The Study of Geomedric Classification Algorithom for Small-Cell Positioning Network
碩士 === 元智大學 === 通訊工程學系 === 105 === The thesis proposes a normalization multi-layer perception geometry classification (NMPGC) device and iterative geometry training (IGT) algorithm for reducing the positioning error of four femtocell evolved Node B (FeNB) time difference of arrival (TDOA) measuremen...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2017
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/bgcs45 |
| Summary: | 碩士 === 元智大學 === 通訊工程學系 === 105 === The thesis proposes a normalization multi-layer perception geometry classification (NMPGC) device and iterative geometry training (IGT) algorithm for reducing the positioning error of four femtocell evolved Node B (FeNB) time difference of arrival (TDOA) measurements. The proposed NMPGC architecture is realized in the server of the cloud computing platform to identify the optimal geometry of four FeNBs for positioning the macrocell user equipment (MUE) located between two buildings. Six by six neurons are chosen for two hidden layers in order to shorten the convergent time of NMPGC device. The feasibility of the proposed method is demonstrated by means of numerical simulations. In addition, three quadrilateral optimum geometry disposition decision criteria are also analyzed for the validation of the simulation results.
|
|---|