Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm
Received signal strength (RSS) changes of static wireless nodes can be used for device-free localization and tracking (DFLT). Most RSS-based DFLT systems require access to calibration data, either RSS measurements from a time period when the area was not occupied by people, or measurements while a p...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/16/5549 |
| _version_ | 1797522052319543296 |
|---|---|
| author | Ossi Kaltiokallio Roland Hostettler Hüseyin Yiğitler Mikko Valkama |
| author_facet | Ossi Kaltiokallio Roland Hostettler Hüseyin Yiğitler Mikko Valkama |
| author_sort | Ossi Kaltiokallio |
| collection | DOAJ |
| description | Received signal strength (RSS) changes of static wireless nodes can be used for device-free localization and tracking (DFLT). Most RSS-based DFLT systems require access to calibration data, either RSS measurements from a time period when the area was not occupied by people, or measurements while a person stands in known locations. Such calibration periods can be very expensive in terms of time and effort, making system deployment and maintenance challenging. This paper develops an Expectation-Maximization (EM) algorithm based on Gaussian smoothing for estimating the unknown RSS model parameters, liberating the system from supervised training and calibration periods. To fully use the EM algorithm’s potential, a novel localization-and-tracking system is presented to estimate a target’s arbitrary trajectory. To demonstrate the effectiveness of the proposed approach, it is shown that: (i) the system requires no calibration period; (ii) the EM algorithm improves the accuracy of existing DFLT methods; (iii) it is computationally very efficient; and (iv) the system outperforms a state-of-the-art adaptive DFLT system in terms of tracking accuracy. |
| first_indexed | 2024-03-10T08:24:06Z |
| format | Article |
| id | doaj.art-143ff56c55a947a4a31cafb7b3fa1abf |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T08:24:06Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-143ff56c55a947a4a31cafb7b3fa1abf2023-11-22T09:41:42ZengMDPI AGSensors1424-82202021-08-012116554910.3390/s21165549Unsupervised Learning in RSS-Based DFLT Using an EM AlgorithmOssi Kaltiokallio0Roland Hostettler1Hüseyin Yiğitler2Mikko Valkama3Unit of Electrical Engineering, Tampere University, 33720 Tampere, FinlandDepartment of Electrical Engineering, Uppsala University, 75237 Uppsala, SwedenDepartment of Communications and Networking, Aalto University, 02150 Espoo, FinlandUnit of Electrical Engineering, Tampere University, 33720 Tampere, FinlandReceived signal strength (RSS) changes of static wireless nodes can be used for device-free localization and tracking (DFLT). Most RSS-based DFLT systems require access to calibration data, either RSS measurements from a time period when the area was not occupied by people, or measurements while a person stands in known locations. Such calibration periods can be very expensive in terms of time and effort, making system deployment and maintenance challenging. This paper develops an Expectation-Maximization (EM) algorithm based on Gaussian smoothing for estimating the unknown RSS model parameters, liberating the system from supervised training and calibration periods. To fully use the EM algorithm’s potential, a novel localization-and-tracking system is presented to estimate a target’s arbitrary trajectory. To demonstrate the effectiveness of the proposed approach, it is shown that: (i) the system requires no calibration period; (ii) the EM algorithm improves the accuracy of existing DFLT methods; (iii) it is computationally very efficient; and (iv) the system outperforms a state-of-the-art adaptive DFLT system in terms of tracking accuracy.https://www.mdpi.com/1424-8220/21/16/5549received signal strengthlocalization and trackingbayesian filtering and smoothingparameter estimationexpectation-maximization algorithm |
| spellingShingle | Ossi Kaltiokallio Roland Hostettler Hüseyin Yiğitler Mikko Valkama Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm Sensors received signal strength localization and tracking bayesian filtering and smoothing parameter estimation expectation-maximization algorithm |
| title | Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm |
| title_full | Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm |
| title_fullStr | Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm |
| title_full_unstemmed | Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm |
| title_short | Unsupervised Learning in RSS-Based DFLT Using an EM Algorithm |
| title_sort | unsupervised learning in rss based dflt using an em algorithm |
| topic | received signal strength localization and tracking bayesian filtering and smoothing parameter estimation expectation-maximization algorithm |
| url | https://www.mdpi.com/1424-8220/21/16/5549 |
| work_keys_str_mv | AT ossikaltiokallio unsupervisedlearninginrssbaseddfltusinganemalgorithm AT rolandhostettler unsupervisedlearninginrssbaseddfltusinganemalgorithm AT huseyinyigitler unsupervisedlearninginrssbaseddfltusinganemalgorithm AT mikkovalkama unsupervisedlearninginrssbaseddfltusinganemalgorithm |