Abstract: An approach is provided for in-parking navigation based on mobile device sensor data, the resulted semantic events, and an estimated parking occupancy level. The approach, for example, involves receiving parking information from in-parking navigation system(s) of vehicle(s) and/or mobile device(s) associated with the vehicle(s) traveling in a parking facility with no or a positioning satellite coverage below a threshold. The parking information indicates parking spot location(s) occupied by the vehicle(s). The in-parking navigation system(s) determines the at least one parking spot location based on tracking multi-modal trajectories of the mobile device(s). The multi-modal trajectories comprise vehicle trajectory segment(s) traveling within the parking facility and pedestrian trajectory segment(s) traveling to/from pedestrian entry or exit point(s) of the parking facility. The approach also involves determining an occupancy level of the parking facility based on the parking information.

Abstract: An approach is provided for detecting an on-boarding or off-boarding event based on mobile device sensor data. The approach, for example, involves retrieving sensor data collected from at least one sensor of a mobile device that is fixed in a stationary position relative to a vehicle. The approach also involves processing the sensor data to determine roll angle data for the vehicle over a time window. The approach further involves processing the roll angle data to determine one or more transitions of a roll angle value of the vehicle between one or more value levels. The approach further involves determining an on-boarding event, an off-boarding event, or a combination thereof based on the one or more transitions. The approach further involves providing the on-boarding event, the off-boarding event, or a combination thereof as an output.

Abstract: An approach is provided for in-parking navigation based on mobile device sensor data, the resulted semantic events, and an estimated parking occupancy level. The approach, for example, involves receiving parking information from in-parking navigation system(s) of vehicle(s) and/or mobile device(s) associated with the vehicle(s) traveling in a parking facility with no or a positioning satellite coverage below a threshold. The parking information indicates parking spot location(s) occupied by the vehicle(s). The in-parking navigation system(s) determines the at least one parking spot location based on tracking multi-modal trajectories of the mobile device(s). The multi-modal trajectories comprise vehicle trajectory segment(s) traveling within the parking facility and pedestrian trajectory segment(s) traveling to/from pedestrian entry or exit point(s) of the parking facility. The approach also involves determining an occupancy level of the parking facility based on the parking information.

Abstract: An approach is provided for detecting an on-boarding or off-boarding event based on mobile device sensor data. The approach, for example, involves retrieving sensor data collected from at least one sensor of a mobile device that is fixed in a stationary position relative to a vehicle. The approach also involves processing the sensor data to determine roll angle data for the vehicle over a time window. The approach further involves processing the roll angle data to determine one or more transitions of a roll angle value of the vehicle between one or more value levels. The approach further involves determining an on-boarding event, an off-boarding event, or a combination thereof based on the one or more transitions. The approach further involves providing the on-boarding event, the off-boarding event, or a combination thereof as an output.

Abstract: An approach is provided for mapping a parking facility using multi-modal trajectories collected using mobile device(s). The approach, for example, involves collecting sensor data from sensor(s) of mobile device(s). The sensor data represents the multi-modal trajectories comprising (1) vehicle trajectory segments during which the device(s) traveling into/out of a parking facility, and (2) pedestrian trajectory segments during which the device(s) traveling to/from pedestrian entry/exit point(s) of the parking facility. The approach also involves processing the sensor data to determine semantic event(s) associated with parking in the parking facility based on the multi-modal trajectories. The approach further involves determining parking spot location(s) and/or orientation(s) of the parking facility based on the semantic event(s). The approach further involves generating map data indicating the parking spot location(s) and/or orientation(s). The approach further involves providing the map data as an output.

Abstract: An approach is provided for detecting a vehicle door opening or closing event based on sensor data collected during a vehicle idle/stop state. The approach, for example, involves collecting sensor data from one or more sensors of a vehicle, a mobile device in the vehicle, or a combination thereof. The approach also involves determining a time period when the vehicle is in an idle state based on the sensor data. The approach further involves determining a vehicle door open event or a vehicle door close event based on pressure sensor data from at least one pressure sensor of the mobile device collected during the time period. The approach further involves providing the vehicle door open event or the vehicle door close event as an output.

Abstract: There is provided a method of automatically tagging social network posts with geo-location tags, comprising: for each of a plurality of user generated content items uploaded to a social network from a plurality of different client devices: selecting a specific geographic region mapping dataset of a plurality of geographic region mapping datasets corresponding to a specific geographic region identified by an analysis of the respective user generated content post, mapping by the specific geographic region mapping dataset, a generic term to a specific geographic location within the specific geographic region, and tagging the respective user generated content item with a geo-location tag of the specific geographic location within the specific geographic region.

Abstract: A system, a method and a computer program product are provided for determining building type of one or more buildings in a geographic region, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain a plurality of mobility features associated with the one or more buildings. The processor may be configured to determine, using a trained machine learning model, one or more transport modes for the one or more buildings, based on the plurality of mobility features. The processor may be further configured to determine, using the trained machine learning model, the building type of the one or more buildings based on the determined one or more transport modes.

Abstract: A system, a method and a computer program product are provided to determine user profile of one or more users in one or more buildings, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the one or more buildings in a geographic region. The processor may be configured to determine using a trained machine learning model, one or more transport modes for the one or more buildings. The processor may be further configured to obtain indoor mobility data of the one or more users based on the one or more transport modes for the one or more buildings. The processor may be further configured determine the user profile of the one or more users in the one or more buildings.

Abstract: There is provided a method of automatically tagging social network posts with geo-location tags, comprising: for each of a plurality of user generated content items uploaded to a social network from a plurality of different client devices: selecting a specific geographic region mapping dataset of a plurality of geographic region mapping datasets corresponding to a specific geographic region identified by an analysis of the respective user generated content post, mapping by the specific geographic region mapping dataset, a generic term to a specific geographic location within the specific geographic region, and tagging the respective user generated content item with a geo-location tag of the specific geographic location within the specific geographic region.

Abstract: An approach is provided for discovery of semantic nodes for map-based dynamic location sampling. The approach, for instance, involves identifying a semantic node occurring on a road segment. The semantic node is a point of interest on or near the road segment that is different from beginning node and end node of the road segment. The approach also involves calculating an estimated time of arrival at the semantic node based on historical traversal time data for the road segment. The approach further involves determining a sampling rate for a location sensor of vehicle traveling the road segment based on the estimated time of arrival. The approach further involves configuring the location sensor to collect location data using the sampling rate.

Abstract: A system, a method and a computer program product are provided to determine population distribution of users associated with one or more buildings in a geographic region, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the one or more buildings in the geographic region. The processor may be configured to determine using a trained machine learning model, one or more transport modes for the one or more buildings, based on the mobility features. The processor may be further configured to determine, using the trained machine learning model, the population distribution of the users associated with the one or more buildings in the geographic region at a fixed epoch based on the determined one or more transport modes.

Abstract: Various aspects of a method, a system, and a computer program product are disclosed herein in accordance with at least one example embodiment for spatial clustering of a plurality of cells of a geographical location. The method may include generation of cell clusters based on multiple criteria. The method may further include reception of mobility data from one or more external devices associated with the plurality of cells. The mobility data may be further processed to extract observations for generation of feature vectors from the observations. The feature vectors may be normalized to generate one or more clusters of a set of cells of the location. Cluster data associated with the clustering of the plurality of cells may be further used in one or more location based applications.

Abstract: A system, a method and a computer program product are provided to determine population distribution of users associated with one or more buildings in a geographic region, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the one or more buildings in the geographic region. The processor may be configured to determine using a trained machine learning model, one or more transport modes for the one or more buildings, based on the mobility features. The processor may be further configured to determine, using the trained machine learning model, the population distribution of the users associated with the one or more buildings in the geographic region at a fixed epoch based on the determined one or more transport modes.

Abstract: A system, a method and a computer program product are provided to determine mobility pattern of one or more users for buildings, using machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the buildings in a geographic region, entry-exit data of the one or more users for the buildings in the geographic region The processor may be configured to determine, using trained machine learning model, one or more transport modes for the one or more buildings, based on the mobility features. The processor may be configured to determine, using a trained machine learning model, the mobility pattern of the one or more users based on the entry-exit data of the one or more users and the one or more transport modes for the buildings.

Abstract: A system, a method and a computer program product are provided for determining building type of one or more buildings in a geographic region, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain a plurality of mobility features associated with the one or more buildings. The processor may be configured to determine, using a trained machine learning model, one or more transport modes for the one or more buildings, based on the plurality of mobility features. The processor may be further configured to determine, using the trained machine learning model, the building type of the one or more buildings based on the determined one or more transport modes.

Abstract: A system, a method and a computer program product are provided to determine user profile of one or more users in one or more buildings, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the one or more buildings in a geographic region. The processor may be configured to determine using a trained machine learning model, one or more transport modes for the one or more buildings. The processor may be further configured to obtain indoor mobility data of the one or more users based on the one or more transport modes for the one or more buildings. The processor may be further configured determine the user profile of the one or more users in the one or more buildings.

Abstract: A system, a method and a computer program product are provided for determining one or more transport modes for one or more buildings in a geographic region, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain sensor data associated with the one or more buildings for time duration. The processor may be configured to determine mobility features associated with the one or more buildings, based on the sensor data. The processor may be further configured to determine, using a trained machine learning model, the one or more transport modes for the one or more buildings, based on the mobility features.

Abstract: An approach is provided for performing ride-sharing functions based on joint motion using multiple sensor data. The approach, for example, involves retrieving a joint motion prediction indicating whether at least two devices are traveling in a same transportation vehicle. The joint motion prediction is computed based on sensor data collected from the at least two devices using at least one sensor type from among a plurality of sensor types. Each sensor type of the plurality of sensor types is associated with a respective joint motion classifier configured to compute a sensor-type joint motion prediction that is used for generating the joint motion prediction. The approach also involves initiating a ride-sharing function for respective users of the at least two devices based on the joint motion prediction.

Abstract: An approach is provided for recommending services based on map-based dynamic location sampling. The approach, for instance, involves determining a predicted location of a vehicle on a road segment based on an estimated time of arrival at an end node of the road segment. The approach also involves calculating a difference between the predicted location and an actual location sensed by a location of the vehicle. The approach further involves recommending a service for installation on or near the road segment based on the difference.