Systems, methods, and/or apparatuses may be operative to perform a dialysis process that includes a displacer infusion process. The dialysis machine may include at least one processor and a memory coupled to the at least one processor, the memory comprising instructions that, when executed by the processor, may cause the at least one processor to access dialysis information for a dialysis process performed by a dialysis machine, the dialysis information indicating a target substance to be displaced from a binding compound by a displacer, and determine an infusion profile for infusing the displacer into a patient during a displacer infusion process of the dialysis process, the infusion profile determined based on the dialysis information and an infusion constraint. Other embodiments are described.

Systems, methods, and/or apparatuses may be operative to perform a dialysis process that includes a displacer infusion process. The dialysis machine may include at least one processor and a memory coupled to the at least one processor, the memory comprising instructions that, when executed by the processor, may cause the at least one processor to access dialysis information for a dialysis process performed by a dialysis machine, the dialysis information indicating a target substance to be displaced from a binding compound by a displacer, and determine an infusion profile for infusing the displacer into a patient during a displacer infusion process of the dialysis process, the infusion profile determined based on the dialysis information and an infusion constraint. Other embodiments are described.

A method for simulating a microemulsion system in a chemical enhanced oil recovery process is disclosed. The method includes receiving a geological model of a subsurface reservoir that defines a grid having a plurality of cells, determining a surfactant concentration for each cell based on a volume of surfactant and a volume of water within the cell and independently from a volume of oil in the cell, and simulating fluids flowing in the subsurface reservoir. Results from simulation can be used to optimize a chemical enhanced oil recovery process in a subsurface reservoir.

A method for simulating a microemulsion system in a chemical enhanced oil recovery process is disclosed. The method includes receiving a geological model of a subsurface reservoir that defines a grid having a plurality of cells, determining a surfactant concentration for each cell based on a volume of surfactant and a volume of water within the cell and independently from a volume of oil in the cell, and simulating fluids flowing in the subsurface reservoir. Results from simulation can be used to optimize a chemical enhanced oil recovery process in a subsurface reservoir.

An electronic apparatus for compressing a recurrent neural network and a method thereof are provided. The electronic apparatus and the method thereof include a sparsification technique for the recurrent neural network, obtaining first to third multiplicative variables to learn the recurrent neural network, and performing sparsification for the recurrent neural network to compress the recurrent neural network.

An electronic apparatus for compressing a recurrent neural network and a method thereof are provided. The electronic apparatus and the method thereof include a sparsification technique for the recurrent neural network, obtaining first to third multiplicative variables to learn the recurrent neural network, and performing sparsification for the recurrent neural network to compress the recurrent neural network.

In one implementation, first and second messages are received that include encoded position information for a transmitter. It is determined that both were received within some time of a previous message and that the second message was received within some time of the first message. A first location of the transmitter is determined based on the encoded position in the first message and the previously determined location. A second location of the transmitter is determined based on the encoded position in the second message and the previously determined location. It also is determined that the first and second locations are within a threshold distance. An updated second location of the transmitter is determined based on the encoded position information in the second message and the first location. A determination is made that the second location and the updated second location are within a threshold distance.

In one implementation, first and second messages are received that include encoded position information for a transmitter. It is determined that both were received within some time of a previous message and that the second message was received within some time of the first message. A first location of the transmitter is determined based on the encoded position in the first message and the previously determined location. A second location of the transmitter is determined based on the encoded position in the second message and the previously determined location. It also is determined that the first and second locations are within a threshold distance. An updated second location of the transmitter is determined based on the encoded position information in the second message and the first location. A determination is made that the second location and the updated second location are within a threshold distance.

Predictive multi-stage modelling for complex semiconductor device manufacturing process control is provided. In one aspect, a method of predictive multi-stage modelling for controlling a complex semiconductor device manufacturing process includes: collecting geometrical data from metrology measurements made at select stages of the manufacturing process; and making an outcome probability prediction at each of the select stages using a multiplicative kernel Gaussian process, wherein the outcome probability prediction is a function of a current stage and all prior stages. Machine-learning models can be trained for each of the select stages of the manufacturing process using the multiplicative kernel Gaussian process. The machine-learning models can be used to provide probabilistic predictions for a final outcome in real-time for production wafers. The probabilistic predictions can then be used to select production wafers for rework, sort, scrap or disposition.

Real-time dynamic optimization of a process model in an online model-based process control computing environment. A mixed integer nonlinear programming (MINLP) solver utilizes a switch to activate and deactivate a first-principle model of a process unit. The switch enables MINLP behavior by attaching to the first-principle model.