| 1. |
- Nugent, Christopher, et al.
(författare)
-
Improving the Quality of User Generated Data Sets for Activity Recognition
- 2016
-
Ingår i: Ubiquitous Computing and Ambient Intelligence, UCAMI 2016, PT II. - Amsterdam : Springer Publishing Company. - 9783319487991 - 9783319487984 ; , s. 104-110
-
Konferensbidrag (refereegranskat)abstract
- It is fully appreciated that progress in the development of data driven approaches to activity recognition are being hampered due to the lack of large scale, high quality, annotated data sets. In an effort to address this the Open Data Initiative (ODI) was conceived as a potential solution for the creation of shared resources for the collection and sharing of open data sets. As part of this process, an analysis was undertaken of datasets collected using a smart environment simulation tool. A noticeable difference was found in the first 1-2 cycles of users generating data. Further analysis demonstrated the effects that this had on the development of activity recognition models with a decrease of performance for both support vector machine and decision tree based classifiers. The outcome of the study has led to the production of a strategy to ensure an initial training phase is considered prior to full scale collection of the data.
|
|
| 2. |
- Synnes, Kåre, 1969-, et al.
(författare)
-
CyberParks Songs and Stories : Enriching Public Spaces with Localized Culture Heritage Material such as Digitized Songs and Stories
- 2019
-
Ingår i: CyberParks - The Interface Between People, Places and Technology. - Cham : Springer. - 9783030134167 ; , s. 224-237
-
Bokkapitel (refereegranskat)abstract
- This chapter offers theoretical considerations and reflections on technological solutions that contribute to digitally supported documentation, access and reuse of localised heritage content in public spaces. It addresses immaterial cultural heritage, including informal stories that could emerge and be communicated by drawing hyperlinks between digitised assets, such as songs, images, drawings, texts and more, and not yet documented metadata, as well as augmenting interaction opportunities with interactive elements that relate to multiple media stored in databases and archives across Europe. The aim is to enable cultural heritage to be experienced in novel ways, supported by the proliferation of smartphones and ubiquitous Internet access together with new technical means for user profiling, personalisation, localisation, contextawareness and gamification. The chapter considers cyberparks as digitally enhanced public spaces for accessing and analyzing European cultural heritage and for enriching the interpretation of the past, along with theoretical ramifications and technological limitations. It identifies the capacities of a proposed digital environment together with design guidelines for interaction with cultural heritage assets in public spaces. The chapter concludes with describing a taxonomy of digital content that can be used in order to enhance association and occupation conditions of public spaces, and with discussing technological challenges associated with enriching public spaces with localized cultural heritage material.
|
|
| 3. |
- Cruciani, Federico, et al.
(författare)
-
Personalized Online Training for Physical Activity monitoring using weak labels
- 2018
-
Ingår i: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). - : IEEE. - 9781538632277 ; , s. 567-572
-
Konferensbidrag (refereegranskat)abstract
- The use of smartphones for activity recognition is becoming common practice. Most approaches use a single pretrained classifier to recognize activities for all users. Research studies, however, have highlighted how a personalized trained classifier could provide better accuracy. Data labeling for ground truth generation, however, is a time-consuming process. The challenge is further exacerbated when opting for a personalized approach that requires user specific datasets to be labeled, making conventional supervised approaches unfeasible. In this work, we present early results on the investigation into a weakly supervised approach for online personalized activity recognition. This paper describes: (i) a heuristic to generate weak labels used for personalized training, (ii) a comparison of accuracy obtained using a weakly supervised classifier against a conventional ground truth trained classifier. Preliminary results show an overall accuracy of 87% of a fully supervised approach against a 74% with the proposed weakly supervised approach.
|
|
| 4. |
- Drugge, Mikael, et al.
(författare)
-
Eventcasting with a wearable computer
- 2004
-
Ingår i: Proceedings, 24th International Conference on Distributed Computing Systems workshops. - Los Alamitos, Calif : IEEE Computer Society Press. - 0769520871 ; , s. 408-413, s. 408-413
-
Konferensbidrag (refereegranskat)abstract
- Traditionally, interaction methods for wearable computers have focused on input to the computer itself, yet little has been done when it comes to allowing interaction with the surrounding environment. Pervasive computing, on the other hand, offers access to computational power from any place all the time, yet most interaction techniques utilize either physical hardware or monitoring of the user in order to receive input. This paper presents a novel form of interaction by which a wearable computer user can interact with and control a pervasive computing environment in a natural and intuitive manner. Using sensors, the user can be allowed to literally "throw" events into the environment as a way of interacting with devices and computers
|
|
| 5. |
- Hallberg, Josef, et al.
(författare)
-
Positioning with Bluetooth
- 2003
-
Ingår i: 10th International Conference on Telecommunications. - Piscataway, NJ : IEEE Communications Society. - 0780376617 ; , s. 954-958
-
Konferensbidrag (refereegranskat)abstract
- This paper presents an evaluation of Bluetooth positioning in a general positioning platform. Proceeding the evaluation a Bluetooth based positioning system was implemented in order to complement the theoretical evaluation with empirical tests. Three different ways of positioning with Bluetooth have been developed. With a registered positioning service a Bluetooth device has an active role in the positioning task as it sends a position on request. A Bluetooth device can also take a more passive role in a positioning task, where the unique address of the device is used by a connected device to look up respective position in a database. It is also possible to forward a position gained from the positioning platform using the peer to peer characteristics in Bluetooth. This paper does also contain a discussion on the theoretical time requirements for a positioning system based on Bluetooth. Empirical tests show that these requirements hold.
|
|
| 6. |
- Nilsson, Marcus, et al.
(författare)
-
A study on users' preference on interruption when using wearable computers and head mounted displays
- 2005
-
Ingår i: Third IEEE International Conference on Pervasive Computing and Communications, PerCom 2005. - Los Alamitos : IEEE Computer Society Press. - 0769522998 ; , s. 149-158, s. 149-158
-
Konferensbidrag (refereegranskat)abstract
- An important part of making a wearable computer un-obtrusive is the user interface and the way it interrupts the user. The amount of interruption that have to be made on the users primary task should be minimized. Usage without interruption is of course best for the performance of the primary task but is often not possible as many tasks that the wearable computer is involved in do need interaction with the user. It is therefore important to understand what type of interruption that will benefit the user most. The question about which interruption that causes the least amount of stress for the user is as important as which interruption that gives the best performance. This paper continues on previous work where performance of the users was measured for different types of interruption. In this paper subjective data is analyzed to understand how to build user interfaces for wearable computers and head mounted displays that considers stress and other subjective variables.
|
|
| 7. |
|
|
| 8. |
- Karvonen, Niklas, 1979-
(författare)
-
Unobtrusive Activity Recognition in Resource-Constrained Environments
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis discusses activity recognition from a perspective of unobtrusiveness, where devices are worn or placed in the environment without being stigmatising or in the way. The research focuses on performing unobtrusive activity recognition when computational and sensing resources are scarce. This includes investigating unobtrusive ways to gather data, as well as adapting data modelling and classification to small, resource-constrained, devices.The work presents different aspects of data collection and data modelling when only using unobtrusive sensing. This is achieved by considering how different sensor placements affects prediction performance and how activity models can be created when using a single sensor, or when using a number of simple binary sensors, to perform movement analysis, recognise everyday activities, and perform stress detection. The work also investigates how classification can be performed on resource-constrained devices, resulting in a novel computation-efficient classifier and an efficient hand-made classification model. The work finally sets unobtrusive activity recognition into real-life contexts where it can be used for interventions to reduce stress, sedentary behaviour and symptoms of dementia.The results indicate that activities can be recognised unobtrusively and that classification can be performed even on resource-constrained devices. This allows for monitoring a user’s activities over extensive periods, which could be used for creating highly personal digital interventions and in-time advice that help users make positive behaviour changes. Such digital health interventions based on unobtrusive activity recognition for resource-constrained environments are important for addressing societal challenges of today, such as sedentary behaviour, stress, obesity, and chronic diseases. The final conclusion is that unobtrusive activity recognition is a cornerstone necessary for bringing many digital health interventions into a wider use.
|
|
| 9. |
- Kikhia, Basel, et al.
(författare)
-
Structuring and Presenting Lifelogs based on Location Data
- 2014
-
Ingår i: Pervasive Computing Paradigms for Mental Health. - Cham : Encyclopedia of Global Archaeology/Springer Verlag. - 9783319115634 ; , s. 133-144
-
Konferensbidrag (refereegranskat)abstract
- Lifelogging techniques help individuals to log their life and retrieve important events, memories and experiences. Structuring lifelogs is a major challenge in lifelogging systems since the system should present the logs in a concise and meaningful way to the user. In this paper the authors present an approach for structuring lifelogs as places and activities based on location data. The structured lifelogs are achieved using a combination of density-based clustering algorithms and convex hull construction to identify the places of interest. The periods of time where the user lingers at the same place are then identified as possible activities. In addition to structuring lifelogs the authors present an application in which images are associated to the structuring results and presented to the user for reviewing. The system is evaluated through a user study consisting of 12 users, who used the system for 1 day and then answered a survey. The proposed approach in this paper allows automatic inference of information about significant places and activities, which generates structured image-annotated logs of everyday life.
|
|
| 10. |
- Kikhia, Basel, et al.
(författare)
-
Structuring and presenting lifelogs based on location data
- 2012
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Lifelogging techniques help individuals to log their life and retrieve important events, memories and experiences. Structuring lifelogs is a major challenge in lifelogging systems since the system should present the logs in a concise and meaningful way to the user. In this article the authors present a novel approach for structuring lifelogs as places and activities based on location data. The structured lifelogs are achieved using a combination of density-based clustering algorithms and convex hull construction to identify the places of interest. The periods of time where the user lingers at the same place are then identified as possible activities. In addition to structuring lifelogs the authors present an application in which images are associated to the structuring results and presented to the user for reviewing. The proposed approach allows automatic inference of information about significant places and activities, which generates structured image-annotated logs of everyday life.
|
|
