|
Performance Comparison of UWB-Fingerprinting Positioning with RBF Neural Network and k-Nearest Neighbor in an Indoor Environment |
|---|---|
| รหัสดีโอไอ | |
| Creator | Wipassorn Winitchaikul |
| Title | Performance Comparison of UWB-Fingerprinting Positioning with RBF Neural Network and k-Nearest Neighbor in an Indoor Environment |
| Contributor | Jirapat Sangthong, Kannika Limpisawat, Pichaya Supanakoon, Sathaporn Promwong |
| Publisher | Faculty of Information Science and Technology, Mahanakorn University of Technology |
| Publication Year | 2555 |
| Journal Title | Journal of Information Science and Technology |
| Journal Vol. | 3 |
| Journal No. | 1 |
| Page no. | 16-22 |
| Keyword | ultra wideband (UWB), indoor positioning, radial basis function (RBF) neural network, k-nearest-neighbor (k-NN) |
| URL Website | https://tci-thaijo.org/index.php/JIST |
| Website title | Journal of Information Science and Technology |
| ISSN | 2651-1053 |
| Abstract | In recent years, an indoor positioning system has been widely used in medical, industrial, public safety and transportation. In addition, its important requirement is high accuracy in dense multipath fading environments. This paper studies on indoor positioning using radial basis function (RBF) neural network and k-nearest-neighbor (k-NN) based on ultra wideband (UWB) signal. The channel transfer function was measured using vector network analyzer (VNA) at the frequency ranging from 3 GHz to 11 GHz. The path losses and the delay times of first three paths were investigated to build the fingerprints and signatures. The accuracy of this work is studied and shown in the term of cumulative distribution function (CDF). From the results, RBF neural network provides better accuracy than k-NN. Thus, RBF neural network is more suitable for an indoor positioning. |
