A New Three-Dimensional Indoor Positioning Mechanism Based on Wireless LAN

Abstract

The researches on two-dimensional indoor positioning based on wireless LAN and the location fingerprint methods have become mature, but in the actual indoor positioning situation, users are also concerned about the height where they stand. Due to the expansion of the range of three-dimensional indoor positioning, more features must be needed to describe the location fingerprint. Directly using a machine learning algorithm will result in the reduced ability of classification. To solve this problem, in this paper, a “divide and conquer” strategy is adopted; that is, first through k-medoids algorithm the three-dimensional location space is clustered into a number of service areas, and then a multicategory SVM with less features is created for each service area for further positioning. Our experiment shows that the error distance resolution of the approach with k-medoids algorithm and multicategory SVM is higher than that of the approach only with SVM, and the former can effectively decrease the “crazy prediction.”

A Smartphone 3D Positioning Method using a Spinning Magnet Marker

“…Zandbergen et al [1], Cheng et al [2], and Alam et al [3] studied a positioning method using the radio field intensity fingerprint from from Wi-Fi access points. However, these methods require recreating fingerprints when the environment changes.…”

“…In addition, when it is possible to estimate the route of a visitor within an accuracy of several centimeters, it is possible to estimate the behavior pattern of visitors in detail. Various in- 1 Graduate School of Engineering, Nagoya University, Nagoya, Aichi 464-0814, Japan 2 Institutes of Innovation for Future Society, Nagoya University, Nagoya, Aichi 464-8601, Japan 3 IoT Business Department, NTT DOCOMO, INC., Yokosuka, Kanagawa 239-8536, Japan 4 Research Laboratories, NTT DOCOMO, INC., Yokosuka, Kanagawa 239-8536, Japan 5 Product Department, NTT DOCOMO, INC., Yokosuka, Kanagawa 239-8536, Japan 6 R&D Information Service Department, DOCOMO Technology, Inc., Yokosuka, Kanagawa 239-8536, Japan 7 Faculty of Information Science, Aichi Institute of Technology, Toyota, Aichi 470-0392, Japan a) nabeko@ucl.nuee.nagoya-u.ac.jp door positioning methods have been studied to date. For example, there are methods based on radio waves such as Wi-Fi access points [1], [2], [3], [4], BLE (Bluetooth Low Energy) [5], [6], [7], and UWB (Ultra Wide Band) technology [8].…”

Random Forest Based Coarse Locating and KPCA Feature Extraction for Indoor Positioning System

“…In terms of the SVM method (optimized by genetic algorithm) [10,11] and the proposed RF method, their subregions are able to be defined freely. Therefore the number of RPs within a region is set according to the corners or partitions of the building and then assigned to both methods.…”

“…Moreover, the coarse locating scheme can also work on three-dimensional scenario for discriminating different floors or as the basis for positioning on a size-reduced radio map. In addition, compared with some typical machine learning techniques, such as artificial neural network (ANN) [8] and support vector machine (SVM) [9][10][11], the proposed RF based coarse positioning method shows a better performance in terms of classification accuracy and training time complexity.…”

The Novel Performance Evaluation Method of the Fingerprinting-Based Indoor Positioning

“…In [12], k-Nearest Neighbours (k-NN) is applied with particle filter (PF) by reducing the probability of wrong prediction. In [13], Support vector machine (SVM) is improved performance by classified data from divided groups by kmedroids. Although, Support vector machine with kernel is powerful and complex algorithm for positioning, it heavily utilizes processor and memory [14].…”