Methods of deriving location information of a wireless device include deriving, in the continuous domain, a location of a wireless device and at least one time and location varying path loss function parameter. The coordinates and parameter are derived based on signal strength measurements made at the wireless device, with the measured signals originating from a plurality of wireless transmitters, such as access points. The derived path loss function parameter can include one or more of a path loss exponent parameter, an intercept parameter, a receiver antenna gain parameter, transmitter antenna gain parameter, or a transmit power parameter.

Aspects of the present invention provide systems and methods for distributed signal processing of indoor localization signals wherein statistical algorithms and machine learning are used in place of a fingerprint map. The disclosure relates to calculation of angle and distance based on measurements of an indoor localization signal, followed by energy-efficient distribution of signal processing. Local signal processing is performed using any of multiple eigen structure algorithms or a linear probabilistic inference, before cloud-based signal processing is performed using a nonlinear probabilistic inference and machine learning that's been trained with historical data transmitted by the base stations and time-of-day location patterns. Without having to generate and constantly update an energy-exorbitant fingerprint map, the disclosed system reduces localization error to merely 50 cm with 95% probability without compromising energy-efficiency to rival the accuracy of indoor localization systems that utilize fingerprinting.

A system identifies a first position of a tag in a clinical environment based on first times at which first receivers received a first wireless signal from the tag. The system estimates a second position of the tag in the clinical environment based on second times at which second receivers received a second wireless signal from the tag. The system determines that a boundary is located between the first position and the second position, defines a path range around the first position of the tag based on an expected movement of the tag during a time interval between the first and second wireless signals, determines that the boundary lacks a door within the path range, adjusts the second position of the tag based on the boundary map, and transmits a message indicating that the tag is located at the adjusted position at the second time.

An area determination system includes a decision unit, a calculation unit, and a determination unit. The decision unit decides, based on a strength of a radio signal transmitted from a transmitter and received by a receiver, a location of the transmitter. The calculation unit calculates a presence determination value. The presence determination value is based on a number of times that the location of the transmitter is determined to be in a presence determination region during a presence determination time period. The presence determination region corresponds to a target area. The determination unit, when a presence condition is satisfied, determine that the transmitter is in the target area. The presence condition is that a state where the presence determination value is greater than or equal to a presence threshold continues for a presence determination time.

Embodiments described herein provide means by which a civic location of a target mobile device may be determined using crowdsourced information from other mobile devices. The information can include information regarding Access Points (APs) and/or other access nodes obtained by the other mobile devices, as well as respective locations of the other mobile devices. A server, for example, can use this information to determine a coverage heatmap for each AP. Coverage heatmaps can be used, along with civic location information, to determine a civic location of a target mobile device based on the target mobile device's detection and possible measurements of wireless signals from one or more of the APs.

A monitoring system includes a first sensor and a second sensor, at least one of which is a camera. A computer system coupled to the first and second sensors includes a memory and stored object types and associations between objects of the object types. The computer system is configured to infer a first association between a first and second object by retrieving an input from at least one of the sensors, determining the object types of the first and second objects and inferring a specific interaction at a monitored location based on the sensor inputs.

Examples herein involve estimating a first position of a mobile device based on first communication signals, assigning a first set of particles to a number of respective first sampling locations within a threshold distance of the first position, adjusting the assignment of the first set of particles to second sampling locations based on movement of the mobile device, and estimating a second position of the mobile device based on the second sampling locations.

A two-way signal positioning method and a two-way signal positioning system thereof are disclosed. The method includes the following steps: controlling a locating device to be measured to transmit a plurality of positioning signals of a plurality of transmission powers; causing a plurality of known locating devices to receive the plurality of positioning signals and return a plurality of response signals to the locating device to be measured; recording the strengths of the plurality of positioning signals, the strengths of the plurality of response signals, the plurality of corresponding receiving times and the coordinates of the plurality of known locating devices to a database; identifying the known locating devices corresponding to the stronger signals; and obtaining a signal strength-distance function and a signal strength-distance standard deviation function from the database so as to identify the device location of the locating device to be measured.

A position estimation method for estimating a position of a mobile terminal includes: an acquisition step of acquiring distance values and radio wave intensity values between communication devices provided in a vehicle and the mobile terminal by communicating the communication devices with the mobile terminal; a communication availability determination step of determining that a corresponding communication device is communicable when the distance value is not more than a first value and the intensity value is not less than a second value; an area determination step of, based on a result of the communication availability determination step and communication maps mapping communicable ranges of the communication devices, determining an area where the mobile terminal exists by superimposing the communication maps; and an estimation step of estimating the position of the mobile terminal based on a result of the area determination step.

A machine learning method performed by a communication network monitoring device in which an incoming signaling record is received that includes radio signal attributes from a UE in the cellular communication network. A determination is made as to whether the UE incoming signaling record contains location (GPS) data. If the UE incoming signaling record contains GPS data, a machine learning model is generated for determining a location of future UEs in the communication network utilizing the GPS data and the radio signal attributes from the incoming UE signaling record. And if GPS data is not included in the UE incoming signaling record, then first a corrected TA value is determined which is then used, along with other radio signal attributes of the UE, to determine/predict a geolocation for the UE using machine learning techniques.