Abstract: A method for improving performance of a trained machine learning model includes adding a second classifier with a second objective function to a first classifier with a first objective function. Rather than minimizing a function of errors for the first classifier, the second objective function is used to directly reduce the number errors of the first classifier.

Abstract: Methods, systems, and devices are described for identifying noisy regions in a skin conductance signal. The signal is divided into a plurality of windows. Two or more features of the signal within a first window are computed. At least one of the two or more features being in a frequency domain. At least two of the features are combined to obtain at least a first metric. The first metric is compared to a corresponding threshold. The first window is identified as a noisy region of the skin conductance signal based on the comparison.

Abstract: A method for improving performance of a trained machine learning model includes adding a second classifier with a second objective function to a first classifier with a first objective function. Rather than minimizing a function of errors for the first classifier, the second objective function is used to directly reduce the number errors of the first classifier.

Abstract: A method of adaptively selecting a configuration for a machine learning process includes determining current system resources and performance specifications of a current system. A new configuration for the machine learning process is determined based at least in part on the current system resources and the performance specifications. The method also includes dynamically selecting between a current configuration and the new configuration based at least in part on the current system resources and the performance specifications.

Abstract: Various arrangements for delivery of relevant content to a mobile device of a user are presented. Physiological state data and image data related to the user of the mobile device may be received by a host computer system from a mobile device. The image data may be analyzed to identify a characteristic of the image. The physiological state data may also be analyzed. Content to deliver to the mobile device of the user may be selected at least partially based on the physiological state data of the user and the characteristic of the image. The content may be transmitted to the mobile device.

Abstract: A biometric security method and apparatus for a capacitive sensor system is provided herein, where the method may include capturing a set of raw capacitive frames for a body part via the capacitive sensor system, wherein each raw capacitive frame includes a distribution of a plurality of capacitance levels measured from the body part; creating a capacitive profile based on the set of raw capacitive frames; comparing a first value in the capacitive profile to a second value in a biometric template generated from an enrolled body part, wherein the first value and the second value are located at a similar location with respect to the capacitive profile; and, generating an authentication signal based on a difference between the first value and the second value.

Abstract: Systems, methods, devices, and apparatuses for associating a user emotion with electronic media are described. Contact between a user of a device and a biopotential electrode array that is integrated with the device is detected. Electrodermal data of the user is acquired via the biopotential electrode array. The user emotion is derived based at least in part on the acquired electrodermal data. The user emotion is then associated with the electronic media.

Abstract: A biometric security method and apparatus for a capacitive sensor system is provided herein, where the method may include capturing a set of raw capacitive frames for a body part via the capacitive sensor system, wherein each raw capacitive frame includes a distribution of a plurality of capacitance levels measured from the body part; creating a capacitive profile based on the set of raw capacitive frames; comparing a first value in the capacitive profile to a second value in a biometric template generated from an enrolled body part, wherein the first value and the second value are located at a similar location with respect to the capacitive profile; and, generating an authentication signal based on a difference between the first value and the second value.

Abstract: Various arrangements for delivery of relevant content to a mobile device of a user are presented. Physiological state data and image data related to the user of the mobile device may be received by a host computer system from a mobile device. The image data may be analyzed to identify a characteristic of the image. The physiological state data may also be analyzed. Content to deliver to the mobile device of the user may be selected at least partially based on the physiological state data of the user and the characteristic of the image. The content may be transmitted to the mobile device.

Abstract: Various arrangements for delivery of relevant content to a mobile device of a user are presented. Physiological state data and image data related to the user of the mobile device may be received by a host computer system from a mobile device. The image data may be analyzed to identify a characteristic of the image. The physiological state data may also be analyzed. Content to deliver to the mobile device of the user may be selected at least partially based on the physiological state data of the user and the characteristic of the image. The content may be transmitted to the mobile device.

Abstract: Methods, systems, and devices are described for collecting physiological data using a configurable biopotential array. The array is embedded on a surface area of a handheld device. The array includes a number of electrode tiles. The electrodes include biosensors to collect the physiological data of a user. The electrodes are polled to detect contact with the user's skin. Electrodes in contact with the skin are electrically coupled to form an active electrode area. The coupled electrodes collect the physiological data relating to the user via the biosensors. The electrodes are decoupled after contact with the user's skin is terminated. The physiological data is analyzed and an emotional state or health state of the user is determined from the analyzed data.

Abstract: Methods, systems, and devices are described for identifying noisy regions in a skin conductance signal. The signal is divided into a plurality of windows. Two or more features of the signal within a first window are computed. At least one of the two or more features being in a frequency domain. At least two of the features are combined to obtain at least a first metric. The first metric is compared to a corresponding threshold. The first window is identified as a noisy region of the skin conductance signal based on the comparison.

Abstract: Systems, methods, devices, and apparatuses for associating a user emotion with electronic media are described. Contact between a user of a device and a biopotential electrode array that is integrated with the device is detected. Electrodermal data of the user is acquired via the biopotential electrode array. The user emotion is derived based at least in part on the acquired electrodermal data. The user emotion is then associated with the electronic media.

Abstract: Handheld devices using an array of stainless steel electrodes located on an edge and/or back of the handheld devices for acquiring electrodermal activity are provided. The stainless steel electrode array may allow for the skin conductance level (SCL) or skin conductance response (SCR) on an individual to be measured and collected. The skin conductance signal may be related to sympathetic nervous system activity which is a major component of human emotion, known as arousal, or emotional intensity such as anxiety, stress, fear, or excited, etc.

Abstract: Various arrangements for delivery of relevant content to a mobile device of a user are presented. Physiological state data and image data related to the user of the mobile device may be received by a host computer system from a mobile device. The image data may be analyzed to identify a characteristic of the image. The physiological state data may also be analyzed. Content to deliver to the mobile device of the user may be selected at least partially based on the physiological state data of the user and the characteristic of the image. The content may be transmitted to the mobile device.

Abstract: Various arrangements for delivery of relevant content to a mobile device of a user are presented. Physiological state data and image data related to the user of the mobile device may be received by a host computer system from a mobile device. The image data may be analyzed to identify a characteristic of the image. The physiological state data may also be analyzed. Content to deliver to the mobile device of the user may be selected at least partially based on the physiological state data of the user and the characteristic of the image. The content may be transmitted to the mobile device.

Abstract: Methods, systems, and devices are described for collecting physiological data using a configurable biopotential array. The array is embedded on a surface area of a handheld device. The array includes a number of electrode tiles. The electrodes include biosensors to collect the physiological data of a user. The electrodes are polled to detect contact with the user's skin. Electrodes in contact with the skin are electrically coupled to form an active electrode area. The coupled electrodes collect the physiological data relating to the user via the biosensors. The electrodes are decoupled after contact with the user's skin is terminated. The physiological data is analyzed and an emotional state or health state of the user is determined from the analyzed data.

Abstract: Various arrangements for delivery of relevant content to a mobile device of a user are presented. Physiological state data and image data related to the user of the mobile device may be received by a host computer system from a mobile device. The image data may be analyzed to identify a characteristic of the image. The physiological state data may also be analyzed. Content to deliver to the mobile device of the user may be selected at least partially based on the physiological state data of the user and the characteristic of the image. The content may be transmitted to the mobile device.