A modified WKNN indoor Wi-Fi localization method with differential coordinates

Yen, Lei; Yan, Ching-Hsiang; Renu, Sakthidasan; Belay, Abebe; Lin, Hsin‐Piao; Ye, Yu-Shan

doi:10.1109/icasi.2017.7988299

Cited by 26 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a grouping scheme for measurement techniques (lateration, angulation, fingerprint, Cell-ID, radio frequency identification (RFID)), and another scheme to explain the algorithms (triangulation, scene analysis, and proximity detection), accompanied by application sites and level of accuracy. Yen et al extended their studies to approaches that approach methods based on the k nearest neighbor (KNN) and methods of the weighted k nearest neighbor (WKNN) [ 36 ]. The WKNN method was designed to adjust the weights for each of the K coordinates based on their corresponding errors in the relationship, where smaller errors introduce larger weights.…”

Section: Related Workmentioning

confidence: 99%

A Review of Technologies and Techniques for Indoor Navigation Systems for the Visually Impaired

Simões

Machado

Sales

et al. 2020

Sensors

View full text Add to dashboard Cite

Technologies and techniques of location and navigation are advancing, allowing greater precision in locating people in complex and challenging conditions. These advances have attracted growing interest from the scientific community in using indoor positioning systems (IPSs) with a higher degree of precision and fast delivery time, for groups of people such as the visually impaired, to some extent improving their quality of life. Much research brings together various works that deal with the physical and logical approaches of IPSs to give the reader a more general view of the models. These surveys, however, need to be continuously revisited to update the literature on the features described. This paper presents an expansion of the range of technologies and methodologies for assisting the visually impaired in previous works, providing readers and researchers with a more recent version of what was done and the advantages and disadvantages of each approach to guide reviews and discussions about these topics. Finally, we discuss a series of considerations and future trends for the construction of indoor navigation and location systems for the visually impaired.

show abstract

Section: Related Workmentioning

confidence: 99%

A Review of Technologies and Techniques for Indoor Navigation Systems for the Visually Impaired

Simões

Machado

Sales

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The rapid growth of smart city [1], [2] and smart mobile terminals have triggered high-precision indoor localization requirements. Although satellite positioning systems, such as global positioning system (GPS) [3], or Beidou navigation system [4], have been developed with sub-meter level outdoor localization accuracy, they can hardly achieve the same level in the indoor environment due to satellite signal occlusions. To address this issue, the indoor localization technologies utilize more diversified wireless signals, including wireless fidelity (WiFi) [5], Bluetooth low energy (BLE) [6], and increasingly popular 3GPP LTE/5G technology [7].…”

Section: Introductionmentioning

confidence: 99%

“…Although the fingerprint based schemes provide a more accurate localization results in general [15], the bottleneck is to find a nonlinear relationship between the target location and the corresponding fingerprints. Conventional machine learning algorithms, such as K-nearest neighbor (KNN) [16], weighted K-nearest neighbor (WKNN) [17] and restricted Boltzmann machine (RBM) [18], suffer from high computational complexity in the online stage, which are rarely used in the practical deployment. Recently, with the development of deep learning, convolutional neural network (CNN) [19], deep residual sharing learning [20], and recurrent neural networks (RNNs) [21] have been proposed to learn this nonlinear relation and achieved sub-meter level localization accuracy while maintaining a reasonable implementation complexity simultaneously.…”

Section: Introductionmentioning

confidence: 99%

A Novel GCN based Indoor Localization System with Multiple Access Points

Sun

Xie

Pan

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rapid development of indoor locationbased services (LBSs), the demand for accurate localization keeps growing as well. To meet this demand, we propose an indoor localization algorithm based on graph convolutional network (GCN). We first model access points (APs) and the relationships between them as a graph, and utilize received signal strength indication (RSSI) to make up fingerprints. Then the graph and the fingerprint will be put into GCN for feature extraction, and get classification by multilayer perceptron (MLP).In the end, experiments are performed under a 2D scenario and 3D scenario with floor prediction. In the 2D scenario, the mean distance error of GCN-based method is 11m, which improves by 7m and 13m compare with DNN-based and CNN-based schemes respectively. In the 3D scenario, the accuracy of predicting buildings and floors are up to 99.73% and 93.43% respectively. Moreover, in the case of predicting floors and buildings correctly, the mean distance error is 13m, which outperforms DNN-based and CNNbased schemes, whose mean distance errors are 34m and 26m respectively.

show abstract

“…Zihan Liu proposed to use the correlation between main neighbor and (K-1) auxiliary neighbors, and it combining it with the variance weighting method [20]. Lei Yen proposed the differential coordinate based WKNN using Wi-Fi technology to further improve the accuracy [21]. Long Cheng proposed an improved weighted KNN algorithm to calculate the final positioning coordinates of the measurement point [22].…”

Section: Introductionmentioning

confidence: 99%

A Novel High Precision and Low Consumption Indoor Positioning Algorithm for Internet of Things

et al. 2019

View full text Add to dashboard Cite

Internet of Things (IoT) is digitizing the world, and indoor positioning is one of the important applications of them. Indoor positioning refers to the realization of positioning in the indoor environment. The recent research on indoor positioning focuses on Wi-Fi-based methods since GPS cannot achieve the desired effect. A core algorithm in those methods is the K nearest neighbor (KNN) search. In this paper, we proposed an improved indoor positioning algorithm named IpKNN with better accuracy and efficiency. The IpKNN mainly includes two parts. The first part is to use the proposed clustering algorithm to classify the data set, which can improve the computational efficiency. The second part is to improve the positioning accuracy by using the proposed KNN algorithm. The proposed algorithm can achieve high precision and low consumption, and the experiment results also proved it.INDEX TERMS Internet of Things (IoT), indoor positioning, clustering, KNN algorithm, IpKNN.

show abstract

A modified WKNN indoor Wi-Fi localization method with differential coordinates

Cited by 26 publications

References 7 publications

A Review of Technologies and Techniques for Indoor Navigation Systems for the Visually Impaired

A Review of Technologies and Techniques for Indoor Navigation Systems for the Visually Impaired

A Novel GCN based Indoor Localization System with Multiple Access Points

A Novel High Precision and Low Consumption Indoor Positioning Algorithm for Internet of Things

Contact Info

Product

Resources

About