Abstract
With the ubiquitous deployment of wireless systems and pervasive availability of smart devices, indoor localization is empowering numerous location-based services. With the established radio maps, WiFi fingerprinting has become one of the most practical approaches to localize mobile users. However, most fingerprint-based localization algorithms are computation-intensive, with heavy dependence on both offline training phase and online localization phase. In this paper, we propose CNNLoc, a Convolutional Neural Network (CNN) based indoor localization system with WiFi fingerprints for multi-building and multi-floor localization. Specifically, we devise a novel classification model and a novel positioning model by combining a Stacked Auto-Encoder (SAE) with a one-dimensional CNN. The SAE is utilized to precisely extract key features from sparse Received Signal Strength (RSS) data while the CNN is trained to effectively achieve high accuracy in the positioning phase. We evaluate the proposed system on the UJIIndoorLoc dataset and Tampere dataset and compare the performance with several state-of-the-art methods. Moreover, we further propose a newly collected WiFi fingerprinting dataset UTSIndoorLoc and test the positioning model of CNNLoc on it. The results show CNNLoc outperforms the existing solutions with 100% and 95% success rates on building-level localization and floor-level localization, respectively.
Highlights
Indoor Location-Based Services (ILBSs) have become an essential component for various indoor applications, such as location based wireless advertising, information retrieval and pedestrian navigation [1]
1) Convolutional Neural Network (CNN) MODEL OPTIMIZATION To make the comparison more reasonable, we evaluate the structure of a CNN model with the same Stacked Auto-Encoder (SAE) model by adopting the SAE(256-128-64) from [25], where the SAE contains three hidden layers of 256, 128 and 64 neurons
2) SAE MODEL OPTIMIZATION we evaluate the performance of different SAE models by using the same CNN model
Summary
Indoor Location-Based Services (ILBSs) have become an essential component for various indoor applications, such as location based wireless advertising, information retrieval and pedestrian navigation [1]. Various indoor localization techniques have been proposed using different types of modalities, including WiFi, visible light, acoustic, cellular network and their combinations [3]. The majority of localization techniques utilize Received Signal Strength (RSS) from Wireless Access Points (WAPs) to deduce the locations of mobile users with the pre-constructed fingerprint database. This building has 18 levels, including 4 basement levels. Since the bottom and top floors are not public active areas, UTSIndoorLoc dataset covers 16 floors of this building. 4) There are totaly 589 different Wireless Access Points (WAPs) included in the dataset The main features of the UTSIndoorLoc dataset are as follows. 1) It covers an area of approximately 44,000 square meters and contains WiFi fingerprinting data for 16 floors. 2) The total number of sample points at different locations is 1840. 3) In a total of 9494 sample data, 9107 samples are used for the training session and the rest 387 are used for the testing session. 4) There are totaly 589 different Wireless Access Points (WAPs) included in the dataset
Sign-in/Register to view highlights & summary 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.
