Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication
The weighted <i>K</i>-nearest neighbor (WKNN) algorithm is a commonly used fingerprint positioning, the difficulty of which lies in how to optimize the value of <i>K</i> to obtain the minimum positioning error. In this paper, we propose an adaptive residual weighted <i>...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/16/4432 |
| _version_ | 1797559494937411584 |
|---|---|
| author | Shiwu Xu Chih-Cheng Chen Yi Wu Xufang Wang Fen Wei |
| author_facet | Shiwu Xu Chih-Cheng Chen Yi Wu Xufang Wang Fen Wei |
| author_sort | Shiwu Xu |
| collection | DOAJ |
| description | The weighted <i>K</i>-nearest neighbor (WKNN) algorithm is a commonly used fingerprint positioning, the difficulty of which lies in how to optimize the value of <i>K</i> to obtain the minimum positioning error. In this paper, we propose an adaptive residual weighted <i>K</i>-nearest neighbor (ARWKNN) fingerprint positioning algorithm based on visible light communication. Firstly, the target matches the fingerprints according to the received signal strength indication (RSSI) vector. Secondly, <i>K</i> is a dynamic value according to the matched RSSI residual. Simulation results show the ARWKNN algorithm presents a reduced average positioning error when compared with random forest (81.82%), extreme learning machine (83.93%), artificial neural network (86.06%), grid-independent least square (60.15%), self-adaptive WKNN (43.84%), WKNN (47.81%), and KNN (73.36%). These results were obtained when the signal-to-noise ratio was set to 20 dB, and Manhattan distance was used in a two-dimensional (2-D) space. The ARWKNN algorithm based on Clark distance and minimum maximum distance metrics produces the minimum average positioning error in 2-D and 3-D, respectively. Compared with self-adaptive WKNN (SAWKNN), WKNN and KNN algorithms, the ARWKNN algorithm achieves a significant reduction in the average positioning error while maintaining similar algorithm complexity. |
| first_indexed | 2024-03-10T17:46:12Z |
| format | Article |
| id | doaj.art-be04eafe305d4ef792115d7805643c84 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T17:46:12Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-be04eafe305d4ef792115d7805643c842023-11-20T09:31:22ZengMDPI AGSensors1424-82202020-08-012016443210.3390/s20164432Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light CommunicationShiwu Xu0Chih-Cheng Chen1Yi Wu2Xufang Wang3Fen Wei4Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, ChinaDepartment of Aeronautical Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanKey Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, ChinaKey Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, ChinaKey Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, ChinaThe weighted <i>K</i>-nearest neighbor (WKNN) algorithm is a commonly used fingerprint positioning, the difficulty of which lies in how to optimize the value of <i>K</i> to obtain the minimum positioning error. In this paper, we propose an adaptive residual weighted <i>K</i>-nearest neighbor (ARWKNN) fingerprint positioning algorithm based on visible light communication. Firstly, the target matches the fingerprints according to the received signal strength indication (RSSI) vector. Secondly, <i>K</i> is a dynamic value according to the matched RSSI residual. Simulation results show the ARWKNN algorithm presents a reduced average positioning error when compared with random forest (81.82%), extreme learning machine (83.93%), artificial neural network (86.06%), grid-independent least square (60.15%), self-adaptive WKNN (43.84%), WKNN (47.81%), and KNN (73.36%). These results were obtained when the signal-to-noise ratio was set to 20 dB, and Manhattan distance was used in a two-dimensional (2-D) space. The ARWKNN algorithm based on Clark distance and minimum maximum distance metrics produces the minimum average positioning error in 2-D and 3-D, respectively. Compared with self-adaptive WKNN (SAWKNN), WKNN and KNN algorithms, the ARWKNN algorithm achieves a significant reduction in the average positioning error while maintaining similar algorithm complexity.https://www.mdpi.com/1424-8220/20/16/4432visible light communicationindoor positioning systemfingerprint positioningweighted <i>K</i>-nearest neighbordistance metric |
| spellingShingle | Shiwu Xu Chih-Cheng Chen Yi Wu Xufang Wang Fen Wei Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication Sensors visible light communication indoor positioning system fingerprint positioning weighted <i>K</i>-nearest neighbor distance metric |
| title | Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication |
| title_full | Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication |
| title_fullStr | Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication |
| title_full_unstemmed | Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication |
| title_short | Adaptive Residual Weighted <i>K</i>-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication |
| title_sort | adaptive residual weighted i k i nearest neighbor fingerprint positioning algorithm based on visible light communication |
| topic | visible light communication indoor positioning system fingerprint positioning weighted <i>K</i>-nearest neighbor distance metric |
| url | https://www.mdpi.com/1424-8220/20/16/4432 |
| work_keys_str_mv | AT shiwuxu adaptiveresidualweightedikinearestneighborfingerprintpositioningalgorithmbasedonvisiblelightcommunication AT chihchengchen adaptiveresidualweightedikinearestneighborfingerprintpositioningalgorithmbasedonvisiblelightcommunication AT yiwu adaptiveresidualweightedikinearestneighborfingerprintpositioningalgorithmbasedonvisiblelightcommunication AT xufangwang adaptiveresidualweightedikinearestneighborfingerprintpositioningalgorithmbasedonvisiblelightcommunication AT fenwei adaptiveresidualweightedikinearestneighborfingerprintpositioningalgorithmbasedonvisiblelightcommunication |