Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

Abstract: A method for ranking messages of conversation graphs in a messaging platform includes classifying messages of a conversation graph into a plurality of sections based on content quality of the messages, where the plurality of sections include a first section and a second section. The first section has messages from the conversation graph determined as higher quality than messages of the second section. The method includes determining a plurality of predictive outcomes for each of a plurality of messages of the conversation graph using predictive models, ranking the messages of the first section based on the predictive outcomes for the messages of the first section, and transmitting at least a subset of the messages of the first section to be rendered on a client application according to the rank.

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

Abstract: Systems and methods for a medical device are provided. The handheld medical device includes a housing including a front and rear side. A diaphragm is located in the center of the rear side of the housing. Three or less rear electrodes, configured to collect electromagnetic signals from the chest region of a patient, are located in a semi-circular in shape that encircles the diaphragm on the rear side of the housing. Two front electrodes located on the front side of the housing collect signals from the left and right index fingers of the patient. A screen is located between the two front electrodes. The device may include a transmitter, in some cases a Bluetooth module, for coupling the medical device to a user device. The user device includes an application that receives the signals and performs analysis on them. The five electrode inputs are used to calculate seven ECG channels.

Abstract: Systems and methods for electronically monitoring chest sounds and/or sensing electrical cardiac signals such as ECG signals are provided. In one embodiment, a hybrid stethdiographer has a sensing assembly with a chestpiece and a user interface. Stethdiographer also includes a conduit, a power source compartment, a pair of binaurals and a corresponding pair of earpieces. The user interface includes a record button, a mode selector and a display screen. The chestpiece includes a diaphragm and a plurality of electrical cardiac sensors.

Abstract: According to an aspect, a method for ranking messages of conversation graphs in a messaging platform using machine-learning signals includes receiving a conversation view request to retrieve messages of a conversation graph stored on a messaging platform and determining a plurality of predictive outcomes for each of a plurality of messages of the conversation graph using predictive models. The determining step may include obtaining a plurality of signals relevant to the predictive models, the plurality of signals including data structure-related signals relating to the conversation graph and inputting the plurality of signals to the predictive models. The method includes ranking the plurality of messages based on the predictive outcomes and transmitting at least a subset of the plurality of messages to be rendered on a client application according to the rank.

Abstract: According to an aspect, a method for ranking messages of conversation graphs in a messaging platform using predictive outcomes includes receiving, over a network, a conversation view request to retrieve messages of a conversation graph stored on a messaging platform, and determining, by the messaging platform, a plurality of predictive outcomes for each of a plurality of messages of the conversation graph using predictive models. The plurality of predictive outcomes includes a reciprocal engagement probability. The method includes ranking, by the messaging platform, the plurality of messages based on the predictive outcomes, and transmitting, by the messaging platform, over the network, at least a subset of the plurality of messages to be rendered on a client application according to the rank.

Abstract: Systems and methods for electronically monitoring chest sounds and/or sensing electrical cardiac signals such as ECG signals are provided. In one embodiment, a hybrid stethdiographer has a sensing assembly with a chestpiece and a user interface. Stethdiographer also includes a conduit, a power source compartment, a pair of binaurals and a corresponding pair of earpieces. The user interface includes a record button, a mode selector and a display screen. The chestpiece includes a diaphragm and a plurality of electrical cardiac sensors.

Abstract: Described are systems to manage the rate of energy delivery to computing devices. The computing devices may connect to a shared data and power distribution system. Techniques are described for distributing energy to the computing devices directly or via an energy and data delivery device using limits determined for the computing devices. Once the energy transfer to the computing devices is complete, the limits on the rate of energy delivery may be rescinded.

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

Abstract: Described are systems and techniques for determining a position of one or more people within a physical environment, such as an aisle in a fulfillment center. In some instances, the aisle is instrumented with a plurality of radio frequency receivers (RFRXs), active infrared transmitter-receiver pairs (AIRTRPs), and passive infrared (PIR) proximity sensors. A radio frequency-emitting tag carried by the user is detected by the RFRX to determine an identity and approximate position along the length of the aisle. Data indicating obscuration of beams from one or more of the AIRTRPs provides further refinement as to position along the length of the aisle. Data from the PIR provides disambiguation as to which side of the aisle the user is on. Accordingly, the user may be identified and precisely positioned in the aisle.

Abstract: Systems and methods for electronically monitoring chest sounds and/or sensing electrical cardiac signals such as ECG signals are provided. In one embodiment, a hybrid stethdiographer has a sensing assembly with a chestpiece and a user interface. Stethdiographer also includes a conduit, a power source compartment, a pair of binaurals and a corresponding pair of earpieces. The user interface includes a record button, a mode selector and a display screen. The chestpiece includes a diaphragm and a plurality of electrical cardiac sensors.

Abstract: Provided is a process including: obtaining source and destination video data, the destination video data being a transformed version of the source video data; for a plurality of blocks in the given source frame, determining a respective source aggregate value that is based on a measure of central tendency of pixel values; for a plurality of blocks in the given destination frame, determining a respective destination aggregate value that is based on a measure of central tendency of pixel values; determining a plurality of differences between source and destination aggregate values; determining a frame aggregate value that is based on a measure of central tendency of the determined differences; and determining a measure of distortion of the destination video data based on the frame aggregate value.

Abstract: Described are systems to manage energy distribution and operation of computing devices (“devices”). The devices may connect to a shared data and power distribution system, such as receiving electrical energy in conjunction with data signals using Power over Ethernet (POE). During activation of the facility, such as after an energy outage, the demand for energy from many devices attempting to startup may exceed the energy capacity available. Described are devices and techniques for distributing energy to devices, coordinating operating mode of the devices, and so forth, to mitigate demand spikes for electrical energy that exceed the capacity of the energy distribution system.

Abstract: Described is an improved active-beacon/passive-listener time difference of arrival navigation system that relies on the multiple beacons to transmit uncoded acoustic pulses of a same frequency that propagate in the system at a same time for high-speed device tracking. Listening devices may receive multiple encoded radio frequency pulses (RF) prior to a single acoustic pulse, and then resolve which RF pulse corresponds to the acoustic pulse using triangulation techniques.

Abstract: Knowing a location of a sensor or other device may be useful in a variety of settings. Described herein are devices and techniques for using modular sections of known dimensions that are configured to couple to one another at predetermined coupling positions. The modular sections may intercommunicate to provide data identifying adjacent modular sections, the respective coupling positions, and where on each of the modular sections a device is attached. By analyzing this data, two- or three-dimensional arrangement data of the modular sections and devices may be generated. Using information about the physical dimensions of the modular sections, spatial coordinates indicative of where the devices are located in space may be determined. As devices or modular sections are added, removed, or replaced, the arrangement and the corresponding spatial coordinates may be updated to reflect the changes.

Abstract: Provided is a process including: obtaining video data; forming a transform matrix; dynamically forming a first modified quantization matrix; quantizing the first transform matrix with the modified quantization matrix; serializing the first quantized transform matrix to form a first sequence of values; compressing the first sequence of values with entropy coding to produce compressed video data; and forming a video bitstream that includes the compressed video data and a header, the header containing a parameter that instructs a decoder to decode the first block with a quantization matrix different from the modified quantization matrix.

Abstract: Provided is a process including: obtaining source and destination video data, the destination video data being a transformed version of the source video data; for a plurality of blocks in the given source frame, determining a respective source aggregate value that is based on a measure of central tendency of pixel values; for a plurality of blocks in the given destination frame, determining a respective destination aggregate value that is based on a measure of central tendency of pixel values; determining a plurality of differences between source and destination aggregate values; determining a frame aggregate value that is based on a measure of central tendency of the determined differences; and determining a measure of distortion of the destination video data based on the frame aggregate value.

Abstract: Provided is a process for compressing data that includes: obtaining data to be compressed; compressing the data with a first DCT compression algorithm to obtain a first DCT amplitude matrix; compressing the data with a second DCT compression algorithm to obtain a second DCT amplitude matrix, the second DCT compression algorithm compressing the data more than the first algorithm; modifying the second DCT amplitude matrix based on a value in the first DCT amplitude matrix.