|
| Ref | Year | Scenario | Application | P/A | Own deployment |
|
| [22] | 2003 | Indoor | One of the earliest approaches on precise positioning using Wi-Fi (precision 2.6m) | A | Yes |
| [23] | 2006 | Indoor | Wi-Fi fingerprint to identify the general location and applying logistic regression to distinguish between finer-grained locations. | A | Yes |
| [24] | 2006 | Indoor, office building | Precise positioning. PDR combined with Wi-Fi to reduce the accumulated error | A | Yes |
| [25] | 2007 | Outdoor and indoor | Creation of Wi-Fi map. Positioning comparing with the created map | A | Yes. Own hardware. Offline analysis |
| [26] | 2007 | Indoor, campus | Comparison of positioning and tracking methods using Wi-Fi | P | No. Offline |
| [27] | 2008 | Indoor, campus | Estimate the position using Wi-Fi and tracking with PDR | A | Yes |
| [28] | 2009 | Indoor, campus | Real time Wi-Fi positioning, web portal to check user's positions | A | Yes |
| [39] | 2009 | Indoor, campus | Count of users in different buildings. Analysis of users' mobility between buildings | P | No. Institutional APs |
| [57] | 2010 | Indoor, campus and office building | Coarse position with Wi-Fi and Bluetooth. Graph of user co-occurrence. | A | No. Offline |
| [43] | 2010 | Indoor, campus and office building | Calculate of stay length based on Wi-Fi positioning. Analysis of favorite locations | A | No. Offline |
| [44] | 2011 | Indoor, campus | Extension to [39]. User characterization based on their mobility patterns | P | No. Institutional APs |
| [29] | 2011 | Indoor, tunnel in construction | Precise positioning in real time of workers inside a constructing tunnel using Wi-Fi (precision 5m) | P | Yes. Own AP deployment |
| [30] | 2012 | Indoor, campus | Creation of Wi-Fi fingerprint map. Map usage to positioning with smartphone application | A | No |
| [36] | 2012 | Indoor, campus | Study of crowd movement Wi-Fi based. Analysis of mobility patterns, users' arrivals and departures from campus | P | No. Institutional APs |
| [58] | 2013 | Indoor | Wi-Fi path analysis in real time. | A | No. Institutional APs |
| [33] | 2014 | Indoor and outdoor, campus | Analyze pedestrian destination frequencies in an area of 55 hectares of a university campus during 5 weekdays. | P | No. Institutional APs and Radius server |
| [59] | 2014 | Indoor, campus | Localization and tracking system exploiting particle filters to combine dead reckoning, Wi-Fi RSS-based analyzing and knowledge of floor plan together. (precision 0.7m) | A | |
| [60] | 2015 | Indoor, shopping mall | Wi-Fi Channel State Information analysis to detect shopper activities | P | Yes. Own AP deployment |
| [31] | 2015 | Indoor | Precise positioning based on sensor fusion combining Wi-Fi, PDR and landmarks. Smartphone application. (Positioning 1m) | A | No. Smartphones |
| [32] | 2015 | Indoor, parking | Precise positioning combining Wi-Fi RSS and electromagnetic field map | | |
| [37] | 2015 | Outdoor, concert. Indoor, campus | Portable Wi-Fi based user count. Analysis of crowds in concert and in campus | P | Yes. Raspberry Pi based |
| [61] | 2015 | Outdoor | Creation of Wi-Fi map using GPS | A | |
| [62] | 2016 | Indoor | Precise positioning combining Wi-Fi and PDR | A | No. Smartphones |
| [34] | 2016 | Indoor, airport | User path detection. Combining Wi-Fi, GPS, PDR and Bluetooth to create a multilevel map and study of user's trajectory prediction | A | No. Smartphones |
| [45] | 2016 | Indoor, campus | Analysis of users' activities. User tagging based on activities registered | P | No. Institutional APs |
| [46] | 2016 | Indoor and outdoor, campus | Analysis of user movements to different food points to predict the operation of new stores based on price and location | P | No. Institutional APs |
| [63] | 2017 | Indoor | Crowdsourcing positioning based on Wi-Fi fingerprint | A | No. Institutional APs |
| [41] | 2018 | Indoor | Coarse positioning, room level precision, based on probabilistic Wi-Fi fingerprint. Usage of Hidden Markov chain models to analyze user movement. | P | No. Institutional APs |
| [35] | 2016 | Indoor | Trajectory analysis based on Hidden Markov chain models | P | No. Institutional APs |
| [42] | 2017 | Indoor | Estimate the number of participants and their space and time evolution in an area of about 167 hectares during 2016 Open Day of the European JRC | P | No. Institutional APs |
| [47] | 2016 | Indoor
Outdoor | Study mobility-related activities in a campus of 440 hectares based on the 2700 APs of the institutional network and additional opt-in smartphone application | A | No. Institutional APs |
| [53] | 2014 | Indoor | Classify users in a hospital (e.g., patient, doctor, administrative) by checking the number of hours and the positions of a user over time based on the institutional Wi-Fi network | P | No. Institutional APs |
| [38] | 2012 | Indoor | Identify flocks walking in a building and their behavior based on signal strength from the institutional Wi-Fi and using clustering techniques | P | No. Institutional APs |
| [45] | 2016 | Indoor | Analyze users’ occupation (based on Markov models) as well as regular and irregular hours in a university campus | P | No. Institutional APs |
| [40] | 2016 | Indoor | Analyze room utilization and people tracking providing heat maps. Analyze device statistics | A | No. Institutional APs |
| [48] | 2017 | Indoor
Outdoor | Analyze people mobility monitoring and tracking in Smart Cities and traffic in a highway (e.g., driving behavior, traffic forecasting) | P | Yes. Raspberry Pi based |
| [49] | 2018 | Indoor
Outdoor | Provide user localization, user profiling, and device classification | A | Yes. Raspberry Pi based |
| [54] | 2005 | Indoor
Outdoor | Analyze Wi-Fi tracking records gathered during more than one year in Madeira to classify users as tourists or locals and identify touristic spots | P | Yes. Based on TP-Link MR3240v2 home router |
| [56] | 2017 | Indoor | Obtain semantic trajectories. Classify users based on their locations. Analyze the probability of a user going to a specific shop based on their history and propose the creation of a recommender based on the whole dataset | - | - |
|
