See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/312562960

A Digital Diary Making System Based on User Life-Log

Conference Paper · December 2016

DOI: 10.1007/978-3-319-51969-2_17

CITATIONS READS

0 3,475

3 authors, including:

Byungseok Kang
University of Derby
42 PUBLICATIONS   324 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Special Issue on: CloudIoT: Convergence services between the Cloud and IoT View project

All content following this page was uploaded by Byungseok Kang on 01 November 2017.

The user has requested enhancement of the downloaded file.

 A Digital Diary Making System Based on User Life-Log

Yechan Park ✉ , Byungseok Kang, and Hyunseung Choo

( )

College of Software, Sungkyunkwan University, Suwon, Korea

{dpcks001,byungseok,choo}@skku.edu

Abstract. A common digital diary system is a software technology that proactively

suggests contents of interest to users based on various kinds of context information.
It provides benefits to users and meets their satisfaction. This research was motivated
by our interest in understanding the criteria for measuring the success of a diary
making system from users’ point of view. Even though existing work has introduced
a wide range of criteria such as users’ biological information, picture, movie, etc. In
this paper, we propose a digital diary making system which aimed at measuring the
user emotion from their life-log data (daily-life photos). We can get those life-log data
from user’s smartphone storage. The final product of digital diary includes feeling,
time, and physical location information.

Keywords: Life-log · Digital diary · User emotion · Diary making system

1 Introduction

Smartphones are rising the mobile phone market [1]; they are not just phones; they also
act as media players, gaming consoles, personal calendars, storage, etc. They are small
size portable computers with fewer computing capabilities than PCs. However, unlike
PCs, users can carry their smartphone with them at all times. The ubiquity of mobile
phones and their computing capabilities provide an opportunity of using them as a life-
logging device. Life-logs [2, 3] are used to record user daily life events and assist them
in memory augmentation. In a more technical sense, life-logs sense and store users
contextual information from their environment through sensors, which are core compo‐
nents of life-logs.
A life-logging by digital system [4, 5] means to record our daily life in detail. To
date we have only relied on our human memory to record and remember our daily expe‐
rience. The human brain tends to quickly lose the details of his/her experiences. There‐
fore, we record special events such as party and travel with photos and videos. Excluding
such special events, we rarely record the daily experiences that are the major part of our
life; what we do at most is write a short diary. Because of developing technologies related
to information and communication technology (ICT), ubiquitous and high bandwidth
4G/LTE mobile networks we believe that we will be able to automatically capture and
record our daily experiences. With this context, research on the capture and retrieval of
life-logs is emerging quickly.
Several works introduce capturing a life-log [6–9] by audio and video with various
sensors such as a GPS (location), gyros, physiological sensors (brain wave), acceleration

© Springer International Publishing AG 2016

C.-H. Hsu et al. (Eds.): IOV 2016, LNCS 10036, pp. 206–213, 2016.
DOI: 10.1007/978-3-319-51969-2_17
 A Digital Diary Making System Based on User Life-Log 207

sensors (motion), documents, annotations and emails. Retrieval is the most important
problem for the life-log system. The amount of multimedia data captured is very large,
and the problem is to find valuable photo/image through the data. Remembering the
feeling or emotion of our experiences is easier than remembering details of them, so the
emotion can provide valuable keys for life-logging system. We have developed a user
emotion based life-logging system, by which we can take a photo by parameters such
as time, location, and emotion. In the following sections, a literature review on life-
logging system and platform technologies are presented in Sect. 2. In Sect. 3, we detail
our proposed digital diary making system. Finally, we conclude the paper in Sect. 4.

2 Related Work

The field of life-logging is a relatively new but rapidly expanding area of research and
it has been recognize that a visual life-log should be segmented into manageable shots,
activities and events to make it manageable. In this section we discuss the most known
contributions of life-logs in the literature. Life-log sources can be classified into sub
categories from various perspectives. From one view point, they can be classified into
biological data, multimedia data, etc. Figure 1 shows the categorization of previous
works for life-log sources.

Fig. 1. Classification of life-log

In [10], they introduced a smartphone-based personal data management and person‐

ality analysis system. In their system, the smartphone functions as not only a source of
personal data but also a gateway to manage other wearable and communicate with a
server that keeps personal data in a larger amount and a longer period. In [11] investi‐
gated how life-logs from commercial wearable trackers and smartphone sensors can be
leveraged to automatically provide patients with knowledge for self-reflection on their
disease. In this paper, they present an architecture for the acquisition of life-logs, fusion,
storage and prototype GUI for the visualization of quality of life indicators.
The work of [12] introduced state-of-the-art literature on wearable diaries and life-
logging systems, and discuss the key issues and main challenges. The multimedia-based
diary system offers an aesthetic user interface that encourages users to reflect on their
day, to evaluate their emotional reactions which are measured by wearable bio-sensors
and visualized as colorful images. In [13], they developed a platform for recording,
storing, and accessing a personal lifetime archive. The goals of proposed system
included understanding the effort to digitize a lifetime of legacy multimedia contents.
In [2] presented continuous capture of life-log with various sensors and additional data.
Furthermore, they proposed an effective retrieval methods using multimedia contents.
Their life-log system contains video, audio, acceleration sensor, gyro, GPS, annotations,
documents, web pages, and emails.
208 Y. Park et al.

Fig. 2. Basic architecture and modules of proposed system

In [14] presented an application to support users to do their homework, especially

self-monitoring of user behaviors. By collecting life-logs of users via smart phones, their
proposed application estimates user activities based on life-logs. The work of [15]
described digital diary concept in more detail and also provide an overview of related
diary and timeline applications. Additionally, they presented a proof of concept imple‐
mentation as well as results of an early user experience evaluation.

3 Proposed System

This section presents the software implementation of the life-log based digital diary
making system. Our system mainly classified into three parties: user smartphone, project
Oxford [16] server and System Sens Plus (SSP) server. We adapt Oxford server for
image processing and modified standard source of System Sens [17] system for storing
user photos.

3.1 Architecture and Modules

Our system has adopted the client/server mode where the smartphone acts as a client
and project Oxford and System Sens acts as a server. The general system architecture
and modules in both client and server sides are shown in Fig. 2. For the client, the
smartphone itself can provide a plenty of usage data and sensing data. For instance, an
iPhone has two integrated interfaces, HomeKit and HealthKit. In addition, sensors
embedded in a smartphone can also be used to get GPS, light, acceleration, pressure and
other data. Currently many wearable offer a network such as Bluetooth to connect a
smartphone. Thus, a smartphone can take the data from wearable such as smart watch,
bracelet, ring, etc. Further, a smartphone can be used to get information such as weather
from outside APPs and SNS via the Internet.
 A Digital Diary Making System Based on User Life-Log 209

In our system, smartphone client includes two main modules such as camera and
dairy application. In case of camera, this module equipped high-quality sensors,
powerful shooting modes and multitude of camera settings, smartphones have shown
point-and-shoot cameras the door. The main function of this module is collecting and
merging user photos. The other main module of smartphone is diary application module.
This module associated with data select and data retrieval. We developed this application
under the Android 6.0 code name Marshmallow [18].
The Project Oxford server is developed by Microsoft. We use the API of this server
to provide user emotion based on “Face Recognition” technology. This Oxford server
automatically recognizes faces in photos, group faces that look alike and verifies whether
two faces are the same. It can be used for things like easily recognizing which users are
in certain photos and allowing a user to log in using face authentication. It’s the same
technology that guesses how old a person looks based on a photograph. This server
includes communication manager, data analysis and data extraction module. Data anal‐
ysis module is the key in Oxford server.
System Sens [17] is developed by UCLA research center. This system help
researcher capture usage context in their deployments in an extendible way. System Sens
is designed to be unobtrusive-it has no user interface to minimize impact on usage, and
it has a small footprint in terms of memory, CPU, and energy consumption. The DB
module is for persistently keeping all data from many users. The communication module
provides stable and safe communications between a smartphone and two servers are
essential in the system. We modified original source code of System Sens for effectively
managing the user photos and related tagging information. Therefore, we called this
system as System Sens Plus.

3.2 Photo Collection and Diary Making Process

The personal data in our system is from various sources in different forms. It is thus
necessary to control and coordinate the data collections from the multiple sources. The
data collection control is according to a file of the collection schedules that is stored in
the System Sens Plus. The schedules specify that when data will be captured or acquired
for user smartphone. Due to the data heterogeneity, the schedule for a data source is
decided with considerations of data change rate, collection condition, local DB capacity,
upload situation, etc. Another factor to be considered in setting the schedules is the
energy consumption of a smartphone battery. It is necessary to make some tradeoff
between the frequency of data collection and the reduction of power usage.
210 Y. Park et al.

Fig. 3. Flow chart for collection user photos

To collect user photos, smartphone takes a photo and sends it to the Oxford server.
After that, Oxford server analyzes received photo whether human face or not based on
the rules of its image processing engine. Next, the server tags emotion information based
on analyzing result of receiving photo. Finally, System Sens Plus stores user photo and
its tagging data (emotion, time, and location). The detail data collection process is
described in Fig. 3.
To provide life-log diary, we developed Android base diary application and installed
it to the user smartphone. Android is an open source and Linux-based operating system
for mobile devices such as smartphones and tablet computers. Android was developed
by the Open Handset Alliance, led by Google, and other companies. For this experi‐
mental study, we use newly published Android Marshmallow. Figure 4 shows basic step
of producing digital diary. Firstly, user executes diary application from his/her mobile
device and selects one event. Secondly, diary application requests associated data to
System Sens Plus server. Finally, user application retrieves the results. Figure 5 shows
the screenshot of life-log diary. We divide user emotion into three categories [19, 20]
such as happiness, neutral, and sadness. Our system also provides daily emotion
 A Digital Diary Making System Based on User Life-Log 211

Fig. 4. Flow chart for producing life-log diary

information and Google Map service based on physical location of user photos (see
Fig. 5).

Fig. 5. Output of digital diary

212 Y. Park et al.

4 Conclusion

To overcome the limitation of making digital diary, we implemented an emotion based

life-logging which is familiar to user. We proposed digital diary system reflecting user
preference based on emotion and context information which can obtain from mobile
devices. For future works, we will verify the usefulness from usability tests, and enlarge
the data set including the number of case samples as well as the types of various user
activities.

Acknowledgments. This work was supported in part by the Ministry of Science, ICT and Future
Planning, South Korea, Institute for Information and Communications Technology Promotion
through the G-ITRC Program under Grant IITP-2015-R6812-15-0001 and in part by the National
Research Foundation of Korea within the Ministry of Education, Science and Technology through
the Priority Research Centers Program under Grant 2010-0020210.

References

1. Goasduff, L., Pettey, C.: Gartner says worldwide smartphone sales soared in fourth quarter of
2011 with 47 percent growth, April 2012
2. Aizawa, K., Tancharoen, D., Kawasaki, S., Yamasaki, T.: Efficient retrieval of life log based
on context and content. In: Proceedings of the 1st ACM Workshop on Continuous Archival
and Retrieval of Personal Experiences, pp. 22–31. ACM (2004)
3. Hori, T., Aizawa, K.: Context-based video retrieval system for the life-log applications. In:
Proceedings of the 5th ACM SIGMM International Workshop on Multimedia Information
Retrieval, pp. 31–38. ACM (2003)
4. Tancharoen, D., Yamasaki, T., Aizawa, K.: Practical experience recording and indexing of
life log video. In: Proceedings of the 2nd ACM Won Continuous Archival and Retrieval of
Personal Experiences, pp. 61–66. ACM (2005)
5. Minamikawa, A., Kotsuka, N., Honjo, M., Morikawa, D., Nishiyama, S., Ohashi, M.: Rfid
supplement for mobile-based life log system. In: 2007 International Symposium on
Applications and the Internet Workshops (2007)
6. Hwang, K.-S., Cho, S.-B.: Landmark detection from mobile life log using a modular Bayesian
network model. Expert Syst. Appl. 36(10), 12065–12076 (2009)
7. Abe, M., Morinishi, Y., Maeda, A., Aoki, M., Inagaki, H.: A life log collector integrated with
a remote-controller for enabling user centric services. IEEE Trans. Cons. Electron. 55(1), 295–
302 (2009)
8. Ryoo, D.-W., Bae, C.: Design of the wearable gadgets for life-log services based on utc. IEEE
Trans. Cons. Electron. 53(4), 1477–1482 (2007)
9. Makino, Y., Murao, M., Maeno, T.: Life log system based on tactile sound. In: Kappers,
A.M.L., Erp, J.B.F., Bergmann Tiest, W.M., Helm, F.C.T. (eds.) EuroHaptics 2010. LNCS,
vol. 6191, pp. 292–297. Springer, Heidelberg (2010). doi:10.1007/978-3-642-14064-8_42
10. Guo, A., Ma, J.: A smartphone-based system for personal data management and personality
analysis. In: 2015 IEEE International Conference on Computer and Information Technology;
Ubiquitous Computing and Communications; Dependable, Autonomic and Secure
Computing; Pervasive Intelligence and Comput ing (CIT/IUCC/DASC/PICOM), pp. 2114–
2122. IEEE (2015)
 A Digital Diary Making System Based on User Life-Log 213

11. Zini, F., Reinstadler, M., Ricci, F.: Life-logs aggregation for quality of life monitoring. In:
Proceedings of the 5th International Conference on Digital Health 2015, pp. 131–132. ACM
(2015)
12. Machajdik, J., Hanbury, A., Garz, A., Sablatnig, R.: Affective com - puting for wearable diary
and lifelogging systems: an overview. In: Machine Vision-Research for High Quality
Processes and Products-35th Workshop of the Austrian Association for Pattern Recognition.
Austrian Computer Society (2011)
13. Gemmell, J., Bell, G., Lueder, R.: Mylifebits: a personal database for everything. Commun.
ACM 49(1), 88–95 (2006)
14. Kawanishi, N., Tamai, M., Hasegawa, A., Takeuchi, Y., Tajika, A., Ogawa, Y., Furukawa,
T.: Lifelog-based estimation of activity diary for cognitive behavioral therapy. In: Adjunct
Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous
Computing and Proceedings of the 2015 ACM International Symposium on Wearable
Computers, pp. 1251–1256. ACM (2015)
15. Jilek, C., Maus, H., Schwarz, S., Dengel, A.: Diary generation from personal information
models to support contextual remembering and reminiscence. In: 2015 IEEE International
Conference on Multimedia & Expo Workshops (ICMEW), pp. 1–6. IEEE (2015)
16. Microsoft Cognitive Services. https://www.microsoft.com/cognitive-services/. Accessed 23
Aug 2016
17. Mahajan, F.R., Estrin, D.: Systemsens: a tool for monitoring usage in smartphone research
deployments. In: Proceedings of the Sixth International Workshop on MobiArch, pp. 25–30.
ACM (2011)
18. Android6.0 Marshmallow. https://www.android.com/. Accessed 23 Aug 2016
19. Lopes, P.N., Salovey, P., Coté, S., Beers, M., Petty, R.E.: Emotion regulation abilities and the
quality of social interaction. Emotion 5(1), 113 (2005)
20. Gross, J.J., Thompson, R.A.: Emotion regulation: conceptual foundations (2007)

View publication stats