Abstract: A method for securing an interblockchain transaction includes receiving, from a first user application, a registration request including a first permissioned blockchain public key and a first permissionless blockchain public key. The method also includes performing, by the processing circuitry, receiving, from a second user application, a second registration request including a second permissioned blockchain public key and a second permissionless blockchain public key. The permissioned blockchain public keys are valid on the permissioned blockchain and the permissionless blockchain public keys are valid on the permissionless public blockchain. In addition, the method includes receiving, from the first user application, a transaction identification, the transaction identification identifying a first transfer transaction executed on the permissionless public blockchain. The transaction identification identifies the first and second permissionless blockchain public keys.

Abstract: A method for securing a cryptocurrency transaction on a permissioned blockchain, which involves cryptocurrencies of a permissionless public blockchain, includes receiving a join request including a transaction identification. The transaction identification identifies an enroll transaction involving a public smart contract deployed on the permissionless public blockchain, the enroll transaction identifying a permissioned blockchain public key being valid on the permissioned blockchain and transferring a cryptocurrency balance to the public smart contract. The method further includes verifying that the enroll transaction was properly executed, crediting an account corresponding to the permissioned blockchain public key with the cryptocurrency balance, and receiving a send request identifying a second cryptocurrency balance and a second permissioned blockchain public key being valid on the permissioned blockchain.

Abstract: A method for securing an interblockchain transaction includes receiving, from a first user application, a registration request including a first permissioned blockchain public key and a first permissionless blockchain public key. The method also includes performing, by the processing circuitry, receiving, from a second user application, a second registration request including a second permissioned blockchain public key and a second permissionless blockchain public key. The permissioned blockchain public keys are valid on the permissioned blockchain and the permissionless blockchain public keys are valid on the permissionless public blockchain. In addition, the method includes receiving, from the first user application, a transaction identification, the transaction identification identifying a first transfer transaction executed on the permissionless public blockchain. The transaction identification identifies the first and second permissionless blockchain public keys.

Abstract: A method for predicting a patient outcome from a caretaker episode includes receiving a current episode snapshot of the caretaker episode comprising multi-modal data of the patient from an electronic health records (EHR) system, the multi-modal data including one or more available data modalities and one or more missing data modalities. The multi-modal data is applied as input to an embedding model having a submodel for each of the data modalities. A first embedding is generated for each of the available data modalities. A second embedding is generated for each of the missing data modalities using corresponding embeddings of neighbors in an episode snapshot graph. The first and second embeddings are combined to obtain a complete embedding. The patient outcome is predicted based on the complete embedding for the current episode snapshot using a machine learning component which has been trained using patient outcomes of the historical episode snapshots.

Abstract: A method for predicting a patient outcome from a caretaker episode includes receiving a current episode snapshot of the caretaker episode comprising multi-modal data of the patient from an electronic health records (EHR) system, the multi-modal data including one or more available data modalities and one or more missing data modalities. The multi-modal data is applied as input to an embedding model having a submodel for each of the data modalities. A first embedding is generated for each of the available data modalities. A second embedding is generated for each of the missing data modalities using corresponding embeddings of neighbors in an episode snapshot graph. The first and second embeddings are combined to obtain a complete embedding. The patient outcome is predicted based on the complete embedding for the current episode snapshot using a machine learning component which has been trained using patient outcomes of the historical episode snapshots.

Abstract: An appointment scheduling device for scheduling an appointment for a patient to visit a health provider includes an embedder, a predictor, and a scheduler. The embedder receives input data about the patient. The input data is associated with a request to schedule the appointment with the health provider. The embedder generates an embedding based on the input data. The predictor receives the embedding and predicts an appointment parameter based on the embedding. The scheduler schedules the appointment based on the appointment parameter.

Abstract: A system for collaborative load balancing within a community of a plurality of energy nodes includes a central allocation server and a plurality of local agent servers. Each of the local agent servers is connected to a respective one of the energy nodes and has a processor configured to: receive input variables or parameters; predict, using the received input variables or parameters, a non-zero energy generation amount that power generation equipment can generate over a planning horizon and an energy consumption amount that will be consumed over the planning horizon; solve, using the energy generation amount and the energy consumption amount, an optimization problem over the planning horizon; and communicate a solution to the optimization problem to the central allocation server. Each of the energy nodes includes power generation equipment, power transmission equipment, and power storage equipment.

Abstract: A method for controlling energy supply to different units includes receiving, by an aggregator, the demand request signal, and performing, by the aggregator, an allocation of the requested demand modification to the units based on a negotiating process with the units for minimizing an impact of the allocation on a future operation of another utility or of other utilities. Each unit is connected to multiple utilities for receiving enemy for operating its energy systems. A demand request signal is provided by at least one operational entity and/or by at least one utility for requesting a demand modification of a utility and/or of one form of energy.

Abstract: A method controls load balancing within an energy system that includes a renewable energy source for sharing local renewable energy consumption between a predetermined number of users who operate time delay-tolerant loads and a back-up energy source for providing back-up energy. Use cases of appliances of the users are defined by power profiles that are in each case based on a duration and energy consumption of a task or an array of subtasks. One or more use cases has a user specified deadline. A scheduler, in a first level, performs a control of load balancing by scheduling or time-shifting use of the loads so as to provide a start time assignment for each of the tasks or sub tasks based on a maximization of the local renewable energy consumption among the users. The scheduler, in a second level, assigns the renewable energy to the appliances using the start time assignments.

Abstract: A system and method perform electricity and heat load balancing within a community of energy nodes. The system includes a central control device to solve an optimization problem over a planning horizon and to run an allocation algorithm. Local agent devices communicate with the central control device. Each local agent device receives input parameters from an energy node. Each energy node includes electricity generation equipment, electrical heat-generating equipment, and power transmission equipment, electricity storage equipment and thermal storage equipment. The local agent devices operate the electrical heat-generating equipment based on an allocation instruction received from the central control device. The central control device receives status information from the local agent devices to determine an amount of energy to be converted from electricity to heat by the electrical heat-generating equipment of the energy nodes, to provide the allocation instruction to the energy nodes.

Abstract: A system for collaborative load balancing within a community of a plurality of energy nodes includes a central allocation server and a plurality of local agent servers. Each of the local agent servers is connected to a respective one of the energy nodes and has a processor configured to: receive input variables or parameters; predict, using the received input variables or parameters, a non-zero energy generation amount that power generation equipment can generate over a planning horizon and an energy consumption amount that will be consumed over the planning horizon; solve, using the energy generation amount and the energy consumption amount, an optimization problem over the planning horizon; and communicate a solution to the optimization problem to the central allocation server. Each of the energy nodes includes power generation equipment, power transmission equipment, and power storage equipment.

Abstract: A system for collaborative load balancing within a community of energy nodes includes a central allocation control device and local agent devices each associated with an energy node. The local agent devices solve an optimization problem over a planning horizon and communicate the solution to the central allocation control device. The central allocation control device uses the solutions in an allocation algorithm so as to determine an amount of energy which will be received from or supplied to individual ones of the energy nodes and provide the collaborative load balancing within the community.

Abstract: A method for controlling energy supply to different units includes receiving, by an aggregator, the demand request signal, and performing, by the aggregator, an allocation of the requested demand modification to the units based on a negotiating process with the units for minimizing an impact of the allocation on a future operation of another utility or of other utilities. Each unit is connected to multiple utilities for receiving enemy for operating its energy systems. A demand request signal is provided by at least one operational entity and/or by at least one utility for requesting a demand modification of a utility and/or of one form of energy.

Abstract: A method controls load balancing within an energy system that includes a renewable energy source for sharing local renewable energy consumption between a predetermined number of users who operate time delay-tolerant loads and a back-up energy source for providing back-up energy. Use cases of appliances of the users are defined by power profiles that are in each case based on a duration and energy consumption of a task or an array of subtasks. One or more use cases has a user specified deadline, A scheduler, in a first level, performs a control of load balancing by scheduling or time-shifting use of the loads so as to provide a start time assignment for each of the tasks or sub tasks based on a maximization of the local renewable energy consumption among the users. The scheduler, in a second level, assigns the renewable energy to the appliances using the start time assignments.

Abstract: A system for collaborative load balancing within a community of energy nodes includes a central allocation control device and local agent devices each associated with an energy node. The local agent devices solve an optimization problem over a planning horizon and communicate the solution to the central allocation control device. The central allocation control device uses the solutions in an allocation algorithm so as to determine an amount of energy which will be received from or supplied to individual ones of the energy nodes and provide the collaborative load balancing within the community.

Abstract: A system and method perform electricity and heat load balancing within a community of energy nodes. The system includes a central control device to solve an optimization problem over a planning horizon and to run an allocation algorithm. Local agent devices communicate with the central control device. Each local agent device receives input parameters from an energy node. Each energy node includes electricity generation equipment, electrical heat-generating equipment, and power transmission equipment, electricity storage equipment and thermal storage equipment. The local agent devices operate the electrical heat-generating equipment based on an allocation instruction received from the central control device. The central control device receives status information from the local agent devices to determine an amount of energy to be converted from electricity to heat by the electrical heat-generating equipment of the energy nodes, to provide the allocation instruction to the energy nodes.