS USING SENSING COMPUTING RESEARCH , 2014 .

[3]  Shah Khusro,et al.  SmartOntoSensor: Ontology for Semantic Interpretation of Smartphone Sensors Data for Context-Aware Applications , 2017, J. Sensors.

[4]  Kimmo Roimela,et al.  Experience Explorer: A Life-Logging Platform Based on Mobile Context Collection , 2009, 2009 Third International Conference on Next Generation Mobile Applications, Services and Technologies.

[5]  James A. Landay,et al.  MyExperience: a system for in situ tracing and capturing of user feedback on mobile phones , 2007, MobiSys '07.

[6]  Rob Kitchin,et al.  ‘Outlines of a World Coming into Existence’: Pervasive Computing and the Ethics of Forgetting , 2007 .

[7]  Jiang Zhu,et al.  Mobile Lifelogger - Recording, Indexing, and Understanding a Mobile User's Life , 2010, MobiCASE.

[8]  William E. Jones,et al.  Context in information behavior research , 2007 .

[9]  Kaisa Väänänen,et al.  I don't mind being logged, but want to remain in control: a field study of mobile activity and context logging , 2010, CHI.

[10]  Katarzyna Wac,et al.  UbiqLog: a generic mobile phone-based life-log framework , 2013, Personal and Ubiquitous Computing.

[11]  Chaitali Chakrabarti,et al.  Lifelogging: Archival and retrieval of continuously recorded audio using wearable devices , 2012, 2012 IEEE International Conference on Emerging Signal Processing Applications.

[12]  Kiyoharu Aizawa,et al.  Efficient retrieval of life log based on context and content , 2004, CARPE'04.

[13]  Alan F. Smeaton,et al.  LifeLogging: Personal Big Data , 2014, Found. Trends Inf. Retr..

[14]  Rami Albatal,et al.  Senseseer mobile-cloud-based Lifelogging framework , 2013, 2013 IEEE International Symposium on Technology and Society (ISTAS): Social Implications of Wearable Computing and Augmediated Reality in Everyday Life.

[15]  Mohsin Ali Memon,et al.  A Digital Diary: Remembering the Past Using the Present Context , 2016 .

[16]  Michal Jacovi,et al.  Pensieve: augmenting human memory , 2008, CHI Extended Abstracts.

[17]  Vannevar Bush,et al.  As we may think , 1945, INTR.

[18]  Steve Mann,et al.  Wearable Computing: A First Step Toward Personal Imaging , 1997, Computer.

[19]  Cathal Gurrin,et al.  The smartphone as a platform for wearable cameras in health research. , 2013, American journal of preventive medicine.