开源软件名称（OpenSource Name）：

开源软件地址(OpenSource Url)：

开源编程语言(OpenSource Language)：

开源软件介绍(OpenSource Introduction)：

ELEC 681 Project: A Machine Learning Approach to Wi-Fi Fingerprint based Localization

Automatic user localization consists of estimating the position of the user (latitude, longitude and altitude) by using an electronic device, usually a mobile phone. Outdoor localization problem can be solved very accurately thanks to the inclusion of GPS sensors into the mobile devices. However, indoor localization is still an open problem mainly due to the loss of GPS signal in indoor environments. With the widespread use of Wi-Fi communication in indoor environments, Wi-Fi or wirless local area network (WLAN) based positioning gained popularity to solve indoor localization.

WLAN-based positioning systems utilize the Wi-Fi received signal strength indicator (RSSI) value. In this project, we focus on fingerprint-based localization. Fingerprinting technique consists of two phases: calibration and positioning. In the calibration phase, an extensive radio map is built consisting of RSSI values from multiple Wi-Fi Access Points (APs) at different known locations. This calibration data is used to train the localization algorithm. In the positioning phase, when a user reports the RSSI measurements for the multiple APs, the fit algorithm predicts the user position.

A key challenge in wireless localization is that RSSI value at a given location can have large fluctuations due to Wi-Fi interference, user mobility, environmental mobility etc. In this project, we design, implement and evaluate machine learning algorithms for WLAN fingerprint-based localization.

For comparison, we utilize the UJIIndoorLoc dataset[1], the first publicly available dataset created for benchmarking WLAN fingerprint localization algorithms. The dataset consists of 19937 calibration records and 1111 positioning records. Each Wi-Fi fingerprint record consists of user ID, timestamp, received signal strength intensity of 520 Access Points and location information including latitude, longitude, floor etc.

[1] Joaquín Torres-Sospedra, Raúl Montoliu, Adolfo Martínez-Usó, Tomar J. Arnau, Joan P. Avariento, Mauri Benedito-Bordonau, Joaquín Huerta. UJIIndoorLoc: A New Multi-building and Multi-floor Database for WLAN Fingerprint-based Indoor Localization Problems. In Proceedings of the Fifth International Conference on Indoor Positioning and Indoor Navigation, 2014.