Abstract: A method for identifying and manipulating objects may include obtaining, from an image sensor, image sensor data; identifying, using the image sensor data, a location of an object; controlling a robotic element, which includes the image sensor, to move towards the location of the object; determining a slippage based on contact between the image sensor and the object; and controlling a movement of the robotic element based on the determined slippage.

Abstract: A linear accelerator in data communication with a computing device and a programmable logic controller and including a magnetron, an electron gun that is configured to direct an accelerated beam of electrons at a target thereby generating a beam of X-rays, a primary collimator positioned beyond the target in a direction of the beam of X-rays, a secondary collimator coupled to an end of the primary collimator at which the beam of X-rays exit the primary collimator, an attenuating element and a calorimeter positioned within the primary collimator, and a reference detector positioned within the secondary collimator and configured to measure an X-ray radiation dose output of the linear accelerator on a pulse-by-pulse basis.

Abstract: A package receiving container, including a main body to store at least one item therein, a lid assembly movably disposed on at least a portion of the main body to prevent access within the main body while closed and facilitate access within the main body while opened, a lock disposed on at least a portion of the lid assembly to prevent the lid assembly from opening in response to being locked; and a control unit disposed within at least a portion of the main body to monitor for receipt of the at least one item within the main body and sending a signal to an external device that the at least one item has been delivered in response to the main body receiving the at least one item.

Abstract: A method of sensing an interaction with an object using a semitransparent tactile surface (STS) sensor having an image sensor and a semitransparent membrane includes capturing, by the image sensor, a stream of images; separating the stream of images into a visual stream including light traveling through the semitransparent membrane and a tactile stream including light reflecting off of the semitransparent membrane; and processing the visual stream and tactile stream through a multimodal deep neural network.

Abstract: Physical and/or financial instruments may optimally hedge the cash flow of one or more renewable energy generators based on a desired risk and return profile of renewable infrastructure investors. Baseline revenues may be determined based on forward-looking electricity market price scenarios corresponding to qualified market products intended for sale from the renewable energy generators. Risk and return metrics of cash flows of the renewable energy generators may be determined. At least one physical hedge and/or financial hedge may be added. The size and operation of the renewable energy generators along with any physical hedges, or financial hedges, or both physical and financial hedges, may be optimized across multiple market price scenarios of qualified market products to optimize investor-tailored risk and return utility functions.

Abstract: A server may receive a first traffic data and a second traffic data from a first base station and a second base station; obtain a first augmented traffic data for the first base station, based on the first traffic data and a subset data of the second traffic data; obtain a second augmented traffic data for the second base station, based on the second traffic data and a subset data of the first traffic data; obtain a first artificial intelligence (AI) model via imitation learning based on the first augmented traffic data; obtain a second AI model imitation learning based on the second augmented traffic data; obtain a generalized AI model via knowledge distillation from the first AI model and the second AI model; and predict a future traffic load of each of the first base station and the second base station based on the generalized AI model.

Abstract: Parameters for load balancing in a cellular communication system are determined. The cellular communication system performance is measured by key performance indicators (KPIs). A policy (artificial intelligence model) is obtained to optimize the cellular communication system performance with respect to the KPIs. The policy for determining parameters used for load balancing the cellular communication system is obtained using meta multi-objective reinforcement learning (meta MORL). A distilled policy may be obtained to initialize the meta MORL determination. Various loss functions may be used to obtain the distilled policy.

Abstract: A method of forecasting a future load may include: obtaining source data sets and a target data set that have been collected from a plurality of source base stations and a target base station, respectively; among a plurality of source machine learning models, selecting at least one machine learn source model that has a traffic load prediction performance higher than that of a target machine learning model through a negative transfer analysis; obtaining model weights to be applied to the target machine learning model and the selected at least one source machine learning model via an attention neural network that is jointly trained with the target machine learning model and the selected source machine learning models; obtaining a load forecasting model for the target base station by combining the target machine learning model and the selected at least one source machine learning model according to the model weights; and predicting a future communication traffic load of the target base station based on the load

Abstract: Systems, methods, and devices may enable management of a renewable power asset. A control device may generate a Day-Ahead (DA) pricing model, a Real-Time (RT) pricing model and a renewable generation model for the renewable power asset. Optimal DA commitments may be determined, and an optimal RT schedule estimated. A DA power delivery strategy and an RT power delivery strategy may be determined. The determined DA and RT power delivery strategies may be evaluated based on obtained real power prices. The DA and RT power delivery strategies may be redetermined, and the renewable power asset may be controlled to deliver power the DA and RT power delivery strategies. The value of the renewable power asset may be maximized while bounding financial risks and returns associated with scheduling the renewable power asset as tailored to risk preferences of the renewable power asset owner or operator.

Abstract: A system and method measures the thickness of wear liners coupled to wear substrates of industrial equipment. The system includes at least one ultrasonic transducer wear sensor device coupled intermediate the wear liner and wear substrate and a data acquisition device configured to receive thickness data from the wear sensor device. The ultrasonic transducer wear sensor device is battery powered in one embodiment and passivated in an additional embodiment and powered through an interrogation signal.

Abstract: A external accessory can allow a mobile device to perform microscopy imaging with Type-C ultraviolet (UVC) light excitation. The external accessory includes a compound lens placed in front of a camera lens of the mobile device. A light transparent optical window configured to be placed in front of the compound lens and positioned such that a front surface of the optical window overlaps the front focal plane of the compound lens. One or more light emitting diode (LED) that emits UVC light positioned at one or more side-edges of the optical window. The one or more LED emits UVC light through the optical window so that the UVC light undergoes total internal reflection. An externally triggered LED driver configured to power and control the LED(s).

Abstract: Described herein are systems and methods for improving light-sheet microscopy with cost-effective and simplified components. Such cost-effective and simplified components can be implemented in a light focusing system, a light generation system, and/or in imaging system. The light focusing system can be improved by attaching a voice coil motor to a focusing lens to increase the imagable field of view. The light generation system can be improved with a multimode laser diode to increase the uniformity of the beam profile and to increase the usable optical power. The imaging system can be improved by using a fluid chamber with positive cylindrical optical window for minimizing spherical aberrations.

Abstract: Described herein are methods for imaging a fluorescent bioassay (including a substrate, such as dispersed cellular sample, exposed to one or more exogenous fluorophore and/or fluorescent probe that accumulate in a structure of interest). The bioassay can be excited with Type-C ultraviolet (UVC) light produced by one or more light emitting diode (LED). The UVC can have a center wavelength that causes emission by the fluorescent bioassay. A digital optical device can collect a signal emitted from the fluorescent bioassay in response to the excitation. The methods relate in particular to Microscopy with Ultraviolet Surface Excitation (MUSE) imaging.

Abstract: Systems, methods, and devices may enable management of a renewable power asset. A control device may generate a Day-Ahead (DA) pricing model, a Real-Time (RT) pricing model and a renewable generation model for the renewable power asset. Optimal DA commitments may be determined, and an optimal RT schedule estimated. A DA power delivery strategy and an RT power delivery strategy may be determined. The determined DA and RT power delivery strategies may be evaluated based on obtained real power prices. The DA and RT power delivery strategies may be redetermined, and the renewable power asset may be controlled to deliver power the DA and RT power delivery strategies. The value of the renewable power asset may be maximized while bounding financial risks and returns associated with scheduling the renewable power asset as tailored to risk preferences of the renewable power asset owner or operator.

Abstract: A method of load forecasting using multi-task deep learning includes obtaining references data corresponding to commodity consuming objects, clustering the commodity consuming objects into clusters based on the obtained reference commodity consumption data; obtaining cluster models based on: reference commodity consumption data, reference environmental data, and reference calendar data; inputting, into the cluster models, present data corresponding to the commodity consuming objects; and predicting, based on an output of the cluster models, a future commodity consumption for the commodity consuming objects. The cluster models include multi-task learning processes having joint loss functions.

Abstract: An apparatus distributing communication load over a plurality of communication cells may select action centers from random cell reselection values, based on a standard deviation of an internet protocol (IP) throughout over the plurality of communication cells; input a first vector indicating a communication state of a communication system and a second vector indicating the standard deviation of the IP throughout of the plurality of communication cells, to a neural network to output a sum of the action centers and offsets as cell reselection parameters; and transmit the cell reselection parameters to the communication system to enable a base station of the communication system to perform a cell reselection based on the cell reselection parameters.

Abstract: Physical and/or financial instruments may optimally hedge the cash flow of one or more renewable energy generators based on a desired risk and return profile of renewable infrastructure investors. Baseline revenues may be determined based on forward-looking electricity market price scenarios corresponding to qualified market products intended for sale from the renewable energy generators. Risk and return metrics of cash flows of the renewable energy generators may be determined. At least one physical hedge and/or financial hedge may be added. The size and operation of the renewable energy generators along with any physical hedges, or financial hedges, or both physical and financial hedges, may be optimized across multiple market price scenarios of qualified market products to optimize investor-tailored risk and return utility functions.

Abstract: A communication system for digital key pairing of a vehicle includes a network transceiver configured for communication via one or more networks with at least one secure server, and a controller. The controller is configured to pre-provision the vehicle with pairing password verifiers for digital key programming to support digital key programming when the vehicle is offline with the at least one secure server, and/or provide end-to-end secure communication between the controller and the at least one secure server by generating and utilizing (i) at least one timestamp, (ii) at least one unique vehicle ID, and (iii) at least one random number in messages communicated between the controller and the at least one secure server.

Abstract: Rapid and data-efficient training of an artificial intelligence (AI) algorithm are disclosed. Ground truth data are not available and a policy must be learned based on limited interactions with a system. A policy bank is used to explore different policies on a target system with shallow probing. A target policy is chosen by comparing a good policy from the shallow probing with a base target policy which has evolved over other learning experiences. The target policy then interacts with the target system and a replay buffer is built up. The base target policy is then updated using gradients found with respect to the transition experience stored in the replay buffer. The base target policy is quickly learned and is robust for application to new, unseen, systems.

Abstract: A method, computer program, and computer system are provided for load forecasting. Datasets corresponding to source machine learning models and a target domain base model are identified. A set of forecasting models corresponding to the identified datasets are learned. An ensemble model is determined from the learned set of forecasting models based on gradient boosting. An available resource is allocated based on the ensemble model.