=Paper=
{{Paper
|id=Vol-2097/paper3
|storemode=property
|title=Smart Self-Management for Better Working
|pdfUrl=https://ceur-ws.org/Vol-2097/paper3.pdf
|volume=Vol-2097
|authors=Fabienne Lambusch
|dblpUrl=https://dblp.org/rec/conf/emisa/Lambusch18
}}
==Smart Self-Management for Better Working==
https://ceur-ws.org/Vol-2097/paper3.pdf
Smart Self-Management for Better Working
Fabienne Lambusch1
Abstract: Work intensification and blurring boundaries between private and professional life
constitute major challenges in today's society. High working pressure and imbalances between life
domains can cause serious physical and mental health problems. Thus, personal self-management
becomes increasingly important to cope with high work demands while considering personal
resources. In recent years, sensor technology has become ubiquitous and enables new kinds of data
collection. This PhD research proposal discusses how information technology can be used to support
the enhancement of self-management competencies. The proposed approach considers a wide range
of data from several sensors that will be analysed to provide the user with comprehensive feedback.
By using smart devices, it will be possible to give situational feedback even in a mobile context.
Keywords: Self-Management, Sensors, Assistance, Work Organisation, Stress Prevention.
1 Introduction
Mobile devices such as smartphones or tablets are widely used and help us to work, learn,
and manage our social relationships. All this can be done independently of location and
time. While there are many benefits, the boundaries between life domains can become
vague with a high flexibility. Furthermore, the increasing usage of information and
communication technology can cause a high intensity of work. Resulting stress threatens
motivation, performance, wellbeing, and health [LGC04, BS05]. Especially for the
increasing proportion of knowledge-intense work [Ru17], these challenges are amplified
greatly since this kind of work goes along with a high self-responsibility. Therefore, it is
a major challenge to carefully deal with individual freedoms and resources in order to
avoid overload. In this context, individual self-management becomes increasingly
important. In a recent study, 55% of the respondents indicated a need to develop
competencies in this field [Ru17]. Self-management comprises the willingness and ability
to manage the own life responsibly and to shape it in such a way that productivity,
motivation, well-being, and balance in life are promoted and maintained over the long
term [Gr12]. As sensor technology and smart devices are increasingly integrated in
everyday life, these technologies may serve as a remedy to support people in self-
management. The aim of the presented PhD project is to develop a concept for an
assistance system supporting the diverse aspects of self-management. The next section
describes the key features of the proposed approach. Section 3 presents potential
components of an assistance system and Section 4 describes the next steps.
1
University of Rostock, Chair of Business Information Systems, Albert-Einstein-Straße 22, 18059 Rostock,
fabienne.lambusch@uni.rostock.de
17 Fabienne Lambusch
2 Proposed Approach
Enhancing self-management competencies may include the need to observe one’s
everyday behaviour, recognise necessary development steps, consequently drive the
development through concrete actions, and perform progress checks. Performing all these
actions may be challenging. The key research question for the described PhD project is,
how the potential of sensors and smart devices can be used to assist individuals in their
self-management. By using devices that are easy to integrate in daily life, a wide range of
data can be collected continuously and at runtime. Collecting data over the long term and
combining data from several sources will enable providing comprehensive feedback for
self-management. Moreover, the use of smart and wearable devices allows to remind the
user of taking actions or to intervene in certain situations unobtrusively even in a mobile
context [MW15]. In summary, the proposed innovative approach for self-management
assistance comprises the following central aspects:
Consideration of several areas and individual factors of self-management
Use of mobile and unobtrusive devices with built-in sensors
Data collection at execution time
Aggregation and analysis of data from multiple sources
Feedback on development over time
Situational guidance and interventions at execution time
3 Potential Components
A central point of the project is to bridge the gap between research in self-management
and sensor-based assistance systems. As a first step, the literature was analysed to find
features that are relevant for self-management and that can be supported by the use of
technology. The development of the system concept follows the core idea that information
systems essentially acquire or receive information, process it, and deliver relevant results
to the user. Therefore, potential components for the steps data collection, data analysis,
and feedback generation are identified and described in the following. At the current phase
of the project, a prototypic implementation of data collection and storage is developed.
Data Collection. To assist users in everyday work, data needs to be collected mainly
without user intervention and in an unobtrusive way. As smartphones and personal
computers are already widespread and integrated in daily life, these devices easily lend
itself to collect data. Furthermore, wearables such as smartwatches are unobtrusive, light-
weight, and do not interfere the user in daily processes. Smartwatches have numerous
built-in sensors [KMM17] and deliver more accurate physiological data than smartphones
[Sh15]. To consider especially the wellbeing and health aspects of self-management,
relevant data can comprise the user’s activity level (e.g. walking vs. sitting) and
physiological data (e.g. heart rate). To detect the environmental context, for example, if a
user is currently in the office or in a public park, outdoor positioning (via GPS) and indoor
positioning (e.g. via Wi-Fi, Bluetooth, or ultrasonic [Ly15]) can be used. Finally, it is
Smart Self-Management 18
possible to identify software-based work and to monitor contents related to used
applications via additional software running on the devices. The software could then run
in the background and record all types of events. By doing so, information from digital
calendars, mailing programs, writing tools, web browsers, or other tools can be retrieved.
Such information shows, for example, if the user currently is in a meeting, works on a
document, browses for information on the web or is engaged in organising and
communication. Selected data will be stored in a database. As data shall be collected and
analysed over time, the open source time series database InfluxDB2 is chosen for
implementation. It is then possible to efficiently analyse the time series data.
Data Analysis. The retrieved variety of data has to be aggregated and combined in order
to provide the user comprehensive feedback. Therefore, complex data analysis will be
necessary to detect patterns, to recognise the need for interventions, and to analyse
developments over time. Four important components of complex information are
identified yet. The first component is intended to analyse time spent on certain activities.
Using the broad range of collected information such as location, appointments, and motion
of a user, even activities where no operations on a device are performed could be
monitored. The second component focuses on workload, because a high workload in the
long-term can lead to decrements in performance, motivation, wellbeing and health
[Ho97]. To determine the general workload, the amount of tasks, appointments, emails,
opened files, and physical activity could be considered. In regard to individual workload,
changes in a user’s cognitive performance caused by mental workload can be estimated
by considering heart rate variability [Ts17]. Biological rhythms as the third component
considers the human’s circadian rhythms that drive the patterns of cognitive, behavioural,
and physiological processes (e.g. activity, sleep, and mood). Individual rhythms should be
considered, because rhythm disruption can lead to negative effects like reduced
motivation, performance, and health [FK14]. Biological rhythms could already be
associated with patterns of smartphone app use [Mu16]. Thus, the data collected from
background software on the personal computer and smartphone could be used for this
component. Furthermore, physiological and activity data would add high further value in
order to determine these rhythms or their disruption. The fourth component is conceived
for analysing the productivity status with respect to individual resources. For example, if
decreased cognitive performance is recognised, taking a break for recovery may be
productive, but randomly surfing the internet when performance is high may be not.
Therefore, information from time-consuming activities, workload, and biological rhythms
could be combined in order to analyse productivity over the long term.
Feedback Generation. The system is envisioned to support the user in reflecting
behaviour as well as in taking action for development. For the first, information on
development over time that is delivered from data analysis will be presented to the user.
Furthermore, users shall have the opportunity to define goals related to the information
presented, for example, to work on high-leverage tasks at performance peaks. In order to
encourage the user to take action for self-development, the system is envisioned to give
2
https://www.influxdata.com/
19 Fabienne Lambusch
situational feedback by providing recommendations on carrying out or omitting activities
together with a reason for the certain recommendation. The feedback could be delivered
by personal computers in a stationary context and by smartphones or smartwatches in a
mobile context. In the following, possible recommendation features are described. The
system could, for example, recognise a conflict of activities to a user defined goal and
remind to pursue the goal. Furthermore, the assistance could recommend a next task, e.g.
according to an urgent deadline recognised through an appointment. Similarly, the system
could intervene distracting actions like randomly browsing the internet. Regarding
wellbeing and health it is considered important to have recommendations of breaks and
relaxation. Generating such feedback could depend on workload and biological rhythms.
The system could recommend a break, e.g. if decreased cognitive performance is
predicted. Finally, existing mechanisms of digital calendars that warn the user when
appointments overlap could be extended to also regard workload and biological rhythms.
The system could then recommend a suitable date and time of an appointment according
to these factors, when the user is about to plan it.
4 Next Steps
The development of the system concept is seen as an iterative process by which relevant
features are identified, selected components are implemented prototypically, and the
concept is evaluated and possibly adjusted. Currently, a prototypical implementation of
the identified data collection components is carried out for a first experimental run. In this
process, an important step will be to develop an appropriate interaction of the proposed
devices and technologies. Furthermore, the suitability of retrieved data has to be examined.
Physiological data from current smartwatches, for example, may be more accurate in
workload monitoring, if user activities are characterised by little movement [Bi16]. If
higher accuracy will be required, approaches to filter misleading data could be used
[Ra17]. Sensor data could additionally be contrasted against answers from psychology
questionnaires. These can, for example, reflect a person’s experiences of positive or
negative moods [QKK09]. Considering not only measured data, but also subjective
appraisal will have an impact on the quality of system feedback to enhance individual self-
management skills. Next, the main focus of situational feedback will be specified in order
to determine which analysis components actually will be part of the project. To this end,
requirements will be determined from empirical studies. When components for data
analysis are selected, their prototypical implementation will be arranged. After collecting
first practical experiences, it will be possible to elaborate the system components.
References
[Bi16] Binsch, O.; Wabeke, T.; van Bluereplein, A.; Valk, P.: Comparison of three different
physiological wristband sensor systems and their applicability for resilience- and work
load monitoring. In 2016 IEEE 13th International Conference on Wearable and
Implantable Body Sensor Networks (BSN), pp. 272-276, 2016.
Smart Self-Management 20
[BS05] Béjean, S.; Sultan-Taïeb, H.: Modeling the economic burden of diseases imputable to
stress at work. The European Journal of Health Economics, 6(1), 16-23, 2005.
[FK14] Foster, R. G.; Kreitzman, L.: The rhythms of life: what your body clock means to you!.
Experimental Physiology, 99: 599–606, 2014.
[Gr12] Graf, A.: Selbstmanagement-Kompetenz in Unternehmen nachhaltig sichern: Leistung,
Wohlbefinden und Balance als Herausforderung, Springer Gabler, Wiesbaden, 2012.
[Ho97] Hockey, G. R. J.: Compensatory control in the regulation of human performance under
stress and high workload: A cognitive-energetical framework, Biological Psychology,
Vol. 45 Issues 1–3, pp. 73-93, 1997.
[KMM17] Kilintzis, V.; Maramis, C.; Maglaveras, N.: Wrist sensors - An application to acquire
sensory data from Android Wear® smartwatches for connected health. 2017 IEEE
EMBS International Conference on Biomedical & Health Informatics (BHI), Orlando,
FL, 2017, pp. 125-128, 2017.
[LGC04] Leka, S.; Griffiths, A.; Cox, T.: Work Organisation and Stress: systematic problem
approaches for employers, managers and trade unions representatives. Protecting
Workers’ Health series no. 3, Geneva: World Health Organisation, 2004.
[Ly15] Lymberopoulos, D.; Liu, J.; Yang, X.; Choudhury, R. R.; Handziski, V.; Sen, S.: A
realistic evaluation and comparison of indoor location technologies: experiences and
lessons learned. In Proceedings of the 14th International Conference on Information
Processing in Sensor Networks (IPSN '15). ACM, New York, NY, USA, 178-189, 2015.
[Mu16] Murnane, E. L.; Abdullah, S.; Matthews, M.; Kay, M.; Kientz, J. A.; Choudhury, T.;
Gay, G.; Cosley, D.: Mobile manifestations of alertness: Connecting biological rhythms
with patterns of smartphone app use. In Proceedings of the 18th International
Conference on Human-Computer Interaction with Mobile Devices and Services, pp.
465-477. ACM, 2016.
[MW15] Maier, J.; Wörndl, W.: Rating Methods for Proactive Recommendation on
Smartwatches, 2015.
[QKK09] Quirin, M.; Kazén, M.; Kuhl, J.: When nonsense sounds happy or helpless: the implicit
positive and negative affect test (IPANAT). Journal of personality and social
psychology, 97(3), 500-516, 2009.
[Ra17] Ra, H. K.; Ahn, J.; Yoon, H. J.; Yoon, D.; Son, S. H.; Ko, J.: I am a Smart watch, Smart
Enough to Know the Accuracy of My Own Heart Rate Sensor. In Proceedings of the
18th International Workshop on Mobile Computing Systems and Applications pp. 49-
54, 2017.
[Ru17] Rump, J. et al.: HR Report 2017 - Kompetenzen für eine digitale Welt. 2017.
[Sh15] Shoaib, M.; Bosch, S.; Scholten, H.; Havinga, P. J. M.; Incel, O. D.: Towards detection
of bad habits by fusing smartphone and smartwatch sensors, 2015 IEEE International
Conference on Pervasive Computing and Communication Workshops (PerCom
Workshops), St. Louis, MO, 2015, pp. 591-596, 2015.
[Ts17] Tsunoda, K.; Chiba, A.; Yoshida, K.; Watanabe, T.; Mizuno, O.: Predicting Changes in
Cognitive Performance Using Heart Rate Variability, IEICE TRANSACTIONS on
Information and Systems, 100(10), 2411-2419, 2017.