Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors
Although the availability of sensor data is becoming prevalent across many domains, it still remains a challenge to make sense of the sensor data in an efficient and effective manner in order to provide users with relevant services. The concept of virtual sensors provides a step towards this goal, h...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/3/477 |
| _version_ | 1798038783910739968 |
|---|---|
| author | Agnes Tegen Paul Davidsson Radu-Casian Mihailescu Jan A. Persson |
| author_facet | Agnes Tegen Paul Davidsson Radu-Casian Mihailescu Jan A. Persson |
| author_sort | Agnes Tegen |
| collection | DOAJ |
| description | Although the availability of sensor data is becoming prevalent across many domains, it still remains a challenge to make sense of the sensor data in an efficient and effective manner in order to provide users with relevant services. The concept of virtual sensors provides a step towards this goal, however they are often used to denote homogeneous types of data, generally retrieved from a predetermined group of sensors. The DIVS (Dynamic Intelligent Virtual Sensors) concept was introduced in previous work to extend and generalize the notion of a virtual sensor to a dynamic setting with heterogenous sensors. This paper introduces a refined version of the DIVS concept by integrating an interactive machine learning mechanism, which enables the system to take input from both the user and the physical world. The paper empirically validates some of the properties of the DIVS concept. In particular, we are concerned with the distribution of different budget allocations for labelled data, as well as proactive labelling user strategies. We report on results suggesting that a relatively good accuracy can be achieved despite a limited budget in an environment with dynamic sensor availability, while proactive labeling ensures further improvements in performance. |
| first_indexed | 2024-04-11T21:45:05Z |
| format | Article |
| id | doaj.art-971f799996834d58a38ba7446f5c432a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:45:05Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-971f799996834d58a38ba7446f5c432a2022-12-22T04:01:26ZengMDPI AGSensors1424-82202019-01-0119347710.3390/s19030477s19030477Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual SensorsAgnes Tegen0Paul Davidsson1Radu-Casian Mihailescu2Jan A. Persson3Internet of Things and People Research Center, Department of Computer Science and Media Technology, Malmö University, 20506 Malmö, SwedenInternet of Things and People Research Center, Department of Computer Science and Media Technology, Malmö University, 20506 Malmö, SwedenInternet of Things and People Research Center, Department of Computer Science and Media Technology, Malmö University, 20506 Malmö, SwedenInternet of Things and People Research Center, Department of Computer Science and Media Technology, Malmö University, 20506 Malmö, SwedenAlthough the availability of sensor data is becoming prevalent across many domains, it still remains a challenge to make sense of the sensor data in an efficient and effective manner in order to provide users with relevant services. The concept of virtual sensors provides a step towards this goal, however they are often used to denote homogeneous types of data, generally retrieved from a predetermined group of sensors. The DIVS (Dynamic Intelligent Virtual Sensors) concept was introduced in previous work to extend and generalize the notion of a virtual sensor to a dynamic setting with heterogenous sensors. This paper introduces a refined version of the DIVS concept by integrating an interactive machine learning mechanism, which enables the system to take input from both the user and the physical world. The paper empirically validates some of the properties of the DIVS concept. In particular, we are concerned with the distribution of different budget allocations for labelled data, as well as proactive labelling user strategies. We report on results suggesting that a relatively good accuracy can be achieved despite a limited budget in an environment with dynamic sensor availability, while proactive labeling ensures further improvements in performance.https://www.mdpi.com/1424-8220/19/3/477virtual sensorssensor fusionmachine learningdynamic environmentsInternet of Things |
| spellingShingle | Agnes Tegen Paul Davidsson Radu-Casian Mihailescu Jan A. Persson Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors Sensors virtual sensors sensor fusion machine learning dynamic environments Internet of Things |
| title | Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors |
| title_full | Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors |
| title_fullStr | Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors |
| title_full_unstemmed | Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors |
| title_short | Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors |
| title_sort | collaborative sensing with interactive learning using dynamic intelligent virtual sensors |
| topic | virtual sensors sensor fusion machine learning dynamic environments Internet of Things |
| url | https://www.mdpi.com/1424-8220/19/3/477 |
| work_keys_str_mv | AT agnestegen collaborativesensingwithinteractivelearningusingdynamicintelligentvirtualsensors AT pauldavidsson collaborativesensingwithinteractivelearningusingdynamicintelligentvirtualsensors AT raducasianmihailescu collaborativesensingwithinteractivelearningusingdynamicintelligentvirtualsensors AT janapersson collaborativesensingwithinteractivelearningusingdynamicintelligentvirtualsensors |