A Novel Convolutional Neural Network Based Indoor Localization Framework With WiFi Fingerprinting

Song, Xudong; Fan, Xiaochen; Xiang, Chaocan; Ye, Qianwen; Liu, Leyu; Wang, Zumin; He, Xiangjian; Yang, Ning; Fang, Gengfa

doi:10.1109/access.2019.2933921

Cited by 165 publications

(121 citation statements)

References 31 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…Their approach uses only two APs for floor detection, which significantly reduces the computational complexity. Furthermore, a convolutional neural network (CNN)-based indoor localization system was proposed by Song et al [30], which uses the SAE network to extract one-dimensional CNN and key features of the dataset. Their optimized CNN replaces general matrix multiplication, which reduces computational complexity.…”

Section: Related Workmentioning

confidence: 99%

An Indoor Positioning and Navigation System Using Named Data Networking

et al. 2020

View full text Add to dashboard Cite

Named data networking (NDN) is a new and promising Internet architecture, which aims to replace the current transmission control protocol/Internet protocol (TCP/IP)-based Internet. The NDN internet architecture has introduced several benefits in numerous applications. An NDN-based indoor positioning and navigation system can further optimize existing localization technologies with reduced the server load and faster response time. In this study, an NDN-based approach for the existing Wi-Fi fingerprinting-based indoor positioning and navigation was investigated. Among the many features of NDN, the network-level caching can reduce the computational load and response time of the localization and navigation server. The theoretical analysis of the runtime complexity shows that the NDN's network-level caching performance is better than those of the conventional algorithms. In this paper, naming methods for different services and a server-side algorithm for handling the NDN requests are proposed. The real-world implantation and testing results show a better overall performance than that of TCP/IP. This network-level optimization for indoor positioning and navigation opens new opportunities because it can be combined with other application-level optimization techniques for more efficient indoor positioning and navigation in the future.

show abstract

Section: Related Workmentioning

confidence: 99%

An Indoor Positioning and Navigation System Using Named Data Networking

et al. 2020

View full text Add to dashboard Cite

show abstract

“…45 The achieved results suggest that the DNN approach might achieve comparable results to the traditional approaches. 45,46 Therefore, the DNN-based Wi-Fi method is chosen as an example to explain how to apply the auto-calibration idea into Wi-Fi fingerprinting. The auto-calibration idea can be combined with other Wi-Fi fingerprinting methods as well.…”

Section: Auto-calibration For Wi-fi Fingerprint In Indoor Scenariosmentioning

confidence: 99%

“…In this paper, we use a Deep Neural Networks (DNN)‐based Wi‐Fi fingerprint method to illustrate the effectiveness of our proposed method. According to suggestions in related works, conventional Wi‐Fi positioning solutions are time‐consuming with parameter tuning. Machine learning approaches are an alternative solution due to less parameter tuning .…”

Section: Location‐related Activity Detection and Positioning In Indoomentioning

confidence: 99%

“…Machine learning approaches are an alternative solution due to less parameter tuning . The achieved results suggest that the DNN approach might achieve comparable results to the traditional approaches . Therefore, the DNN‐based Wi‐Fi method is chosen as an example to explain how to apply the auto‐calibration idea into Wi‐Fi fingerprinting.…”

Section: Location‐related Activity Detection and Positioning In Indoomentioning

confidence: 99%

See 1 more Smart Citation

Integration of positioning and activity context information for lifelog in urban city area

Kamiya

et al. 2019

NAVIGATION

View full text Add to dashboard Cite

Smartphone‐based Lifelog (automatically annotating the users' daily experience from multisensory streams on smartphones) is in great need. Accurate positioning under any situation is one of the most significant techniques for a desirable Lifelog. This paper proposes to detect location‐related activities and use the activity information to improve positioning accuracy. In the proposed system, a human activity recognition module is developed to extract location‐related activities from multisensory streams of smartphones. After that, the proposed system integrates activity information with PDR‐based positioning results in a context‐based map‐matching framework. The developed system can be used for both outdoor and indoor scenarios. Moreover, the developed indoor positioning method is used to determine the positions of calibration points automatically in an auto‐calibration Wi‐Fi positioning system. The proposed methods achieve 3.1‐m accuracy in outdoor and average 2.2‐m accuracy in indoor situations.

show abstract

“…However, highprecision indoor positioning based on GNSS has not been achieved since indoor GNSS signals are usually weak or even nonexistent. Therefore, some positioning technologies such as ultrawideband (UWB) [1,2], Bluetooth [3], WiFi [4,5], radio frequency identification (RFID) [6,7], computer vision [7], ultrasonic [8], inertial navigation system (INS) [9], pseudolite [10], and geomagnetic fields [11] were presented to achieve indoor positioning with high accuracy and strong availability.…”

Section: Introductionmentioning

confidence: 99%

WiFi RTT Indoor Positioning Method Based on Gaussian Process Regression for Harsh Environments

Cao

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

A novel two-way ranging approach was introduced into the Wireless Fidelity (WiFi) standard, and its ranging accuracy reached one meter in a low multipath environment. However, in harsh environments due to multipath or non-line of sight (NLOS), the range measurement based on the WiFi round trip time (RTT) usually has low accuracy and cannot maintain the one-meter accuracy. Thus, this paper proposes an indoor positioning method based on Gaussian process regression (GPR) for harsh environments. There are two stages in the proposed method: construction of a positioning model and location estimation. In the model construction stage, based on known positions of access points (APs), we can determine the position coordinates of some ground points and the reference distances between them and the APs, and the offline ranging difference fingerprints can be generated by the reference distances, which means that there is no need to collect data. Gaussian process regression (GPR) utilizes offline ranging difference fingerprints based on the reference distance to establish a positioning model, and the particle swarm optimization (PSO) algorithm is employed to estimate the GPR hyperparameters. In the location estimation stage, the gathered actual range measurements generate the online ranging difference fingerprint, which is the input data of the positioning model. The output of the model is the estimated position of the smartphone. Experimental results show that the mean errors (MEs) of the proposed method and Least Squares (LS) algorithm are 1.097 and 3.484 meters, respectively, in a harsh environment, and the positioning accuracy of the proposed method improved by 68.5% compared with the LS algorithm.

show abstract

A Novel Convolutional Neural Network Based Indoor Localization Framework With WiFi Fingerprinting

Cited by 165 publications

References 31 publications

An Indoor Positioning and Navigation System Using Named Data Networking

An Indoor Positioning and Navigation System Using Named Data Networking

Integration of positioning and activity context information for lifelog in urban city area

WiFi RTT Indoor Positioning Method Based on Gaussian Process Regression for Harsh Environments

Contact Info

Product

Resources

About