On-body activity recognition in a dynamic sensor network

Lombriser, Clemens; Bharatula, Nagendra Bhargava; Roggen, Daniel; Tröster, Gerhard

doi:10.4108/bodynets.2007.114

Cited by 58 publications

(31 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Seven sensors have been selected including accelerometer, temperature, altimeter, gyroscope, barometer, light, and heart rate monitor. These sensors have been used in several prior works [5,6,7,9,12,13,14,15]. A study showed that by using gyroscope and magnetometer with accelerometer, the classification accuracy is increased by 17% [13].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A practical multi-sensor activity recognition system for home-based care

Chernbumroong

Cang

2014

Decision Support Systems

View full text Add to dashboard Cite

To cope with the increasing number of ageing population, a type of care which can help prevent or postpone entry into institutional care is preferable. Activity recognition can be used for home-based care in order to help elderly people to remain at home as long as possible. This paper proposes a practical multi-sensor activity recognition system for home-based care utilizing on-body sensors. Seven types of sensors are investigated on their contributions toward activity classification. We collected a real data set through the experiments participated by a group of elderly people. Seven classification models are developed to explore contribution of each sensor.We conduct a comparison study of four feature selection techniques using the developed models and the collected data. The experimental results show our proposed system is superior to previous works achieving 97% accuracy.The study also demonstrates how the developed activity recognition model can be applied to promote a home-based care and enhance decision support system in health care.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The results indicated improvement in accuracy after added barometer. Accelerometer and light sensor were used in [14] to detect seven office worker activities. A study showed that combining acceleration and heart rate improve accuracy of estimation of energy expenditure by 1.4% [15].…”

Section: Related Workmentioning

confidence: 99%

A practical multi-sensor activity recognition system for home-based care

Chernbumroong

Cang

2014

Decision Support Systems

View full text Add to dashboard Cite

show abstract

“…Several persons also wanted the button functions to be different while standing. We suggest using a built-in accelerometer and refer to, e.g., [12], [15] for projects and links to more advanced recognition methods.…”

Section: Optimal Position Of Controls Influenced By Posturementioning

confidence: 99%

Evaluating capacitive touch input on clothes

Holleis

Schmidt

Paasovaara

et al. 2008

Proceedings of the 10th International Conference on Human Computer Interaction With Mobile Devices and Services

View full text Add to dashboard Cite

Wearable computing and smart clothing have attracted a lot of attention in the last years. For a variety of applications, it can be seen as potential future direction of mobile user interfaces. In this paper, we concentrate on usability and applicability issues concerned with capacitive touch input on clothing. To be able to perform user studies, we built a generic platform for attaching, e.g., capacitive sensors of different types. On top of that, several prototypes of wearable accessories and clothing and implemented various application scenarios. We report on two studies we undertook with these implementations with a user group randomly sampled at a shopping mall. We provide a significant set of guidelines and lessons learned that emerged from our experiences and those studies. Thus, developers of similar projects have to put major efforts into minimizing the delay between button activation and feedback and to make location and identification of controls and their function as simple and quick as possible. Issues that have to be treated in all designs include the requirement of onehanded interaction and that, even for minimal functionality, to find a general solution with regard to layout and button-tofunction mapping is hardly possible. Additionally, in order to generate a satisfactory user experience good usability must be combined with aesthetical factors.

show abstract

“…This has also the advantage that the amount of information which has to be delivered bottom-up in the tree decreases drastically, which preserves energy due to the reduced wireless communication, and makes such a system feasible for accurate activity recognition (cf. [6]). Since different activity classes (e.g.…”

Section: An Approach For Opportunistic Activity Recognitionmentioning

confidence: 99%

A Self-organizing Approach to Activity Recognition with Wireless Sensors

Holzmann

Haslgrübler

2009

Self-Organizing Systems

View full text Add to dashboard Cite

Abstract. In this paper, we describe an approach to activity recognition, which is based on a self-organizing, ad hoc network of body-worn sensors. It makes best use of the available sensors, and autonomously adapts to dynamically varying sensor setups in terms of changing sensor availabilities, characteristics and on-body locations. For a widespread use of activity recognition systems, such an opportunistic approach is better suited than a fixed and application-specific deployment of sensor systems, as it unburdens the user from placing specific sensors at predefined locations on his body. The main contribution of this paper is the presentation of an interaction model for the self-organization of sensor nodes, which enables a cooperative recognition of activities according to the demands of a user's mobile device. We implemented it with an embedded system platform, and conducted an evaluation showing the feasibility and performance of our approach.

show abstract

On-body activity recognition in a dynamic sensor network

Cited by 58 publications

References 18 publications

A practical multi-sensor activity recognition system for home-based care

A practical multi-sensor activity recognition system for home-based care

Evaluating capacitive touch input on clothes

A Self-organizing Approach to Activity Recognition with Wireless Sensors

Contact Info

Product

Resources

About