Wireless communication system and method and system for detection of position of radio mobile station
First Claim
1. A method of detecting a position of a particular mobile station in a radio communication system including at least the mobile station, a plurality of base stations and a control station, said method comprising the steps of:
- measuring only reception strength levels of radio signals from said plurality of base stations at a plurality of measuring points using at least one mobile station of said radio communication system;
transmitting a result of the measurement from said at least one mobile station to said control station through one of said base stations;
performing a learning operation in said control station through a neural network, to learn a correlation between said strength levels of said radio signals and the position of said at least one mobile station on the basis of said measurement results at said plurality of measuring points and on the basis of position data of said measuring points,said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each of said input layer nodes corresponds to one of said base stations,said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving said reception strength levels at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points;
conveying measurement results of strength levels of said radio signals from each of said plurality of base stations, measured by said particular mobile station at an arbitrary point, to said control station through one of said base stations; and
estimating by said control station a position of said particular mobile station which has provided said measurement results, on the basis of said correlation between said strength levels of said radio signal and a position of said at least one mobile station attained through the learning operation.
2 Assignments
0 Petitions
Accused Products
Abstract
A method of detecting a position of a radio mobile station in radiocommunications, which is capable of accurately and simply finding the position of the mobile station. At a measuring point the mobile station measures the reception radio strength levels from a plurality of base stations and conveys the measurement results through the base station to a control station. The control station learns, through a neural network, the correlation between the reception radio strength levels and the position of the mobile station on the basis of the measurement results at a plurality of measuring points and the positions of the measuring points. Subsequently, when the mobile station communicates to the control station the reception radio strength levels measured at an arbitrary point, the control station estimates the position of the mobile station, causing those measurement results, on the basis of the correlation obtained through the learning.
142 Citations
25 Claims
-
1. A method of detecting a position of a particular mobile station in a radio communication system including at least the mobile station, a plurality of base stations and a control station, said method comprising the steps of:
-
measuring only reception strength levels of radio signals from said plurality of base stations at a plurality of measuring points using at least one mobile station of said radio communication system; transmitting a result of the measurement from said at least one mobile station to said control station through one of said base stations; performing a learning operation in said control station through a neural network, to learn a correlation between said strength levels of said radio signals and the position of said at least one mobile station on the basis of said measurement results at said plurality of measuring points and on the basis of position data of said measuring points, said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each of said input layer nodes corresponds to one of said base stations, said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving said reception strength levels at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; conveying measurement results of strength levels of said radio signals from each of said plurality of base stations, measured by said particular mobile station at an arbitrary point, to said control station through one of said base stations; and estimating by said control station a position of said particular mobile station which has provided said measurement results, on the basis of said correlation between said strength levels of said radio signal and a position of said at least one mobile station attained through the learning operation. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A mobile station radio communication system comprising:
-
a mobile station, a plurality of base stations and a control station, said control station detecting a position of said mobile station, wherein; said mobile station includes radio signal strength measuring means for measuring strength levels of said radio signal from each of said plurality of base stations, and said control station includes; position input means for inputting positions of a plurality of measuring points; position learning processing means for learning, through a neural network, a correlation between said strength levels of said radio signals measured by said mobile station at each of said plurality of measuring points and the positions of said plurality of measuring points inputted through said position input means, said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each node corresponds to one of said base stations, said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving reception strength levels at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; and position estimation processing means for estimating a position of said mobile station at the measuring time, on the basis of strength levels of said radio strength from each of said plurality of base stations measured by said mobile station at an arbitrary point, by using correlation learned by said position learning processing means. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 25)
-
-
20. A mobile station radio communication system comprising:
-
a mobile station, a plurality of base stations and a control station, and a control station, said control station detecting a position of said mobile station, wherein; said mobile station includes radio signal strength measuring means for measuring strength levels of said radio signal from each of said plurality of base stations, and said control station includes; position storage means for storing data indicative of a position of each of a plurality of measuring points and an ID of said mobile station, said position storage means storing said data in correspondence with each of said measuring points; position learning processing means for learning, through a neural network, a correlation between said strength levels of said radio signals corresponding to each of said measuring points and the positions of said plurality of measuring points inputted through said position input means, said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each node corresponds to one of said base stations, said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving reception strength levels at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; and position estimation processing means for estimating a position of said mobile station at the measuring time, on the basis of strength levels of said radio strength from each of said plurality of base stations measured by said mobile station at an arbitrary point, by using correlation learned by said position learning processing means.
-
-
21. A method of detecting the position of a mobile station in a radio communication system including at least the mobile station, a plurality of base stations and a control station, said method comprising the steps of:
-
determining a plurality of measuring points in advance, said measuring points being distributed as evenly as practicable over an area in which said plurality of base stations are located; measuring at each measuring point only a strength of a radio signal from one or more of said base stations where reception is available, and recording the measurement result in combination with positional information of the measuring points; forming a neural network for learning correlations between measurement results at respective measuring points and the positional information thereof so that said neural network outputs positional information of said measuring points in receipt of said result of measurement, providing said neural network a number of input layer nodes corresponding in number to the number of said base stations so that each node corresponds to one of said base stations, providing said neural network a plurality of output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving reception strength levels at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; measuring at one or more unknown points a strength of a radio signal from one or more base stations when said mobile station is within said area; and inputting said radio signal strength obtained in said step of measuring at one or more unknown points to said neural network so as to determine a position of said mobile station.
-
-
22. A radio communication system comprising at least one mobile station, a plurality of base stations and a control station adapted to determine a position of a mobile station, a plurality of measuring points being determined in advance, said measuring points being distributed as evenly as practicable over an area in which said plurality of base stations are located, said system comprising:
-
first measuring means for measuring at each of said measuring points only a strength level of a radio signal from one or more of said base stations where reception is available; means for recording the measurement result in combination with positional information of the measuring points, said positional information being inputted in advance; means for forming a neural network to learn a correlation between said strength levels of said radio signals and the position of said mobile station on the basis of said measurement results at said plurality of measuring points and on the basis of position data of said measuring points, said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each of said input layer nodes corresponds to one of said base stations, said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving reception strength levels at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; second measuring means for measuring at one or more unknown points a strength of a radio signal from one or more base stations when said mobile station is within said area; and means for inputting to said neural network said strength of said radio signal obtained by said second measuring means so as to o determine a position of said mobile station.
-
-
23. A method of detecting a position of a particular mobile station in a radio communication system including at least the mobile station, a plurality of base stations and a control station, said method comprising the steps of:
-
measuring only reception strength levels of radio signals from said plurality of base stations at a plurality of measuring points using at least one mobile station of said radio communication system; transmitting a result of the measurement from said at least one mobile station to said control station through one of said base stations; converting said reception strength levels of said radio signals transmitted from said at least one mobile station into theoretical distances between said base stations and said at least one mobile station; performing a learning operation in said control station through a neural network, to learn a correlation between said theoretical distances and the position of said at least one mobile station on the basis of said measurement results at said plurality of measuring points and on the basis of position data of said measuring points, said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each node corresponds to one of said base stations, said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that it will output positional information of said respective measuring points when receiving said theoretical distance at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; conveying measurement results of strength levels of said radio signals, from each of said plurality of base stations, as measured by said particular mobile station at an arbitrary point, to said control station through one of said base stations; and estimating by said control station a position of said particular mobile station which has provided said measurement results, on the basis of said correlation between said strength levels of said radio signal and a position of said at least one mobile station attained through the learning operation.
-
-
24. A mobile station radio communication system comprising:
-
at least one mobile station, a plurality of base stations and a control station, said control station detecting a position of a mobile station, wherein; said mobile station includes radio signal strength measuring means for measuring reception strength levels of said radio signal from each of said plurality of base stations, and said control station includes; position input means for inputting positions of a plurality of measuring points; means for converting said reception strength levels of said radio signals transmitted from said mobile station into theoretical distances between said base stations and said mobile station; position learning processing means for learning, through a neural network, a correlation between said strength levels of said radio signals measured by said mobile station at each of said plurality of measuring points and the positions of said plurality of measuring points inputted through said position input means, said neural network having a plurality of input layer nodes corresponding in number to the number of said base stations so that each node corresponds to one of said base stations, said neural network having output layer nodes whose number is sufficient for indicating positional information whereby said neural network learns such that said neural network outputs positional information of said respective measuring points when receiving said theoretical distance at each of said base stations corresponding to each of said respective nodes of said input layer with respect to all of said measuring points; and position estimation processing means for estimating a position of said mobile station at the measuring time, on the basis of strength levels of said radio strength from each of said plurality of base stations measured by said mobile station at an arbitrary point, by using correlation learned by said position learning processing means.
-
Specification