Abstract: Testing prototype indices is provided. The method comprises receiving input of a number of historical index values and performing a number of Monte Carlo simulations based on the historical index values to predict future index values. A number of attributes of the historical index values are calculated, and the Monte Carlo simulations are correlated with the attributes to identify a filtered subset of predicted future index values having an accuracy above a defined threshold. The filtered subset of predicted future index values are fed into a deep neural network (DNN) that outputs a confidence score for each of the filtered subset of predictive future index values.

Abstract: Security incident detection based on historian configuration data collected over time is described. Historic configuration data associated with a computing device is updated based on received configuration data indicative of a change in configuration of the computing device in a computer system. The historic configuration data indicates changes to configurations of the computing device over a time period. A determination that relationship between the computing device and an entity of the computer system has changed is made based on the updated historic configuration data. The updated historic configuration data is provided as input to a machine learning (ML) model configured to generate an indication of whether the updated historic configuration data evidences a security incident. In response to the ML model generating an indication that the updated historic configuration data evidences a security incident, a security alert indicative of the evidenced security incident is generated.

Abstract: Disclosed is an apparatus for estimating disturbance flowing into a control system on the basis of input/output data. The apparatus includes an input unit, and an estimator configured to, when input data (u) is provided to the control system through the input unit and thus output data is acquired, estimate the input data (u) from the acquired output data, based on a system model matrix corresponding to an input/output relation model of the control system. Accordingly, efficiency of the apparatus may be improved.

Abstract: An iterative learning-based energy-saving control method for a piezoelectric motor, comprising: setting a sampling period of a piezoelectric motor (101); obtaining an expected output trajectory of the piezoelectric motor, and performing sampling according to the sampling period to obtain a sampled expected output sequence (102); setting an initial control input signal of the piezoelectric motor (103); obtaining an actual control input signal according to a mapping relation of the initial control input signal, and transmitting the actual control input signal to the piezoelectric motor to obtain an actual output position (104); obtaining a mapping relation of the output position of the piezoelectric motor according to the actual output position, and sampling the mapping relation according to the sampling period to obtain a sampled actual output sequence (105); calculating the difference between the sampled expected output sequence and the sampled actual output sequence to obtain a sampling error function sequen

Abstract: Coordinated control systems and methods of controlling an actual process are provided. The coordinated control systems and methods of controlling an actual process utilize a nonlinear dynamic model, where measured disturbing variables are incorporated into the nonlinear dynamic model, and predictive controller calculations.

Abstract: A heating, ventilation, or air conditioning (HVAC) system for one or more building zones includes airside HVAC equipment that provide air to the one or more building zones and a controller. The controller obtains predictive models to predict values of a first control objective and a second control objective for the one or more building zones as a function of control decision variables for the airside HVAC equipment. The controller performs a Pareto optimization for a time period using the one or more predictive models to determine multiple sets of Pareto optimal values of the control decision variables and corresponding sets of Pareto optimal values of the first control objective and the second control objective for the time period. The controller operates the airside HVAC equipment to provide the air to the one or more building zones in accordance with a selected set of the Pareto optimal values.

Abstract: A controller for heating, ventilation, or air conditioning (HVAC) equipment that is operable to affect an environmental condition of a building is configured to obtain predictive models that predict values of a carbon emissions control objective and another control objective as a function of control decision variables for the HVAC equipment. The controller executes an optimization process using the predictive models to produce sets of optimization results corresponding to different values of the control decision variables, the carbon emissions control objective, and the other control objective. The controller selects from the sets of optimization results based on the values of the carbon emissions control objective and the other control objective. The controller operates the HVAC equipment to affect the environmental condition of the building in accordance with the values of the control decision variables corresponding to a selected set of the optimization results.

Abstract: A control system for automatic operation of a coker includes a drum feeder operable to modulate a feed of oil into a coke drum of the coker and a controller. The controller is configured to obtain an objective function that defines a control objective as a function of one or more controlled variables affected by modulating the feed of oil into the coke drum and use a predictive model and the objective function to generate a target coker feed rate indicating a target rate at which to feed the oil into the coke drum. The predictive model is configured to predict values of the one or more controlled variables predicted to result from the target coker feed rate. The controller is configured to operate the drum feeder using the target coker feed rate to modulate the feed of oil into the coke drum.

Abstract: A distributed control system (DCS) of an industrial process plant includes a data center storing a plant information model that includes a description of physical components, the control framework, and the control network of the plant using a modeling language. A set of exposed APIs provides DCS applications access to the model, and to an optional generic framework of the data center which stores basic structures and functions from which the DCS may automatically generate other structures and functions to populate the model and to automatically create various applications and routines utilized during run-time operations of the DCS and plant. Upon initialization, the DCS may automatically sense the I/O types of its interface ports, detect communicatively connected physical components within the plant, and automatically populate the plant information model accordingly. The DCS may optionally automatically generate related control routines and/or I/O data delivery mechanisms, HMI routines, and the like.

Abstract: Disclosed are a system and method for training and managing a prediction model, and a master apparatus and a slave apparatus for the same. there is provided a system for training and managing a prediction model, the system including a master apparatus configured to generate a prediction model, train the prediction model, and obtain the trained prediction model; and a slave apparatus configured to collect data, transmit the data to the master apparatus, receive the prediction model or the trained prediction model from the master apparatus, and operate based on the prediction model or the trained prediction model. The master apparatus is further configured to generate the prediction model or train the prediction model based on the data transmitted from the slave apparatus.

Abstract: An environmental control system for a building is shown. The system includes a control device operable affect a static pressure in a conduit, a building device operable to affect a flow rate of a fluid through the conduit, and a controller including a processing circuit configured to perform a volumetric control process to generate a control signal for the drive device. The processing circuit is further configured to receive an operating position signal of the control device. The processing circuit is further configured to determine an estimated static pressure level within the duct using the operating position signal of the control device and update the control signal based on the estimated static pressure level determined using the operating position. The processing circuit is further configured to operate the drive device based on the updated control signal to affect the flow rate of the fluid.

Abstract: A priori geo-referenced data is obtained for a worksite, along with field data that is collected by a sensor on a work machine that is performing an operation at the worksite. A predictive model is generated, while the machine is performing the operation, based on the geo-referenced data and the field data. A model quality metric is generated for the predictive model and is used to determine whether the predictive model is a qualified predicative model. If so, a control system controls a subsystem of the work machine, using the qualified predictive model, and a position of the work machine, to perform the operation.

Abstract: A second action is identified by the edged device. The second action is associated with a second networked device of the plurality of networked devices in the environment. The second networked device is unrelated to the first networked device. A relationship is detected between the first networked device and the second networked device by the edge device. A network device bubble is generated by the edge device. The network device bubble is based on the relationship that is detected.

Abstract: The disclosure herein generally relates to the field of privacy preserving in an application, and, more particularly, to enabling privacy in an application using fully homomorphic encryption. The disclosure more specifically refers to enabling a most optimal FHE for privacy preserving for the application based on a set of constraints using a disclosed set of optimization tasks. The set of optimization tasks comprise a multi objective-multi constraint optimization task and a single objective-multi constraint optimization task, that identifies an optimal FHE library, along with an associated FHE functionality and an optimal configuration of the associated FHE functionality based on the set of constraints. The identified FHE library along with the associated FHE functionality and the optimal configuration of the associated FHE functionality facilitate optimal implementation of privacy in the applications.

Abstract: A method controls a user interface and an air-conditioning unit of a vehicle. The user interface includes display and operating elements. The method displays a plurality of the elements on the user interface, receives at least two operation parameters of the air-conditioning unit, determines one or more display parameters for a first element from the plurality of elements on the basis of the at least two operation parameters, and displays the first element on the basis of the one or more display parameters.

Abstract: Systems, methods, and computer-readable medium storing instructions can be used to predict insurance information. One of the methods includes obtaining information about an insured entity. The method includes providing the information to a machine learning system, the machine learning system trained to provide insurance information based on the provided information. The method includes in response to providing the information, receiving a prediction of the insurance information. The method also includes adjusting an insurance premium based on the prediction.

Abstract: Embodiments of the present invention disclose system to determine the best model to perform lead scoring for a given data set. The system can perform a multi-step iterative procedure including variable selection, feature set selection, training data selection, model development, model validation and process optimization. The system also performs local and global optimizations iteratively to determine the best possible model for a given scenario.

Abstract: An engine system incorporating an engine, one or more sensors, and a controller. The controller may be connected to the one or more sensors and the engine. The one or more sensors may be configured to sense one or more parameters related to operation of the engine. The controller may incorporate an air-path state estimator configured to estimate one or more air-path state parameters in the engine based on values of one or more parameters sensed by the sensors. The controller may have an on-line and an off-line portion, where the on-line portion may incorporate the air-path state estimator and the off-line portion may configure and/or calibrate a model for the air-path state estimator.

Abstract: A controller for a central plant having subplants operating to produce resources consumed by a building. The controller includes a processing circuit including a processor and memory storing instructions executed by the processor. The memory includes an offline rank generator that receives historical subplant allocation data and generates subplant ranks based on the historical subplant allocation data, each of the subplant ranks is associated with one of the subplants and defines a priority of each subplant with respect to production of a resource relative to other subplants that produce the resource. The memory also includes a high level optimizer that uses the subplant ranks associated with each of the subplants to determine resource allocation of the subplants according to the subplant ranks. The processing circuit is operates the subplants according to the resource allocation.

Abstract: A setting method according to the present invention determines a desired time response in an optimum servo control structure corresponding to a servo control structure of a control target, calculates a predetermined gain corresponding to the desired time response, and calculates a first weighting coefficient Qf, a second weighting coefficient Q, and a third weighting coefficient R of a predetermined Riccati equation according to the Riccati equation on the basis of the predetermined gain. The first weighting coefficient Qf, the second weighting coefficient Q, and the third weighting coefficient R are set as a weighting coefficient corresponding to a terminal cost, a weighting coefficient corresponding to a state quantity cost, and a weighting coefficient corresponding to a control input cost, respectively, in a predetermined evaluation function for model prediction control.

Abstract: A method and apparatus for dithering hydraulic valves to mitigate static friction (“stiction”) associated with the hydraulic valves. A first hydraulic valve and a second hydraulic valve are dithered to mitigate stiction associated with those valves. The dithering of the first and second hydraulic valves also cause dithering of a main hydraulic valve associated with the first and second hydraulic valves. Accordingly, stiction of three hydraulic valves of a hydraulic system is mitigated.

Abstract: The present disclosure provides an air conditioning apparatus and a method for controlling same. The method for controlling an air conditioning apparatus comprises the steps of: the air conditioning apparatus receiving, from an external server, user sleep information acquired on the basis of data on time for which the air conditioning apparatus is operated in a sleep cooling mode used during the user's sleep; and operating in the cooling mode on the basis of the user sleep information. Specifically, at least part of an operation for acquiring the user sleep information on the basis of the user's control command may use an artificial intelligence model obtained by learning according to at least one of a machine learning, a neural network, and a deep learning algorithm.

Abstract: In one aspect, a computing device-implemented method includes receiving at least one triggering event signal from one or more components of a heat recovery system. The method also includes determining, based in part on the at least one triggering event signal, a computation workload assignment to be executed on one or more computation devices. The method further includes sending one or more command signals to the one or more computation devices. The one or more command signals include a portion of the computation workload assignment for execution by the one or more computation devices. The method also includes initiating capture of heat energy to be stored in one or more heat reservoirs, the heat energy being generated by the one or more computation device based upon the computation workload assignment.

Abstract: A plant data classification device according to one aspect of the invention includes: a data classification unit that classifies multidimensional operation data into categories; an evaluation index calculation unit that calculates an evaluation index of a category from a value of the operation data; a classification result evaluation unit that calculates a variation in the evaluation index for each category and determines whether the variation in the evaluation index is less than or equal to a reference value; and a parameter changing unit that changes, when it is determined that the variation in the evaluation index exceeds the reference value, a value of a parameter that defines a size of a category of the data classification unit in a direction of decreasing the size of the category.

Abstract: A processing device is provided which comprises memory and a processor. The processor is configured to receive an array of floating point numbers each having a plurality of bits used to represent a probability value. For each floating point number, the processor is configured to replace values in a portion of the bits used to represent the probability value with index values to represent an index corresponding to a location of a corresponding floating point number in the memory. The processor is also configured to process the floating point numbers using SIMD instructions to execute one of an argmax operation and an argmin operation.

Abstract: The disclosure describes a system that includes a closed-loop reference module, an adaptation module, and a control module. The closed-loop reference module is configured to execute a reference model that represents operation of an engine and determine a reference control signal and a reference state trajectory signal. The adaptation module is configured to determine an adaptation signal based on a difference between the reference state trajectory signal and an engine state trajectory signal representative of actual operation of the engine. The control module is configured to receive the reference control signal from the closed-loop reference module, the adaptation signal from the adaptation module, and the engine state trajectory signal. The control module is further configured to determine a demand signal based on the engine state trajectory signal, the adaptation signal, and the reference control signal, and output the demand signal to control operation of at least one engine component.

Abstract: A performance management method and an electronic device are provided. The method is applied to the electronic device with a system processor and includes: sensing a temperature of the electronic device and determining whether the temperature is greater than a first temperature setting value; when the temperature is not greater than the first temperature setting value, initiating a frequency increasing procedure; when the temperature is greater than the first temperature setting value, determining whether the temperature is greater than a second temperature setting value, where the second temperature setting value is greater than the first temperature setting value; when the temperature is greater than the first temperature setting value and is not greater than the second temperature setting value, initiating a first frequency reducing procedure; and when the temperature is greater than the second temperature setting value, initiating a second frequency reducing procedure or turning off the system processor.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for an adaptive oracle-trained learning framework for automatically building and maintaining models that are developed using machine learning algorithms. In embodiments, the framework leverages at least one oracle (e.g., a crowd) for automatic generation of high-quality training data to use in deriving a model. Once a model is trained, the framework monitors the performance of the model and, in embodiments, leverages active learning and the oracle to generate feedback about the changing data for modifying training data sets while maintaining data quality to enable incremental adaptation of the model.

Abstract: A method of generating a controller for a continuous process. The method includes receiving from a storage memory, off-line stored values of one or more controlled variables and one or more manipulated variables of the continuous process over a plurality of time points. The off-line stored values are used to train a first neural network to operate as a predictor of the controlled variables. Then, the method includes training a second neural network to operate as a controller of the continuous process using the first neural network after it was trained to operate as the predictor for the continuous process and employing the second neural network as a controller of the continuous process.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for code review assistance for dynamically typed languages. An example apparatus to analyze a segment of code includes a function identifier to identify a first input of a first function call included in the segment of the code, a parameter type vector (PTV) estimator model to estimate a first data structure based on the first input, the PTV estimator model generated via a set of reviewed code, a PTV determiner to generate a second data structure based on a data parameter type of the first input, an error comparator to determine a first reconstruction error based on the first data structure, and the second data structure and a recommendation generator to, if the first reconstruction error does not satisfy a recommendation threshold, generate a first recommendation to review the first function call.

Abstract: Embodiments of the invention are directed to systems, methods, and computer program products for a parameter archival storage system for image processing models. The system is configured for read-optimized compression storage of machine-learning neural-network based image processing models with reduced storage by separately storing weight filter bits. The system is configured to construct weigh parameter objects associated with the plurality of neural network layers of an image processing model, such that the image processing model can be reconstructed from the weigh parameter objects. The system may discard the hierarchical linked architecture of the second image processing model and store the second image processing model at the at least one hosted model versioning system repository by storing only the weigh parameter objects.

Abstract: Developing intelligent systems which take into consideration the economical, environmental, and safety factors of the modern society, is one of the main challenges of this century. Progress in the fields of mobile robots, control architectures, artificial intelligence, advanced technologies, and computer vision allows us to now envisage a smart environment future. The rise of the connected objects known as the “Internet of Things” (IoT) will rival past technological marvels. This disclosure introduces a time synchronous communication IoT network and use of absolute time of day and a navigation/protection mechanism by various objects to navigate freely, without interference and collision in a smart environment.

Abstract: A method of producing advanced carbon materials can include extracting a coal sample from a location, performing a spectral analysis on the coal sample, determining one or more desired advanced carbon materials based at least in part on spectral analysis, extracting an amount of coal from the location, beneficiating the amount of coal, and processing the beneficiated amount of coal to produce the one or more desired advanced carbon materials from at least some of the amount of coal.

Abstract: An online system uses multiple machine learning models to select content for providing to a user of the online system. Specifically, the online system trains a general model that intakes a first set of features and outputs predictions at a general level. The online system further trains a residual model that intakes a second set of features. The residual model predicts a residual (e.g., an error) of the predictions outputted by the general model. Therefore, the predicted residual from the residual model is combined with the prediction from the general model in order to correct for the over-generality of the general model. The online system may use the combined prediction to send content to users.

Abstract: The dynamic complexity and the operational risk inherent in a system are defined and incorporated into a mathematical model of the system. The mathematical model is emulated to predict the states of instability that can occur within the operation of the system. Dynamic complexity of a service is demonstrated where there is an observed effect where the cause can be multiple and seemingly inter-related effects of a many-to-one or many-to-many relationship. Having assessed the dynamic complexity efficiency and the operational risk index of a service (e.g., a business, process or information technology), these indexes can be employed to emulate all attributes of a service, thereby determining how a service responds in multiple states of operation, the states where the dynamic complexity of a service can occur, optimal dynamic complexity efficiency of a service, and the singularities wherein a service becomes unstable.

Abstract: Embodiments detailed herein relate to systems and methods to zero a tile register pair. In one example, a processor includes decode circuitry to decode a matrix pair zeroing instruction having fields for an opcode and an identifier to identify a destination matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded matrix pair zeroing instruction to zero every element of a left matrix and a right matrix of the identified destination matrix.

Abstract: A method of determining a requirements characterization profile for an entity is disclosed. The method comprises the steps of receiving classification parameters defining a requirement for an entity and selecting, in dependence on the classification parameters, a set of entities from a database of previously assessed entities. The method further comprises retrieving from the database characterization parameters of the selected set of entities, and constructing, in dependence on the characterization parameters, a requirements characterization profile for the entity. An apparatus is provided that comprised means for performing such a method.

Abstract: Methods and apparatus are described by which time-series data captured during the automated testing of software applications may be analyzed. Change-point detection is used to partition the time-series data, and an expected variance of data within each partition is determined. Because the partitioning of the test data provides a high level of confidence that the data points in a given partition conform to the same distribution, data points that represent meaningful changes in application performance can be more confidently and efficiently identified.

Abstract: A parameter optimization method includes: a parameter search is performed on an input parameter, an output response value and a target value through a plurality of optimization schemes to search for a plurality of candidate recommended parameters. Each optimization scheme is assigned to a weight value according to user historical decision information. At least one recommended parameter is selected from the candidate recommended parameters according to the weight values. An user interface is provided for a user to input a decision instruction. A new input parameter is selected from the at least one recommended parameter according to the decision instruction; the new input parameter is inputted into the target system; and a new output response value is evaluated whether meets a specification condition. The user historical decision information is updated based on the decision instruction to adjust the weight values.

Abstract: 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.

Abstract: The settling time of machine learning is shortened. A machine learning device is configured to perform machine learning related to optimization of coefficients of a transfer function of an IIR filter of a feedforward calculation unit with respect to a servo control device configured to control a servo motor configured to drive an axis of a machine tool, a robot, or an industrial machine using feedforward control by a feedforward calculation unit having the IIR filter. The machine learning device represents a zero-point at which the transfer function of the IIR filter is zero and a pole at which the transfer function diverges infinitely in polar coordinates using a radius r and an angle ?, respectively, and searches for and learns, within a predetermined search range, the radius r and the angle ? to thereby perform the optimization of the coefficients of the transfer function of the IIR filter.

Abstract: A system implements changes to improve control effectiveness. The system is typically configured for determining at least one stored control of a plurality of controls similar or identical to a present control from a control library comprising the plurality of controls; extracting a consideration set of indicators associated with the stored control from the control library; applying a regression algorithm on the consideration set of indicators; determining a threshold correlation or threshold number of indicators for inclusion in a final equation relating a subset of the consideration set of indicators with control effectiveness of the control; reducing a number of the subset of the consideration set of indicators based on the threshold correlation or threshold number; finalizing the final equation with the number of the subset, each having a corresponding coefficient; and automatically performing an action configured to improve effectiveness of the control based on the final equation.

Abstract: An imaging apparatus includes a clamp level is multiplied by a first feedback gain, and correct a signal of a part of photoelectric conversion portions of a unit pixel in an opening region based on a result of multiplication in which an error amount between a signal of a part of a photoelectric conversion portions of the unit pixel in a light-shielded region and a clamp level is multiplied by a second feedback gain, and thus the signal of the unit pixel can be corrected precisely.

Abstract: An estimation results display system that, in the case of displaying an estimation result derived using a learning model, enables persons to recognize how condition determination is performed to select the learning model is provided. Input means 91 receives input of information associating information indicating a learning model selected depending on a determination result of whether or not an attribute in estimation data including one or more types of attributes satisfies one or more types of conditions and an estimation result derived using the learning model. Display means 92 displays the estimation result, in association with the information indicating the learning model used for deriving the estimation result and a condition subjected to determination of whether or not satisfied by the attribute in the estimation data when selecting the learning model.

Abstract: The present disclosure relates to a method of trajectory planning for maneuvers for an ego vehicle (E) equipped with a sensor systems, a prediction systems, a control system, and a decision-making system. The method includes determining possible lateral motion trajectories of a requested maneuver, longitudinal safety critical zones which correspond to each of the determined possible lateral motion trajectories, a longitudinal motion trajectory of the requested maneuver, lateral safety critical zones which correspond to the determined longitudinal motion trajectory of the requested maneuver, and a lateral motion trajectory of the requested maneuver. The present disclosure also relates to a driver assistance system arranged to perform the method and a vehicle including such a system.

Abstract: Embodiments of the present invention provide a system for indicator regression and modeling for implementing system changes to improve control effectiveness. The system is typically configured for presenting, prompting for and receiving a selection from a list of controls from a user, via a control effectiveness application user interface on a user device. The system is also for receiving two or more consideration indicators from the user device, via the control effectiveness application user interface forming a consideration set; applying a regression algorithm on the consideration set of indicators; reducing a number of the subset of the consideration set of indicators based on a threshold correlation or a threshold number; finalizing the final equation with the number of the subset, each having a corresponding coefficient; and, in response to finalizing the final equation, automatically performing an action configured to improve effectiveness of the control based on the final equation.

Abstract: A system and method for additive manufacturing of otherwise thermosetting polymers, such as PAI, is disclosed. The system includes fast-curing hardware that facilitates curing each deposited layer before a successive layer is deposited. This reduces the time to provide a finished part from weeks to hours.

Abstract: An autonomous driving method includes: determining a risk of a target vehicle based on either one or both of a driving characteristic and an appearance characteristic of the target vehicle; and autonomously controlling a host vehicle based on the risk.

Abstract: A controller arrangement includes a controller, an actuator, and a measuring element. The measuring element captures a control variable with a predetermined sampling rate in consecutive sampling cycles and transmits it to the controller. The controller compares the control variable with a predetermined reference variable and determines how the control variable differs from the reference variable. The controller, in a first cycle, starts with a predetermined regulating variable and outputs it to the actuator, and subsequently determines how the control variable differs from the reference variable; in a second cycle, the controller varies the regulating variable based on the difference of the control variable from the reference variable in the first cycle, and outputs it to the actuator, and subsequently determines how the control variable differs from the reference variable; in a third cycle, the controller varies the regulating variable and outputs it to the actuator.

Abstract: To perform reinforcement learning enabling to prevent complicated adjustment of coefficients of backlash compensation and backlash acceleration compensation.