Abstract: Systems, methods and computer-readable memory devices are provided for greater efficiency in the configuration of a database cluster for performing a query workload. A database cluster configuration system is provided that includes a database cluster comprising one or more compute resources configured to perform database queries. A query workload comprising a plurality of queries is received. An initial workload-level configuration is applied. For each query of the query workload, a query-level configuration is generated using a query configuration model corresponding to each query in a contextual Bayesian optimization with centroid learning while also leveraging the query plan for each executing query for query characterization and including application of virtual operators. Query events are collected and used to update the corresponding query configuration model. The workload-level configuration is updated based on the query events and cached for use during a subsequent execution of the workload.

Abstract: Various methods and systems are provided for an automated clinical exam workflow. In one example, method comprises performing a signal quality check of an electronic stethoscope at a first recording location on a subject, recording physiological data for an exam at the first recording location via the electronic stethoscope in response to the signal quality check satisfying a quality threshold, and outputting a signal quality alert in response to the signal quality check not satisfying the quality threshold. In this way, clinically relevant data may be obtained with reduced user effort and fewer manual inputs.

Abstract: The description relates to executing an inference query relative to a database management system, such as a relational database management system. In one example a trained machine learning model can be stored within the database management system. An inference query can be received that applies the trained machine learning model on data local to the database management system. Analysis can be performed on the inference query and the trained machine learning model to generate a unified intermediate representation of the inference query and the trained model. Cross optimization can be performed on the unified intermediate representation. Based upon the cross-optimization, a first portion of the unified intermediate representation to be executed by a database engine of the database management system can be determined, and, a second portion of the unified intermediate representation to be executed by a machine learning runtime can be determined.

Abstract: Approaches described herein can capture an audio signal using at least one microphone while a user of an electronic device is determined to be asleep. At least one audio frame can be determined from the audio signal. The at least one audio frame represents a spectrum of frequencies detected by the at least one microphone over some period of time. One or more sounds associated with the at least one audio frame can be determined. Sleep-related information can be generated. The information identifies the one or more sounds as potential sources of sleep disruption.

Abstract: Approaches described herein can determine one or more breathing phase patterns over a period of time using audio data captured by at least one microphone. The audio data can include one or more snores. A breathing phase pattern included within the period of time can be determined based at least in part on sensor data captured by one or more sensors in the electronic device. A determination can be made that a first breathing phase pattern represented by the audio data and a second breathing phase pattern represented by the sensor data are correlated. A determination can be made that the first breathing phase pattern represented by the audio data and the second breathing phase pattern represented by the sensor data both correspond to a user wearing the electronic device.

Abstract: A method and apparatus for providing biofeedback during a meditation exercise are disclosed. In one aspect, the wearable device includes one or more biometric sensors and a user interface. The method may involve prompting the user, via the user interface, to perform a meditation exercise, the meditation exercise being associated with a target physiological metric related to the physiology of the user. The method may involve measuring, based on output of at least one of the one or more biometric sensors, a physiological metric of the user during the meditation exercise. The method may involve determining a performance score indicating the user's performance during the meditation exercise based on comparing the measured physiological metric with the target physiological metric. The method may involve providing, via the user interface, based on the performance score, feedback information indicative of the user's performance during the meditation exercise.

Abstract: In an embodiment, a data processing method comprises obtaining one or more photoplethysmography (PPG) signals from one or more PPG sensors of a monitoring apparatus, the PPG signals being generated based upon optically detecting pulsed variations in blood flow; obtaining a motion sensor signal from a motion sensor in the monitoring apparatus; identifying, based upon the motion sensor signal, one or more periods of motion (e.g., low motion) of the monitoring apparatus; and selectively obtaining and storing segments of the PPG signals based on a temporal relationship between the segments of the PPG signals and the identified periods of motion.

Abstract: Approaches described herein can determine one or more breathing phase patterns over a period of time using audio data captured by at least one microphone. The audio data can include one or more snores. A breathing phase pattern included within the period of time can be determined based at least in part on sensor data captured by one or more sensors in the electronic device. A determination can be made that a first breathing phase pattern represented by the audio data and a second breathing phase pattern represented by the sensor data are correlated. A determination can be made that the first breathing phase pattern represented by the audio data and the second breathing phase pattern represented by the sensor data both correspond to a user wearing the electronic device.

Abstract: The present application relates to a network, apparatus, and method for allocating clusters of computing nodes for programming jobs. A network includes a plurality of datacenters including computing resources configurable to instantiate nodes for executing programming jobs on a cluster. The computing resources at one of the datacenters are configured to: provision a live pool including a number of clusters, each cluster in the live pool including a plurality of nodes imaged with a configuration for executing the programming jobs in parallel on the cluster; receive a request from a user to execute a programming job; allocate a cluster from the live pool to the user for the programming job when the cluster is available; evict the cluster from the live pool; and provision a new cluster within the live pool to meet the number of clusters. The number of clusters may be optimized based on linear programming and machine-learning.

Abstract: In an embodiment, a data processing method comprises obtaining one or more photoplethysmography (PPG) signals from one or more PPG sensors of a monitoring apparatus, the PPG signals being generated based upon optically detecting pulsed variations in blood flow; obtaining a motion sensor signal from a motion sensor in the monitoring apparatus; identifying, based upon the motion sensor signal, one or more periods of motion (e.g., low motion) of the monitoring apparatus; and selectively obtaining and storing segments of the PPG signals based on a temporal relationship between the segments of the PPG signals and the identified periods of motion.

Abstract: The cloud-based query workload optimization system disclosed herein the cloud-based query workloads optimization system receives query logs from various query engines to a cloud data service, extracts various query entities from the query logs, parses query entities to generate a set of common workload features, generates intermediate representations of the query workloads, wherein the intermediate representations are agnostic to the language of the plurality of the queries, identifies a plurality of workload patterns based on the intermediate representations of the query workloads, categorizes the workloads in one or more workload type categories based on the workload patterns and the workload features, and selects an optimization scheme based on the category of workload pattern.

Abstract: Learned workload synthesis is disclosed. In an aspect of the present disclosure, a time series dataset corresponding to a target workload is received. A set of performance characteristics is determined from the time series dataset. A call is provided to a prediction model to determine a candidate query sequence based on the determined set of performance characteristics. A synthetic workload is generated based on the determined candidate query sequence. A synthetic workload is generated based on the determined candidate query sequence. A first similarity between a first performance profile of the synthetic workload and a second performance profile of the target workload meets a workload performance threshold condition. A performance insight is determined based on the synthetic workload. In a further aspect, the prediction model is trained to predict performance profiles based on workload profiles generated by executing benchmark queries using hardware and/or software configurations.

Abstract: The present description relates generally to methods and systems for an electronic stethoscope device with an active headset, including a speaker to project audio data generated by a chestpiece, the headset defining a closed back volume for the speaker. In this way, the headset provides a back volume of the speakers in order to tune the frequency response of the speakers to a target frequency mimicking the frequency produced by a conventional acoustic stethoscope.

Abstract: The present description relates generally to methods and systems for power management of a digital (e.g., electronic) stethoscope. In one example, an electronic stethoscope includes a chestpiece configured to be positioned on a patient, the chestpiece including a sensor, wherein the chestpiece further includes a computer processing unit (CPU) operatively coupled to a memory storing instructions that, when executed by the CPU, cause the CPU to automatically activate the electronic stethoscope in response to detecting a touch input via the sensor.

Abstract: An automated tuning service is used to automatically tune, or modify, the operational parameters of a large-scale cloud infrastructure. The tuning service performs automated and fully data/model-driven configuration based from learning various real-time performance of the cloud infrastructure. Such performance is identified through monitoring various telemetric data of the cloud infrastructure. The tuning service leverages a mix of domain knowledge and principled data-science to capture the essence of our cluster dynamic behavior in a collection of descriptive machine learning (ML) models. The ML models power automated optimization procedures for parameter tuning, and inform administrators in most tactical and strategical engineering/capacity decisions (such as hardware and datacenter design, software investments, etc.).

Abstract: Approaches described herein can capture an audio signal using at least one microphone while a user of an electronic device is determined to be asleep. At least one audio frame can be determined from the audio signal. The at least one audio frame represents a spectrum of frequencies detected by the at least one microphone over some period of time. One or more sounds associated with the at least one audio frame can be determined. Sleep-related information can be generated. The information identifies the one or more sounds as potential sources of sleep disruption.

Abstract: An automated tuning service is used to automatically tune, or modify, the operational parameters of a large-scale cloud infrastructure. The tuning service performs automated and fully data/model-driven configuration based from learning various real-time performance of the cloud infrastructure. Such performance is identified through monitoring various telemetric data of the cloud infrastructure. The tuning service leverages a mix of domain knowledge and principled data-science to capture the essence of our cluster dynamic behavior in a collection of descriptive machine learning (ML) models. The ML models power automated optimization procedures for parameter tuning, and inform administrators in most tactical and strategical engineering/capacity decisions (such as hardware and datacenter design, software investments, etc.).

Abstract: Embodiments described herein enable tracking machine learning (“ML”) model data provenance. In particular, a computing device is configured to accept ML model code that, when executed, instantiates and trains an ML model, to parse the ML model code into a workflow intermediate representation (WIR), to semantically annotate the WIR to provide an annotated WIR, and to identify, based on the annotated WIR and ML API corresponding to the ML model code, data from at least one data source that is relied upon by the ML model code when training the ML model. A WIR may be generated from an abstract syntax tree (AST) based on the ML model code, generating provenance relationships (PRs) based at least in part on relationships between nodes of the AST, wherein a PR comprises one or more input variables, an operation, a caller, and one or more output variables.

Abstract: Linguistic schema mapping via semi-supervised learning is used to map a customer schema to a particular industry-specific schema (ISS). The customer schema is received and a corresponding ISS is identified. An attribute in the customer schema is selected for labeling. Candidate pairs are generated that include the first attribute and one or more second attributes which may describe the first attribute. A featurizer determines similarities between the first attribute and second attribute in each generated pair, one or more suggested labels are generated by a machine learning (ML) model, and one of the suggested labels is applied to the first attribute.

Abstract: Approaches described herein can capture an audio signal using at least one microphone while a user of an electronic device is determined to be asleep. At least one audio frame can be determined from the audio signal. The at least one audio frame represents a spectrum of frequencies detected by the at least one microphone over some period of time. One or more sounds associated with the at least one audio frame can be determined. Sleep-related information can be generated. The information identifies the one or more sounds as potential sources of sleep disruption.