56 results about "Perceptual system" patented technology

An apparatus and method for training the sensory perceptual system in a language learning impaired (LLI) subject is provided. The apparatus and method incorporates a number of different programs to be played by the subject. The programs artificially process selected portions of language elements, called phonemes, so they will be more easily distinguished by an LLI subject, and gradually improves the subject's neurological processing of the elements through repetitive stimulation. The programs continually monitor a subject's ability to distinguish the processed language elements, and adaptively configures the programs to challenge and reward the subject by altering the degree of processing. Through adaptive control and repetition of processed speech elements, and presentation of the speech elements in a creative fashion, a subject's temporal processing of acoustic events common to speech are significantly improved.

The present invention leverages analysis methods, such as expected value of information techniques, rate-based techniques, and random selection technique, to provide a fusion of low-level streams of input data (e.g., raw data) from multiple sources to facilitate in inferring human-centric notions of context while reducing computational resource burdens. In one instance of the present invention, the method utilizes real-time computations of expected value of information in a greedy, one-step look ahead approach to compute a next best set of observations to make at each step, producing “EVI based-perception.” By utilizing dynamically determined input data, the present invention provides utility-directed information gathering to enable a significant reduction in system resources. Thus, of the possible input combinations, the EVI-based system can automatically determine which sources are required for real-time computation relating to a particular context.

Disclosed is an apparatus and method of constructing a user behavior pattern based on an event log that is a record of events generated in a context-aware system environment. An apparatus and method of constructing a user behavior pattern based on an event log according to an embodiment of the invention intelligently and actively provides the most applicable service in consideration of a specific user and a location thereof to a user, on the basis of a constructed user behavior pattern.

The invention provides a deep learning vision classifying method based on electroencephalogram data. The deep learning vision classifying method based on electroencephalogram data mainly comprises electroencephalogram data acquisition, electroencephalogram learning, electroencephalogram feature extracting and automatic classifying. The process of the method comprises the following steps: learning a brain activity vision classifying manifold with recognition capability by electroencephalogram data induced by a visual object stimulating factor and a recurrent neural network; then training a regressor based on a convolutional neural network; mapping an image to a learned manifold; and finally, carrying out automated vision classifying task through a computer by features based on human brain to obtain an image classifying result. Compared with a convolutional neural network method, the deep learning vision classifying method based on electroencephalogram data has the advantages that the classifying ability and the generalization ability are competitive; an image sign based on brain in a novel mode is used, and significative insight which is associated with a human vision perceptual system is provided; and images can be effectively projected to a new manifold based on biology, so that the development mode of an object classifier can be changed fundamentally.

A context knowledge modeling method is provided. The context knowledge modeling method includes the steps of: a) defining a context knowledge space as a two-dimensional space based on an abstract level and an application domain of knowledge; b) locating a share ontology as a highest level of the abstract level for defining a common ontology concept at a plurality of applications and services performed in various environment and domains; c) locating at least one of domain ontologies as a lower abstract level than the share ontology by taking over the ontology concept defined at the share ontology and defining a class and an attribute specialized at a corresponding domain and a developing application; and d) locating one or more instance bases expressing knowledge about real objects to have a lower abstract level than the domain ontologies.

The present invention discloses an active power distribution network situation awareness system and method based on distributed monitoring and multi-source information fusion. The system includes a multi-source information fusion unit, a source load prediction unit, a distribution network power flow analysis unit, a power distribution network state estimation unit, a power distribution network risk analysis and early warning unit and a situation display visualization unit. The method comprises the following steps that: 1) fusion analysis is performed on a plurality of kinds of information of a distributed monitoring system and a data interaction bus; 2) on the basis of fusion information and user behavior prediction, distributed power source prediction and feeder-level load prediction are carried out; 3) power distribution network state estimation is carried out according to real-time measurement data and load prediction data; 4) on the basis of a source load prediction result and a power distribution network state estimation result, distributed power source-containing power distribution network power flow analysis is carried out; 5) risk quantitative analysis and early warning for various kinds of operation scenes are carried out through using a multi-attribute risk assessment method on the basis of the operation power flow and operating state of a power distribution network; and 6) the operating state and situation change of the power distribution network are displayed in an overall and detailed parallel display manner.

The invention, which belongs to the intelligent robot technology field, relates to an intelligent mobile robot platform capable of carrying out autonomic movements. The autonomic mobile robot platform comprises a movement driving system, an environment perceptual system and a platform control system. Compared with a current mobile robot with a normal moving mode, the provided mobile robot swings a leg arm mechanism as well as utilizes acting forces generated by an inverse deviation wheel and medium on the ground or in the space, so that stable movements of the robot are realized and thus an expressive force of a moving behavior of the robot is more outstanding. Besides, the mobile robot can carry out perception on the environment autonomically as well as has strong behavior adaptation capability on a width change of a moving channel of the robot. The provided platform can be used as an experiment and verification platform of a plurality of research fields including multi-robot coordinated formation, an amphibious robot and a micro-nano robot movement prototype and the like.

The invention relates to the field of access control technology, in particular to an intelligent robot access control system and a control method thereof. The intelligent robot access control system comprises a door end processing system, a door end sensory perceptual system, a door end expression system, a door opening / closing system, and a locking / unlocking system, wherein the door end processing system is connected with the door end sensory perceptual system, the door end expression system, the door opening / closing system, the lock locking / unlocking system, a cloud server system and a network terminal respectively through i / o interfaces; and the door end processing system is connected with the cloud server system and the network terminal in a network communication manner. The inventionhas functions of intelligent sensory perception and expression. Based on intelligent recognition, a humanized door opening / closing control mode is set up so that a conventional security anti-theft door is endowed with properties of a unique intelligent robot, and the user experience is greatly enhanced; therefore, the invention is worthy of promotion and application.

An apparatus and method for training the sensory perceptual system in a human is provided. The apparatus and method incorporates a number of different programs to be played by the human. The programs artificially process selected portions of language elements, called phonemes, so they will be more easily distinguished by a human, and gradually improves the human's neurological processing of the elements through repetitive stimulation. The programs continually monitor a human's ability to distinguish the processed language elements, and adaptively configures the programs to challenge and reward the human by altering the degree of processing. Rewards are presented to the human when correct selections are made. Surprise rewards are randomly presented to the human when correct selections are made. Surprise rewards are provided randomly to the human to surprise and further reward the human during training.

A car networking perceptual system based on OFDM and radar-communication integration comprises a data fusion unit, a driving-information obtaining unit, an echo signal extraction unit, a signal modulation unit, a signal demodulation unit, and a wireless transceiving unit, which are connected with each other. A construction method of the car networking perceptual system based on OFDM and radar-communication integration comprises thirteen steps. By using OFDM to finish the modulation and transmission sharing of self driving information in the invention, on one hand, the car networking perceptual system could demodulate the travelling speed, working condition and movement characteristic data of other vehicles in a cooperative communication mode, on the other hand, a non-cooperative radar detection mode could be used to measure the relative position and motion information between the car and other vehicles around the car so as to provide peripheral target movement conditions for a driver or an automatic drive system in real time to help the driver or the automatic drive system to adopt necessary reasonable measures, thereby improving traffic safety.

A portable early learning sensory system configured to aid the development of a child through interaction with a caregiver and to provide the caregiver with an explanation regarding the use of the objects in system to illicit developmentally appropriate responses from the child. The portable early learning sensory system includes tactile learning components, visual learning components, auditory learning components, and caregiver assistance guides associated with each learning component. The caregiver assistance guides contain information on how to use the learning components effectively with the child in order to illicit the developmentally appropriate response from the child, developmental milestones, and safety information.

A method and system for matching digital information flow to the human perception system. In various embodiments, multi-monitor (multimon) support is leveraged to take advantage of multiple windowing and window positioning to separate elements of different tasks into information planes (which are based on a concept of “triage and focus”). Triage watches the flow of incoming information and determines the nature of the information. Based on the nature of the information and principles of human perception, Focus (or defocus) displays the information where the information is best viewed.

The invention discloses a context awareness system based on wearable equipment, and a control method. The system processes data information by use of a decision-grade data fusion technology, determines a result and automatically arranges an intelligent household according to the result. The system comprises an information acquisition module, an information processing module and a contextual mode arrangement module. The information acquisition module comprises such sensors as an optical sensor, a humidity sensor, a pulse sensor, a blood oxygen sensor, a heart rate sensor, a body temperature sensor, a motion acceleration and acceleration transducer and the like. The information processing module comprises a mobile client, a server, a controller and the like, and the sensors transit acquired data to a medium-client through Bluetooth, transmit the data to the server through WiFi, perform analysis processing on the data and obtain a result. The contextual mode arrangement module intelligently arranges the intelligent household according to the determining result through the controller. The information acquisition module transmits information acquired by a sensor equipment apparatus worn on a person and a sensor equipment apparatus fixed in a room to a mobile client.

The invention relates to a supervised self feedback-based context awareness system, a working method and application thereof. The context awareness system includes a context information acquisition module, a context information processing module, a context information application module and a user module which are connected with one another successively, wherein the user module is connected with the context information processing module. According to the supervised self feedback-based context awareness system of the invention, a dynamic context information credibility evaluation mechanism is added into the context awareness system, so that context information inconsistency elimination is performed by using credibility; discovering able people and putting them at suitable posts embodies correct cognition for the credibility of hold context information; and the context awareness system can fuse multi-source information and make correct decisions so as to provide prerequisites for appropriate services.

The invention discloses an efficient reconstruction method in a compression perceptual system, relates to a data processing method which is used for solving the problem that the precision and the speed cannot be improved simultaneously in the existing reconstruction method and comprises the following steps: firstly arranging a measurement value Y0 into a form for easily realizing a reconstruction algorithm, if one-dimensional reconstruction is required, ensuring that the measurement value is not arranged, and if two-dimensional reconstruction is required, vectorizing the measurement value to obtain Y; then enabling the k to be equal to 1, uk to be equal to 0 and vk to be equal to 0, thus obtaining expressions as shown in the specification; performing non-contribution iteration in an iterative step to compute the times s of the non-contribution iteration; if the change times s of the vk just enable the uk+1 to change, containing the following iterative formulas as shown in the specification in the iterative steps to judge an expression as shown in the specification, then judging whether the judgment is met so as to determine whether to converge the iteration, iterating until the iteration is converged; and finally, if an one-dimensional signal is required to reconstruct, directly using signal sparseness to represent a reconstruction original signal, and if a two-dimensional signal is required to reconstruct, inversely vectorizing a sparseness coefficient u, and using the sparseness of the image to represent the reconstruction original image. The efficient reconstruction method can be applied to the reconstruction of the one-dimensional or two-dimensional signal in the compression perceptual system.

The invention relates to a self-adaptive subjective and objective weight context sensing system based on feedback and a working method thereof. The context sensing system comprises an original context information collection module, a context fusion module, a context reasoning module, a context application module and a user module. The user module is connected with the context fusion module. According to the context sensing system, a self-adaptive subjective and objective weight distribution mechanism based on user feedback is introduced into the context fusion module, contribution rates of subjective and objective weights of various context information are dynamically adjusted and optimized, the context information fusion accuracy and efficiency are improved, and the system can provide relatively intelligent and personalized service for a user.

The invention provides an autonomous robot and a control method, device and system thereof and a computer readable medium. The autonomous robot comprises a perceptual system and a control system. Thecontrol system is configured to dynamically adjust the behavior safety threshold of the autonomous robot based on the motion state of the autonomous robot for controlling the motion behavior of the autonomous robot based on the perceptual data of the perceptual system and the dynamically adjusted behavior safety threshold. According to the autonomous robot and the control method, device and systemthereof and the computer readable medium, the behavior safety threshold of the autonomous robot is dynamically adjusted based on the motion state of the autonomous robot so as to ensure correct control of the behavior of the autonomous robot in various application scenes, improve the reliability of the autonomous robot and then enhance the user experience.

The invention provides a multi-rotor wing robot in a liquid medium. The multi-rotor wing robot comprises a streamline closed shell, an N-rotor wing body, a control unit, N cylindrical seal covers, an automatic floating device, a remote control system, a sensory perceptual system and a man-machine interactive system, wherein the N cylindrical seal covers penetrate through the closed shell from top to bottom, and are uniformly and symmetrically distributed; a plurality of rotor wings of the multi-rotor wing body are respectively positioned inside the N seal covers, and rotary surfaces of the N rotor wings are positioned on the same plane; the control unit is used for controlling the motion of the multi-rotor wing robot. The multi-rotor wing robot solves the problem that the robot in the liquid medium is single in posture and inflexible during motion in the prior art, and can automatically float in emergency circumstances such as power failure or power shortage.

The invention discloses an information security situation awareness system of an AI-based metering automation system, and relates to the technical field of situation awareness of a power distributionnetwork. The system is characterized in that a data collection module collects the power consumption information of the users, the collected information is cleaned, fused and clustered through a big data analysis module, and feature information is extracted; the artificial intelligence technology module constructs an expert database according to the historical data processed by the big data analysis module, performs artificial intelligence training learning on the real-time feature information and adds the real-time feature information to the expert database to form expert diagnosis criteria and methods; the information security simulation test module performs a cyclic simulation test and a fault injection reliability test according to the obtained diagnosis criterion and method provided by the expert database; a test result evaluates the quality risk level through the situation awareness information safety evaluation module, so that more accurate evaluation and prediction of faults orinformation safety occurrence probability and risk than manual observation and calculation are obtained, and the early warning module processes the result and gives an early warning through the datadisplay module.

A new hearing profile assessment plays each of a plurality of frequency tones multiple times at a plurality of loudness levels. For each frequency, the patient indicates which tones that they can hear, establishing minimum-amplitude thresholds for each frequency. The assessment adapts loudness levels until the patient indicates consistent minimum-amplitude thresholds for each frequency. Also, a new system for training the hearing of a subject is disclosed. The system instructs the subject to vocalize various sound items and remember the sounds that they vocalize. The system plays either recorded samples of the subject's own voice, or comparison samples of a synthesized voice or other's vocalizations of the same sound items. The system prompts the subject to compare the played samples with the sounds they remembered vocalizing. The system uses the feedback to adjust sound processing parameters for a hearing aid, cochlear implant, sound output devices, or a training program.

A method is provided for utilizing the human perceptual system by providing a spectrum of event log data for viewing. Event log data is received. Events of the event log data are mapped to an x-axis of a spectrum based on time, where the events of the event log data correspond to a time slot on the x-axis. Categories for the events are mapped to a y-axis of the spectrum, where the y-axis is a frequency axis, and where each of the categories respectively corresponds to a frequency of the multiple frequencies. Strength of events are mapped to a z-axis of the spectrum, where the z-axis is a magnitude axis, and where a magnitude value reflects the significance of the events happened at a particular time slot in a particular category. The magnitude of events (z-axis) of the event log data may be further mapped to a line thickness of the spectrum for the multiple frequencies. The spectrogram of the event log data is presented in a two-dimensional graphical format in time, frequency, and magnitude for observation by a user.

The disclosure provides a real-time traffic situation awareness system. In one embodiment, the real-time traffic situation awareness system receives driving data from a car, wherein the driving data comprises an image, GPS data, and gyroscope sensor data. The real-time traffic situation awareness system comprises an image processing unit, a feature extraction unit, a feature matrix database, a data grouping unit, and a situation awareness unit. The image processing unit processes the image to generate a processed image. The feature extraction unit generates a data point according to the processed image, the GPS data, and the gyroscope sensor data. The data grouping unit searches the feature matrix database for a plurality of feature groups of an optimal feature matrix corresponding to a geographic area according to the GPS data of the data point. The situation awareness unit analyzes the feature groups to generate traffic information.

A method for establishing a relationship between a physical structure of reflectance spectra as defined in a Euclidean color space and a perceptual space of color appearance defined in terms of human perception of colors is performed by obtaining a cube root spectrum of the physical reflectance spectrum in a selected spectral range, reconstructing the cube root of the physical reflectance spectrum by a weighted linear combination of three basis functions, the weights of the linear combination of the basis functions constituting the coordinates in a three-dimensional Euclidean color space with respect to which similarities and differences among reflectance spectra in metric terms and a color characterized in a perceptual space of color appearance can be analyzed, and making an analytic comparison between a physical system in the three-dimensional Euclidean color space and the perceptual system by means of a linear transformation therebetween.

The invention relates to a mobile crowd sensing system reward distribution method based on reputation prediction, belongs to the technical field of mobile crowd sensing. The core of the method is thateach data provider on a task platform, namely a "worker", is endowed with a reputation which is based on the behavior of the "worker" in a task in the past. A future behavior of the "worker" is predicted based on the reputation, and basic salaries are distributed to the "worker" prior to the start of the next task. 'Workers' continuously efforts to buy a better reputation, thereby obtaining the priority to be subject to the right to be subject, and thus obtaining more rewards. Meanwhile, after the worker actually participates in the task, the difference between the actual performance of the worker and the reputation prediction value is measured, and reward and punishment are conducted on reward on the basis of existing salary. According to the method, the quality of workers can be accurately monitored and evaluated, the reputation and the quality are combined, an incentive mechanism has reward optimality, and attacks of new adders and switch attacks are effectively prevented.

The invention belongs to the technical field of automatic control, and relates to a control method used for an assistance exoskeleton system. According to the dependency degree of a human body on the assistance exoskeleton system, control over the assistance exoskeleton system is divided into coarse control and fine control; and according to the specific method, firstly, a sensory perceptual system analyzes the motion state of the human body currently, according to the different motion states such as low-speed walking, standing, squatting and high-speed walking, through the coarse control method, motor control is used for controlling the pressure of an oil source, and therefore the hydraulic control amount required by the different motion states is achieved; meanwhile, on the basis of the coarse control, in order to more precisely control the motion state of the exoskeleton, the fine control is adopted, the postures of podites of the tail end of the exoskeleton are adjusted through the hydraulic cylinder elongation amount, the expected postures are achieved, and finally the exoskeleton can precisely achieve the different motion states; a power control device of the assistance exoskeleton system is composed of a hydraulic pump controlled by a servo motor and a hydraulic cylinder controlled by a servo valve; and the coarse control correspondingly adjusts the pressure of the oil source, and the fine control correspondingly adjusts displacement of the hydraulic cylinder.

The invention discloses an incentive method of a crowd sensing system based on a behavioral economics preference theory. The incentive method mainly comprises the following steps: 1) issuing a task bya platform; 2) selecting a task by a user; 3) determining a participation plan; 4) selecting a participating user by the platform; 5) reporting perception data by the user; 6) reward payment; Aimingat the platform end, a context effect in behavior economics is introduced into a task release mechanism, and a function of the attraction degree of the task to the user in crowd sensing is established, thereby improving the enthusiasm of the user; Aiming at the user side, a new reward payment mechanism is designed to correct a utility function based on traditional economics, so that the utility ofthe user is improved; According to the theory and experiment about the scene effect and fairness preference in the behavior economics, parameter debugging is carried out on the new model, the platform cost is reduced to a certain degree, the benefits of the platform side and the user side are improved, and therefore the social benefits are further improved.

The invention relates to an emitter of trackside environmental perception. The emitter of trackside environmental perception comprises a first serial-parallel conversion module, a constellation mapping module, a discrete fractional order inverse Fourier transform module, a first parallel-serial conversion module, a first digital-to-analogue conversion module and a first emitting module. Accordingto the emitter of the trackside environmental perception, a collector of the trackside environmental perception, a receiver of the trackside environmental perception and a communication sensory perceptual system of the trackside environmental perception, communication data is processed through the emitter, and a communication and radar integrated signal with communication and radar perception functions is generated. Trackside environmental parameters can be collected through the collector, an echo signal and the communication and radar integrated signal sent by other emitters can be received through the receiver, in addition, the receiver further can receive the trackside environmental parameters obtained by the collector, namely, whether a track is safe or not is judged further through radar perception and sensing perception while communication is met. According to the emitter of the trackside environmental perception, the collector of the trackside environmental perception, the receiver of the trackside environmental perception and the communication sensory perceptual system of the trackside environmental perception, the collection speed is high, detection dead zones are removed,the building cost is greatly reduced, and safety level of a track traffic system is improved.

The present invention leverages analysis methods, such as expected value of information techniques, rate-based techniques, and random selection technique, to provide a fusion of low-level streams of input data (e.g., raw data) from multiple sources to facilitate in inferring human-centric notions of context while reducing computational resource burdens. In one instance of the present invention, the method utilizes real-time computations of expected value of information in a greedy, one-step look ahead approach to compute a next best set of observations to make at each step, producing “EVI based-perception.” By utilizing dynamically determined input data, the present invention provides utility-directed information gathering to enable a significant reduction in system resources. Thus, of the possible input combinations, the EVI-based system can automatically determine which sources are required for real-time computation relating to a particular context.

The invention relates to a display screen energy saving method. The method includes the steps of acquiring a first input image; acquiring first illumination layer information and first reflection layer information according to the first input image; establishing an attenuation model with the first input image, the first illumination layer information and the first reflection layer information; processing the first illumination layer information with the attenuation model to obtain second illumination layer information; conducting illumination compensation processing on the second illuminationlayer information to obtain third illumination layer information; acquiring an output image according to the third illumination layer information and the first reflection layer information. In the method, three image features including local variance, skin color and brightness are extracted based on image content to adjust illumination layers so as to reconstruct the image scene, the contrast of the image can be improved, and detailed information of the image can be better highlighted; meanwhile, the skin color area which the human eyes are interested in is protected, and thus the reconstructed image better conforms to the human vision perceptual system.

A method and system for matching digital information flow to the human perception system. In various embodiments, multi-monitor (multimon) support is leveraged to take advantage of multiple windowing and window positioning to separate elements of different tasks into information planes (which are based on a concept of “triage and focus”). Triage watches the flow of incoming information and determines the nature of the information. Based on the nature of the information and principles of human perception, Focus (or defocus) displays the information where the information is best viewed.