3D Indoor localization based on spectral clustering and weighted backpropagation neural networks

Peng, Linlin; Liu, Junyu; Sheng, Min; Zhang, Yan; Hou, Danni; Zheng, Yang; Li, Jiandong

doi:10.1109/iccchina.2017.8330353

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where d p,q is the ground truth of the distance between the Tx and Rx p . The model training process is aimed at minimizing the loss L d in (16) with Q training samples. The ranging phase of the CNN-DE method is completed once the estimated distances from all Rxs are gathered.…”

Section: B Conventional Cnn-de Methodsmentioning

confidence: 99%

“…A spectral clustering and weighted backpropagation neural networks RSS-based method was proposed for 3D indoor localization. [16] Localization research using UWB technology ToA, AoA…”

Section: Rnn Neural Networkmentioning

confidence: 99%

“…The related work for localization systems is summarized in Table 1. Most studies on localization are based on twodimensional (2D) environments, and only a few are based on three-dimensional (3D) localization systems [8]- [16]. The UWB technology is widely used in indoor localization systems because of characteristics such as high definition, robust against multipath effect and can penetrate various obstacles.…”

Section: A Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Deep Gated Recurrent Unit-Based 3D Localization for UWB Systems

2021

View full text Add to dashboard Cite

The localization system has been extensively studied because of its diverse applicability, for example, in the Internet of Things, automatic management, and unmanned aerial vehicle services. There have been numerous studies on localization in two-dimensional (2D) environments, but those in three-dimensional (3D) environments are scarce. In this paper, we propose a novel localization method that utilizes the gated recurrent unit (GRU) and ultra-wideband (UWB) signals. For the purpose of this study, we considered that the UWB transmitter (Tx) and many UWB receivers (Rx) were placed inside a confined space. The input of the proposed model was generated from the UWB signals that are sent from the Tx to the Rxs, and the output was the location of the Tx. The proposed GRU-based model converts the localization problem into a regression problem by combining the ranging and positioning phase. Thus, the proposed model can directly estimate the location of the Tx. Our proposed GRU-based method achieves 15 and four times shorter execution times for the training and testing, respectively, compared to the existing convolutional neural network (CNN)-based localization methods. The input data can also be easily generated with low complexity. The rows of the input matrix are the downsampled version of the UWB received signal. Throughout numerous simulation results, our novel localization method can achieve a lower root-mean-squared error up to 0.8 meters compared to the recently proposed existing CNN-based method. Furthermore, the proposed method operates well inside a confined space with fixed volume but varying width, height, and depth. INDEX TERMS 3D localization; deep learning; gated recurrent unit (GRU); recurrent neural network (RNN); ultra-wideband (UWB) system.

show abstract

Section: B Conventional Cnn-de Methodsmentioning

confidence: 99%

“…A spectral clustering and weighted backpropagation neural networks RSS-based method was proposed for 3D indoor localization. [16] Localization research using UWB technology ToA, AoA…”

Section: Rnn Neural Networkmentioning

confidence: 99%

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Gated Recurrent Unit-Based 3D Localization for UWB Systems

2021

View full text Add to dashboard Cite

show abstract

“…On the basis of BPNN, Abdelhadi M et al proposed to firstly cluster the fingerprint vectors, and the fingerprint vectors were divided according to similarity by spectral clustering. Then, the back-propagation neural network was used to train each cluster, which saved time due to parallel training [13]. Wang X et al proposed a novelty method to train the dataset which is based on Deep Learning, and the model trained by Deep Learning can obtain high accuracy [17].…”

Section: Related Workmentioning

confidence: 99%

A Reliable Localization Algorithm Based on Grid Coding and Multi-Layer Perceptron

Sun¹,

Zhang

Ren³

2020

IEEE Access

View full text Add to dashboard Cite

The traditional RSS-based fingerprint localization algorithm needs RSS values from all access points (AP) at each reference point (RP). In the large-scale indoor environment, the increasing of the number of APs will lead to establish a large-scale fingerprint database, which occupies a lot of storage space. In this paper, we propose a new reliable localization algorithm, which firstly utilizes quantized RSS to encode the monitoring region which has been divided into grids, so as to specify the grids that the interested target appears roughly. Then, we utilize Multi-Layer Perceptron (MLP) to train the grid regions in which the beacons deployment is non-isomorphic and obtain the accurate localization result. Due to the same deployment of isomorphic regions, it is imperative to train only one model to replace the others, which greatly reduces the computation of neural network. It can be concluded from the experimental results that compared with the traditional MLP-based fingerprint localization algorithm, the proposed algorithm reduces the size of fingerprint database over 80% with guarantee of localization accuracy. Moreover, our algorithm can obtain better localization accuracy compared with the other latest quantization based localization algorithm. INDEX TERMS Grid coding, multi-layer perceptron, indoor localization.

show abstract

“…Recently, Li [20] proposed an automatic impedance matching method based on BPNN, and Liu [21] used BPNN to analyze high-power LED photoelectrothermal. Linlin [22] propose 3D indoor localization by implementing BPNN. Lilik [23] and Dimililer [24] used it to detect the lung cancer on CT scan images.…”

Section: Hidden Neuron Usage In the Literaturementioning

confidence: 99%

Review and analysis of hidden neuron number effect of shallow backpropagation neural networks

Şekeroğlu¹,

Dimililer²

2020

NNW

View full text Add to dashboard Cite

Shallow neural network implementations are still popular for real-life classification problems that require rapid achievements with limited data. Parameters selection such as hidden neuron number, learning rate and momentum factor of neural networks are the main challenges that causes time loss during these implementations. In these parameters, the determination of hidden neuron numbers is the main drawback that affects both training and generalization phases of any neural system for learning efficiency and system accuracy. In this study, several experiments are performed in order to observe the effect of hidden neuron number of 3-layered backpropagation neural network on the generalization rate of classification problems using both numerical datasets and image databases. Experiments are performed by considering the increasing number of total processing elements, and various numbers of hidden neurons are used during the training. The results of each hidden neuron number are analyzed according to the accuracy rates and iteration numbers during the convergence. Results show that the effect of the hidden neuron numbers mainly depends on the number of training patterns. Also obtained results suggest intervals of hidden neuron numbers for different number of total processing elements and training patterns.

show abstract

3D Indoor localization based on spectral clustering and weighted backpropagation neural networks

Cited by 6 publications

References 14 publications

Deep Gated Recurrent Unit-Based 3D Localization for UWB Systems

Deep Gated Recurrent Unit-Based 3D Localization for UWB Systems

A Reliable Localization Algorithm Based on Grid Coding and Multi-Layer Perceptron

Review and analysis of hidden neuron number effect of shallow backpropagation neural networks

Contact Info

Product

Resources

About