High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point
In this letter, we propose an indoor visible light positioning technique using a Modified Momentum Back-Propagation (MMBP) algorithm based on received signal strength (RSS) with sparse training data set. Unlike other neural network algorithms that require a large number of training data points to lo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/10/2324 |
| _version_ | 1828347552048611328 |
|---|---|
| author | Haiqi Zhang Jiahe Cui Lihui Feng Aiying Yang Huichao Lv Bo Lin Heqing Huang |
| author_facet | Haiqi Zhang Jiahe Cui Lihui Feng Aiying Yang Huichao Lv Bo Lin Heqing Huang |
| author_sort | Haiqi Zhang |
| collection | DOAJ |
| description | In this letter, we propose an indoor visible light positioning technique using a Modified Momentum Back-Propagation (MMBP) algorithm based on received signal strength (RSS) with sparse training data set. Unlike other neural network algorithms that require a large number of training data points to locate accurately, we have realized high-precision positioning for 100 test points with only 20 training points in a 1.8 m × 1.8 m × 2.1 m localization area. In order to verify the adaptability of the MMBP algorithm, we experimentally demonstrate two different training data acquisition methods adopting either even or arbitrary training sets. In addition, we also demonstrate the positioning accuracy of the traditional RSS algorithm. Experimental results show that the average localization accuracy optimized by our proposed algorithm is only 1.88 cm for the arbitrary set and 1.99 cm for the even set, while the average positioning error of the traditional RSS algorithm reaches 14.34 cm. Comparison indicates that the positioning accuracy of our proposed algorithm is 7.6 times higher. Results also show that the performance of our system is higher than some previous reports based on RSS and RSS fingerprint databases using complex machine learning algorithms trained by a large amount of training points. |
| first_indexed | 2024-04-14T00:41:06Z |
| format | Article |
| id | doaj.art-06f788aa70694be8a6cd78b77284d87b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T00:41:06Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-06f788aa70694be8a6cd78b77284d87b2022-12-22T02:22:10ZengMDPI AGSensors1424-82202019-05-011910232410.3390/s19102324s19102324High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training PointHaiqi Zhang0Jiahe Cui1Lihui Feng2Aiying Yang3Huichao Lv4Bo Lin5Heqing Huang6Key Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, Beijing 100081, ChinaKey Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, Beijing 100081, ChinaKey Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, Beijing 100081, ChinaKey Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, Beijing 100081, ChinaKey Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, Beijing 100081, ChinaChina Academy of Electronics and Information Technology, Beijing 100041, ChinaChina Academy of Electronics and Information Technology, Beijing 100041, ChinaIn this letter, we propose an indoor visible light positioning technique using a Modified Momentum Back-Propagation (MMBP) algorithm based on received signal strength (RSS) with sparse training data set. Unlike other neural network algorithms that require a large number of training data points to locate accurately, we have realized high-precision positioning for 100 test points with only 20 training points in a 1.8 m × 1.8 m × 2.1 m localization area. In order to verify the adaptability of the MMBP algorithm, we experimentally demonstrate two different training data acquisition methods adopting either even or arbitrary training sets. In addition, we also demonstrate the positioning accuracy of the traditional RSS algorithm. Experimental results show that the average localization accuracy optimized by our proposed algorithm is only 1.88 cm for the arbitrary set and 1.99 cm for the even set, while the average positioning error of the traditional RSS algorithm reaches 14.34 cm. Comparison indicates that the positioning accuracy of our proposed algorithm is 7.6 times higher. Results also show that the performance of our system is higher than some previous reports based on RSS and RSS fingerprint databases using complex machine learning algorithms trained by a large amount of training points.https://www.mdpi.com/1424-8220/19/10/2324neural networkindoor visible light positioninghigh accuracyLED |
| spellingShingle | Haiqi Zhang Jiahe Cui Lihui Feng Aiying Yang Huichao Lv Bo Lin Heqing Huang High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point Sensors neural network indoor visible light positioning high accuracy LED |
| title | High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point |
| title_full | High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point |
| title_fullStr | High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point |
| title_full_unstemmed | High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point |
| title_short | High-Precision Indoor Visible Light Positioning Using Modified Momentum Back Propagation Neural Network with Sparse Training Point |
| title_sort | high precision indoor visible light positioning using modified momentum back propagation neural network with sparse training point |
| topic | neural network indoor visible light positioning high accuracy LED |
| url | https://www.mdpi.com/1424-8220/19/10/2324 |
| work_keys_str_mv | AT haiqizhang highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint AT jiahecui highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint AT lihuifeng highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint AT aiyingyang highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint AT huichaolv highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint AT bolin highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint AT heqinghuang highprecisionindoorvisiblelightpositioningusingmodifiedmomentumbackpropagationneuralnetworkwithsparsetrainingpoint |