Disclosed within is a closed loop controller having: (a) a signal processing and statistics subsystem sampling an input data stream from at least one sensor, calculating real-time continuous statistics in the input data stream based on a sliding window technique, and outputting one or more classifications based on the real-time statistics; and (b) an intelligent fuzzy logic controller receiving the one or more classifications from the signal processing and statistics subsystem, accessing a heuristic rule set based on expert knowledge, and outputting a noninvasive stimulation pattern based on the one or more classifications and the heuristic rule set.

The invention relates to a modular production plant for continuous production and/or preparation of biopharmaceutical products, a computer-implemented method for process control of the modular plant for production of biopharmaceutical and biological macromolecular products, in particular of proteins, e.g. monoclonal antibodies, vaccines, nucleic acids such as DNA, RNA and plasmids and derivatives thereof.

The instant disclosure provides an ability to use an array of data inputs to enter a network and thereby provide a realtime improvable database. The present invention is novel in its ability to maximize the customer's interface with a pest control system, thus allowing for maximum efficiency for current and future designs as well as a high level of compatibility with ancillary regulatory, financial and planning type functions.

Methods and apparatus for providing a comprehensive decision support system to include predictions, recommendations with consequences and optimal follow-up actions in specific situations are described. Data is obtained from multiple disparate data sources, depending on the information deemed necessary for the situation being modeled. The decision support system provides a prediction or predictions and a recommendation or a choice of recommendations based on the correlative analysis and/or other analyses. Also described are methods and apparatus for developing application specific decision support models. The decision support model development process may include identifying multiple disparate data sources for retrieval of related information, selection of classification variables to be retrieved from the data sources, assignment of weights to each classification variable, selecting and/or defining rules, and selecting and/or defining analysis functions.

The present invention provides a method for an optimal scheduling decision of an air compressor group based on a simulation technology, which belongs to the technical field of information. The present invention uses expert experience to construct an air compressor energy consumption model sample set, and applies a least squares algorithm to learn relevant parameters of an air compressor energy consumption model; uses maximum energy conversion efficiency and minimum economic cost based on an equivalent electricity as target functions, and applies the simulation technology and a depth first tree search algorithm to solve a multi-target optimal scheduling model of the air compressor group; and finally uses a fuzzy logic theory to describe the preferences of decision makers, and introduces the decision maker preference information into interactive decision making, thereby assisting production staff to formulate safe, economical, efficient and environmentally friendly operation schemes to achieve an operation mode of maximum resource utilization of the air compressor group. The method also has wide application value in different industrial fields.

The disclosure discloses an inhomogeneous sample equalization method and system for a product assembly process. The method includes the following steps of: A: calculating a similarity among different samples; B: constructing a fuzzy compatibility matrix S for representing the similarity among all the samples, and constructing a fuzzy compatibility space X with different granule layers through the fuzzy compatibility matrix S; C: based on a granular calculating mode, screening out a granule layer with a maximum comprehensive value of an information increment and the similarity among the samples from the fuzzy compatible space X to serve as an optimal granule layer; and D: carrying out equalization processing on the sample of the optimal granule layer.

A system for detecting and responding to an anomaly in a chaotic environment, comprising one or more autonomous agent devices and a central server comprising a processor and non-transitory memory. The memory stores instructions that cause the processor to receive a first set of sensor readings from one or more remote electronic sensors, during a first time window, the sensor readings recording pseudo-Brownian change in one or more variables in the chaotic environment; determine, based on the first set of sensor readings, an expected range of the one or more variables during a second time window after the first time w window; receive a second set of sensor readings from the one or more remote electronic sensors during the second time window recording change in the one or more variables: determine, based on the second set of sensor readings, that one variable of the one or more variables is not within the expected range; and cause the one or more autonomous agent devices to attempt to mitigate a potential harm indicated by the one variable being outside of the expected range.

A machine learning device, which detects an operator, communicates with a database registering information concerning the operator, and learns display of an operation menu based on the information concerning the operator, includes a state observation unit which observes an operation history of the operation menu; and a learning unit which learns the display of the operation menu on the basis of the operation history of the operation menu observed by the state observation unit.

According to some embodiments a competence module is provided to: receive an objective; select a machine learning model associated with the objective; receive data from the at least one data source; determine at least one next input based on the received data; determine whether the at least one next input is in a competent region or is in an incompetent region of the machine learning model; when the at least one next input is inside the competent region, generate an output; determine an estimate of uncertainty for the generated output; when the uncertainty is below an uncertainty threshold, the machine learning model is competent and when the uncertainty is above the uncertainty threshold, the machine learning model is incompetent; and operate the physical asset based on one of the competent and incompetent state of the machine learning model. Numerous other aspects are provided.

A system for detecting and responding to an anomaly in a chaotic environment, comprising one or more autonomous agent devices and a central server comprising a processor and non-transitory memory. The memory stores instructions that cause the processor to receive a first set of sensor readings from one or more remote electronic sensors, during a first time window, the sensor readings recording pseudo-Brownian change in one or more variables in the chaotic environment; determine, based on the first set of sensor readings, an expected range of the one or more variables during a second time window after the first time window; receive a second set of sensor readings from the one or more remote electronic sensors during the second time window recording change in the one or more variables; determine, based on the second set of sensor readings, that one variable of the one or more variables is not within the expected range; and cause the one or more autonomous agent devices to attempt to mitigate a potential harm indicated by the one variable being outside of the expected range.