Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.

Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.

Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.

Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.

Abstract: Examples of systems, apparatuses, and methods for determining whether CPR is being conducted based on an impedance signal are described. An example system may include a defibrillator including a cardiopulmonary resuscitation (CPR) analyzer configured to detect an impedance signal between electrodes applied to a chest of a patient. The CPR analyzer may be further configured to transform the impedance signal to a frequency domain representation to provide transformed frequency data, and to detect peaks within the transformed frequency data. The CPR analyzer may be further configured to classify the impedance signal as one of CPR or no CPR based on the detected peaks. The CPR analyzer may be further configured to determine a chest compression rate based on the detected peaks.

Abstract: Examples of systems, apparatuses, and methods for classification of electrocardiogram signals during cardiopulmonary resuscitation are described. An example system may include a defibrillator comprising an electrocardiogram analyzer. The electrocardiogram analyzer may be configured to apply a prediction modeling technique to an electrocardiogram signal to generate a predicted signal. The electrocardiogram signal may be captured from a patient undergoing cardiopulmonary resuscitation. The electrocardiogram analyzer may be further configured to subtract the predicted signal from the electrocardiogram signal to generate an error signal and to classify a rhythm of the electrocardiogram signal as one of a shockable rhythm or non-shockable based on the error signal. Decision parameters derived from the signals may be used in conjunction with a machine learning technique to classify the electrocardiogram signal.

Abstract: Methods and systems for improving an ultrasound image quality are provided. On demand transmission of unsustainably high power ultrasonic pulses are temporary or spatially interleaved with low power, zero power, or standard ultrasonic pulses. In response to a user initiated trigger, a physiological trigger, a system trigger, or external equipment trigger, the unsustainably high power pulses provide better signal-to-noise ratio and/or allow increased imaging frequencies for difficult to image patients in any of various modes, such as B-modes, harmonic B-mode responsive to tissue or contrast agent, or color flow modes. Unsustainably high power ultrasonic pulses cause an increase in the tissue temperature within the body and at the interface between the transducer and the skin. Standard imagining or standard high power pulses may increase either temperature by around 6° C., such as from a body normal 37° C. to an average of 43° C. over time.

Abstract: Methods and systems for improving an ultrasound image quality are provided. On demand transmission of unsustainably high power ultrasonic pulses are temporary or spatially interleaved with low power, zero power, or standard ultrasonic pulses. In response to a user initiated trigger, a physiological trigger, a system trigger, or external equipment trigger, the unsustainably high power pulses provide better signal-to-noise ratio and/or allow increased imaging frequencies for difficult to image patients in any of various modes, such as B-modes, harmonic B-mode responsive to tissue or contrast agent, or color flow modes. Unsustainably high power ultrasonic pulses cause an increase in the tissue temperature within the body and at the interface between the transducer and the skin. Standard imagining or standard high power pulses may increase either temperature by around 6° C., such as from a body normal 37° C. to an average of 43° C. over time.