Abstract: In one example, a method is described. The method includes: obtaining network traffic data including at least one user agent, where the user agent is associated with a client device coupled to a network at a media exposure measurement location, and where the user agent comprises a string of characters defining client device attributes, comparing one or more of the client device attributes to candidate device attributes stored in an audience measurement database, based on the comparison, selecting, from a set of candidate device attributes, a set of target device attributes corresponding to a target device identifier, determining a number of occurrences of the set of target device attributes in the network traffic data, and based on a determination that the number of occurrences is above a threshold, outputting the target device identifier as the device identifier that corresponds to the user agent.

Abstract: In one example, a method is described. The method includes: obtaining network traffic data characterizing network activity of devices coupled to a network at a media exposure measurement location, processing the network traffic data to generate, for each of multiple devices: activity parameters, each characterizing a network activity of the device, processing the activity parameters using an IoT classification model that includes a decision tree having: (i) multiple internal nodes, each internal node associated with an activity parameter threshold, and (ii) multiple leaf nodes, each leaf node associated with either the IoT device type or the other device type, based on the decision tree, selecting, from the device identifiers included in the network traffic data, a target device identifier corresponding to a leaf node in the decision tree that is associated with the IoT device type, and outputting the target device identifier.

Abstract: In one example, a method is described. The method includes: obtaining network traffic data characterizing network activity of devices coupled to a network at a media exposure measurement location, processing the network traffic data to generate, for each of multiple devices: activity parameters, each characterizing a network activity of the device, processing the activity parameters using an IoT classification model that includes a decision tree having: (i) multiple internal nodes, each internal node associated with an activity parameter threshold, and (ii) multiple leaf nodes, each leaf node associated with either the IoT device type or the other device type, based on the decision tree, selecting, from the device identifiers included in the network traffic data, a target device identifier corresponding to a leaf node in the decision tree that is associated with the IoT device type, and outputting the target device identifier.

Abstract: In one example, a method is described. The method includes: obtaining network traffic data characterizing network activity of devices coupled to a network at a media exposure measurement location, processing the network traffic data to generate, for each of multiple devices: activity parameters, each characterizing a network activity of the device, processing the activity parameters using an IoT classification model that includes a decision tree having: (i) multiple internal nodes, each internal node associated with an activity parameter threshold, and (ii) multiple leaf nodes, each leaf node associated with either the IoT device type or the other device type, based on the decision tree, selecting, from the device identifiers included in the network traffic data, a target device identifier corresponding to a leaf node in the decision tree that is associated with the IoT device type, and outputting the target device identifier.

Abstract: In one example, a method is described. The method includes: obtaining network traffic data including at least one user agent, where the user agent is associated with a client device coupled to a network at a media exposure measurement location, and where the user agent comprises a string of characters defining client device attributes, comparing one or more of the client device attributes to candidate device attributes stored in an audience measurement database, based on the comparison, selecting, from a set of candidate device attributes, a set of target device attributes corresponding to a target device identifier, determining a number of occurrences of the set of target device attributes in the network traffic data, and based on a determination that the number of occurrences is above a threshold, outputting the target device identifier as the device identifier that corresponds to the user agent.

Abstract: In one example, a method is described. The method includes: obtaining a non-persistent device identifier; obtaining network traffic data specifying, for each of multiple network devices, a network device identifier, one or more network device parameters, and a network time stamp; comparing user device parameters to network device parameters; selecting, based on the parameter comparison, one or more candidate device identifiers; comparing, for each candidate device identifier, the user device time stamp with the network time stamp associated with the candidate device identifier; selecting, based on the time stamp comparison, a target device identifier from the one or more candidate device identifiers; and updating the non-persistent device identifier associated with the user-associated device at a media exposure measurement location using the target device identifier selected from the one or more candidate device identifiers included in the network traffic data.