Abstract
The intelligent use of deep learning (DL) techniques can assist in overcoming noise and uncertainty during fingerprinting-based localization. With the rise in the available computational power on mobile devices, it is now possible to employ DL techniques, such as convolutional neural networks (CNNs), for smartphones. In this paper, we introduce a CNN model based on received signal strength indicator (RSSI) fingerprint datasets and compare it with different CNN application models, such as AlexNet, ResNet, ZFNet, Inception v3, and MobileNet v2, for indoor localization. The experimental results show that the proposed CNN model can achieve a test accuracy of 94.45% and an average location error as low as 1.44 m. Therefore, our CNN model outperforms conventional CNN applications for RSSI-based indoor positioning.
Highlights
Despite decades of research, effective products for indoor localization products are still unavailable, while indoor localization-based service demand continues to increase swiftly in smart cities [1]
While the dataset collected during measurement was in a text format, the deep learning (DL) code was designed for a comma-separated values (CSV) input file
This paper presents a novel approach to indoor localization that is proven sufficiently efficient to achieve a low error distance with high test accuracy
Summary
Effective products for indoor localization products are still unavailable, while indoor localization-based service demand continues to increase swiftly in smart cities [1]. Most of the research aims to provide a widely used indoor localization scheme and achieve satisfactory performance similar to that of GPS in outside environments Of these approaches [2,3,4,5], fingerprinting-based methods are the most widely used due to their effectiveness and the infrastructure’s independence. We propose a new and efficient framework that employs CNN-based Wi-Fi fingerprinting to achieve a superior level of indoor localization accuracy for a user with a smartphone. We constructed a CNN model with optimum performance for RSSI-based fingerprint indoor localization with dataset Schemes 1 and 2 [11], which were subsequently used to enhance indoor localization robustness and accuracy.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
