Support Vector Regression Based Indoor Location in IEEE 802.11 Environments

Abstract

The wide spread of the 802.11-based wireless technology brings about a good opportunity for the indoor positioning system. In this paper, we present a new 802.11-based indoor positioning method using support vector regression (SVR), which consists of offline training stage and online location stage. The model that describes the relations between the position and the received signal strength (RSS) of the mobile device is established at the offline training stage by SVR, and at the online location stage the exact position is determined by this model. Due to the complex indoor environment, RSS is vulnerable and changeable. To address this issue, data filtering rules obtained through statistical analysis are applied at offline training stage to improve the quality of training samples and thus improve the quality of prediction model. At the online location stage,k-times continuous measurement is utilized to obtain the high quality RSS input, which guarantees the consistency with the training samples and improves the position accuracy of mobile devices. Performance evaluation shows that the proposed method has a higher positioning accuracy compared with the probability and neutral network method, and the demand for the storage capacity and computing power is also low at the same time.

A Soft Range Limited K-Nearest Neighbors Algorithm for Indoor Localization Enhancement

“…The former uses a similarity metric to differentiate the measured signal and the fingerprint data in the database before estimating the user's position as the closest fingerprint location in the signal space. Some typical examples of this approach are artificial neural network (ANN) [6], [7], support vector machine (SVM) [6], [8] and K nearest neighbors (KNN) [9], [10], all of which require the collection of the fingerprints in the training phase to be compared with the measured signal in the testing phase for localization. Among these algorithms, ANN estimates location nonlinearly from the input by a chosen activation function and adjustable weightings [7].…”

A novel smartphone application for indoor positioning of users based on machine learning

“…As can be seen in this figure, the proposed method gains the minimum error by using the Matern kernel. In another evaluation, we use Matern kernel and compare the performance of the proposed GPR based positioning with some of recent and known algorithms including KNN [8], SVR [15], PCA-SVR [13] and theoretical Cramer-Rao lower bound (CRLB) in terms of RMSE. As can be seen in figure 8, the proposed method performs best among others with nearest distance to theoretical bounds.…”

“…Some of the most frequently used maximum likelihood based methods are, k-nearest neighbor (KNN) [8], neural networks (NN) [2], deep learning [22] and support vector regression (SVR) [15] (which sometimes is called support vector machine regression). All these mentioned methods are generally called deterministic approaches in which the distribution of output (the coordinates of user's location) is not estimated.…”

Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization

“…In order to improve the precision, some regression machine learning algorithms are applied. Support Vector Regression (SVR) [31,32,33] is used to find the positioning function that controls the accumulative error. However, the computational complexity of the SVR algorithm is cubic in the number of training data, because its solution process involves n-order positive definite matrix inversion [34].…”