Abstract: An intelligent audio analytic apparatus (IAAA) and method for space system. The IAAA comprises a processor, a computer readable medium, and a communication module. The instructions include audio data processing algorithms configured to identify and predict impending anomalies associated with the space system using at least one neural network.

Abstract: The present technology is directed to dynamically adjusting an autonomous vehicle (AV) system based on deep learning optimizations. An AV management system can generate a downscaling signal based on a result of comparing a complexity of an environment for an AV to navigate with a predetermined complexity threshold. Further, the AV management system can perform a downscaling of a neural network associated with an AV system based on the downscaling signal and determine a scenario to test the downscaled neural network in a simulation. The AV management system can adjust one or more parameters of the AV system based on simulated outputs and perform the simulation of the AV based on the adjusted one or more parameters of the AV system and the downscaled neural network to generate simulated performance data. Furthermore, the AV management system can compare the simulated performance data with a predetermined performance threshold.

Abstract: Drive envelope determination is described. In an example, a vehicle can capture sensor data while traversing an environment and can provide the sensor data to computing system(s). The sensor data can indicate agent(s) in the environment and the computing system(s) can determine, based on the sensor data, a planned path through the environment relative to the agent(s). The computing system(s) can also determine lateral distance(s) to the agent(s) from the planned path. In an example, the computing system(s) can determine modified distance(s) based at least in part on the lateral distance(s) and information about the agents. The computing system can determine a drive envelope based on the modified distance(s) and can determine a trajectory in the drive envelope.

Abstract: The feedback control device takes information regarding a control deviation between a measured value and a target value of a controlled object as input, and outputs a control amount for the controlled object; comprising: a first control unit that takes information regarding the control deviation as input, and outputs a first control amount for the controlled object; a second control unit that takes information regarding the control deviation as input and outputs a second control amount for the controlled object, and in which a parameter for calculating the second control amount is determined by machine learning; an operation unit that operates the controlled object using the first control amount output from the first control unit and the second control amount output from the second control unit; and a sampling unit for thinning out at a predetermined period information regarding the control deviation input to the second control unit.

Abstract: Computer-implemented methods for training a neural network, as well as for implementing audio encoders and decoders via trained neural networks, are provided. The neural network may receive an input audio signal, generate an encoded audio signal and decode the encoded audio signal. A loss function generating module may receive the decoded audio signal and a ground truth audio signal, and may generate a loss function value corresponding to the decoded audio signal. Generating the loss function value may involve applying a psychoacoustic model. The neural network may be trained based on the loss function value. The training may involve updating at least one weight of the neural network.

Abstract: The present invention reduces the probability of malfunction occurrence when performing predictive control of a device being controlled. In this control device of one aspect of the present invention, a prediction model for a control variable is used to calculate a prediction value from a measured value of the control variable, and a desired command value of the control variable is determined by correcting a desired basic value in accordance with the calculated prediction value. The degree of correction is determined on the basis of weight. The control device controls the operation of the device being controlled according to the determined desired command value. The control device assesses whether the device being controlled is operated appropriately on the basis of monitoring data relating to the operation result of the device being controlled, and optimizes the weight of the correction to make appropriate control possible based on the assessment result.

Abstract: An edge computing device is provided that includes a plurality of input electrodes that are communicatively coupled to one or more communication channels of a programmable logic controller that implements control logic to control a controlled device. The edge computing device furthers include a processor configured to, at a training time, receive signals via the plurality of input electrodes, detect inputs to the one or more communication channels and outputs from the one or more communication channels of the programmable logic controller, generate a set of training data based on the detected inputs and outputs of the programmable logic controller, and train an artificial intelligence model using the generated set of training data. The processor is further configured to, at a run-time, emulate the control logic of the programmable logic controller using the trained artificial intelligence model.

Abstract: Provided are an integrated circuit chip apparatus and a related product, the integrated circuit chip apparatus being used for executing a multiplication operation, a convolution operation or a training operation of a neural network. The present technical solution has the advantages of a small amount of calculation and low power consumption.

Abstract: A decoding method and apparatus in an artificial neural network for speech recognition. The decoding method in the artificial neural network for speech recognition includes performing a first decoding task of decoding a feature including speech information and at least one token recognized up to current time, using a shared decoding layer included in the artificial neural network, performing a second decoding task of decoding the at least one token, using the shared decoding layer, and determining an output token to be recognized subsequent to the at least one token based on a result of the first decoding task and a result of the second decoding task.

Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.

Abstract: Computer implemented methods and systems are provided for training a machine learning architecture for surgical performance tracking and measurement based on surgical procedure video data set. The methods and systems include, in a first aspect, a sequential relation architecture and a dimensionality reduction architecture. In a second aspect, the methods and systems include a surgical instrument instance segmentation architecture, a decomposition model, and a sequential relation architecture. The video data is processed on a frame level to generate compressed or reduced representations of the video data.

Abstract: A non-transitory, computer-readable recording medium stores a program of reinforcement learning by a state-value function. The program causes a computer to execute a process including calculating a temporal difference (TD) error based on an estimated state-value function, the TD error being calculated by giving a perturbation to each component of a feedback coefficient matrix that provides a policy; calculating based on the TD error and the perturbation, an estimated gradient function matrix acquired by estimating a gradient function matrix of the state-value function with respect to the feedback coefficient matrix for a state of a controlled object, when state variation of the controlled object in the reinforcement learning is described by a linear difference equation and an immediate cost or an immediate reward of the controlled object is described in a quadratic form of the state and an input; and updating the feedback coefficient matrix using the estimated gradient function matrix.

Abstract: A method for operating a heating device for thermal conditioning preforms made of a thermoplastic material in which each respective one of the preforms is prepared for a subsequent forming process during which the preforms are formed into containers with a forming fluid fed under pressure into the preforms. The heating device is operated in at least a first operating state and a second operating state. The second operating state is a startup phase of the heating device during which a temperature of the heating device approaches an equilibrium temperature of a thermodynamically stable equilibrium state of the heating device. The first operating state is a continuous operation state following the startup phase. The second operating state is operated with a heating output value that varies over time. Furthermore, the invention relates to a heating device and a machine having a heating device, which are configured to implement the method.

Abstract: A system for stimulating a well extending through a subterranean earthen formation includes a surface pump configured to pressurize a well stimulation fluid to a current surface pressure measurable by a surface sensor package, a well stimulation line extending between the surface pump and a wellhead positioned at an upper end of the well, wherein the well stimulation line is configured to flow the well stimulation fluid into the well, and a monitoring system in signal communication with the surface sensor package and including a screen-out predictor module stored in a memory of the monitoring system, wherein the screen-out predictor module is configured to predict a future surface pressure of the well stimulation fluid based on the current surface pressure measured by the surface sensor package, and wherein the monitoring system is configured to provide an indication of the predicted future surface pressure of the well stimulation fluid.

Abstract: A machine learning system that includes three machine learning models implemented in a hardware processor, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the three machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module is implemented in hardware and receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.

Abstract: Provided are embodiments for a system for designing a layout for a smoke detection system, the system include a storage medium, the storage medium being coupled to a computing engine. The computing engine is configured to receive one or more inputs, model transport and dispersion of smoke in an environment based on the one or more inputs, wherein the model is based on a computational fluid dynamics (CFD) function, and detect the smoke using a plurality of probes. The computing engine is also configured to define a layout of the smoke detectors based on the smoke detectors being able to detect the smoke in the environment, and provide a map of the smoke detectors for the layout. Also provided are embodiments for a method to design a layout for a smoke detection system.

Abstract: The invention relates to a field off artificial intelligence (AI) technologies, and discloses a method and an apparatus for high-order iterative self-learning control for a robotic fish, and a storage medium; the control method performs preferential iterative calculation on control gain elements in the control gain set to obtain a target control gain set; and performs high-order iterative calculation according to the target control gains, the first control input thrust and the first tracking error to obtain a target control input thrust, and then controls a robotic fish to swing according to the target control input thrust to obtain an expected speed. In this way, complete tracking and rapid convergence of a swim speed of a robotic fish in the whole operation space may be achieved.

Abstract: In order to track a mobile body in an efficient manner, a server collects passage trail information relating to a mobile body to be tracked from a camera provided in an information-centric network to thereby track the mobile body. Specifically, the server transmits a request message which designates a search area and a search period to the information-centric network, requesting the information-centric network to provide passage trail information relating to the mobile body, the passage trail information being acquired by the camera; receives a response message including the passage trail information; and collects the passage trail information associated with the search area and the search period designated by the request message to thereby generate tracking information.

Abstract: One or more first parameters associated with an electronic device manufacturing process are monitored. An artificial neural network associated with the one or more first parameters is determined. One or more second parameters are determined using the artificial neural network. The one or more first parameters are adjusted using the one or more second parameters.

Abstract: A machine learning device that performs reinforcement learning with respect to a servo control apparatus that controls target device having a motor, including: outputting action information including adjustment information of coefficients of a transfer function of a controller gain to a controller included in the servo control apparatus; acquiring, from the servo control apparatus, state information including a deviation between an actual operation of the target device and a command input to the controller, a phase of the motor, and the coefficients of the transfer function of the controller gain when the controller operates the target device based on the action information; outputting a value of a reward in the reinforcement learning based on the deviation included in the state information; and updating an action-value function based on the value of the reward, the state information, and the action information.

Abstract: Some embodiments of the invention provide efficient, expressive machine-trained networks for performing machine learning. The machine-trained (MT) networks of some embodiments use novel processing nodes with novel activation functions that allow the MT network to efficiently define with fewer processing node layers a complex mathematical expression that solves a particular problem (e.g., face recognition, speech recognition, etc.). In some embodiments, the same activation function (e.g., a cup function) is used for numerous processing nodes of the MT network, but through the machine learning, this activation function is configured differently for different processing nodes so that different nodes can emulate or implement two or more different functions (e.g., two or more Boolean logical operators, such as XOR and AND). The activation function in some embodiments is a periodic function that can be configured to implement different functions (e.g., different sinusoidal functions).

Abstract: A Building Automation Monitor and Control System (BAMCS) can discover building automation control devices operating on various communication protocols, and can enable a user to control multiple building automation control devices that use different communication protocols through a single user interface. A dealer can create a user site, discover building automation control devices, and sell a license to a user to be able to access a site control module over the internet.

Abstract: Node controllers in power distribution networks in accordance with embodiments of the invention enable dynamic frequency control. One embodiment includes a node controller comprising a network interface a processor; and a memory containing a frequency control application; and a plurality of node operating parameters describing the operating parameters of a node, where the node is selected from a group consisting of at least one generator node in a power distribution network wherein the processor is configured by the frequency control application to calculate a plurality of updated node operating parameters using a distributed process to determine the updated node operating parameter using the node operating parameters, where the distributed process controls network frequency in the power distribution network; and adjust the node operating parameters.

Abstract: Document consumption and value add service techniques and systems are described. In one example, a digital medium environment is configured to control availability of a value add service to consumers of a document. Consumption data is collected from a plurality of client devices. The consumption data describes characteristics of consumption of the document by respective client devices. A readership index is calculated that describes an amount of overall consumption of the document by the plurality of client devices. Responsive to a determination by the computing device that the readership index has exceeded a threshold, the value add service that relates to the document is exposed for interaction by at least one of the plurality of client devices.

Abstract: An adaptive hybrid control method and apparatus are provided for performing active queue management in a data packet routing device which adaptively combines fuzzy controller logic, alone or in combination with RBF-PID control logic, to provide improved management of network congestion by applying a nonlinear model for buffer utilization to at least a buffer size measure for the target buffer to generate at least a fuzzy membership function adjustment signal, and then supplying the fuzzy membership function adjustment signal to a first controller to automatically tune membership function parameters of the first controller, where the first controller calculates a first packet select probability value for the data packet based at least partly on the fuzzy membership function adjustment signal and an error measure between the buffer size setpoint and the buffer size measure.

Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.

Abstract: Aspects of a neural network convolution device are described herein. The aspects may include a matrix transformer and a matrix multiplication module. The matrix transformer may be configured to receive an input data matrix and a weight matrix, transform the input data matrix into a transformed input data matrix based on a first transformation matrix, and transform the weight matrix into a transformed weight matrix based on a second transformation matrix. The matrix multiplication module may be configured to multiply one or more input data elements in the transformed input data matrix with one or more weight elements in the transformed weight matrix to generate an intermediate output matrix. The matrix transformer may be further configured to transform the intermediate output matrix into an output matrix based on an inverse transformation matrix.

Abstract: A method and system are disclosed for optimizing load scheduling for a power plant having one or more power generator units. An exemplary method and corresponding system can involve detecting an event indicative of a need for adapting one or more constraints for an objective function used in load scheduling. On such detection, the objective function is analysed to determine adaptive constraint values for the one or more constraints for optimally solving the objective function. These adaptive constraint values can be used to solve the objective function and the solution of the objective function with the one or more adapted constraint values can be used to operate the one or more power generation units of the power plant.

Abstract: A neural network unit (NNU) includes N neural processing units (NPU). Each NPU has an arithmetic unit and an accumulator. First and second multiplexed registers of the N NPUs collectively selectively operate as respective first and second N-word rotaters. First and second memories respectively hold rows of N weight/data words and provide the N weight/data words of a row to corresponding ones of the N NPUs. The NPUs selectively perform: multiply-accumulate operations on rows of N weight words and on a row of N data words, using the second N-word rotater; convolution operations on rows of N weight words, using the first N-word rotater, and on rows of N data words, the rows of weight words being a data matrix, and the rows of data words being elements of a convolution kernel; and pooling operations on rows of N weight words, using the first N-word rotater.

Abstract: An interactive assistance system and method for computer-aided control optimization for a technical system is provided. For example, a gas or wind turbine, in particular for optimizing the action sequence or the control variables of the plant (e.g. gas supply, compression), wherein an input terminal is provided for reading at least one status parameter providing a first system status of the technical system, and at least one setting parameter for adapting a reward function. A simulation module having a pre-trained neuronal network, simulating the plant, serves to simulate an action sequence on the technical system, starting from the first system status and to the prediction of the resulting statuses of the technical system.

Abstract: A control system that corrects differential pressure measurements with downhole annulus pressure information is disclosed. When differential pressure is zeroed with the BHA off-bottom, the annulus pressure value is baselined. During drilling, a controller receives surface differential pressure measurements and annulus pressure measurements. As the controller receives each new annulus pressure measurement, it compares it to the baseline annulus pressure value to obtain a different annulus pressure value. The controller corrects the surface differential pressure measurements with the annulus pressure measurements. As the controller receives each new surface differential pressure measurement, it subtracts out the current difference annulus pressure value. As a result, the modified surface differential pressure measurement remains a reflection of mud motor performance that removes the influence of the increased density of the fluid, thereby improving autodrilling control.

Abstract: In one embodiment, a device in a network maintains a machine learning-based recursive model that models a time series of observations regarding a monitored entity in the network. The device applies sparse dictionary learning to the recursive model, to find a decomposition of a particular state vector of the recursive model. The decomposition of the particular state vector comprises a plurality of basis vectors. The device determines a mapping between at least one of the plurality of basis vectors for the particular state vector and one or more human-readable interpretations of the basis vectors. The device provides a label for the particular state vector to a user interface. The label is based on the mapping between the at least one of the plurality of basis vectors for the particular state vector and the one or more human-readable interpretations of the basis vectors.

Abstract: Devices and methods are provided for processing network nodes. For example, a sorting request is detected; one or more first network nodes to be sorted are acquired corresponding to the sorting request; a first characteristic matrix is constructed based on at least information associated with the first network nodes; association information between the first network nodes is acquired; a sparse matrix is constructed based on at least information associated with the association information between the first network nodes; iterative multiplication is performed on the sparse matrix and the first characteristic matrix to obtain a second characteristic matrix upon convergence; and the first network nodes are sorted based on at least information associated with the second characteristic matrix.

Abstract: A method for commissioning a sensor series circuit configured in a daisy chain topology. A second sensor being downstream from a first sensor. The method includes furnishing a first switch signal to the first sensor to close the first switch, the first switch signal being furnished in response to a successful initialization of the first sensor, monitoring a function of the second sensor during initialization of the second sensor to ascertain whether the second sensor exhibits a fault upon initialization or is initialized correctly, and to furnish a fault signal if it is ascertained that the second sensor exhibits a fault upon initialization; and outputting a suppression signal to the first sensor if the fault signal has been furnished, to prevent the first switch from being closed.

Abstract: Flow balancing includes selecting, for each down hole flow control valve of a well, a transformed well performance curve corresponding to a first down hole flow control valve pressure to obtain transformed well performance curves. The well includes a lateral including the down hole flow control valves. Using a constraint set that includes a balancing condition for the lateral, a network optimization analysis is performed on the transformed well performance curves to generate a set of choke positions corresponding to each down hole flow control valve. Network modeling of the well is performed based on the set of choke positions to obtain a second down hole flow control valve pressure for each down hole flow control valve. Using the set of choke positions, a field operation is performed for the well based on the second down hole flow control valve pressure being within a threshold difference of the first down hole flow control valve pressure for each down hole flow control valve.

Abstract: A method for browsing a collection of digital images on a soft-copy display comprising: receiving a collection of digital images; interactively user selecting a digital image using a user interface; determining a plurality of subsets of the digital images, wherein each subset shares a common category with the selected digital image; and displaying the subsets of digital images on the soft-copy display, together with the selected digital image.

Abstract: Examples described herein involve detecting known impairments or other known conditions using a neural network. An example implementation involves receiving data indicating a response of a playback device as captured by a microphone. The implementation also involves determining an input vector by projecting a response vector that represents the response of the playback device onto a principle component matrix representing variance caused by one or more known impairments. The implementation further involves providing the determined input vector to a neural network that includes an output layer comprising neurons that correspond to respective known impairments.

Abstract: In one embodiment, techniques are shown and described relating to learning machine based computation of network join times. In particular, in one embodiment, a device computes a join time of the device to join a computer network. During joining, the device sends a configuration request to a server, and receives instructions whether to provide the join time. The device may then provide the join time to a collector in response to instructions to provide the join time. In another embodiment, a collector receives a plurality of join times from a respective plurality of nodes having one or more associated node properties. The collector may then estimate a mapping between the join times and the node properties and determines a confidence interval of the mapping. Accordingly, the collector may then determine a rate at which nodes having particular node properties report their join times based on the confidence interval.

Abstract: A technique for detecting full-system idle state in an adaptive-tick kernel includes detecting non-timekeeping CPU idle state, initiating a hysteresis period, waiting for the hysteresis period to end, manipulating a data structure whose state indicates whether a scheduling clock tick may be disabled on all CPUs, and disabling the scheduling clock tick if the data structure is in an appropriate state. In a first embodiment, non-timekeeping CPUs manipulate a global counter when entering an idle state, but add hysteresis to avoid thrashing the counter. Timekeeping is turned off based on the count maintained on the global counter. In a second embodiment, a Read-Copy Update (RCU) dynticks-idle subsystem running on a timekeeping CPU manipulates a global state variable whose states indicate whether all non-timekeeping CPUs are in an idle state, and if so, for how long. Timekeeping is turned off based on the state of the global state variable.

Abstract: A multi-modal digital terminal adapter (DTA), and associated methods and computer-readable media, are disclosed for determining a current mode of operation of the DTA, selectively activating and/or deactivating one or more receiving modules based at least in part on the current mode of operation, and routing an incoming signal to one or more receiving modules based at least in part on one or more characteristics of the signal to initiate processing of the signal in accordance with the current mode of operation for the multi-modal DTA.

Abstract: A method for automatically tracking multiple objects from a sequence of video images that may extract raw data about participating elements in a sporting, or other event, in a way that does not interfere with the actual participating elements in the event. The raw data may include the position and velocity of the players, the referees, and the puck, as well as the team affiliation of the players. These data may be collected in real time and may include accounting for players moving fast and unpredictably, colliding with and occluding each other, and getting in and out of the playing field. The video sequence, captured by a suitable sensor, may be processed by a suitably programmed general purpose computing device.

Abstract: An apparatus and method are provided for automatically generating a deterministic target differential equation system for evaluating an output differential equation system with stochastic input parameters with a device for providing a weighted sum of orthogonal basic functions inserted into the output differential equation system, which forms a stochastic random variable. A multiplication device for multiplying the output differential equation system by the orthogonal basic functions and an integration device for integrating the output differential equation system which is multiplied by the orthogonal basic functions to generate the deterministic target differential equation system are provided. A control device calculates stochastic output parameters based on the deterministic target differential equation system generated and accordingly controls a mechanical or electronic adjustment element. The apparatus may be suitable for use in a robust regulating and control circuit for regulating an installation, e.g.

Abstract: Methods and systems for reducing the required footprint of SNoW-based classifiers via optimization of classifier features. A compression technique involves two training cycles. The first cycle proceeds normally and the classifier weights from this cycle are used to rank the Successive Mean Quantization Transform (SMQT) features using several criteria. The top N (out of 512 features) are then chosen and the training cycle is repeated using only the top N features. It has been found that OCR accuracy is maintained using only 60 out of 512 features leading to an 88% reduction in RAM utilization at runtime. This coupled with a packing of the weights from doubles to single byte integers added a further 8× reduction in RAM footprint or a reduction of 68× over the baseline SNoW method.

Abstract: A method for aggregate load management includes determining whether a load capacity limit within a utility power network will be exceeded, selecting an aggregated demand reduction target to remain within capacity bounds if the load capacity limit is to be exceeded, selecting a demand reduction strategy, and sending a control signal that includes a randomized PWM level, based on the strategy, to a controller in a load component of the utility system based on the reduction target. A method for component load management includes receiving a control signal from a utility system based on a utility demand reduction strategy, converting the signal into randomized PWM control of the load component in accordance therewith, receiving an updated control signal based on utility system monitoring of an aggregate load of a component of the utility system, and converting the updated signal into randomized PWM control of the load component in accordance therewith.

Abstract: A heat dissipation control system comprises a sensing unit, an artificial neural network computing unit, and two heat dissipation units. The artificial neural network computing unit performs computation for controlling based on a plurality of electronic-device temperatures sent out by the sensing unit. The computation for controlling performs a back propagation algorithm on an objective function which is defined a as the square of an error function. Accordingly, cooling effects suitable for the heat dissipation units are generated in order to achieve an optimum heat dissipation effect.

Abstract: The present invention relates to a control system comprising a control interface between one or more wind turbine generators and a power grid, where the wind turbine generators are coupled to the power grid and contribute to the power production of the grid. The control interface is arranged to receive a set of event data. In embodiments, the set of event data may be any data available to a SCADA system. The set of event data is analyzed in terms of predetermined event rules comprising at least one predefined event condition and a set of adaptive event conditions. Based on the analysis an event output is provided in order to control a parameter of the one or more wind turbine generators. In embodiments, the control system may be implemented in, or in connection with a SCADA system, moreover, the event output may be based on fuzzy logic, a neural network or statistical analysis.

Abstract: A feed forward system includes an input device configured to receive a desired response of the mechanical system and a trainable system configured to generate a feed forward signal that drives the mechanical system based on the desired response. The trainable system is trained based on a plurality of measured responses of the mechanical system.

Abstract: A present invention relates to a novel hybrid intelligent control system and method for power generating apparatuses, in which the control system comprises: a fuzzy sliding mode speed controller, embedded with a fuzzy inference mechanism so as to be used for controlling the speed of a power generating apparatus; and a radial basis function network (RBFN) pitch controller, being embedded with an on-line training RBFN so as to be used for controlling the pitch angle of a turbine coupled to the power generating apparatus. In a variable-speed energy conversion system using the aforesaid control system, the turbine can be driven to operate at its maximum efficiency by adjusting its blade pitch angle in response to the variation of the input flowing into the turbine, while allowing the shaft speed of the power generating apparatus to be controlled by a fuzzy interference mechanism so as to achieve its maximum power output.

Abstract: A control system for optimizing an oxy-fuel power plant comprises an optimizer in communication with the oxy-fuel power plant; the oxy-fuel power plant being operative to recycle carbon dioxide from a flue gas stream to a boiler; a control platform; the control platform being operative to control the oxy-fuel power plant; and a simulator; the simulator being operative to simulate performance of the oxy-fuel power plant.

Abstract: A prediction method that estimates the real-time position of a mobile device based on previously observed data is provided. The present invention can be used in real-time navigation, including providing real-time alerts of an upcoming destination and notifications of emergency events in close geographic proximity. The prediction method utilizes neural networks and/or functions generated using genetic algorithms in estimating the mobile device's real-time position. The prediction method provides reliable Location-Based Services (LBS) in events where traditional positioning technologies become unreliable. It is also seamless, as the user remains unaware of any interruption in accessing the positioning technology.