Many applications in Internet of Things (IoT) require an ubiquitous localization to provide their services. Whereas the global navigation satellite systems is mainly used in outdoor environment, multiple solutions based on mobile sensors or wireless communication infrastructures exist for indoor localization. One of them is the fingerprinting approach which consists in collecting the signals at known locations in a studied area and estimating the locations of new incoming signals thanks to the collected database. This approach interests many researches due to its connection with machine learning concepts. In this paper we propose to implement a deep learning architecture for a fingerprinting localization based on Wi-Fi channel frequency responses in IoT context. Our solution, DelFin reduces the median and 9-th quantile localization errors up to 50% and 47% respectively compared to other fingerprinting methods. DelFin has been tested with different spatial distributions of training locations in the studied area and still performed the best results.

The proliferation of location-based services highlights the need to develop an accurate indoor localization solution. The global navigation satellite system does not deliver good accuracy indoors because of weak signal. One solution is to piggyback Wi-Fi technology, which is widespread in offices and domestic environments. This wireless communication has a promising future, with the possibility to estimate locations with a single gateway by combining channel state information with fingerprinting. However, the existing solutions are often limited to a specific setup and are hard to replicate in other situations. Furthermore, channel state information consists of complex data, which hampers the learning phase of machine learning techniques. This paper assesses the performances of unsupervised data complexity reduction methods by considering different data collection scenarios with multiple antenna elements at the anchor gateway. The study puts forward an evaluation method based on five heuristic scores to guide the design of future fingerprinting solutions based on channel state information. This has been extended to several spatial distributions of training locations, and we show that the kernel entropy component analysis is more suitable for implementation than the principal component analysis, the factor analysis, the independent component analysis and the kernel principal component analysis.

No abstract

No abstract