Abstract: A positioning control device includes a position-command generation unit to generate a position command by which a shape of an acceleration in an accelerating section and a decelerating section is determined on the basis of a position command parameter, a drive control unit to drive a motor such that a detected position value of the motor or a control target follows the position command, an evaluation unit to calculate an evaluation value regarding positioning performance on the basis of a detected position value of the motor or the control target during execution of positioning control on the control target, and a learning unit to obtain a learning result by learning a relation between the position command parameter and the evaluation value when positioning control is executed plural times, while changing each of shapes of an acceleration in an accelerating section and a decelerating section independently.

Abstract: Provided are a material testing machine that can improve the responsiveness and the stability and perform a feedback control for a test condition, and a method for controlling a material testing machine. A monitor amount conversion unit (23) calculates an estimation testing force by multiplying an elongation amount measured by an elongation amount measurement unit (22) by a control stiffness of a test piece (TP). A material test control unit (24) determines an operation amount for a servo motor (43) for reducing a deviation between an actual testing force applied to the test piece (TP) and a target testing force according to a test condition based on an estimation testing force, and executes a tensile test for the test piece (TP).

Abstract: A system including a tracking device, sensors, and an operations management engine (OME), and a method for managing operations and assets, for example, motorized and non-motorized equipment, associated with multiple entities, are provided. The OME dynamically receives asset data from the tracking device and operating parameters of the assets from one or more sensors in real time. The OME dynamically determines multiple data elements, for example, location, asset status, operating status, asset proximity to asset requirement, etc., associated with each asset by processing logical combinations of the asset data and the operating parameters, based on which the OME determines actions associated with the assets to be executed. The OME generates an interactive, graphical map interface that renders a visual representation of the assets, a geography containing the assets, associated operations, and the data elements in real time for real-time monitoring and facilitating execution of the actions.

Abstract: Technologies for detecting cyber-attacks against electrical distribution devices include a controller. The controller includes circuitry to determine a first measured value of a first operational parameter of a transformer based upon one or more signals received from one or more sensors of the transformer. The circuitry is also to determine a second measured value of a second operational parameter of the transformer based upon one or more signals received from the one or more sensors of the transformer, calculate a first expected value of the first operational parameter based on the second measured value of the second operational parameter and a model of the transformer that relates the first and second operational parameters, compare the first measured value of the first operational parameter to the first expected value of the first operational parameter, and identify when a difference between the first measured value and the first expected value exceeds a first threshold.

Abstract: A learning method detects anomalies and is implemented on a microcontroller including at least one memory, the microcontroller being configured to receive data sets coming from at least one sensor, the memory being configured to store a maximum number of categories, a category including at least a signature and an occurrence.

Abstract: First, the system obtains time-series sensor data. Next, the system identifies missing values in the time-series sensor data, and fills in the missing values through interpolation. The system then divides the time-series sensor data into a training set and an estimation set. Next, the system trains an inferential model on the training set, and uses the inferential model to replace interpolated values in the estimation set with inferential estimates. If there exist interpolated values in the training set, the system switches the training and estimation sets. The system trains a new inferential model on the new training set, and uses the new inferential model to replace interpolated values in the new estimation set with inferential estimates. The system then switches back the training and estimation sets. Finally, the system combines the training and estimation sets to produce preprocessed time-series sensor data, wherein missing values are filled in with imputed values.

Abstract: Deep learning models and other complex models provide accurate representations of complex industrial processes. However, these models often fail to satisfy properties needed for their use in closed loop systems such as Advanced Process Control. In particular, models need to satisfy gain-constraints. Methods and systems embodying the present invention create complex closed-loop compatible models. In one embodiment, a method creates a controller for an industrial process. The method includes accessing a model of an industrial process and receiving indication of at least one constraint. The method further includes constructing and solving an objective function based on at least one constraint and the model of the industrial process. The solution of the objective function defines a modified model of the industrial process that satisfies the received constraint and can be used to create a closed-loop controller to control the industrial process.

Abstract: A system and method for creating and making use of customer profiles, including energy consumption patterns. Devices within a service point, using the active load director, may be subject to control events, often based on customer preferences. These control events cause the service point to use less power. Data associated with these control events, as well as related environment data, are used to create an energy consumption profile for each service point. This can be used by the utility to determine which service points are the best targets for energy consumption. In addition, an intelligent load rotation algorithm determines how to prevent the same service points from being picked first each time the utility wants to conserve power.

Abstract: A machine tool management system connects an external server and a large number of NC devices controlling the external server and respective machine tools through a network. The system collects several kinds of signal data from the NC device of each machine tool to the external server. In the system, the external server stores a maintenance period model and a refinement algorithm and obtains a next maintenance period from the maintenance period model.

Abstract: A computer-implemented method to control technical equipment that performs a production batch-run of a production process, the technical equipment providing data in a form of time-series from a set of data sources, the data sources being related to the technical equipment, includes: accessing a reference time-series with data from a previously performed batch-run of the production process, the reference time-series being related to a parameter for the technical equipment; and while the technical equipment performs the production batch-run: receiving a production time-series with data, identifying a sub-series of the reference time-series, and comparing the received time-series and the sub-series of the reference time-series, to provide an indication of similarity or non-similarity, in case of similarity, controlling the technical equipment during a continuation of the production batch-run, by using the parameter as control parameter.

Abstract: A plasma processing apparatus 100 is equipped with a shower head 16 and a placing table 2 facing each other. A first RF power supply 10a is configured to apply a RF power to any one of the shower head 16 or the placing table 2 without igniting plasma. A measuring device 204 is configured to measure a physical quantity of the RF power applied by the first RF power supply 10a. A process controller 91 is configured to acquire an inter-electrode distance by using the measured physical quantity of the RF power in a correlation function of the inter-electrode distance and the physical quantity of the RF power.

Abstract: A computer-implemented method, a system, and at least one computer-readable storage device are provided. A measured value related to operation of a device is periodically received for each respective reporting period. If the measured value indicates unhealthy operation of the device, a distance of the measured value from a predetermined abnormal threshold is determined and stored in a data store. Based on the determined distance, a number of most recent reporting periods included in a window is determined. All stored distances determined from measured values received before the window of the most recent reporting periods are deleted from the data store. An occurrence of a device failure is determined based on the stored distances in the data store after the deleting. In response to determining the occurrence of the device failure, an action is performed.

Abstract: A motor noise detecting device according to an embodiment of the present disclosure includes a signal sensing part for sensing an acoustic signal generated from an object to be tested, a data acquisition part for receiving the acoustic signal sensed by the signal sensing part and converting it into an acoustic digital signal, and a data analysis part for receiving and analyzing the acoustic digital signal to perform a detection on whether the object to be tested is abnormal. In addition, the signal sensing part includes an AE (Acoustic Emission) sensor for sensing an elastic wave included in the acoustic signal, and the data analysis part generates result data of analyzing the acoustic digital signal, analyzes the generated result data through a pre-learned model, and detects whether the object to be tested is abnormal.

Abstract: A design method of aero-engine on-line optimization and multivariable control based on model prediction control realizes aero-engine multivariable control and on-line optimization according to thrust, rotational speed and other needs under the condition of meeting constraints. The first part is a prediction model acquisition layer that continuously establishes a small deviation linear model of an aero-engine near different steady state points based on the actual operating state of the aero-engine in each control cycle and external environment parameters and that supplies model parameters to a controller; and the second part is a control law decision-making layer which is a closed loop structure that consists of a model prediction controller and an external output feedback. The model prediction controller determines the output of the controller at next moment by solving a linear optimization problem according to an engine model in the current state, a control instruction and relevant constraints.

Abstract: An anomaly detecting device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations includes: when first series data are input, extracting a series feature amount being a feature amount of a signal included in the first series data; calculating a series probability distribution being a probability distribution which the series feature amount follows; storing a reference probability distribution being a probability distribution designated as a reference for the series feature amount in the first series data; calculating a state feature amount representing a fluctuation condition of the series probability distribution with respect to the reference probability distribution; and detecting an anomaly of the first series data, based on a plurality of the state feature amounts calculated from the first series data.

Abstract: A technique for performing data parallel training of a neural network model is disclosed that incorporates batch normalization techniques using partial populations to generate normalization parameters. The technique involves processing, by each processor of a plurality of processors in parallel, a first portion of a sub-batch of training samples allocated to the processor to generate activations for the first portion of the sub-batch. Each processor analyzes the activations and transmits statistical measures for the first portion to an additional processor that reduces the statistical measures from multiple processors to generate normalization parameters for a partial population of the training samples that includes the first portion from each of the plurality of processors. The normalization parameters are then transmitted back to each of the processors to normalize the activations for both the first portion and a second portion of the sub-batch of training samples allocated to each processor.

Abstract: Generating fault indications for an additive manufacturing machine based on a comparison of the outputs of multiple process models to measured sensor data. The method receiving sensor data from the additive manufacturing machine during manufacture of at least one part. Models are selected from a model database, each model generating expected sensor values for a defined condition. Difference values are computed between the received sensor data and an output of each of the models. A probability density function is computed, which defines, for each of the models, a likelihood that a given difference value corresponds to each respective model. A probabilistic rule is applied to determine, for each of the models, a probability that the corresponding model output matches the received sensor data. An indicator is output of a defined condition corresponding to a model having the highest match probability.

Abstract: A method for prediction of key performance parameters of an aero-engine in transition condition. Bench test data for an aero-engine in transition condition provided by a research institute is used for establishing a training dataset and a testing dataset first; parameter combination is used for predicting and analyzing engine exhaust temperature based on the idea of information fusion; and the method of rolling windows is used for rolling learning in order to predict the parameters such as low pressure rotor speed and exhaust temperature of an engine from the perspective of practical engineering application.

Abstract: An output device with which an operator can understand a progress state of machine learning from evaluation function values is provided. The output device includes: an information acquisition unit that acquires a plurality of evaluation function values which use servo data or are calculated using the servo data from a machine learning device that performs machine learning with respect to a servo control device that controls a servo motor that drives a shaft of a machine tool, a robot, or an industrial machine; and an output unit that outputs the plurality of acquired evaluation function values. The output unit may include a display unit that displays the plurality of evaluation function values on a display screen.

Abstract: The subject technology receives code corresponding to a neural network (NN) model, the code including particular operations that are performed by the NN model. The subject technology determines, among the particular operations, a set of operations that are to be allocated to a cache of the electronic device that is to execute the NN model. The subject technology generates a set of cache indicators corresponding to the determined set of operations. The subject technology compiles the code and the generated set of cache indicators to provide a compiled binary for the NN model to execute on a target device.

Abstract: Systems and methods for controlling a fluid-based system are disclosed. The systems and methods may include generating a model output using a model processor, processing a model input vector and setting a model operating mode, and setting dynamic states of the model processor, the dynamic states input to an open loop model based on the model operating mode. Synthesized parameters are generated as a function of the dynamic states and the model input vector based on a series of utilities, where at least one of the utilities is a configurable utility including one or more sub-utilities. An estimated state of the model is determined based on at least one of a prior state and the synthesized parameters. An actuator associated with the control device is directed as a function of a model output, where the model output includes an estimated thrust value for the control device.

Abstract: In some embodiments, an apparatus and a system, as well as a method and an article, may operate to receive parameters for a first node of a network, the network including a plurality of segments through which an object is to be routed and a plurality of nodes, including the first node, representative of intersections of two or more segments of the plurality of segments; to generate segment lengths for segments between the first node and neighboring nodes to identify a nearest neighboring node with a shortest segment length relative to the first node; and to repeat operations of receiving parameters, generating segment lengths, and identifying nearest neighboring nodes until a route has been identified between a first endpoint and a second endpoint of the network. Additional apparatus, systems, and methods are disclosed.

Abstract: A principal component calculating unit (13) for calculating a principal component of a plurality of sensor data collected from a device, and a physical quantity for failure determination calculating unit (11) for calculating a physical quantity to be used for failure determination on the basis of the plurality of sensor data are provided. Further, an operation state classification unit (14) for generating classification, for each operation state, of the sensor data collected from the device, using the principal component calculated by the principal component calculating unit (13) and the physical quantity calculated by the physical quantity for failure determination calculating unit (11) is provided.

Abstract: A method for foreign object debris detection in a gas turbine engine may comprise receiving, by a controller, a plurality of master configuration parameters, receiving, by the controller, a plurality of individual configuration parameters in response to the plurality of master configuration parameters, receiving, by the controller, a first time-series data from a database, pre-processing, by the controller, the first time-series data to generate a second time-series data, implementing, by the controller, an anomaly detector model, the anomaly detector model configured to generate a third time-series data, and implementing, by the controller, a foreign object debris (FOD) damage model, the FOD damage model receiving the third time-series data. The pre-processing the first time-series data, the implementing the anomaly detector model, and the implementing the FOD damage model may be defined by the plurality of individual configuration parameters.

Abstract: A control device includes feature amount generating means for generating a feature amount suitable for detecting an anomaly that occurs in a control target from data that relates to the control target, machine learning means for carrying out machine learning using the feature amount generated by the feature amount generating means, anomaly detecting means for detecting the anomaly, based on the feature amount generated by the feature amount generating means and an anomaly detection parameter determined based on a learning result of the machine learning and used in detection of the anomaly that occurs in the control target, instructing means for instructing the anomaly detecting means to perform detection of the anomaly, and data compressing means for data-compressing the feature amount generated by the feature amount generating means, and providing the data-compressed feature amount to the machine learning means and the anomaly detecting means.

Abstract: A system and method for creating and making use of customer profiles, including energy consumption patterns. Devices within a service point, using the active load director, may be subject to control events, often based on customer preferences. These control events cause the service point to use less power. Data associated with these control events, as well as related environment data, are used to create an energy consumption profile for each service point. This can be used by the utility to determine which service points are the best targets for energy consumption. In addition, an intelligent load rotation algorithm determines how to prevent the same service points from being picked first each time the utility wants to conserve power.

Abstract: A path planning method of an intelligent robot includes: (1) dividing the operating space into a plurality of rectangular virtual regions having areas of n*m square meters; (2) controlling the intelligent robot to traverse each rectangular virtual region with bow-shaped behavior; (3) when moving in bow-shape, building a raster map with the distance information acquired by distance information sensor, angle information acquired by angle information sensor, collision information acquired by collision detection sensor and obstacle information acquired by obstacle detection sensor, and marking the pass points, obstacle points and collision points; (4) analyzing the raster map in real time to judge if the entire operating space has been fully traversed: if so, moving to step (5); otherwise, returning to step (2); (5) controlling the intelligent robot to make an alongst behavior, and marking the alongst behavior points on the raster map.

Abstract: The present invention belongs to the technical field of health monitoring for civil structures, and a dynamically non-Gaussian anomaly identification method is proposed for structural monitoring data. First, define past and current observation vectors for the monitoring data and pre-whiten them; second, establish a statistical correlation model for the whitened past and current observation vectors to obtain dynamically whitened data; then, divide the dynamically whitened data into two parts, i.e., the system-related and system-unrelated parts, which are further modelled by the independent component analysis; finally, define two statistics and determine their corresponding control limits, respectively, it can be decided that there is anomaly in the monitoring data when each of the statistics exceeds its corresponding control limit.

Abstract: The life expectancy of a component of a vehicle that is being observed is predicted. A processing unit is fed with status data of components of selected vehicles. Moreover, the processing unit is fed with an operating parameter for each of the components of the selected vehicles. The operating parameter influences the status data of the respective component. The processing unit determines a function between the operating parameter and the status data for each of the selected components. One function, which fits best for the component of the observed vehicle, is selected by an algorithm. The processing unit is fed with an operating parameter of the component of the observed vehicle. The processing unit predicts the life expectancy of the component of the observed vehicle using the selected function and the operating parameter of the component of the observed vehicle.

Abstract: Systems, methods, and non-transitory computer-readable media can be configured to perform receiving a notification of a maintenance event associated with a resource. The method includes retrieving historic maintenance data in relation to the resource with which the fault is associated, the maintenance information originating from a time period preceding the time of the maintenance event. The method includes identifying at least a portion of the retrieved historic maintenance data as being indicative of the maintenance event. The method also includes causing the portion of the retrieved historic maintenance data identified as being indicative of the maintenance event to be stored as a precursor signal of the maintenance event. The method also includes causing future maintenance data received from a plurality of resources related to the resource with which the maintenance event is associated to be monitored to predict a future occurrence of the maintenance event in the plurality of resources.

Abstract: A cooker hotplate control system, to heat to and maintain a foodstuff at a preset temperature the system comprising an electric hotplate; a power input to provide electricity to heat the hot plate and a controller to govern said power input; a temperature sensor to determine the temperature of the hotplate; an infrared sensor spatially separated from and to detect infrared radiation emitted by a foodstuff or a vessel containing a foodstuff on the hotplate; a first processor to determine the temperature of a foodstuff or a vessel from the detected infrared radiation and a first data storage means to store said data; a second processor, the second processor calculating the first and second time derivatives of the temperature data; a first fuzzy logic controller receiving as input the first and second time-derivative data from the second processor and producing an output to the controller, said output governing the amount of power supplied to the hotplate, the first fuzzy logic controller being active to bring a

Abstract: Regularization of neural networks. Neural networks can be regularized by obtaining an original neural network having a plurality of first-in-first-out (FIFO) queues, each FIFO queue located between a pair of nodes among a plurality of nodes of the original neural network, generating at least one modified neural network, the modified neural network being equivalent to the original neural network with a modified length of at least one FIFO queue, evaluating each neural network among the original neural network and the at least one modified neural network, and determining which neural network among the original neural network and the at least one modified neural network is most accurate, based on the evaluation.

Abstract: A method of processing sensor logs is described. The method includes accessing a first sensor log and a corresponding first reference log. Each of the first sensor log and the first reference log includes a series of measured values of a parameter according to a first time series. The method also includes accessing a second sensor log and a corresponding second reference log. Each of the second sensor log and the second reference log includes a series of measured values of a parameter according to a second time series. The method also includes dynamically time warping the first reference log and/or and second reference log by a first transformation between the first time series and a common time-frame and/or a second transformation between the second time series and the common time-frame. The method also includes generating first and second warped sensor logs by applying the or each transformation to the corresponding ones of the first and second sensor logs.

Abstract: A plant control system comprises a target value calculating part calculating a target value r of a control output x of a plant, a target value correcting part correcting the target value so as to calculate a corrected target value w, and a feedback controller determining a control input. The target value correcting part, if making the control output change to the target value, sets the corrected target value so that an amount of correction of the target value becomes equal to or less than a predetermined value, then changes the corrected target value so that the amount of correction of the target value becomes larger than the predetermined value, then changes the corrected target value so that the amount of correction of the target value becomes equal to or less than the predetermined value before the control output reaches the target value.

Abstract: According to one embodiment, a sensor failure diagnosis device includes a drift estimator and a global rank determiner. The drift estimator estimates, based on data on measured values from sensors contained in a plurality of sensor groups including a sensor under inspection, whether or not drift failure that is steady deviation of a measured value from a true value has occurred in the sensor under inspection or a degree of the drift failure. The global rank determiner determines global ranks that are priorities of the plurality of sensor groups in the inspection based on a plurality of estimated results by the drift estimator.

Abstract: Embodiments are described for detecting a data organization issue in a storage system by analyzing static and dynamic layout characteristics for data stored in the storage system, workload characteristics for applications utilizing the data, virtualization effects of the storage system on the organization of the data, input/output characteristics of processes storing the data in the storage system, and cache usage characteristics of the data. For fragmentation issues, the system uses the analysis to provide defragmentation advisories to reduce fragmentation by at least one of: re-layout or re-tiering of the data in the data storage system, or cache memory reconfiguration.

Abstract: Systems and methods for controlling a fluid-based system are disclosed. The systems and methods may include a model processor for generating a model output, the model processor including a set state module for setting dynamic states, the dynamic states input to an open loop model based on the model operating mode, where the open loop model generates current state derivatives, solver state errors, and synthesized parameters as a function of the dynamic states and a model input vector. A constraint on the state derivatives and solver state errors is based a series of utilities that are based on mathematical abstractions of physical laws that govern behavior of the component. The model processor may include an estimate state module for determining an estimated state of the model based on at least one of a prior state, the current state derivatives, the solver state errors, and the synthesized parameters.

Abstract: A mobile radar system for visualizing forward looking topography is configured with at least two phased-array antennas to form a forwarding looking phased-array interferometer.

Abstract: Systems, methods, and computer-readable media are disclosed for customization of user profiles. The systems, methods, and computer-readable media described herein may improve user experiences and speed of operation. In an example embodiment described herein, a method may include providing to a first device from a second device, data associated with a first user account, the data associated with the first user account comprising first user profile data for a first user profile associated with the first user account, wherein the first user profile data comprises first historical data, first one or more recommended products, or first one or more user preferences and second user profile data for a second user profile associated with the first user account, wherein the second user profile data comprises second historical data, second one or more recommended products, or second one or more user preferences.

Abstract: A system for generating a graphical user interface in a client device. The system may include a processor in communication with the client device and a database. The processor may execute: receiving a request for occupancy information of a specified merchant; obtaining a plurality of credit card authorizations associated with the merchant; generating a posted transaction array based on the credit card authorizations; removing outlier members of the posted transaction array by applying a threshold filter; generating a transaction frequency array based on the posted transaction array, the transaction frequency array comprising weekdays and aggregated transactions associated with the weekdays; modifying the transaction frequency array by applying a transformation to the aggregated transactions; generating a smoothed array by applying a kernel density estimate to the transaction frequency array; and generating a graphical user interface displaying information in the smoothed array.

Abstract: A plant control device of the present invention includes a register configured to register a simulated dangerous condition which is a simulated representation of an operation condition under which a plant is dangerous, a first acquirer configured to acquire an operation condition of the plant, a learner configured to learn the operation condition acquired and the simulated dangerous condition registered and produce an operation model of the plant, a determiner configured to determine an operation parameter of the plant on the basis of the operation condition acquired and the operation model produced, and an instructor configured to instruct an operation of the plant on the basis of the operation parameter determined.

Abstract: A method includes aggregating multiple zones of an indoor structure, each zone having associated comfort limits, formulating an aggregated single zone model predictive control (MPC) problem representative of the multiple zones for a heating ventilation and air conditioning (HVAC) system, determining optimal aggregated actions as a function of the aggregated single zone model predictive control problem, simulating an optimal trajectory of indoor qualities, and determining zone temperature setpoints to comply with the comfort limits for each zone and pre-cool the indoor structure.

Abstract: A method for performing an earth formation borehole-related task includes: calculating a contribution to stress at each grid cell volume of interest in a geo-cellular model from other grid cell volumes that are at elevations above the grid cell volume of interest by use of the Mindlin Formulation using difference values between actual and linear approximation density values and Poisson's ratio values; adding all contributions to the stresses from all other grid cell volumes that are at elevations above the grid cell volume of interest to provide a stress tensor correction; adding first approximation of stress tensor components to the stress tensor correction to provide a total stress value; constructing a resulting stress tensor for the earth formation using the total stress values for the grid cell volumes of interest; and performing the borehole-related task using borehole-related equipment and the resulting stress tensor for the earth formation.

Abstract: A method and system for creating contact center models are described. Model parameters may be derived from and optimized using historical data. The model parameters may be used to construct an analytic model, which said analytic model may be used to create a contact center model using the optimized parameters. In an embodiment, a distribution may be determined that is demonstrative of a virtual representation of the historical environment of the contact center operation environment at different time intervals. The distribution may be used to transform inputs where there is a discrepancy between the simulation model time interval and the time interval for a generated forecast.

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 method of estimating a number of persons gathered at an Area of Interest during an observation time interval on a day, wherein the Area of Interest is covered by a mobile telecommunication network including plural communication stations each of which is configured to manage communications of User Equipment in one or more served areas in a covered geographic region over which the mobile telecommunication network provide services.

Abstract: A method of estimating a number of persons gathering at an Area of Interest during a time interval on a day, wherein the Area of Interest is defined by an Area of Interest center and an Area of Interest radius and is covered by a mobile telecommunication network including plural communication stations each of which is configured to manage communications of user equipment in one or more served areas in a covered geographic region over which the mobile telecommunication network extends.

Abstract: A system executing a closed loop control on data for cloud-based applications includes an industrial automation device configured to generate cloud variables, a cloud-based application on a network device with cloud-computing infrastructure, an industrial controller controlling the industrial automation device by a user-defined program which receives the cloud variables, a cloud agent communicating with the user-defined control program and the cloud-based application. The cloud agent collects the cloud variables and sends them to the cloud-based application. The cloud-based application determines updated optimized cloud variables and notifies the cloud agent with the updated optimized cloud variables. The cloud agent reloads the updated optimized cloud variables and notifies the user-defined control program with the updated optimized cloud variables.

Abstract: A system for providing a computer language with which to write rules is provided. The system may include a rules container, a rules classes container and an engine/graph. The rules classes container may provide a code library of rules and unit test from which to inherit. The system may also include a rules GUI that may accept code of a rule in a code field window. The rules GUI may also include a documentation presentation window. The documentation presentation window may include a non-editable, reader-friendly view of the rule. Viewing the documentation window adjacent to the code field window may enable a user to understand the code and edit the code. Each rule may depend from another rule or provide a dependency for another rule. The system may save the rules into the rules container. The engine/graph may create a graph of the rules documentation based on the dependencies.

Abstract: An action recognition system and method are provided. The action recognition system includes an image capture device configured to capture an actual image depicting an object. The action recognition system includes a processor configured to render, based on a set of 3D CAD models, synthetic images with corresponding intermediate shape concept labels. The processor is configured to form a multi-layer CNN which jointly models multiple intermediate shape concepts, based on the rendered synthetic images. The processor is configured to perform an intra-class appearance variation-aware and occlusion-aware 3D object parsing on the actual image by applying the CNN thereto to generate an image pair including a 2D and 3D geometric structure of the object. The processor is configured to control a device to perform a response action in response to an identification of an action performed by the object, wherein the identification of the action is based on the image pair.