| 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. |
- Cleland, Ian, et al.
(författare)
-
Collection of a Diverse, Naturalistic and Annotated Dataset for Wearable Activity Recognition
- 2018
-
Ingår i: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). - : IEEE. ; , s. 555-560
-
Konferensbidrag (refereegranskat)abstract
- This paper discusses the opportunities and challenges associated with the collection of a large scale, diverse dataset for Activity Recognition. The dataset was collected by 141 undergraduate students, in a controlled environment. Students collected triaxial accelerometer data from a wearable accelerometer whilst each carrying out 3 of the 18 investigated activities, categorized into 6 scenarios of daily living. This data was subsequently labelled, anonymized and uploaded to a shared repository. This paper presents an analysis of data quality, through outlier detection and assesses the suitability of the dataset for the creation and validation of Activity Recognition models. This is achieved through the application of a range of common data driven machine learning approaches. Finally, the paper describes challenges identified during the data collection process and discusses how these could be addressed. Issues surrounding data quality, in particular, identifying and addressing poor calibration of the data were identified. Results highlight the potential of harnessing these diverse data for Activity Recognition. Based on a comparison of six classification approaches, a Random Forest provided the best classification (F-measure: 0.88). In future data collection cycles, participants will be encouraged to collect a set of “common” activities, to support generation of a larger homogeneous dataset. Future work will seek to refine the methodology further and to evaluate model on new unseen data.
|
|
| 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. |
- 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.
|
|
| 5. |
|
|
| 6. |
- 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.
|
|
| 7. |
- 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.
|
|
| 8. |
- 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.
|
|
| 9. |
|
|
| 10. |
- Beattie, Mark, et al.
(författare)
-
A Collaborative Patient-Carer Interface for Generating Home Based Rules for Self-Management
- 2015
-
Ingår i: Smart Homes and Health Telematics. - New York : Encyclopedia of Global Archaeology/Springer Verlag. - 9783319144238 - 9783319144245 ; , s. 93-102
-
Konferensbidrag (refereegranskat)abstract
- The wide spread prevalence of mobile devices, the decreasing costs of sensor technologies and increased levels of computational power have all lead to a new era in assistive technologies to support persons with Alzheimer’s disease. There is, however, still a requirement to improve the manner in which the technology is integrated into current approaches of care management. One of the key issues relating to this challenge is in providing solutions which can be managed by non-technically orientated healthcare professionals. Within the current work efforts have been made to develop and evaluate new tools with the ability to specify, in a non-technical manner, how the technology within the home environment should be monitored and under which conditions an alarm should be raised. The work has been conducted within the remit of a collaborative patient-carer system to support self-management for dementia. A visual interface has been developed and tested with 10 healthcare professionals. Results following a post evaluation of system usability have been presented and discussed.
|
|
