Think globally, fit locally: unsupervised learning of low dimensional manifolds
The Journal of Machine Learning Research
Estimating Location Using Wi-Fi
IEEE Intelligent Systems
Context-aware, self-scaling Fuzzy ArtMap for received signal strength based location systems
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special issue on neural networks for pattern recognition and data mining
The Horus location determination system
Wireless Networks
A novel infrastructure WLAN locating method based on neural network
Proceedings of the 4th Asian Conference on Internet Engineering
Survey of Wireless Indoor Positioning Techniques and Systems
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Indoor geolocation science and technology
IEEE Communications Magazine
| Hi-index | 0.00 |
An important requirement for many novel location based services, is to determine the locations of people, equipment, animals, etc. The accuracy and response time of estimation are critical issues in location estimation system. Most of the location estimation system suffers with the problem of scalability and unavailability of all the access points at all the location for large site. In this paper, we have proposed a distributed semi-supervised location estimation method, which divide the location estimation system into subsystems. Our method partition the input signal space and output location space into clusters on the basis of visibility of access points at various locations of the site area. Each cluster of input signal space together with output location subspace is used to learn the association between Received Signal Strength fingerprint and their respective location in a subsystem. Previous methods for location estimation in indoor wireless networks require a large amount of labeled data for learning the radio map. However, labeled instances are often difficult, expensive, or time consuming to obtain, as they require great efforts, meanwhile unlabeled data may be relatively easy to collect. So, the use of semi-supervised learning is more feasible. On each subsystem at first, we use Locally Linear Embedding to reduce the dimensions of data, and then we use semi-supervised learning algorithm to learn the radio map. The algorithm performs nonlinear mapping between the received signal strengths from nearby access points and the user's location. It is shown that the proposed Distributed Semi-Supervised Locally Linear Embedding scheme has the advantage of robustness, scalability, useful in large site application and is easy in training and implementation. We have compared our results with Distributed Subtract on Negative Add on Positive (DSNAP) and benchmark method RADAR. Experimental results show that our method provide better results in terms of accuracy and response time in comparison to centralized systems, in which a single system is used for large site as well as with DSNAP and benchmark method RADAR.