Abstract: In one embodiment, a method includes receiving one or more input signals comprising one or more event signals associated with an event and one or more user signals associated with a user, where the input signals include time-based signals, each of which includes an event time or a user arrival time, and the input signals further include location-based signals, each of which includes an event location or a user location. The method may further include determining, using a trained machine-learning model, whether the user attended the event according to the input signals, and presenting, to a target user, an indication of whether the user attended the event. The machine-learning model may be trained on list of tuples, each of which includes a user identifier, an event identifier, and an indication of whether the user identified by the user identifier attended the event identified by the event identifier.

Abstract: Systems and methods herein enable a mobile device to detect that a user is traveling in association with a vehicle based at least on motion data. In some embodiments, accelerometer data is used. Motion data is leveraged in combination with various observations regarding vehicular movement to determine whether or not a mobile device is located in or on the vehicle. For instance, before entering the state of vehicular movement, it can be determined that the user is first in a walking state (e.g., walking to the car, bus, etc., and entering it). Likewise, after exiting the state of vehicular movement, the user re-enters the walking state (e.g., after stepping out of the car, bus, etc., the user again begins walking). Further, it can be determined that when the user is in the walking state, the accelerometer signals appear different to any accelerometer signals seen in the vehicular movement state.

Abstract: In one embodiment, a method includes receiving one or more input signals comprising one or more event signals associated with an event and one or more user signals associated with a user, where the input signals include time-based signals, each of which includes an event time or a user arrival time, and the input signals further include location-based signals, each of which includes an event location or a user location. The method may further include determining, using a trained machine-learning model, whether the user attended the event according to the input signals, and presenting, to a target user, an indication of whether the user attended the event. The machine-learning model may be trained on list of tuples, each of which includes a user identifier, an event identifier, and an indication of whether the user identified by the user identifier attended the event identified by the event identifier.

Abstract: Disclosed is an apparatus and method for power efficient processor scheduling of features. In one embodiment, features may be scheduled for sequential computing, and each scheduled feature may receive a sensor data sample as input. In one embodiment, scheduling may be based at least in part on each respective feature's estimated power usage. In one embodiment, a first feature in the sequential schedule of features may be computed and before computing a second feature in the sequential schedule of features, a termination condition may be evaluated.

Abstract: Systems and methodologies are described that facilitate identifying peers based upon encoded signals during peer discovery in a peer to peer network. For example, direct signaling that partitions a time-frequency resource into a number of segments can be utilized to communicate an identifier within a peer discovery interval; thus, a particular segment selected for transmission can signal a portion of the identifier, while a remainder can be signaled based upon tones communicated within the selected segment. Moreover, a subset of symbols within the resource can be reserved (e.g., unused) to enable identifying and/or correcting timing offset. Further, signaling can be effectuated over a plurality of peer discovery intervals such that partial identifiers communicated during each of the peer discovery intervals can be linked (e.g., based upon overlapping bits and/or bloom filter information).

Abstract: Systems and methods for monitoring the proximity of a personal item are provided. Systems and methods as provided herein allow a computing device to monitor the proximity of a personal item by generating an alert when wireless communications between the computing device and the personal item are lost in an unsafe zone to remind a user of the computing device about the personal item in an attempt to prevent leaving the personal item in the unsafe zone, where it may be susceptible to theft or loss. The provided systems and methods also automatically assign safe zones by analyzing clusters of location data points obtained by the computing device over time to determine a home location and an office location, assigning the home location and the office location as safe zones, and assigning all other locations as unsafe. A user may further manually designate locations as safe zones.

Abstract: Methods, systems, computer-readable media, and apparatuses for determining indoor/outdoor state of a mobile device are presented. In some embodiments, a mobile device may maintain an indoor/outdoor state. The mobile device may include at least one first sensor and at least one second sensor, the first sensor associated with higher power consumption than the second sensor. The mobile device may gate off the first sensor and using the second sensor to obtain a sensor reading, if the second sensor can generate a reading indicative of the indoor/outdoor state of the mobile device. The mobile device may use the first sensor to obtain a sensor reading, if the second sensor cannot generate a reading indicative of the indoor/outdoor state of the mobile device. The mobile device may update the indoor/outdoor state of the mobile device based on a reading received from one of the first and the second sensors.

Abstract: Systems and methods for applying and using context labels for data clusters are provided herein. A method described herein for managing a context model associated with a mobile device includes obtaining first data points associated with a first data stream assigned to one or more first data sources; assigning ones of the first data points to respective clusters of a set of clusters such that each cluster is respectively assigned ones of the first data points that exhibit a threshold amount of similarity and are associated with times within a threshold amount of time of each other; compiling statistical features and inferences corresponding to the first data stream or one or more other data streams assigned to respective other data sources; assigning context labels to each of the set of clusters based on the statistical features and inferences.

Abstract: Disclosed is an apparatus and method for speaker equalization in a mobile device. In one embodiment, placement of a mobile device including a speaker is determined and speaker equalization is performed in accordance with the determined placement.

Abstract: Systems and methods for providing application-controlled, power-efficient context (state) classification are described herein. An apparatus for performing context classification with adjustable granularity as described herein includes a classifier controller configured to receive a request for a context classification and a granularity input associated with the request; and a context classifier communicatively coupled to the classifier controller and configured to receive the request and the granularity input from the classifier controller, to select a resource usage level for the context classification based on the granularity input, wherein a granularity input indicating a higher granularity level is associated with a higher resource usage level and a granularity input indicating a lower granularity level is associated with a lower resource usage level, and to perform the context classification at the selected resource usage level.

Abstract: The disclosure is directed to modifying the operation of one or more hardware subsystems when a new context awareness service begins. An aspect determines a power budget for a plurality of operating context awareness services including the new context awareness service, wherein the power budget is based on a power requirement for each of the plurality of context awareness services, and wherein the power requirement for each of the plurality of context awareness services is based on power utilizations of the one or more hardware subsystems corresponding to the plurality of context awareness services, and allocates power resources to the one or more hardware subsystems based on importances of the plurality of context awareness services and/or the one or more hardware subsystems, wherein the allocation of the power resources is performed within the power budget.

Abstract: Methods, systems, computer-readable media, and apparatuses for inferring context are provided. In one potential implementation, first context information associated with a first duration is identified, second context information is accessed to determine a context segmentation boundary; and the first context information and the second context information is then aggregated to generate an inferred segmented aggregated context. In a further implementation, the first context information is used to average inferred contexts, and the context segmentation boundary is used to reset a start time for averaging the first context information.

Abstract: A method of generating demographic statistics related to an event includes using sensor data acquired at a mobile device to estimate a value for a category of a demographic model of a user of the mobile device; using sensor data acquired at the mobile device to detect an occurrence of the event in which the user of the mobile device participates; and associating the estimated value for the category of the demographic model of the user of the mobile device with the event.

Abstract: Components, methods, and apparatuses are provided that may be used to obtain a plurality of time-referenced features extracted from signals received from one or more inertial sensors of a mobile device, wherein the time-referenced features are provided according to heterogeneous time scales. The time-referenced features are combined over a decision window to infer an activity of a user co-located with the mobile device.

Abstract: Disclosed is an apparatus and method for speaker equalization in a mobile device. In one embodiment, placement of a mobile device including a speaker is determined and speaker equalization is performed in accordance with the determined placement.

Abstract: Information about a context of a mobile device is inferred using measurements from light detectors of the mobile device. The light detectors may be located on multiple different sides of the mobile device. In some embodiments, measurements from one or more cameras may be used to infer context.

Abstract: A position estimate for a mobile device is generated using data from motion sensors, such as accelerometers, magnetometers, and/or gyroscopes, and data from light sensors, such as an ambient light sensor, proximity sensor and/or camera intensity sensor. A plurality of proposed positions with associated likelihoods is generated by analyzing information from the motion sensors and a list of candidate positions is produced based on information from the light sensors. At least one of the plurality of proposed positions is eliminated using the list of candidate positions and a position estimate for the mobile device is determined based on the remaining proposed positions and associated likelihoods. The proposed positions may be generated by extracting features from the information from the motion sensors and using models to generate likelihoods for the proposed positions. The likelihoods may be filtered over time. Additionally, a confidence metric may be generated for the estimated position.

Abstract: System and methods for performing context inference in a computing device are disclosed. In one embodiment, a method of performing context inference includes: determining, at a computing device, a first context class using context-related data from at least one data source associated with a mobile device; and determining, at the mobile device, a fusion class based on the first context class, the fusion class being associated with at least one characteristic that is common to the first context class and a second context class that is different from the first context class.

Abstract: Disclosed is an apparatus and method for speaker equalization in a mobile device. In one embodiment, placement of a mobile device including a speaker is determined and speaker equalization is performed in accordance with the determined placement.

Abstract: In a multi-level power transmission scheme, an access point transmits at one power level, while repeatedly transmitting at a burst power level for short periods of time. For example, a femto cell may transmit a beacon with periodic high power bursts of short duration, while the femto cell transmit power also undergoes high power bursts aligned with the beacon bursts. In a network listen-based power control scheme, an access point listens for one or more parameters sent over-the-air by the network and then defines transmit power based on the received parameter(s). In some aspects, beacon transmit power may be set based on a defined outage radius parameter and the total received signal power on a channel. In some aspects, access point transmit power may be set based on a defined coverage parameter and the received energy associated with signals from access points of a certain type.