Patents
Literature

288results about How to "Robust" patented technology

Method and system for identifying abnormal microblog users

InactiveCN103150374ARobustEasy to implementSpecial data processing applicationsKullback–Leibler divergenceData mining
The invention relates to a method for identifying abnormal microblog users. The method comprises the steps of obtaining a plurality of users' microblog data, storing the microblog data into a database, taking statistical distribution of time intervals of user behaviors as behavior time characteristics of the users according to the microblog data of the users, generating behavior time characteristic vectors and defined parameters, calculating Kullback-Leibler divergence between the behavior time characteristic vectors of the normal users and the behavior time characteristic vectors of the users to be detected, judging the users to be detected with the calculated Kullback-Leibler divergence exceeding the defined parameters as the abnormal users, and extracting and showing keywords of contents of the abnormal users. The invention further provides a system for identifying the abnormal microblog users corresponding to the method. According to the method and system, the keywords of the blog article contents of the abnormal users can be extracted quickly, promulgators of junk information such as marketing and advertisements can be identified accurately, and the method and the system are applicable to detection of multiple microblog service platforms, and has the advantages of high accuracy and efficiency and wide applicability.
Owner:INST OF INFORMATION ENG CAS

Automatic evaluation method of human body action and dance scoring system

The invention discloses an automatic evaluation method of human body action and a dance scoring system. The method comprises the following steps: on the basis of depth data, selecting human body bone nodes and human body outline nodes; on the basis of the human body bone nodes, constructing human body limb vectors, calculating a space included angle between each human body limb vector and a corresponding template limb vector, weighting and normalizing the space included angles, and calculating an accumulation error which is taken as a diversity degree based on the human body bone node analysis; on the basis of the human body outline nodes, constructing human body outline vectors, calculating a space included angle between two adjacent human body outline vectors, constructing an energy function by a diversity value between the space included angle and space included angle of template outlet vectors, solving a minimum value of the energy function by a graph cut method, and taking the minimum value as the diversity degree based on human body outline node analysis; and carrying out weighting and summation on the diversity degree based on the human body bone node analysis and the diversity degree based on the human body outline node analysis, and taking the obtained value to serve as an evaluation parameter used for balancing a matching degree of the human body action and template action so as to realize the automatic evaluation of the human body action.
Owner:中国艺术科技研究所

Self-adaptive controllers and method

InactiveCN101339406AGive full play to the role of online anti-interferenceRobustAdaptive controlFrequency bandSelf adaptive
The invention relates to a self-adaption controller and a method. Concerning about a plurality of uncertain factors of a controlling system in outside world, the invention adopts a self-adaption robustness controlling strategy with high performance. The self-adaption controller comprises that: the output end of a feedforward controller is respectively connected with a position feedback controller, an interference suppressor and a controlled object; one end of the feedforward friction compensation is connected with an input end and the other end is connected with the position feedback controller, the interference suppressor and the controlled object. The self-adaption controlling method comprises that: the self-adaption robustness interference suppressor can online detect and estimate the interference of the system and provide real time compensation; by using a zero phase error tracing method, the feedforward controlling design can realize fine tracing characteristics within limited frequency range. The feedforward friction compensation provides a nonlinear real-time regulation of the friction of the system and improves the whole dynamic performance of the system. The adoption of the self-adaption robustness controller with high performance guarantees the fine dynamic performance of the moving controlled object and fine suppressing ability of outward interference.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI

Fuzzy domain characteristics based optical fiber vibration signal identifying method

The invention provides a fuzzy domain characteristics based optical fiber vibration signal identifying method and mainly aims to solve the problem that existing identifying methods are low in identifying efficiency under the conditions of low sampling rate and similar intrusion events. The fuzzy domain characteristics based optical fiber vibration signal identifying method includes steps of (1) subjecting optical vibration signals to wavelet denoising; (2) subjecting the denoised signals to de-meaning and energy normalization; (3) calculating the normalized signal fuzzy function and sectioning the fuzzy function to be fuzzy domain characteristics; (4) reducing dimensions of sections to construct a signal characteristic set; (5) partitioning the signal characteristic set into a training set and a test set; (6) training an SVM (support vector machine) classifier by the training set; (7) classifying the test set by the trained SVM classifier. The fuzzy domain characteristics based optical fiber vibration signal identifying method effectively extracts the fuzzy domain characteristics of optical fiber vibration signals, has the advantages of high identification rate and wide applicability as compared with the prior art, and can be used for a signal processing subsystem of an optical fiber perimeter security system.
Owner:西安雷谱汇智科技有限公司

Audio scene recognition method and device based on long-term and short time feature extraction

ActiveCN108305616ARobustGood distinctionSpeech recognitionAudio signalFeature combination
The invention relates to an audio scene recognition method and device based on long-term and short time feature extraction. The method comprises: preprocessing an inputted to-be-recognized audio signal; d carrying out short-time audio feature extraction on the pre-processed to-be-recognized audio signal and carrying out long-term audio feature extraction; and carrying out long-term and short-timeaudio feature combination of the to-be-recognized audio signal, inputting the features into a classification model and a fusion model, carrying out classification and identification, and outputting anidentification label of an audio scene. According to the invention, the long-term features of the audio scene are combined based on the conventional short-time feature extraction and complex audio scene information can be represented; the features are inputted into the classification model and the fusion model to carry out classification and identification; and the identification label of the audio scene is outputted. The method and device have advantages of high robustness and good distinguishing performance; the overall characteristics of the scene data can be represented to the great extent; and the recognition efficiency and the stability are high.
Owner:NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT +1

Wavelet transform and Arnold based adaptive gray-scale watermark embedded method

InactiveCN102142258ARobustEnhance confidentiality and securitySpeech analysisSelf adaptiveConvolution
The invention discloses a wavelet transform and Arnold based adaptive gray-scale watermark embedded method which comprises the following steps: carrying out square matrix conversion and scrambling processing on an original watermark image; carrying out wavelet transform (three times) on an original host audio to obtain wavelet low frequency coefficients as the embedded pre-selected position of a watermark; automatically searching an optimal embedded sequence from the low frequency coefficients, wherein the optimal embedded sequence is the optimal embedded position of the watermark; and carrying out convolution on a digital watermark image sequence and the optimal embedded sequence, namely, embedding the digital watermark image into the low frequency coefficients of audios. The method is characterized in that in the process of digital watermark extraction, the audios containing watermarks are detected according to the original audio, and a watermark image sequence is extracted from the audios; and in the process of digital watermark reduction, the length and width of the original image are taken as extraction keys, and the extracted watermarks are reduced through the utilization of reverse Arnold conversion and image reconstruction. The method disclosed by the invention is strong in function, quick in computing speed, easy and convenient to implement, and has certain practical values in the aspects of digital image copyright protection and information hiding.
Owner:SHANGHAI SECOND POLYTECHNIC UNIVERSITY

Depth and breadth neural network combined speech enhancement algorithm of digital hearing aid

ActiveCN105611477ARobustImprove voice qualityHearing aids signal processingFrequency bandDigital hearing aid
The invention discloses a depth and breadth neural network combined speech enhancement algorithm of a digital hearing aid belonging to the speech signal processing technical field. The method comprises following steps: firstly, carrying out speech activity detection to noise contained speech signals; extracting features such as autocorrelation function maximum values and variances of frequency bands of the noise contained speech signals; building a two-value decision device by using a BP neural network; judging speech segments and noise segments; secondly, extracting MFCC and first level MFCC features; detecting noise types by a depth neural network, wherein the depth neural network is formed by cascading a learning vector quantization neural network and the BP neural network; finally, building a breadth neural network formed by connecting various networks in parallel; automatically selecting corresponding neural networks by the breadth neural network according to the noise types; removing the noises, thus obtaining the enhanced speech and improving the speech intelligibility of the hearing aid output speech. According to the algorithm, the training processes of the neural networks are finished offline; the complexity of the test algorithm of the trained networks is low; and therefore, the real timeliness is satisfied.
Owner:BEIJING UNIV OF TECH

Fault diagnosis and safety pre-warning oriented elevator monitoring system and method

The invention discloses a fault diagnosis and safety pre-warning oriented elevator monitoring system and method. A cloud-side processing module is used for receiving data of all machine room board modules and camera modules in multiple elevator cars and achieving the computation and storage functions. The machine room board modules control data of the multiple elevator cars, achieve the computation and temporary storage functions and transmit computation results to the cloud-side module. Elevator car ceiling board modules collect data of the corresponding single elevator cars, transmit the data to elevator car ceilings in an I2C mode to be processed and transmit processing results to the machine room board modules. Elevator car door board modules are used for collecting data of barometer sensors and three-axis acceleration sensors mounted nearby elevator car doors, conducts filtering, integration and vibration analysis on the data and transmit processing results to the corresponding elevator car ceiling board modules for being processed. The fault diagnosis and safety pre-warning oriented elevator monitoring system achieves the real-time monitoring analysis effect through layer-by-layer grading and function decoupling of all the modules and meanwhile improves the elevator running state monitoring and fault pre-warning accuracy.
Owner:ZHEJIANG UNIV

Position sensor-free vector control device for built-in permanent magnetic synchronous motor

ActiveCN102361430AAchieving accurate field orientation controlRobustElectronic commutation motor controlVector control systemsShaft voltageThree-phase
The invention discloses a position sensor-free vector control device for a built-in permanent magnetic synchronous motor and belongs to the field of motor control. The position sensor-free vector control device aims to solve the problems that overlarge position observation error is caused during load disturbance, the system is out of control when a position observed value is restrained to an S-pole direction and the position sensor-free low-speed running control performance of the built-in permanent magnetic synchronous motor cannot be improved effectively in the prior art. The position sensor-free vector control device comprises a rotating speed controller unit, a first current controller unit, a second current controller unit, a high-frequency voltage signal generation unit, a straight shaft voltage superposition unit, a coordinate spinning inverse transformation unit, a power converter unit, a low-pass filter unit, a three phase to two phase coordinate transformation unit, a coordinate spinning transformation unit, a high-frequency current signal processing unit, a rotor position observer unit, a rotating speed calculation unit and a current detection sensor. The control devicecan avoid a phenomenon that the system is out-of-control when the position observed value is restrained to the S-pole direction.
Owner:哈尔滨工大正元信息技术有限公司

Motion control method for autonomous berthing of unmanned surface vessel

ActiveCN108267955AGood real-time and stabilityRobustAdaptive controlSelf adaptiveControl parameters
The invention discloses a motion control method for the autonomous berthing of an unmanned surface vessel and belongs to the unmanned surface vessel autonomous berthing motion control field. The method includes the following steps that: a current control system mode is determined according to the current berthing state of the unmanned surface vessel; the current actual speed or heading of the unmanned surface vessel is obtained, and the control deviation and deviation change rate of the heading or speed are obtained; with the control deviation and deviation change rate of the heading or the speed adopted as the input of a fuzzy controller, an appropriate control parameter variation quantity is selected on the basis of the current control system mode, and a control parameter is updated; andwith e(t) adopted as the input of the controller, and the controller outputs a desired control command to an actuator. According to the motion control method of the invention, improvement is made onthe basis of the traditional PID controller, and the controller has two modes, namely, a remote end mode and a nearshore mode; an adaptive fuzzy control rule is added, so that the controller can dynamically and adaptively adjust the control parameter according to berthing behavior change; and therefore, a motion control problem under the influence of weak maneuverability, large disturbance and a strong bank effect during the autonomous berthing of an under-driven unmanned surface vessel can be solved.
Owner:HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products