Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors
The advances in MEMS technology development allow for small and thus unobtrusive designs of wearable sensor platforms for human activity recognition. Multiple such sensors attached to the human body for gathering, processing, and transmitting sensor data connected to platforms for classification for...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-09-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2227-7080/6/4/89 |
| _version_ | 1818612111563030528 |
|---|---|
| author | Florian Grützmacher Albert Hein Thomas Kirste Christian Haubelt |
| author_facet | Florian Grützmacher Albert Hein Thomas Kirste Christian Haubelt |
| author_sort | Florian Grützmacher |
| collection | DOAJ |
| description | The advances in MEMS technology development allow for small and thus unobtrusive designs of wearable sensor platforms for human activity recognition. Multiple such sensors attached to the human body for gathering, processing, and transmitting sensor data connected to platforms for classification form a heterogeneous distributed cyber-physical system (CPS). Several processing steps are necessary to perform human activity recognition, which have to be mapped to the distributed computing platform. However, the software mapping is decisive for the CPS’s processing load and communication effort. Thus, the mapping influences the energy consumption of the CPS, and its energy-efficient design is crucial to prolong battery lifetimes and allow long-term usage of the system. As a consequence, there is a demand for system-level energy estimation methods in order to substantiate design decisions even in early design stages. In this article, we propose to combine well-known dataflow-based modeling and analysis techniques with energy models of wearable sensor devices, in order to estimate energy consumption of wireless sensor nodes for online activity recognition at design time. Our experiments show that a reasonable system-level average accuracy above 97% can be achieved by our proposed approach. |
| first_indexed | 2024-12-16T15:41:02Z |
| format | Article |
| id | doaj.art-7e7f702efa9343d58d3d51cee1e60dbd |
| institution | Directory Open Access Journal |
| issn | 2227-7080 |
| language | English |
| last_indexed | 2024-12-16T15:41:02Z |
| publishDate | 2018-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj.art-7e7f702efa9343d58d3d51cee1e60dbd2022-12-21T22:25:59ZengMDPI AGTechnologies2227-70802018-09-01648910.3390/technologies6040089technologies6040089Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable SensorsFlorian Grützmacher0Albert Hein1Thomas Kirste2Christian Haubelt3Institute of Applied Microelectronics and Computer Engineering, University of Rostock, 18051 Rostock, GermanyInstitute of Computer Science, University of Rostock, 18051 Rostock, GermanyInstitute of Computer Science, University of Rostock, 18051 Rostock, GermanyInstitute of Applied Microelectronics and Computer Engineering, University of Rostock, 18051 Rostock, GermanyThe advances in MEMS technology development allow for small and thus unobtrusive designs of wearable sensor platforms for human activity recognition. Multiple such sensors attached to the human body for gathering, processing, and transmitting sensor data connected to platforms for classification form a heterogeneous distributed cyber-physical system (CPS). Several processing steps are necessary to perform human activity recognition, which have to be mapped to the distributed computing platform. However, the software mapping is decisive for the CPS’s processing load and communication effort. Thus, the mapping influences the energy consumption of the CPS, and its energy-efficient design is crucial to prolong battery lifetimes and allow long-term usage of the system. As a consequence, there is a demand for system-level energy estimation methods in order to substantiate design decisions even in early design stages. In this article, we propose to combine well-known dataflow-based modeling and analysis techniques with energy models of wearable sensor devices, in order to estimate energy consumption of wireless sensor nodes for online activity recognition at design time. Our experiments show that a reasonable system-level average accuracy above 97% can be achieved by our proposed approach.http://www.mdpi.com/2227-7080/6/4/89human activity recognitionmodel-based designenergy efficiencywearable sensorsdataflow graphssoftware mapping |
| spellingShingle | Florian Grützmacher Albert Hein Thomas Kirste Christian Haubelt Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors Technologies human activity recognition model-based design energy efficiency wearable sensors dataflow graphs software mapping |
| title | Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors |
| title_full | Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors |
| title_fullStr | Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors |
| title_full_unstemmed | Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors |
| title_short | Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors |
| title_sort | model based design of energy efficient human activity recognition systems with wearable sensors |
| topic | human activity recognition model-based design energy efficiency wearable sensors dataflow graphs software mapping |
| url | http://www.mdpi.com/2227-7080/6/4/89 |
| work_keys_str_mv | AT floriangrutzmacher modelbaseddesignofenergyefficienthumanactivityrecognitionsystemswithwearablesensors AT alberthein modelbaseddesignofenergyefficienthumanactivityrecognitionsystemswithwearablesensors AT thomaskirste modelbaseddesignofenergyefficienthumanactivityrecognitionsystemswithwearablesensors AT christianhaubelt modelbaseddesignofenergyefficienthumanactivityrecognitionsystemswithwearablesensors |