Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

Abstract: According to one embodiment, an apparatus includes an interface to receive sensor data from a plurality of sensors of an autonomous vehicle. The apparatus also includes processing circuitry to apply a sensor abstraction process to the sensor data to produce abstracted scene data, and to use the abstracted scene data in a perception phase of a control process for the autonomous vehicle. The sensor abstraction process may include one or more of: applying a Sensor data response normalization process to the sensor data, applying a warp process to the sensor data, and applying a filtering process to the sensor data.

Abstract: An apparatus comprising at least one interface to receive sensor data from a plurality of sensors of a vehicle; and one or more processors to autonomously control driving of the vehicle according to a path plan based on the sensor data; determine that autonomous control of the vehicle should cease; send a handoff request to a remote computing system for the remote computing system to control driving of the vehicle remotely; receive driving instruction data from the remote computing system; and control driving of the vehicle based on instructions included in the driving instruction data.

Abstract: Sensor data is received from a plurality of sensors, where the plurality of sensors includes a first set of sensors and a second set of sensors, and at least a portion of the plurality of sensors are coupled to a vehicle. Control of the vehicle is automated based on at least a portion of the sensor data generated by the first set of sensors. Passenger attributes of one or more passengers within the autonomous vehicles are determined from sensor data generated by the second set of sensors. Attributes of the vehicle are modified based on the passenger attributes and the sensor data generated by the first set of sensors.

Abstract: Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. Example instructions cause a processor to obtain dataset features indicative of a plurality of characteristics of an input dataset, rank, using multiple ranking algorithms, the dataset features, identify feature subsets for respective ones of the ranked dataset features, predict performance metrics based on the feature subsets, and select a final subset based on the predicted performance metrics.

Abstract: Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. The user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input.

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

Abstract: Methods, apparatus, systems and articles of manufacture to analyze time series data are disclosed. An example method includes sub sampling time series data collected by a sensor to generate one or more candidate samples of interest within the time series data. Feature vectors are generated for respective ones of the one or more candidate samples of interest. Classification of the feature vectors is attempted based on a model. In response to a classification of one of the feature vectors, the classification is stored in connection with the corresponding candidate sample.

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

Abstract: Technologies for gesture recognition using downsampling are disclosed. A gesture recognition device may capture gesture data from a gesture measurement device, and downsample the captured data to a predefined number of data points. The gesture recognition device may then perform gesture recognition on the downsampled gesture data to recognize a gesture, and then perform an action based on the recognized gesture. The number of data points to which to downsample may be determined by downsampling to several different numbers of data points and comparing the performance of a gesture recognition algorithm performed on the downsampled gesture data for each different number of data points.

Abstract: Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. The user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input.

Abstract: Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. The user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input.

Abstract: Methods, apparatus, systems and articles of manufacture to analyze time series data are disclosed. An example method includes sub sampling time series data collected by a sensor to generate one or more candidate samples of interest within the time series data. Feature vectors are generated for respective ones of the one or more candidate samples of interest. Classification of the feature vectors is attempted based on a model. In response to a classification of one of the feature vectors, the classification is stored in connection with the corresponding candidate sample.

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

Abstract: Technologies for gesture recognition using downsampling are disclosed. A gesture recognition device may capture gesture data from a gesture measurement device, and downsample the captured data to a predefined number of data points. The gesture recognition device may then perform gesture recognition on the downsampled gesture data to recognize a gesture, and then perform an action based on the recognized gesture. The number of data points to which to downsample may be determined by downsampling to several different numbers of data points and comparing the performance of a gesture recognition algorithm performed on the downsampled gesture data for each different number of data points.

Abstract: Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. The user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input.

Abstract: The present disclosure relates to systems and methods for collecting patient data via a monitoring system, with reduced power consumption. In one embodiment, the monitoring system is configured to emit pulses of light, and detect the light after passing through patient tissue. The light data is emitted sporadically, and a waveform is reconstructed from the sporadically sampled light data. Physiological parameters from the patient may be calculated from the reconstructed waveform. The sporadic sampling may reduce the power consumption by the monitoring system.

Abstract: The present disclosure relates to systems and methods for collecting patient data via a monitoring system, with reduced power consumption. In one embodiment, the monitoring system is configured to emit pulses of light, and detect the light after passing through patient tissue. The light data is emitted sporadically, and a waveform is reconstructed from the sporadically sampled light data. Physiological parameters from the patient may be calculated from the reconstructed waveform. The sporadic sampling may reduce the power consumption by the monitoring system.

Abstract: Various methods and systems for the use of multi-element photoacoustic sensors within medical devices configured for photoacoustic spectroscopy techniques are provided. The photoacoustic sensor includes two or more acoustic detectors spatially configured to increase the probability of a clinician properly placing at least one of the acoustic detectors on the measurement site over the blood vessels of interest. Further, the photoacoustic sensor includes a light delivery system configured to provide multiple light sources to the measurement site, such that each acoustic detector has an adequate light supply within close proximity. The present techniques additionally provide methods for processing each acoustic signal measured at the two or more acoustic detectors to calculate one or more physiological parameters of interest, such as cardiac output.

Abstract: Various methods and systems for the use of capacitance sensors within medical devices configured for patient monitoring are provided. The capacitance sensors are configured to measure a change in capacitance resulting from a material (e.g., human tissue, water, gel, cloth, etc.) placed near (e.g., close proximity to) the medical device and/or resulting from a material making physical contact with the medical device. In certain embodiments, the capacitance sensor may be utilized to detect whether one or more portions of the medical sensor are securely applied to the patient's tissue (e.g., sensor “on”) and/or may be utilized to detect whether one or more portions of the medical sensor fail to maintain secure contact with the patient's tissue (e.g., sensor “off”). Further, in certain embodiments, the capacitance sensor may be utilized to distinguish between one or more types of materials (e.g., human tissue, water-based materials, etc.).