Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 6;22(23):9531.
doi: 10.3390/s22239531.

Improved CNN-Based Indoor Localization by Using RGB Images and DBSCAN Algorithm

Fang Cheng  1 , Guofeng Niu  1 , Zhizhong Zhang  1 , Chengjie Hou  2
Affiliations

Improved CNN-Based Indoor Localization by Using RGB Images and DBSCAN Algorithm

Fang Cheng et al. Sensors (Basel). .

Abstract

With the intense deployment of wireless systems and the widespread use of intelligent equipment, the requirement for indoor positioning services is increasing, and Wi-Fi fingerprinting has emerged as the most often used approach to identifying indoor target users. The construction time of the Wi-Fi received signal strength (RSS) fingerprint database is short, but the positioning performance is unstable and susceptible to noise. Meanwhile, to strengthen indoor positioning precision, a fingerprints algorithm based on a convolution neural network (CNN) is often used. However, the number of reference points participating in the location estimation has a great influence on the positioning accuracy. There is no standard for the number of reference points involved in position estimation by traditional methods. For the above problems, the grayscale images corresponding to RSS and angle of arrival are fused into RGB images to improve stability. This paper presents a position estimation method based on the density-based spatial clustering of applications with noise (DBSCAN) algorithm, which can select appropriate reference points according to the situation. DBSCAN analyses the CNN output and can choose the number of reference points based on the situation. Finally, the position is approximated using the weighted k-nearest neighbors. The results show that the calculation error of our proposed method is at least 0.1-0.3 m less than that of the traditional method.

Keywords: DBSCAN; Wi-Fi fingerprints; convolution neural network (CNN); indoor location.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Received signal strength (RSS) grayscale under different labels (Labels from left to right are ‘2-2’, ‘2-6’, and ‘2-10’ respectively).
Figure 2
Figure 2
Angle of arrival (AOA) grayscale under different labels (Labels from left to right are ‘2-2’, ‘2-6’ and ‘2-10’ respectively).
Figure 3
Figure 3
Complete CNN positioning system implementation (offline training phase and online positioning phase).
Figure 4
Figure 4
RGB images under different labels (Labels from left to right are ‘2-2’, ‘2-6’ and ‘2-10’ respectively).
Figure 5
Figure 5
System design of the LeNet5 CNN network model.
Figure 6
Figure 6
Setting arrangement of simulation area when the number of reference points is 50.
Figure 7
Figure 7
Probability distribution diagram of positioning error when the distance between two reference points is 4 m (Q = 50).
Figure 8
Figure 8
Probability distribution diagram of positioning error when the distance between two reference points is 5 m (Q = 32).
Figure 9
Figure 9
Probability distribution diagram of positioning error when the distance between two reference points is 2 m (Q = 200).
Figure 10
Figure 10
The average localization error for different reference point distances.
See this image and copyright information in PMC

References

    1. Varma P.S., Anand V. Indoor Localization for IoT Applications: Review, Challenges and Manual Site Survey Approach; Proceedings of the 2021 IEEE Bombay Section Signature Conference (IBSSC); Gwalior, India. 18–20 November 2021; pp. 1–6. - DOI
    1. Andò B., Baglio S., Crispino R., Marletta V. An Introduction to Indoor Localization Techniques. Case of Study: A Multi-Trilateration-Based Localization System with User–Environment Interaction Feature. Appl. Sci. 2021;11:7392. doi: 10.3390/app11167392. - DOI
    1. Hasan R., Hasan R., Islam T. Smart City Technology for Disaster Management: Demonstrating the Use of Bluetooth Low Energy (BLE) Beacons for Emergency Alert Dissemination; Proceedings of the 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC); Las Vegas, NV, USA. 8–11 January 2022; pp. 931–932. - DOI
    1. Tekler Z.D., Low R., Yuen C., Blessing L. Plug-Mate: An IoT-based occupancy-driven plug load management system in smart buildings. Build. Environ. 2022;223:109472. doi: 10.1016/j.buildenv.2022.109472. - DOI
    1. Bae Y., Bhattacharya S., Cui B., Lee S., Li Y., Zhang L., Im P., Adetola V., Vrabie D., Leach M., et al. Sensor impacts on building and HVAC controls: A critical review for building energy performance. Adv. Appl. Energy. 2021;4:100068. doi: 10.1016/j.adapen.2021.100068. - DOI

LinkOut - more resources