A Mobile Positioning Method Based on Deep Learning Techniques

Wu, Ling; Chen, Chi‐Hua; Qishan, Zhang

doi:10.20944/preprints201810.0239.v1

Cited by 8 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The role of a time series in text recommendation is very important [20]. For text recommendation, there are two kinds of time, one is the published time of the text, the other is the user' access date to the text.…”

Section: Definition and Exposition Of Time Seriesmentioning

confidence: 99%

Text recommendation based on time series and multi-label information

et al. 2021

View full text Add to dashboard Cite

One of the key functions of the method of text recommendation is to build a correlation analysis to all the text collection. At present, most of the text recommendation methods use the citation network, but less to consider the internal relations, which has become a challenge and an opportunity for the research of text recommendation. Therefore, we propose a new method to ameliorate the above problem based on the time series in this paper. We specify a certain text collection according to the interests of users and integrate the varied label values of the text, then we build the correlation coefficient between text and its related text with the differential analysis, finally the similarity degree of the text is calculated out by using the improved cosine similarity correlation matrix to promote a recommendation of similar text. Our experiments indicate that we are able to ensure the quality of text, with an improvement of accuracy by 8.63% as well as an improvement of recall rate by 5.25%.

show abstract

Section: Definition and Exposition Of Time Seriesmentioning

confidence: 99%

Text recommendation based on time series and multi-label information

et al. 2021

View full text Add to dashboard Cite

show abstract

“…At the same time, the image features extracted from the lower layer of the CNN network model have higher resolution than the image features extracted from the higher layers of the CNN network model. Therefore, the image features extracted from the lower layer of CNN are more conducive to detecting relatively small targets in the image, and improve the positioning accuracy of the detection model [23]. Due to the different features of the low-level and high-level images in the CNN network model, in order to achieve better detection accuracy, the image target detection model needs to fuse the image features extracted by different layers in the model.…”

Section: Faster-rcnn Algorithmmentioning

confidence: 99%

Image target detection algorithm compression and pruning based on neural network

Sun

Yan

2021

ComSIS

View full text Add to dashboard Cite

The main purpose of target detection is to identify and locate targets from still images or video sequences. It is one of the key tasks in the field of computer vision. With the continuous breakthrough of deep machine learning technology, especially the convolutional neural network model shows strong Ability to extract image feature in the field of digital image processing. Although the model research of target detection based on convolutional neural network is developing rapidly, but there are still some problems in practical applications. For example, a large number of parameters requires high storage and computational costs in detected model. Therefore, this paper optimizes and compresses some algorithms by using early image detection algorithms and image detection algorithms based on convolutional neural networks. After training and learning, there will appear forward propagation mode in the application of CNN network model, providing the model for image feature extraction, integration processing and feature mapping. The use of back propagation makes the CNN network model have the ability to optimize learning and compressed algorithm. Then research discuss the Faster-RCNN algorithm and the YOLO algorithm. Aiming at the problem of the candidate frame is not significant which extracted in the Faster- RCNN algorithm, a target detection model based on the Significant area recommendation network is proposed. The weight of the feature map is calculated by the model, which enhances the saliency of the feature and reduces the background interference. Experiments show that the image detection algorithm based on compressed neural network image has certain feasibility.

show abstract

“…LBS is based on the network positioning method adopting machine learning techniques to estimate the locations of mobile devices by RSSIs from networks. Firstly, these methods utilize mobile devices to detect and collect data including coordinates of GPS and RSSIs from cellular network or Wi-Fi network and store them in the fingerprinting database [14][15][16]. Secondly, machine learning models are employed to capture the correlation between GPS coordinates and RSSIs.…”

Section: Related Workmentioning

confidence: 99%

“…Although NN and CNN can estimate the locations effectively, they ignore the temporal characteristics of RSSIs. erefore, researchers adopted the RNN-based method to learn the temporal dependence of RSSIs series data to improve the performance of positioning estimation [9,13,16]. Shi et al proposed an indoor positioning method based on Long Short-Term Memory (LSTM) with RSSIs from Wi-Fi APs [19].…”

Section: Related Workmentioning

confidence: 99%

Gated Recurrent Unit with RSSIs from Heterogeneous Network for Mobile Positioning

Wang

Guo

2021

Mobile Information Systems

Self Cite

View full text Add to dashboard Cite

Recently, research studies on Location-Based Services (LBSs) based on networks including cellular network and Wi-Fi network have gradually become popular. Received Signal Strength Indicators (RSSIs) from the network can be detected and collected by mobile devices to estimate the locations without adopting the Global Positioning System (GPS). Previous research studies utilized the RSSIs of only cellular network or only Wi-Fi network to estimate location, which leads to a two-fold predicament involving error limits of cellular network-based methods and environmental constraints of Wi-Fi network-based methods. In addition, accommodating a highly temporal dependence of RSSI series data, this paper proposed a mobile positioning system based on Gated Recurrent Unit (GRU) with RSSIs from the heterogeneous network. GRU learns the temporal correlation of RSSIs and the relationship between RSSIs and GPS coordinates to estimate the locations of mobile devices. A large number of real experiments have been carried out to verify the performance of the proposed method, and experimental results demonstrate that the proposed method has lower errors (i.e., 5.86 m and 75% of errors within 4 m) compared with Neural Network (NN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM).

show abstract

A Mobile Positioning Method Based on Deep Learning Techniques

Cited by 8 publications

References 16 publications

Text recommendation based on time series and multi-label information

Text recommendation based on time series and multi-label information

Image target detection algorithm compression and pruning based on neural network

Gated Recurrent Unit with RSSIs from Heterogeneous Network for Mobile Positioning

Contact Info

Product

Resources

About