Adaptive Residual Weighted K-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication

Xu, Shiwu; Chen, Chih‐Cheng; Wu, Yi; Wang, Xufang; Wei, Fulong

doi:10.3390/s20164432

Cited by 22 publications

(14 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It has been also investigated the classification problems to improve the communication performance in VLC systems [33][34][35][36][37]. Niu et al suggested a SVM based system to reduce signal distortion in the VLC channel and optical fiber for constellation classification of geometrically-shaped 8QAM [33].…”

Section: Introductionmentioning

confidence: 99%

“…According to experimental results, it is shown that it can be achieved transmission at −2.5 dBm input optical power under the 7% forward error correction (FEC) threshold. In [34], Xu et al improved an adaptive residual weighted Knearest neighbor (ARWKNN) algorithm to reduce the average positioning error in VLC systems compared to the random forest, extreme learning machine, artificial neural network, grid-independent least square, self-adaptive WKNN, WKNN, and KNN. Another indoor positioning system based on VLC was suggested using Machine Learning Classification and Regression algorithms [35].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The modulation classification methods in PPM–VLC systems

Ağır

Sönmez

2023

Opt Quant Electron

View full text Add to dashboard Cite

Intelligent methods have been applied to many fields for a long time. Recently, Visible Light Communication (VLC) systems widely include learning and classification models to improve their performances. The classification of L-Pulse Position Modulation (L-PPM) formats is crucial for VLC systems since the modulation order L is very effective for providing energy efficiency and increasing the transmission capacity. In this paper, therefore, it is reported for the first time, the classification of PPM schemes in VLC systems by using Decision Tree, Knearest neighbor (KNN), Support Vector Machine (SVM), and a Direct Decision-based Linear Model (LM) technique. A novel feature extraction model is derived to be able to classify the type of PPM modulation schemes. A comparison has been given to observe the performance of classification schemes by taking into account the level of Signal to Noise Ratio and the transmission distance between receiver and transmitter. The KNN method gives the best accuracy performance against other schemes at the SNR of 25dB and the distance of 2.32m and more, while the Tree model is superior to KNN at the distances of 2.25m and 2.20m. Additionally, it has been obtained the best accuracy of 97.85% by the Decision Tree Model at the distance of 2.20m.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The modulation classification methods in PPM–VLC systems

Ağır

Sönmez

2023

Opt Quant Electron

View full text Add to dashboard Cite

show abstract

“…Multiple fingerprint location databases were built with different densities of reference tags. Under completely identical configurations of R, Q 1 , and Q 2 as in the TDACC method, the average errors of the NN algorithm (nearest neighbor algorithm) [29], the KNN algorithm (K-nearest neighbor algorithm) [30], and the WKNN algorithm (K-weighted K-neighbor algorithm) [31][32][33] were computed at reference tag intervals of 5 m, 2.5 m, 2 m, and 1 m.…”

Section: Fingerprint Localization Methodsmentioning

confidence: 99%

The Indoor Positioning Method Time Difference of Arrival with Conic Curves Utilizing a Novel Networking RFID System

et al. 2023

View full text Add to dashboard Cite

At present, the demand for accurate indoor positioning at a low cost is increasing. Based on the architecture of networking passive radio frequency identification (RFID) systems, research into passive location algorithms is important for finding a location solution with ultra-low cost, easy implementation, and no required maintenance. In this paper, TDACC (time difference of arrival with conic curves) based on signal propagation time is proposed, which breaks down the positioning problem into solving the intersection of an ellipse and a hyperbola. The results indicate that this method has a positioning error of 0 m in the absence of signal interference. When the time delay fluctuates to 1 ns and 2 ns, the average errors of TDACC are 0.19 m and 0.33 m, respectively. Different from other time-based localization methods, the proposed method only requires two distribution nodes without time synchronization, which reduces the system cost. These results will help to promote the deeper semantic communication level fusion of passive RFID. By improving the coordinate positioning in the semantic prior knowledge base, this method will lead to more efficient and accurate industry applications.

show abstract

“…In [ 9 ] an adaptive residual weighted K-Nearest neighbor (WKNN) fingerprint positioning algorithm based on visible light is proposed. The WKNN algorithm is a commonly used fingerprint positioning algorithm for which its difficulty consists in the optimization of K to obtain the minimum positioning error.…”

Section: Relevant Contributionsmentioning

confidence: 99%