Intelligent Indoor Positioning Based on Artificial Neural Networks

Chin, Wen‐Long; Hsieh, Cheng-Che; Shiung, David; Jiang, Tao

doi:10.1109/mnet.011.2000096

Cited by 24 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in the case of dataset with narrow evaluation area (Fig. 3b), our model performs slightly better than CNN [4]. The difference in MDE is up to 6 cm.…”

Section: P Ementioning

confidence: 80%

“…We see that difference between the best and the worst performing model is almost one meter or 23 per cent for NMDE. For this scenario, the best performing model is CNN [4], but our proposed CNN structures show comparable performance. However, in the case of dataset with narrow evaluation area (Fig.…”

Section: P Ementioning

confidence: 98%

“…In the literature, we found several NN architectures proposed for more accurate position estimation. In [4], [8], authors experiment with fully (i.e. densely) connected NNs (FCNN).…”

Section: R W P Dmentioning

confidence: 99%

“…densely) connected NNs (FCNN). However, feature extraction process using convolutional NNs (CNNs) proved far more effective from the perspective of the performance and the number of weights compared to FCNN [4], [9]- [13]. The top-performing NNs in related work use similar sequence of layers: a convolutional layer, an activation layer and an average pooling layer.…”

Section: R W P Dmentioning

confidence: 99%

“…In order to benchmark the proposed CNN structures, we also implemented some representative NNs for position estimation from the related work [4], [8]- [10]. The evaluation results are presented in Table II, where RMSE and MDE are expressed in meters, and NMDE is given in per-cents.…”

Section: P Ementioning

confidence: 99%

See 4 more Smart Citations

Improving CSI-based Massive MIMO Indoor Positioning using Convolutional Neural Network

Cerar,

Švigelj,

Mohorčič

et al. 2021

Preprint

View full text Add to dashboard Cite

Multiple-input multiple-output (MIMO) is an enabling technology to meet the growing demand for faster and more reliable communications in wireless networks with a large number of terminals, but it can also be applied for position estimation of a terminal exploiting multipath propagation from multiple antennas. In this paper, we investigate new convolutional neural network (CNN) structures for exploiting MIMO-based channel state information (CSI) to improve indoor positioning. We evaluate and compare the performance of three variants of the proposed CNN structure to five NN structures proposed in the scientific literature using the same sets of trainingevaluation data. The results demonstrate that the proposed residual convolutional NN structure improves the accuracy of position estimation and keeps the total number of weights lower than the published NN structures. The proposed CNN structure yields from 2 cm to 10 cm better position accuracy than known NN structures used as a reference.

show abstract

“…However, in the case of dataset with narrow evaluation area (Fig. 3b), our model performs slightly better than CNN [4]. The difference in MDE is up to 6 cm.…”

Section: P Ementioning

confidence: 80%

Section: P Ementioning

confidence: 98%

“…In the literature, we found several NN architectures proposed for more accurate position estimation. In [4], [8], authors experiment with fully (i.e. densely) connected NNs (FCNN).…”

Section: R W P Dmentioning

confidence: 99%

Section: R W P Dmentioning

confidence: 99%

Section: P Ementioning

confidence: 99%

See 3 more Smart Citations

Improving CSI-based Massive MIMO Indoor Positioning using Convolutional Neural Network

Cerar,

Švigelj,

Mohorčič

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Research on the Classification Method of Refrigerator Ingredients Based on Inception Structure

Cui

Wang

et al. 2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

With the continuous development of intelligent refrigerators, users are having higher and higher requirements for smart management of refrigerator contents. When using traditional machine learning algorithms to deal with refrigerator ingredients classification, problems such as slow recognition speed and low accuracy would often arise. At the same time, the classification accuracy is easily affected by the location of the content. Therefore, this paper uses continuous asymmetric convolutions and depthwise separable convolutions to improve the original Inception model and builds a classification prediction network based on the improved Inception model. The steps to applying the said model is as follows: First, we put the Radio Frequency Identification (RFID) tag on the food in the refrigerator, and then we collect the antenna data RSSI received by each tag through the reader. Finally, the RSSI is preprocessed and entered into the classification network to determine the location of the label. The proposed classification network has the advantages of possessing a simple structure, easy expansion of network depth, and fewer training parameters. The experimental results show that compared with other machine learning algorithms and pure convolution networks, the lightweight network model based on the improved Inception structure demonstrates great superiority. Compared with the original Inception structure, the enhanced network model is more lightweight. The number of parameters is reduced by 50%, and the amount of float-point operations is reduced by 34%. Meanwhile, the accuracy of the lightweight model has been improved by 0.6%. Thus the improved model has better prediction performance in the classification of refrigerator content.

show abstract