Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers
<p>Abstract</p> <p>A new approach to indoor localization is presented, based upon the use of Received Signal Strength (RSS) fingerprints containing data from very large numbers of cellular base stations--up to the entire GSM band of over 500 channels. Machine learning techniques ar...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2011-01-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Online Access: | http://jwcn.eurasipjournals.com/content/2011/1/81 |
| _version_ | 1818345631918325760 |
|---|---|
| author | Oussar Yacine Ahriz Iness Denby Bruce Dreyfus Gérard |
| author_facet | Oussar Yacine Ahriz Iness Denby Bruce Dreyfus Gérard |
| author_sort | Oussar Yacine |
| collection | DOAJ |
| description | <p>Abstract</p> <p>A new approach to indoor localization is presented, based upon the use of Received Signal Strength (RSS) fingerprints containing data from very large numbers of cellular base stations--up to the entire GSM band of over 500 channels. Machine learning techniques are employed to extract good quality location information from these high-dimensionality input vectors. Experimental results in a domestic and an office setting are presented, in which data were accumulated over a 1-month period in order to assure time robustness. Room-level classification efficiencies approaching 100% were obtained, using Support Vector Machines in <it>one-versus-one </it>and <it>one-versus-all </it>configurations. Promising results using semi-supervised learning techniques, in which only a fraction of the training data is required to have a room label, are also presented. While indoor RSS localization using WiFi, as well as some rather mediocre results with low-carrier count GSM fingerprints, have been discussed elsewhere, this is to our knowledge the first study to demonstrate that <it>good quality </it>indoor localization information can be obtained, in diverse settings, by applying a machine learning strategy to RSS vectors <it>that contain the entire GSM band</it>.</p> |
| first_indexed | 2024-12-13T17:05:27Z |
| format | Article |
| id | doaj.art-605878f4109b4ce48fdeccd44641fc9b |
| institution | Directory Open Access Journal |
| issn | 1687-1472 1687-1499 |
| language | English |
| last_indexed | 2024-12-13T17:05:27Z |
| publishDate | 2011-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-605878f4109b4ce48fdeccd44641fc9b2022-12-21T23:37:42ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14721687-14992011-01-012011181Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriersOussar YacineAhriz InessDenby BruceDreyfus Gérard<p>Abstract</p> <p>A new approach to indoor localization is presented, based upon the use of Received Signal Strength (RSS) fingerprints containing data from very large numbers of cellular base stations--up to the entire GSM band of over 500 channels. Machine learning techniques are employed to extract good quality location information from these high-dimensionality input vectors. Experimental results in a domestic and an office setting are presented, in which data were accumulated over a 1-month period in order to assure time robustness. Room-level classification efficiencies approaching 100% were obtained, using Support Vector Machines in <it>one-versus-one </it>and <it>one-versus-all </it>configurations. Promising results using semi-supervised learning techniques, in which only a fraction of the training data is required to have a room label, are also presented. While indoor RSS localization using WiFi, as well as some rather mediocre results with low-carrier count GSM fingerprints, have been discussed elsewhere, this is to our knowledge the first study to demonstrate that <it>good quality </it>indoor localization information can be obtained, in diverse settings, by applying a machine learning strategy to RSS vectors <it>that contain the entire GSM band</it>.</p>http://jwcn.eurasipjournals.com/content/2011/1/81 |
| spellingShingle | Oussar Yacine Ahriz Iness Denby Bruce Dreyfus Gérard Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers EURASIP Journal on Wireless Communications and Networking |
| title | Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers |
| title_full | Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers |
| title_fullStr | Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers |
| title_full_unstemmed | Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers |
| title_short | Indoor localization based on cellular telephony RSSI fingerprints containing very large numbers of carriers |
| title_sort | indoor localization based on cellular telephony rssi fingerprints containing very large numbers of carriers |
| url | http://jwcn.eurasipjournals.com/content/2011/1/81 |
| work_keys_str_mv | AT oussaryacine indoorlocalizationbasedoncellulartelephonyrssifingerprintscontainingverylargenumbersofcarriers AT ahriziness indoorlocalizationbasedoncellulartelephonyrssifingerprintscontainingverylargenumbersofcarriers AT denbybruce indoorlocalizationbasedoncellulartelephonyrssifingerprintscontainingverylargenumbersofcarriers AT dreyfusg233rard indoorlocalizationbasedoncellulartelephonyrssifingerprintscontainingverylargenumbersofcarriers |