Eureka-AI is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Eureka AI

945 results about "Data subject" patented technology

Data subject. Data subject refers to any individual person who can be identified, directly or indirectly, via an identifier such as a name, an ID number, location data, or via factors specific to the person’s physical, physiological, genetic, mental, economic, cultural or social identity. In other words, a data subject is an end user whose personal...

Firework identification method and firework identification system based on deep learning of image

InactiveCN104408469AImproving the Speed ​​of Unsupervised LearningFew parametersCharacter and pattern recognitionData setFireworks
The invention discloses a firework identification method and a firework identification system based on deep learning of an image. The firework identification method comprises the following steps of step 1, acquiring a label-free sample image set and a label sample image set; step 2, obtaining a label-free training data set and a label training data set; step 3, performing whitening preliminary processing on training data; step 4, based on the label-free training data subjected to the whitening preliminary processing, constructing a deep neutral network based on sparse self coding by adopting unsupervised learning, and extracting a basic image feature set of the label-free training data; step 5, convolving basic image features and pooling image data; step 6, training a Softmax classifier based on the convolved and pooled label training data set; step 7, inputting the convolved and pooled images to be identified into the trained Softmax classifier to obtain the identification result. According to the firework identification method and the firework identification system disclosed by the invention, the visual identification rate of fireworks and a similar object can be effectively improved, and automatic identification with higher precision for the fireworks can be realized.

High-precision indoor positioning method based on MEMS (Micro Electro Mechanical System) inertial sensor

The invention discloses a high-precision positioning method based on an MEMS (Micro Electro Mechanical System) inertial sensor. The high-precision positioning method comprises the following steps: firstly, fixedly connecting the MEMS inertial sensor on a foot of a pedestrian, enabling the MEMS inertial sensor to sense a motion state of the foot, acquiring foot navigation information of the foot in real time, and realizing transmission by Bluetooth; secondly, holding an Android mobile phone by the pedestrian, and receiving and saving data provided by the MEMS inertial sensor in real time at an Android client; thirdly, carrying out denoising processing on the data; fourthly, obtaining a zero velocity interval by adopting a zero velocity detection algorithm, and then carrying out error correction by combining a zero velocity update algorithm with a state estimation algorithm; fifthly, displaying data subjected to error correction and compensation in real time by the Android client through a user interface. According to the high-precision positioning method disclosed by the invention, extra auxiliary basic setting is not needed; good positioning precision of various complex motion states in indoor positioning can be maintained; real-time correction and error compensation are realized by adopting a mobile terminal, and the motion track is displayed in real time by a user interaction interface.

Internet-of-things gateway and medical monitoring system comprising same

The invention discloses an internet-of-things gateway and a medical monitoring system comprising the same. The gateway comprises a sensing network access unit, a protocol conversion unit and a communication network access unit, wherein the sensing network access unit is used for receiving sensing data input by sensing equipment; the protocol conversion unit is used for analyzing the sensing data, calling a data adapting protocol according to an analysis result, coding the data subjected to secondary analysis by using a ubliquitous machine to machine protocol (UMMP) after performing secondary coding on the sensing data according to the data adapting protocol and outputting the coded sensing data to the communication network access unit; and the communication network access unit is used for selecting an access mode of the data and outputting the coded sensing data to the internet-of-things management platform in the access mode. The system has wide access capability and strong protocol conversion capability, so that the medical monitoring system comprising the internet-of-things gateway can be connected with the medical monitoring equipment supporting an international medical standard protocol to realize comprehensive monitoring on a patient.
Owner:晁彦公 +1

Data transmission method, device and equipment

ActiveCN105472477ALower the thresholdSolve the communication blind spots that are prone to appearSelective content distributionBlind zoneTelecommunications link
The embodiment of the invention discloses a data transmission method. The method comprises the following steps: acquiring collected audio-video data, and performing coding compression on the audio-video data; performing segmenting packetization on the audio-video data subjected to coding compression according to a preset segmenting packetization strategy; allocating data packets to communication links, respectively corresponding to a plurality of configured wireless communication modules, for transmission, wherein at least two communication links corresponding to thewireless communication modules adopt different mobile telecommunication networks for communication; and acquiring network bandwidth information of each communication link in real time, adjusting allocation of the data packets in real time and/or adjusting coding parameters for coding the audio-video data in real time to adjust the code rate of the audio-video data subjected to coding compression. Through adoption of the method, a problem of live broadcast lag phase or failure caused by the fact that the possibility of communication blind zones and poor signals is high when the mobile telecommunication networks are used for audio-video live broadcasting in the prior art is solved, and urgent needs of outdoor live broadcasting and mobile live broadcasting operations are met.

Gear load wireless monitoring system and interactive multi-stage gear physical simulation method finished based on same

The invention belongs to the technical field of gear detection and measurement, in particular relates to a gear load wireless monitoring system and an interactive multi-stage gear physical simulation method finished based on the same. The invention overcomes the defects and limitations of the existing gear monitoring and simulation method. The gear load wireless monitoring system comprises an upper computer and a lower computer, wherein the lower computer is internally arranged on a measured gear structure, and the lower computer with a wireless transmission function is in wireless transmission with the upper computer. The interactive multi-stage gear physical simulation method comprises the following steps of: detecting an external field; carrying out gear solid modeling, and carrying out grid partition on the gear solid model by adopting swept mapping; setting boundary conditions; carrying out finite element analysis; and verifying the data subjected to finite element analysis and actual measurement. According to the invention, wireless data transmission and load identification testing schemes are used for correcting the error of CAE (Computer Aided Engineering) analysis so as to master the stress rule of the gear, thereby providing a basis for fatigue life prediction. The system and method provided by the invention have higher practical and economic values.

Hydroelectric generating set fault diagnosis method and system based on DdAE (Difference Differential Algebraic Equations) deep learning model

The invention relates to the technical field of hydroelectric generating set fault diagnosis, in particular to a hydroelectric generating set fault diagnosis method and system based on a DdAE (Difference Differential Algebraic Equations) deep learning model. The method and the system are established on the basis of the analysis of the original vibration data of the hydroelectric generating set, adeep learning characteristic extraction method based on a multilayer neural network model is adopted, a complex manual processing and feature extraction process is not required, an ASFA (Aquatic Sciences and Fisheries Abstracts) method based on random search is adopted to carry out the structural parameter adjustment and optimization of the DdAE to achieve a purpose of strategy optimization. A deep denoising automatic encoder model is used for realizing the distributed expression of original data, and reconstruction data subjected to feature extraction is input into a Softmax regression modelto judge the work state and the fault type of the hydroelectric generating set. The analysis of a network experiment result indicates that the method can be effectively applied to the hydroelectric generating set fault diagnosis.

Characteristic space-based backward and forward adaptive wave beam forming method

The invention discloses a characteristic space-based backward and forward adaptive wave beam forming method, and relates to the technical field of medical ultrasonic imaging. The method comprises the following steps of: performing focusing delay processing and backward and forward smoothing on a plurality of paths of sampled signals of a received array to obtain a sample covariance matrix estimate; performing diagonal loading on the sample covariance matrix estimate and then combining with a direction vector to calculate an adaptive wave beam forming weight; performing characteristic decomposition on the backward and forward covariance matrix estimate after the diagonal loading to construct a signal subspace; projecting the adaptive wave beam forming weight into the signal subspace to obtain a new adaptive wave beam forming weight; and finally, performing weighted summation on a plurality of paths of data subjected to the backward and forward smoothing by the new adaptive wave beam forming weight so as to obtain a path of adaptive wave beam signal. By using the method, the problems of improving the image resolution and contrast, being sensitive to the direction error and the like existing in the conventional adaptive wave beam forming algorithm are solved, and the overall quality of the ultrasonic imaging is comprehensively improved.

Large line width CO-OFDM system phase noise compensation method of time domain unscented Kalman filter

The invention provides a phase noise compensation method suitable for large line width and high order modulation CO-OFDM system. The method comprises the following steps: performing channel equalization on training symbol data of a receiving terminal after performing Kalman filter on the same in the frequency domain; setting pilot frequency subcarrier data with certain intervals for each OFDM symbol on a transmitting terminal, and performing preset CPE phase noise estimation and compensation at pilot frequency subcarriers in the frequency domain based on extended Kalman filter (EKF); and finally, converting frequency domain data subjected to CPE phase noise compensation into the time domain, and realizing blind ICI phase noise compensation by using the Avg-BL method, then performing pre- judgment, converting the frequency domain data subjected to the judgment into the time domain, applying time domain data and original time domain data of the receiving terminal to time domain unscented Kalman filter, calculating a final phase noise compensation value, and performing compensation. By adoption of the phase noise compensation method, a better phase noise equalization effect is obtained, and the spectrum utilization rate of the system is improved.

Interference suppression method and device based on BeiDou-I satellite signal reception

The invention relates to an interference suppression method based on BeiDou-I satellite signal reception. The method comprises the following steps of: (1) receiving N*(1-theta) BeiDou digital intermediate-frequency data and buffering the front N*theta sampling point data; (2) selecting window functions with the window length of N, combining the received N*(1-theta) BeiDou digital intermediate-frequency data and the received front N*theta sampling point data into N data to be analyzed in time sequence and sequentially multiplying the N data to be analyzed by N window function quotients; (3) carrying out FFT (Fast Fourier Transform) on the N data subjected to windowing treatment and storing the real part data and the imaginary part data of the N frequency points subjected to FFT; (4) calculating the module values of the frequency points subjected to the FFT; (5) calculating a threshold value according to the average value of the module values and the module values the current batch of data under a non-interference environment; (6) calculating attenuation quotients corresponding to interference frequency points; (7) attenuating according to the interference frequency point positions and the attenuation quotients which are acquired through calculation; and (8) carrying out IFFT (Inverse Fast Fourier Transform) on a frequency domain signal subjected to interference suppression.
Owner:宁波喵走科技有限公司 +1

Calculation method for large spatial scale vegetation coverage by combining with unmanned aerial vehicle (UAV) image

The invention discloses a calculation method for large spatial scale vegetation coverage by combining with an unmanned aerial vehicle (UAV) image. The calculation method comprises the following steps: carrying out atmospheric correction and geometrical correction on a remote sensing image, calculating NDVI (Normalized Difference Vegetation Index) and obtaining an effective region according to a predetermined threshold value; splicing UAV pictures and obtaining an orthoimage, registering satellite data subjected to geometrical correction with the spatial position, selecting a typical sample area from the UAV image, and interpreting proportions of all ground objects in the typical sample area by using unsupervised classification; randomly selecting one part of the sample area, and solving the reflectivity of all ground object end elements by using the proportions of all the ground objects in the sample area and the corresponding satellite remote sensing band reflectivity and combining with a least square method; solving the vegetation coverage of all pixels in the effective image area by using a spectral decomposition model and the reflectivity of all the ground object end element; correcting calculation results of the vegetation coverage by using data of a residual sample area. The core of the calculation method disclosed by the invention is based on a method of acquiring the end-element reflectivity of the UAV and a vegetation coverage correction model, and the calculation accuracy of the large spatial scale vegetation coverage can be effectively improved.
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