Monday, September 9, 2013

UbiMI'13 summary

Workshop Videos

Keynote and Q&A session

Workshop papers







Workshop: code + slides

AWARE-activity recognition application:
http://www.awareframework.com/workshop/ubisports.zip

Supporting slides:
http://www.awareframework.com/workshop/slides.pdf

Friday, August 2, 2013

UbiMI'13 Schedule

Dear authors and participants,

Here is the schedule for this year's edition of UbiMI'13 Ubiquitous Mobile Instrumentation. The workshop will be located at: ETH Zentrum - CAB G 52

We look forward to meet you and see you at UbiComp'13!

The UbiMI organizers,

Please note: Each author will present his workshop paper (up to 10 minutes), followed by a short (5 minutes) discussion.

September 8


Session 1
9-9:30 Prof. Vassilis Kostakos - Mobile Instrumentation in Academia
9:30-10 Dr. Jonna Häkkilä - Mobile Instrumentation in Industry
10-10:30 Q&A with keynote speakers

Session 2
11-11:15 Marshall, J.
Smartphone Sensing for Distributed Swim Stroke Coaching and Research
11:15-11:30 Üstev, Y.E., Ersoy, C. and Incel, O.D.
User, Device and Orientation Independent Human Activity Recognition on Mobile Phones: Challenges and a Proposal
11:30-11:45 Gamecho, B., Gardeazabal, L. and Abascal, J.
Combination and Abstraction of Sensors for Mobile Context-Awareness
11:45-12 Böhmer, M., Lander, C. and Krüger, A.
What's in the Apps for Context? Extending a Sensor for Studying App Usage to Informing Context-awareness
12-12:15 Bustos-Jiménez, J., Del Canto, G., Pereira, S., Lalanne, F., Piquer, J., Hourton, G., Cádiz, A. and Ramiro, V.
How AdkintunMobile Measured the World
12:15-12:30 Besaleva, L.I. and Weaver, A.C.
CrowdHelp: Application for Improved Emergency Response through Crowdsourced Information

Session 3 
14:00-14:15 Gustarini, M., Ickin, S. and Wac, K.
Evaluation of Challenges in Human Subjects Studies "In-the-Wild" Using Subjects' Personal Smartphones
14:15-15:00 Q&A discussion amongst participants
15-15:30 AWARE: Introduction

Session 4
16-16:30 AWARE: Demo
16:30-18 AWARE: downloading, installing, setting up!

September 9


Session 1
9-10:30 AWARE: building blocks.

Session 2
11-12:30 AWARE: create, use, and reuse a Context Sensor / Plugin

Session 3
14-15:30 AWARE: create, use, and reuse a Context Provider

Session 4
16-18 AWARE Q&A and wrap-up.

Tuesday, June 11, 2013

UbiMI'13 Papers accepted

Marshall, J. Smartphone Sensing for Distributed Swim Stroke Coaching and Research. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
AbstractCurrent methods of swim stroke learning rely on a combination of external observation by coaches and repetitive drills performed by swimmers. At elite levels, these may be augmented using complex and expensive augmented pool environments and video analysis, but these are not available to most non-professionals. In this paper, I argue that with the wide range of sensors and outputs on a current smartphone, and existing sports-targeted waterproofing, commodity mobile hardware may allow even un-coached amateur swimmers to access timely feedback on their stroke and to improve their swimming. An early prototype of a swim-sensing system demonstrates the potential of mobiles to sense aspects of the swimming stroke. By using commodity hardware it is open to many potential learners, who may in turn provide high quality data to feed back into the development of swim coaching techniques by sports researchers and practitioners.

Gamecho, B., Gardeazabal, L. and Abascal, J. Combination and Abstraction of Sensors for Mobile Context-Awareness. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
Abstract: In this paper, we describe a context server application for mobile computing. Its main objective is to assist developers to exploit context-aware features in their applications. This approach uses the extraction of new context information using a combination of sensors and proposes a sensing abstraction layer to avoid having to deal with specific hardware.

Böhmer, M., Lander, C. and Krüger, A. What's in the Apps for Context? Extending a Sensor for Studying App Usage to Informing Context-awareness. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
Abstract: Mobile phones became multi-purpose devices supporting their users with large variety of applications for various tasks. Not only the number of available applications is increasing, also the number of applications people are using on their devices is growing, as well as the amount of time people spent on their smartphones daily is getting bigger. In this workshop paper, we briefly describe our past work on understanding mobile application usage. We explain our research tool for measuring mobile application usage, called AppSensor, and discuss possibilities to exploit the information of mobile application usage to inform the reasoning about users’ contexts. We contribute our source code to the workshop for a discussion and prototyping of use cases leveraging the information of which application a user is currently using.

Üstev, Y.E., Ersoy, C. and Incel, O.D. User, Device and Orientation Independent Human Activity Recognition on Mobile Phones: Challenges and a Proposal. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
Abstract: Smart phones equipped with a rich set of sensors are explored as alternative platforms for human activity recognition in the ubiquitous computing domain. However, there exist challenges that should be tackled before the successful acceptance of such systems by the masses. In this paper, we particularly focus on the challenges arising from the differences in user behavior and in the hardware. To investigate the impact of these factors on the recognition accuracy, we performed tests with 20 different users focusing on the recognition of basic locomotion activities using the accelerometer, gyroscope and magnetic field sensors. We investigated the effect of feature types, to represent the raw data, and the use of linear acceleration for user, device and orientation-independent activity recognition.

Besaleva, L.I. and Weaver, A.C. CrowdHelp: Application for Improved Emergency Response through Crowdsourced Information. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
Abstract: Emergency resources are often insufficient to satisfy fully the demands for professional help and supplies after a public disaster. Furthermore, in a mass casualty situation, the emphasis shifts from ensuring the best possible outcome for each individual patient to ensuring the best possible outcome for the greatest number of patients. In the past several years, an ongoing movement among crisis management organizations is the incorporation of ubiquitous Web 2.0 tools into their practices for the improvement of their critical situations response. In unison with this trend and the latest discoveries in crowdsourcing, we have developed a system, called CrowdHelp, for real time patient assessment which uses mobile electronic triaging accomplished via crowdsourced and sensor-detected information. With the use of our system, emergency management professionals receive most of the information they need for preparing themselves to perform a timely and accurate treatment of their patients even before dispatching a response team to the event.

Gustarini, M., Ickin, S. and Wac, K. Evaluation of Challenges in Human Subjects Studies "In-the-Wild" Using Subjects' Personal Smartphones. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
Abstract: The experimental setting of Human Mobile Computer Interaction (HCI) studies is moving from the controlled laboratory to the user’s daily-life environments, while employing the users’ own smartphones. These studies are challenging for both new and expert researchers in human subject studies in the HCI field. Within the last three years, we conducted three different smartphone- based user studies. From these studies, we have derived key challenges that we successfully overcame during their execution. In this paper, we present the outcomes and explain the adopted solutions for the challenges identified in the design, development and execution, and data analysis phases during the user studies. Our goal is to give newcomers and junior researchers a practical view on our conducted studies, and help practitioners to reflect on their own studies and possibly apply the proposed solutions.

Bustos-Jiménez, J., Del Canto, G., Pereira, S., Lalanne, F., Piquer, J., Hourton, G., Cádiz, A. and Ramiro, V. How AdkintunMobile Measured the World. In Adj. Proc. UbiComp'13, Ubiquitous Mobile Instrumentation (UbiMI'13)
Abstract: On this article we present the Adkintun Mobile Project: using passive monitors to measure the Quality of Service of Chilean Mobile Internet Providers, based on the metrics of antenna coverage and Internet connectivity. We present the main ideas, design decisions, development issues and setbacks of the project. Our contribution is to present to the readers the whole process of a project like this, which is based in volunteering and political decisions.

Thursday, March 21, 2013

Welcome to UbiMI'13!

Thanks to the rapid development of mobile technologies, smartphones allow people to be reachable anywhere and anytime. In addition to the benefits for end users, researchers and developers can also benefit from the powerful devices that participants potentially carry on a daily basis. This mini-track workshop brings together researchers with an interest on using mobile devices as instruments to collect data and conduct mobile user studies, with a focus on understanding human-behavior, routines and gathering context.

Recruiting a large number of participants for user studies in HCI has been challenging (i.e., participation compensation, location and time differences, etc.). Techniques such as surveys and questionnaires for data collection have taken a new form in recent years, where “in the field” has been replaced with “online”; and automated logging devices have augmented diaries, video recorders and cameras (e.g., Microsoft’s SenseCam, Nokia’s LifeBlog). This shift represents a new trend in research methods, whereby mobile devices are used to collect data on participants and their behaviors.

In this workshop, we bring together researchers who take advantage of the proliferation of mobile devices and use them as instruments for research on ubiquitous computing. We are especially interested in the mobile devices, systems, applications, methods and tools that were built to explore such rich datasets. More so, we want researchers to share their experiences, successes and frustrations on conducting research in such power and processing constrained devices in order to capture a state-of-art on theories, models, methodologies and tools that cope with these challenges.