Abstract: A method for adjusting an installation orientation of an access point within a predefined area with an associated orientation is disclosed. The method includes obtaining, at a computing apparatus, angle of arrival estimates from each access point based on a wireless transmission from a wireless mobile device. The computing device generates an estimated location of the wireless mobile device based on the angle of arrival estimates. Next, the computing device determines an orientation error for each wireless access point based on the angle of arrival estimate of the wireless mobile device and the estimated location of the wireless mobile device. The computing device generates an adjusted orientation of one or more of the access points based on the orientation error of the access point, thereby aligning the adjusted orientation with the orientation of the predefined area.

Abstract: Various systems and methods for counting people. For example, one method involves receiving input data at an analytics system that includes a neural network. The input data includes a representation of an environment, including representations of several people. The method also includes identifying the representations of the people in the representation of the environment. The method also includes updating an output value that indicates the number of people identified as being present in the environment.

Abstract: Techniques for generating a prediction for a location of a mobile device includes a network controller obtaining signal strength information and angle-of-arrival information for mobile devices from a plurality of access points disposed at a location that includes two or more zones. The network controller extracts features from the obtained information. The features indicate whether the mobile devices are more likely in a first zone than in one or more of second zones of the two or more zones. The network controller generates a software model for classifying a mobile device into one of the two or more zones by applying a computer learning process to the extracted features. The network controller uses the software model to generate a prediction indicating that a first mobile device is in one of the two or more zones, and performs an action at the location based on the prediction.

Abstract: A method for adjusting an installation orientation of an access point within a predefined area with an associated orientation is disclosed. The method includes obtaining, at a computing apparatus, angle of arrival estimates from each access point based on a wireless transmission from a wireless mobile device. The computing device generates an estimated location of the wireless mobile device based on the angle of arrival estimates. Next, the computing device determines an orientation error for each wireless access point based on the angle of arrival estimate of the wireless mobile device and the estimated location of the wireless mobile device. The computing device generates an adjusted orientation of one or more of the access points based on the orientation error of the access point, thereby aligning the adjusted orientation with the orientation of the predefined area.

Abstract: A methodology includes determining coarse location coordinates for a mobile device, anchoring the coarse location coordinates to a map, receiving inertial measurement unit data supplied by the mobile device, wherein the inertial measurement unit data is indicative of relative location coordinates of the mobile device, generating an unanchored path of the mobile device based on the relative location coordinates, and anchoring the unanchored path of the mobile device to the map in a position that optimizes a match between the coarse location coordinates and the relative location coordinates of the mobile device.

Abstract: A method including obtaining location estimates of a wireless mobile device inside a structure based on wireless signals transmitted by the wireless mobile device and received at a plurality of wireless access points, wherein the inside of the structure is represented by a plurality of path segments; modeling a transition from a first estimated location of the wireless mobile device to a second estimated location of the wireless mobile device by minimizing a ratio of an angle to a length between the first estimated location and the second estimated location; selecting, based on the modeling a particular path segment of the plurality of path segments; and aligning the second estimated location of the mobile device to the particular path segment. An apparatus and a computer-readable storage media implementing the method are also disclosed.

Abstract: A methodology includes determining coarse location coordinates for a mobile device, anchoring the coarse location coordinates to a map, receiving inertial measurement unit data supplied by the mobile device, wherein the inertial measurement unit data is indicative of relative location coordinates of the mobile device, generating an unanchored path of the mobile device based on the relative location coordinates, and anchoring the unanchored path of the mobile device to the map in a position that optimizes a match between the coarse location coordinates and the relative location coordinates of the mobile device.

Abstract: In one embodiment, a neighbor access point list is obtained. Statistics are maintained for a current access point that a client is currently associated with, including previous access points previous clients have roamed from prior to associating with the current access point, and next access points the previous clients associated with. The neighbor access point list for the client is optimized, by determining one or more previous clients that associated with a same previous access point as the client and prioritizing access points in the optimized neighbor access point list, based on the next access points the one or more previous clients associated with. The optimized neighbor access point list is sent to the client.

Abstract: A method including obtaining location estimates of a wireless mobile device inside a structure based on wireless signals transmitted by the wireless mobile device and received at a plurality of wireless access points, wherein the inside of the structure is represented by a plurality of path segments; modeling a transition from a first estimated location of the wireless mobile device to a second estimated location of the wireless mobile device by minimizing a ratio of an angle to a length between the first estimated location and the second estimated location; selecting, based on the modeling a particular path segment of the plurality of path segments; and aligning the second estimated location of the mobile device to the particular path segment. An apparatus and a computer-readable storage media implementing the method are also disclosed.

Abstract: A methodology includes receiving from a first mobile device a first estimated location of the first mobile device and a first estimated error associated with the first estimated location, the first estimated location being based on first coarse data from a first wireless access point location determination system fused with inertial measurement unit (IMU) data from the first mobile device, receiving from a second mobile device a second estimated location of the second mobile device and a second estimated error associated with the second estimated location, the second estimated location being based on second coarse data from the first wireless access point location determination system fused with IMU data from the second mobile device, and based on the first estimated error and the second estimated error, determining a recommended change to a deployment of a wireless access point associated with the first wireless access point location determination system.

Abstract: A system and method for improved location tracking of a target device based on location estimates for multiple types of location technologies/sensor types. A received signal strength location estimate of a target device based on wireless transmissions made by the target device received at a plurality of receiver devices at known locations in a location region. A first search area for the target device is derived based on the received signal strength location estimate. An ultrasound based area in which the target device is estimated to be is derived based on reception by the target device of a particular ultrasound beacon in the location region. An intersection of the first search area and the ultrasound based area is computed to produce a second search area. A location estimate of the target device in the second search area is computed based at least on the received signal strength location estimate.

Abstract: Systems, methods, and computer program products to perform an operation comprising receiving, from a video monitoring system, a count of people detected at a first location, wherein the video monitoring system comprises a camera configured to capture video of the first location, receiving a count of wireless devices detected in a second location, and applying a first correction factor to the count of wireless devices detected at the second location to determine a number of people present in the second location, wherein the first correction factor is based on the count of people detected by the video monitoring system and a count of wireless devices in the first location.

Abstract: Systems, methods, and computer program products to perform an operation comprising receiving, from a video monitoring system, a count of people detected at a first location, wherein the video monitoring system comprises a camera configured to capture video of the first location, receiving a count of wireless devices detected in a second location, and applying a first correction factor to the count of wireless devices detected at the second location to determine a number of people present in the second location, wherein the first correction factor is based on the count of people detected by the video monitoring system and a count of wireless devices in the first location.

Abstract: Various systems and methods for counting people. For example, one method involves receiving input data at an analytics system that includes a neural network. The input data includes a representation of an environment, including representations of several people. The method also includes identifying the representations of the people in the representation of the environment. The method also includes updating an output value that indicates the number of people identified as being present in the environment.

Abstract: In one embodiment, a neighbor access point list is obtained. Statistics are maintained for a current access point that a client is currently associated with, including previous access points previous clients have roamed from prior to associating with the current access point, and next access points the previous clients associated with. The neighbor access point list for the client is optimized, by determining one or more previous clients that associated with a same previous access point as the client and prioritizing access points in the optimized neighbor access point list, based on the next access points the one or more previous clients associated with. The optimized neighbor access point list is sent to the client.

Abstract: In one embodiment, a method includes obtaining location information associated with a remote device, and processing the location information. Processing the location information includes determining if the remote device is mobile. The method also includes configuring a filter such that at least one parameter indicates that the remote device is mobile if the remote device is mobile, and configuring the filter such that the at least one parameter indicates that the remote device is approximately stationary if the remote device is not mobile. The filter is applied to the location information to generate a filtered location estimate which is arranged to estimate a location of the remote device.

Abstract: An apparatus configured to acquire received signal strength intensities (RSSIs) for a wireless device from a plurality of access points (APs) located on a plurality logical floors. The apparatus is configured to determine which logical floor the wireless device is on by analyzing the RSSIs. The RSSIs for each floor are adjusted with an adjustment value and are selectively weighted with at least two different weight values, and the adjusted and weighted RSSIs for each floor are each summed. The floor with highest sum of adjusted or weighted RSSIs is determined to be the floor the wireless device is on.

Abstract: An apparatus configured to acquire received signal strength intensities (RSSIs) for a wireless device from a plurality of access points (APs) located on a plurality logical floors. The apparatus is configured to determine which logical floor the wireless device is on by analyzing the RSSIs. The RSSIs for each floor are adjusted with an adjustment value and are selectively weighted with at least two different weight values, and the adjusted and weighted RSSIs for each floor are each summed. The floor with highest sum of adjusted or weighted RSSIs is determined to be the floor the wireless device is on. The logical floor is further determined by sorting the RSSIs for each floor and then weighting the sorted RSSIs with the different weight values. The sorted and weighted RSSIs for each floor are summed. The floor with highest sum of weighted sorted RSSIs is determined to be the floor the wireless device is on.

Abstract: An apparatus configured to acquire received signal strength intensities (RSSIs) for a wireless device from a plurality of access points (APs) located on a plurality logical floors. The apparatus is configured to determine which logical floor the wireless device is on by analyzing the RSSIs. The RSSIs for each floor are adjusted with an adjustment value and are selectively weighted with at least two different weight values, and the adjusted and weighted RSSIs for each floor are each summed. The floor with highest sum of adjusted or weighted RSSIs is determined to be the floor the wireless device is on. The logical floor is further determined by sorting the RSSIs for each floor and then weighting the sorted RSSIs with the different weight values. The sorted and weighted RSSIs for each floor are summed. The floor with highest sum of weighted sorted RSSIs is determined to be the floor the wireless device is on.

Abstract: In one embodiment, a method includes obtaining location information associated with a remote device, and processing the location information. Processing the location information includes determining if the remote device is mobile. The method also includes configuring a filter such that at least one parameter indicates that the remote device is mobile if the remote device is mobile, and configuring the filter such that the at least one parameter indicates that the remote device is approximately stationary if the remote device is not mobile. The filter is applied to the location information to generate a filtered location estimate which is arranged to estimate a location of the remote device.