Abstract: A method for time series forecasting includes receiving a time series forecasting query from a user requesting the data processing hardware to perform a plurality of time series forecasts. Each time series forecast is a forecast of future data based on respective current data Simultaneously, for each time series forecast of the plurality of time series forecasts requested by the time series forecasting query, the method includes training a plurality of models for the respective time series forecast. The method also includes determining which model of the plurality of models best fits the respective time series forecast and forecasting the future data based on the determined best fitting model and the respective current data. The method also includes returning, to the user, the forecasted future data for each of the plurality of time series forecasts request by the timer series forecasting query.

Abstract: A bag (e.g., backpack) having a removable panel. The removable panel may be releasably and selectively coupled to the bag using various mechanisms, such as hook-and-loop fasteners, zippers, magnets, clasps, clamps, hooks, buckles, snaps, and buttons. The removable panel acts as the front face of the bag when it is coupled to the bag.

Abstract: An elongate strap support system for anatomical support, pain reduction, or therapeutic treatment includes a package containing a first elongate strap support and at least one additional elongate strap support. In one example, the first elongate strap support includes a woven fabric support layer including synthetic fibers. The woven fabric is shaped so as to form an elongated strap with rounded portions. The woven fabric is substantially resistant to stretching in one direction under such test conditions as those specified in ASTM D3759. The first elongate strap support additionally includes an adhesive layer on the support layer for adhesive attachment of the woven fabric support layer to an outer skin surface of a body and a removable cover layer on the adhesive layer.

Abstract: A neural transformer model with attention is trained to predict candidates to complete a line of source code with a zero-inference capability. The model is trained on an unsupervised training dataset that includes features from source code written in multiple programming languages. The features include a file-level context and a local context, where the file-level context includes a global context, a class context, a function context, and/or a method context for each class, function and/or method of the source code programs used in the training dataset. The local context includes method bodies, function bodies, and/or stand-alone code of main method routines. From these features, the model is able to learn to predict an ordered sequence of code elements that complete a line of source code in a programming language seen and not seen during training.

Abstract: An intelligent property management system comprises an intelligent property management platform. The intelligent property management platform communicates with other system components via respective communication portals. The respective portals comprise a vendor portal, a tenant portal, an investor portal, a security device portal, and a communications service portal. These features enable the intelligent property management system, while utilizing a communication network, to intelligently improve, e.g., maintenance, security, communication, vendors services, and investments relating to managed properties.

Abstract: Methods and systems are provided for a heat shield. In one example, the heat shield is formed of a composite material, the heat shield configured to shield a component from radiated heat. The composite material is a mixture of aluminum particles dispersed in an elastomer matrix.

Abstract: Various embodiments wirelessly detect micro gestures using multiple antenna of a gesture sensor device. At times, the gesture sensor device transmits multiple outgoing radio frequency (RF) signals, each outgoing RF signal transmitted via a respective antenna of the gesture sensor device. The outgoing RF signals are configured to help capture information that can be used to identify micro-gestures performed by a hand. The gesture sensor device captures incoming RF signals generated by the outgoing RF signals reflecting off of the hand, and then analyzes the incoming RF signals to identify the micro-gesture.

Abstract: A seed camera disposed a first location is manually calibrated. A second camera, disposed at a second location, detects a physical marker based on predefined characteristics of the physical marker. The physical marker is located within an overlapping field of view between the seed camera and the second camera. The second camera is calibrated based on a combination of the physical location of the physical marker, the first location of the seed camera, the second location of the second camera, a first image of the physical marker generated with the seed camera, and a second image of the physical marker generated with the second camera.

Abstract: Methods and systems are provided for controlling movement of a mobile medical device drive platform. In one example, a mobile platform includes a chassis configured to house one or more medical devices, an omnidirectional wheel system including an omnidirectional wheel coupled to the chassis, a battery housed in the chassis, the battery configured to supply power to drive the omnidirectional wheel system and/or supply power to operate the one or more medical devices, and a battery charging system housed in the chassis, where the battery charging system is configured to facilitate wired and/or wireless charging of the battery.

Abstract: Embodiments provide methods of disassembling an apparel product. The methods include exposing an adhesive of the apparel product to heat or electromagnetic energy. The adhesive is disposed at least partially disposed between a major component and a minor component of the apparel product. The adhesive includes a shape memory material. The major component forms a base portion of the apparel product and is configured to be supported and worn at least partially over a portion of a wearer. The minor component forms a secondary portion configured to be coupled to the major component with the adhesive. The methods include separating the major component from the minor component adjoined by the adhesive.

Abstract: Systems and methods for monitoring, detecting, and/or intervening with respect to cavitation and pulsation events during hydraulic fracturing operations may include a supervisory controller. The supervisory controller may be configured to receive pump signals indicative of one or more of pump discharge pressure, pump suction pressure, pump speed, or pump vibration associated with operation of the hydraulic fracturing pump. The supervisory controller also may be configured to receive blender signals indicative of one or more of blender flow rate or blender discharge pressure. Based on one or more of these signals, the supervisory controller may be configured to detect a cavitation event and/or a pulsation event.

Abstract: One example includes a differential amplifier, a voltage weighting element, coupled to a voltage source which provides an input voltage, to provide a reference voltage with a constant power limit when the input voltage varies, an error amplifier configured to receive and compare the reference voltage provided from the voltage weighting element and a feedback sensed voltage provided from the differential amplifier to identify whether the sensed voltage exceeds the reference voltage, and a pulse width modulation (PWM) controller, coupled to a power transformer and the error amplifier, that reduces a transformer input current provided to the power transformer based on the comparison of the reference voltage from the voltage weighting element and the feedback sensed voltage from the differential amplifier.

Abstract: Systems and methods for Geiger-mode laser vibrometry are described. An example method for laser vibrometry includes receiving a first time-series of single photon arrivals corresponding to a laser beam reflected from or transmitted through a target, the single photon arrivals including information corresponding to vibrations of the target, each single photon arrival separated in time from another single photon arrival, determining, based on two or more of the single photon arrivals, a discrete time sequence having a binary value, and generating a second time-series by assigning a non-binary value to each of the discrete time points, wherein each of the assigned non-binary values is determined based on a number of discrete time points lacking a photon arrival prior to receiving a photon.

Abstract: Disclosed and described herein are systems and methods that bring together edge technologies into a single, streamlined process that automates the tracking and usage of assets (containers, equipment, mobile storage, etc.). These systems and methods include the use of smart beacons, low power cellular, sensors (strain gauges, level, contact, ohm/voltage, etc.), voice, video, microcontroller advancements, and the like. Conventional systems that have electronic service order and/or tickets are still limited in their functionality because of data, communication and processing hurdles. Disclosed are modern electronic data capture systems (IoT sensors) along with algorithms to assist on the tracking of assets and workers, more quickly capture authorized transactions for billing and remove the manual processes.

Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.

Abstract: Methods and systems for processing communication systems are disclosed. A request for a communication session can be analyzed to determine a device or pool of devices to process the communication session. Data associated with the communication session, including session description data, can be analyzed using rules that associate types of data with corresponding processing devices. The rules can be based on levels of complexity associated with the data, and different pools of processing devices can be associated with different levels of complexity. Thus, communication sessions assigned a level of complexity can be matched with pools of devices associated with the same level of complexity.

Abstract: An apparatus to automatically ignite herbs in a water pipe. The apparatus includes a cap dimensioned to engage a bowl piece of a water pipe and provide a restricted air path to the bowl. A pressure sensor within the cap senses a pressure change response to air being drawn through the air path. Responsive to a signal from the sensor a controller drives an igniter to ignite the herb within the bowl.

Abstract: Presented are Ergodic Spectrum Management (ESM) systems and methods that take advantage of the presence of statistical consistencies (“ergodicity”) and correlations, such as a wireless network's average dimensional consistencies of probability distributions (in time, space, and frequency) of channel gains, to adaptively learn qualitative and quantitative network/user behavior; estimate or predict network performance; and guide locally implemented radio resource management (RRM) decisions of wireless multi-user transmissions in a manner such as to reduce interference and improve latency; connection stability; efficiency; and overall wireless performance. ESM also enhances end-users' Quality of Experience (QoE) by allowing movement across bands and regions as users/devices roam. A remote-cloud-based resource management implementation of ESM's Learn-ed Resource Managers (LRMs) removes the need for heavy edge-computing close to radio cells.

Abstract: A tool holding section opposite the first section with a bore formed in the tool holding section adapted for receiving the shank of the tool. A plurality of stress rods positioned around the bore and comprising a thermal rate of expansion less than a thermal rate of expansion of the tool holding section. The plurality of stress rods form corresponding bulges on the surface of the bore to decrease the inner diameter of the bore to mechanically lock the shank of the tool in the bore.

Abstract: An annular scraper ring for a packing arrangement is disclosed. The annular scraper ring that can form a seal with a plunger included in a fluid end of a reciprocating pump and includes a planar upstream face and an inner surface with a tapered section. The tapered section tapers away from the plunger along a downstream direction so that the scraper ring is widest at the planar upstream face.