Smart Fall

Smart Fall
Starts from:Sat, March 1, 2014
Campus Location

Tags
  • Wearables
  • Fall Detection
  • Smart Home
Class Description

The project deals with the development of a fall and activity recognition system and the integration of the system into a smart home environment. Fall detection and the automatic sending of an emgergency call is especially interesting for elderly people to help them with urgent support.

In this project, a prototypical hardware system (wearable device) is developed that is able to recognize falls and basis human activities. This wearable device is attached to a user’s waist and features low-costs, low energy consumption and a small footprint. Activity recognition is performed locally on the wearable with its limited computational capabilities. Additionally, it is able to communicate wirelessly with a smart home. Therefore, a receiver component is realized that acts as gateway to the home automation bus. The result is an intelligent environment that can react on the current user’s activity.

Furthermore, the rooms of the smart home are equipped with transponders which allow a localization of the wearable inside the home. The combination of fall detection and indoor-localization enables a fast and focused reaction, e.g. by automatically calling a person and guiding the helping person to the fallen person through programmable LED strips. In future, higher-level activities can be inferred by employing the basic human activities, the person’s location and additional smart home sensors. Based on these activities, the home environment can automatically adapt to the demands of the residents, e.g. changing the light color depending on a certain activity.

SmartFallHardware
SmartFallHardware
SmartFallHardware

Publications

  • M. König, H. -J. Lakomek, A. Pörtner, and D. Sprute, “Smart Fall: Entwicklung eines Systems zur Sturz- und Aktivitätenerkennung im Smart Home,” Orthopädie Technik, pp. 30-35, 2017.
    [BibTeX] [Abstract] [Download PDF]

    Das Projekt „Smart Fall“ beschäftigt sich mit einem kostengünstigen System zur Erkennung von Aktivitäten und Stürzen älterer Menschen und der Einbindung des Systems in einen Smart-Home-Kontext. Das entwickelte System umfasst zwei wesentliche Komponenten: Ein sogenanntes Wearable dient als Sensorik zur Erkennung von Stürzen und Aktivitäten einer Person, während eine Empfangskomponente zur Kopplung an das Smart Home dient. Beide Komponenten kommunizieren funkbasiert miteinander. Die Erkennung von Stürzen und eine damit verbundene Alarmierung im Notfall betrifft insbesondere ältere Menschen, die sich möglicherweise nach einem Sturz nicht mehr selbst helfen können. Das Thema hat ebenfalls eine starke Relevanz für Menschen in häuslicher Pflege und in Pflegeeinrichtungen.

    @article{koenig:2017,
    author = {Matthias K{\"o}nig and H.-J. Lakomek and Aljoscha P{\"o}rtner and Dennis Sprute},
    title = {{Smart Fall: Entwicklung eines Systems zur Sturz- und Aktivitätenerkennung im Smart Home}},
    journal={{Orthopädie Technik}},
    pages={30-35},
    year = {2017},
    month={09},
    abstract={Das Projekt „Smart Fall“ beschäftigt sich mit einem kostengünstigen System zur Erkennung von Aktivitäten
    und Stürzen älterer Menschen und der Einbindung des Systems in einen Smart-Home-Kontext. Das entwickelte System umfasst zwei wesentliche Komponenten: Ein sogenanntes Wearable dient als Sensorik zur Erkennung von
    Stürzen und Aktivitäten einer Person, während eine Empfangskomponente zur Kopplung an das Smart Home
    dient. Beide Komponenten kommunizieren funkbasiert miteinander. Die Erkennung von Stürzen und eine damit verbundene Alarmierung im Notfall betrifft insbesondere ältere Menschen, die sich möglicherweise nach einem Sturz nicht mehr selbst helfen können. Das Thema hat ebenfalls eine starke Relevanz für Menschen in häuslicher Pflege und in Pflegeeinrichtungen.},
    url={//www.iot-minden.de/wp-content/uploads/2017/09/OT0917_König.pdf}
    }

  • D. Sprute and M. König, “On-Chip Activity Recognition in a Smart Home,” in 12th International Conference on Intelligent Environments, London, UK, 2016, pp. 95-102.
    [BibTeX] [Abstract] [Download PDF]

    This paper proposes a novel activity recognition system that is integrated into a smart home environment. It is characterized by low costs, high energy efficiency and low intrusiveness to increase the acceptance of the users. Activity recognition is performed locally on a single small-sized wearable device incorporating a microprocessor and a tri-axial accelerometer. After investigating on different feature sets and classification algorithms, the final implementation only considers five time domain features and a C4.5 decision tree classifier resulting in an immediate response. This wearable device is successfully integrated into an intelligent environment by Bluetooth Low Energy wireless communication protocol and openHAB as platform-independent integration software. The integration of the system into the home environment allows reactions of the home depending on the activity which enriches the life quality of the residents. Additionally, the system covers fall detection that enables the home to provide a fallen person with urgent support.

    @inproceedings{sprute:2016b,
    author = {Dennis Sprute and Matthias König},
    title = {{On-Chip Activity Recognition in a Smart Home}},
    booktitle = {{12th International Conference on Intelligent Environments, London, UK}},
    pages={95-102},
    year = {2016},
    month = {09},
    url = {//ieeexplore.ieee.org/document/7723476/},
    abstract = {This paper proposes a novel activity recognition system that is integrated into a smart home environment. It is characterized by low costs, high energy efficiency and low intrusiveness to increase the acceptance of the users. Activity recognition is performed locally on a single small-sized wearable device incorporating a microprocessor and a tri-axial accelerometer. After investigating on different feature sets and classification algorithms, the final implementation only considers five time domain features and a C4.5 decision tree classifier resulting in an immediate response. This wearable device is successfully integrated into an intelligent environment by Bluetooth Low Energy wireless communication protocol and openHAB as platform-independent integration software. The integration of the system into the home environment allows reactions of the home depending on the activity which enriches the life quality of the residents. Additionally, the system covers fall detection that enables the home to provide a fallen person with urgent support.}
    }

  • A. Pörtner, D. Sprute, A. Weinitschke, and M. König, “Integration of a fall detection system into the intelligent building,” in 45. Jahrestagung der Gesellschaft für Informatik, Cottbus, Deutschland, 2015, p. 191–202.
    [BibTeX] [Abstract] [Download PDF]

    Health monitoring and the integration of such systems into homely environments can support healthy aging. In this paper, we focus on the integration of a fall detection system into the intelligent building. We present a low intrusive way to detect falls and locate people inside a building based on the low power wireless technology Bluetooth Smart and a concept how well designed human computer interaction (HCI) concepts inside a building can help to save lives or at least prevent people of heavy injuries.

    @inproceedings{poertner:2015,
    author = {Aljoscha Pörtner and Dennis Sprute and Alexander Weinitschke and Matthias König},
    title = {Integration of a fall detection system into the intelligent building},
    booktitle = {{45. Jahrestagung der Gesellschaft für Informatik, Cottbus, Deutschland}},
    pages = {191--202},
    year = {2015},
    month = {09},
    isbn = {978-3-88579-640-4},
    url = {//subs.emis.de/LNI/Proceedings/Proceedings246/article43.html},
    abstract = {Health monitoring and the integration of such systems into homely environments can support healthy aging. In this paper, we focus on the integration of a fall detection system into the intelligent building. We present a low intrusive way to detect falls and locate people inside a building based on the low power wireless technology Bluetooth Smart and a concept how well designed human computer interaction (HCI) concepts inside a building can help to save lives or at least prevent people of heavy injuries.}
    }

  • D. Sprute, A. Pörtner, A. Weinitschke, and M. König, “Smart Fall: Accelerometer-Based Fall Detection in a Smart Home Environment,” in Inclusive Smart Cities and e-Health: 13th International Conference on Smart Homes and Health Telematics, ICOST 2015, Geneva, Switzerland, 2015, p. 194–205.
    [BibTeX] [Abstract] [Download PDF]

    The detection of falls in an elderly society is an active field of research because of the the enormous costs caused by falls. In this paper, Smart Fall is presented. It is a new accelerometer-based fall detection system integrated into an intelligent building. The developed system consists of two main components. Fall detection is realized inside a small customized wearable device that is characterized by low costs and low-energy consumption. Additionally, a receiver component is implemented which serves as mediator between the wearable device and a Smart Home environment. The wireless connection between the wearable and the receiver is performed by Bluetooth Low Energy (BLE) protocol. OpenHAB is used as platform-independent integration platform that connects home appliances vendor- and protocol-neutral. The integration of the fall detection system into an intelligent home environment offers quick reactions to falls and urgent support for fallen people.

    @inproceedings{sprute:2015,
    author={Sprute, Dennis
    and P{\"o}rtner, Aljoscha
    and Weinitschke, Alexander
    and K{\"o}nig, Matthias},
    title={{Smart Fall: Accelerometer-Based Fall Detection in a Smart Home Environment}},
    bookTitle={{Inclusive Smart Cities and e-Health: 13th International Conference on Smart Homes and Health Telematics, ICOST 2015, Geneva, Switzerland}},
    year={2015},
    publisher={Springer International Publishing},
    pages={194--205},
    abstract={The detection of falls in an elderly society is an active field of research because of the the enormous costs caused by falls. In this paper, Smart Fall is presented. It is a new accelerometer-based fall detection system integrated into an intelligent building. The developed system consists of two main components. Fall detection is realized inside a small customized wearable device that is characterized by low costs and low-energy consumption. Additionally, a receiver component is implemented which serves as mediator between the wearable device and a Smart Home environment. The wireless connection between the wearable and the receiver is performed by Bluetooth Low Energy (BLE) protocol. OpenHAB is used as platform-independent integration platform that connects home appliances vendor- and protocol-neutral. The integration of the fall detection system into an intelligent home environment offers quick reactions to falls and urgent support for fallen people.},
    isbn={978-3-319-19312-0},
    url={//doi.org/10.1007/978-3-319-19312-0_16}
    }

Project Funding

SmartFallHardware