61 results about "Feature relevance" patented technology

Membrane proteins are difficult to express in recombinant form, purify, and characterize, at least in part due to their hydrophobic or partially hydrophobic properties. The membrane scaffold proteins (MSP) of the present invention assemble with target membrane or other hydrophobic or partially hydrophobic proteins or membrane fragments to form soluble nanoscale particles which preserve their native structure and function; they are improved over liposomes and detergent micelles. In the presence of phospholipid, MSPs form nanoscopic phospholipid bilayer disks, with the MSP stabilizing the particle at the perimeter of the bilayer domain. The particle bilayer structure allows manipulation of incorporated proteins in solution or on solid supports, including for use with such surface-sensitive techniques as scanning probe microscopy or surface plasmon resonance. The nanoscale particles, which are robust in terms of integrity and maintenance of biological activity of incorporated proteins, facilitate pharmaceutical and biological research, structure / function correlation, structure determination, bioseparation, and drug discovery.

The membrane scaffold proteins (MSP) of the present invention assemble with hydrophobic or partially hydrophobic proteins to form soluble nanoscale particles which preserve native structure and function; they are improved over liposomes and detergent micelles, in terms of stability and preservation of biological activity and native conformation. In the presence of phospholipid, MSPs form nanoscopic phospholipid bilayer disks, with the MSP stabilizing the particle at the perimeter of the bilayer domain. The particle bilayer structure allows manipulation of incorporated proteins in solution or on solid supports, including for use with such surface-sensitive techniques as scanning probe microscopy or surface plasmon resonance. The nanoscale particles, which are robust in terms of integrity and maintenance of biological activity of incorporated proteins, facilitate pharmaceutical and biological research, structure / function correlations, structure determinations, bioseparations, and drug discovery.

Membrane proteins are difficult to express in recombinant form, purify, and characterize, at least in part due to their hydrophobic or partially hydrophobic properties. Membrane scaffold proteins (MSP) assemble with target membrane or other hydrophobic or partially hydrophobic proteins or membrane fragments to form soluble nanoscale particles which preserve their native structure and function; they are improved over liposomes and detergent micelles. In the presence of phospholipid, MSPs form nanoscopic phospholipid bilayer disks, with the MSP stabilizing the particle at the perimeter of the bilayer domain. The particle bilayer structure allows manipulation of incorporated proteins in solution or on solid supports, including for use with such surface-sensitive techniques as scanning probe microscopy or surface plasmon resonance. The nanoscale particles facilitate pharmaceutical and biological research, structure / function correlation, structure determination, bioseparation, and drug discovery.

The present invention relates a test example generating method based on relationship, comprising the following steps of: selecting the test point of each control of a graphical user interface to be tested, according to types; taking the value of each control according to a principle that all levels of each factor are taken and assembling the related controls completely, and then combining; generating a test example according to the reference relation of the function to be tested and the example template; combining the test examples to generate all test examples of the function to be tested. With boundary value testing and equivalence testing, the method carries out strict, normative and comprehensive test point design according to the common controls in an interface test. The test designing points of each type of controls are solidified into a group of test example generating criterion for citing and expanding. The example is designed with a control relation graph and a function relation graph according to the analysis of control relativity and function relativity, so that the selection of the input value of the test example has more pertinences, thereby being capable of greatly improving the efficiency and the quality of GUI test designing.

The invention solves the problems such as feature extraction, asynchronization and synchronization, feature relevance and data difference value to fuse visual data and laser radar data so as to generate three-dimensional color depth image data, namely a three-dimensional color laser data point cloud, thereby providing precise distance information and rich environment information, effectively overcoming the defects of the traditional laser radar and the visual sensor in the aspects of robustness, information amount, precision and cost. The invention integrates a two-dimensional laser radar, a monocular vision sensor, an inertial navigation data measuring unit, a driving motor and the like into an information fusion-based three-dimensional color laser radar integral unit with universal applicability and high precision, and utilizes inertial navigation data and visual data to perform secondary alignment on laser radar data, the structure is simple, equipment does not need to be subjected to precise calibration, the performance is reliable and stable, the practicability is strong, and the method and the device can be widely used in various indoor and outdoor environments under the motion condition, and have certain universal applicability.

The membrane scaffold proteins (MSP) of the present invention assemble with hydrophobic or partially hydrophobic proteins to form soluble nanoscale particles which preserve native structure and function; they are improved over liposomes and detergent micelles, in terms of stability and preservation of biological activity and native conformation. In the presence of phospholipid, MSPs form nanoscopic phospholipid bilayer disks, with the MSP stabilizing the particle at the perimeter of the bilayer domain. The particle bilayer structure allows manipulation of incorporated proteins in solution or on solid supports, including for use with such surface-sensitive techniques as scanning probe microscopy or surface plasmon resonance. The nanoscale particles, which are robust in terms of integrity and maintenance of biological activity of incorporated proteins, facilitate pharmaceutical and biological research, structure / function correlations, structure determinations, bioseparations, and drug discovery.

The invention provides a wireless terminal and a remote parameter setting method thereof. When a dial-up connection is established by the wireless terminal, a request message to update parameters is sent to a network server by the wireless terminal; equipment information in the request information of the wireless terminal matches with equipment information of a server through the network server; parameter setting information which matches with the equipment information of the wireless terminal is sent; and the parameters are set by using the received parameter setting information through the wireless terminal. The users not only enjoy new function experience brought by technical development, but also do not worry about inconvenience caused by that a wireless router cannot be normally used due to being not familiar with new functions, and further do not worry about complaints from customers or user group churn, which is caused by that the users can not use the terminal for a short time because of updating; and meanwhile, a remote setting function can be simply implanted to all platforms of a data card due to having low relativity with other functions. Furthermore, the remote parameter setting method is simple in operation, and the users can enjoy convenient services.

Membrane proteins are difficult to express in recombinant form, purify, and characterize, at least in part due to their hydrophobic or partially hydrophobic properties. Membrane scaffold proteins (MSP) assemble with target membrane or other hydrophobic or partially hydrophobic proteins or membrane fragments to form soluble nanoscale particles which preserve their native structure and function; they are improved over liposomes and detergent micelles. In the presence of phospholipid, MSPs form nanoscopic phospholipid bilayer disks, with the MSP stabilizing the particle at the perimeter of the bilayer domain. The particle bilayer structure allows manipulation of incorporated proteins in solution or on solid supports, including for use with such surface-sensitive techniques as scanning probe microscopy or surface plasmon resonance. The nanoscale particles facilitate pharmaceutical and biological research, structure / function correlation, structure determination, bioseparation, and drug discovery.

A device (100) for managing a plurality of software items, the device (100) comprising an analysis unit (103) adapted for analyzing a functional correlation between the plurality of software items, and a grouping unit (105) adapted for grouping functionally correlated ones of the plurality of software items together in a common memory space.

The invention discloses a color face identification method based on RGB (red, green and blue) color feature double identification relevance analysis. Identification analysis is applied in R, G, B (red, green and blue) color components and among the same, feature double identification analysis based on relevance is realized in each color component and among different color components, a large amount of identification information can be acquired, classification accuracy is high, and identification capacity is high. The color face identification method based on RGB (red, green and blue) color feature double identification relevance analysis includes: defining intra-class feature relevance matrix and inter-class feature relevance matrix in each training sample set and intra-class feature relevance matrix and inter-class feature relevance matrix among color component training sample sets; defining target function and solving the same to obtain projected training sample feature sets; and obtaining projected test sample features according to the projected training sample feature sets, calculating relevance from the test sample features to the training sample features and classifying the same to a category in which the training sample with the largest relevance is.

The invention relates to an image super-resolution method and system based on depth feature relevance. The method comprises the following steps: acquiring a low-resolution image to be reconstructed; inputting the low-resolution image to be reconstructed into a trained student model for reconstruction to obtain a high-resolution image, wherein the training process of the student model comprises the following steps: taking a low-resolution training image as the input of the student model; taking the high-resolution training image as the output of the student model, taking the overall loss function as a loss function, and utilizing a loss function attenuation mechanism to supervise and train the student model through the high-resolution image and the real image output by the trained teacher model to obtain the trained student model. According to the invention, the high-resolution image is estimated through the image super-resolution model which is small in parameter quantity and high in performance.

The invention discloses a terminal and a terminal function option display method. The terminal comprises a function module, a function option module, a classification module and a display module, wherein the function module is used for providing different terminal functions for a user; the function option module is used for generating different function options and sub-function options according to the different terminal functions of the function module; the classification module is used for classifying the different function options and sub-function options into different tree-shaped branches according to the function dependence of the different function options and sub-function options, such as trunks, branches and leaves, and is used for representing the different function options and sub-function options of every executable function of the terminal; and the display module is used for displaying all function options and sub-function options classified by the classification module in a tree shape, such as the trunks, the branches and the leaves. The terminal function option display method can bring good impression to users and bring convenience to user operation.

A method for processing an image including: identifying a first group of keypoints in the image; for each keypoint of the first group, identifying at least one corresponding keypoint local feature related to the each keypoint; for the at least one keypoint local feature, calculating a corresponding local feature relevance probability; calculating a keypoint relevance probability based on the local feature relevance probabilities of the at least one local feature; selecting keypoints, among the keypoints of the first group, having the highest keypoint relevance probabilities to form a second group of keypoints, and exploiting the keypoints of the second group for analyzing the image. The local feature relevance probability calculated for a local feature of a keypoint is obtained by comparing the value assumed by the local feature with a corresponding reference statistical distribution of values of the local feature.

The invention provides an inter-well connectivity evaluation method based on machine learning, and the method comprises the steps: 1), obtaining a data set which comprises dynamic data and static dataaccording to a numerical simulation technology; 2) performing feature relevance extraction on dynamic data in the sample data set; 3) normalizing the dynamic data and the static data in the reservoirsample; 4) dividing the sample data set into a training set and a test set, and constructing input and output of a machine learning model; 5) training the weight matrix and the bias matrix of the model by using a machine learning method to obtain a training model; 6) verifying the accuracy and effectiveness of the normalized calculation result of the training model; and 7) defining an inter-wellconnectivity coefficient by utilizing the training model according to the stratum average permeability calculated by the dynamic data, and representing the inter-well connectivity. According to the method disclosed by the invention, reservoir geological information is obtained by only needing the dynamic production data of each well, which is most easily obtained in an oil field, so that the inter-well connectivity is obtained.

Membrane proteins are difficult to express in recombinant form, purify, and characterize, at least in part due to their hydrophobic or partially hydrophobic properties. Membrane scaffold proteins (MSP) assemble with target membrane or other hydrophobic or partially hydrophobic proteins or membrane fragments to form soluble nanoscale particles which preserve their native structure and function; they are improved over liposomes and detergent micelles. In the presence of phospholipid, MSPs form nanoscopic phospholipid bilayer disks, with the MSP stabilizing the particle at the perimeter of the bilayer domain. The particle bilayer structure allows manipulation of incorporated proteins in solution or on solid supports, including for use with such surface-sensitive techniques as scanning probe microscopy or surface plasmon resonance. The nanoscale particles facilitate pharmaceutical and biological research, structure / function correlation, structure determination, bioseparation, and drug discovery.

The invention relates to the technical field of data analysis, and discloses a data analysis method and device based on multi-modal data fusion, equipment and a medium, and the method comprises the steps: collecting visual data, audio data and process text data, carrying out the preprocessing and standardization processing of different types of data, constructing a multi-modal data set with aligned timestamps, and storing the multi-modal data set in a database; the method comprises the following steps: extracting a time-frequency dynamic feature and a semantic vector feature, extracting a map structure feature, a time-frequency dynamic feature and a semantic vector feature, fusing the features by using a cross-modal attention mechanism to generate a fused feature vector, finally performing analysis processing based on the fused feature vector, and outputting an analysis result. According to the method, the multi-modal data set with consistent time is constructed, the structural features of various modals are extracted, and the cross-modal attention mechanism is introduced to realize deep fusion of the feature level, so that the problems of single information utilization and weak feature relevance of the existing detection means are solved, and the comprehensiveness of defect detection and the accuracy of fault diagnosis are improved.

The invention discloses a feature extraction method, device and server, and a computer readable memory medium and belongs to the field of the mobile Internet. The method comprises the steps of: pre-grouping a pre-training data set of a wireless side and a user side according to feature relevance, thereby obtaining initial model parameters; carrying out grouping feature relevance computing on the training data set according to the initial model parameters, classifying features of the training data set into corresponding groups, and updating the model parameters; and carrying out iterative optimization on feature contraction variables of each group of features, thereby obtaining a feature selection result of the wireless side and the user side. According to the method, the device, the serverand the computer readable memory medium, through utilization of a feature grouping selection mechanism, feature samples are pre-grouped before feature extraction is carried out; the grouping featurerelevance computing can be carried out on newly increased features; the feature redundancy computing problem can be effectively solved; grouping optimization is further carried out on grouping features through importing of the feature contraction variables; feature grouping selection efficiency is greatly improved; and online dynamic data feature extraction can be supported.

The invention relates to an attention-fused single image rain removal method, which comprises the following steps of: firstly, carrying out batch normalization processing on an input image, and then inputting the input image into an encoder network in which a three-dimensional attention mechanism and a residual dense block structure are combined to obtain high-dimensional features; the global feature relevance is calculated by using a Transform mechanism; reducing the feature matrix to the size of an original input image step by step by using a decoder constructed by a three-dimensional attention residual dense block to obtain an output image; in order to solve the problem that image structure information and detail high-frequency information are erased due to an algorithm in the rain removal process, multi-scale structural loss and a common rain removal loss function are combined to participate in rain removal network training. According to the invention, a rain-removed image with higher quality can be obtained by carrying out rain removal on a single rain image. According to the method, the three-dimensional attention mechanism, the Transform and the coder-decoder architecture are combined, so that the rain removal performance of the network can be better improved.

A system for feature relevance visualization optimization is provided. The system comprises a controller configured for modifying placement of features in a relevance visualization. The controller is further configured to: receive interaction data comprising one or more features positioned in the relevance visualization, wherein the one or more features are defined and measurable properties of the interaction data; construct a logical grouping of the one or more features based on a type of each of the one or more features, wherein similar features are collocated in the relevance visualization; construct a machine learning-based grouping of the one or more features based on relevance calculations for the one or more features; combine the logical grouping and the machine learning-based grouping to generate a combined feature placement, wherein the one or more features are repositioned in the relevance visualization; and output the relevance visualization having the combined feature placement.

The invention provides a multi-modal 3D target detection method and a system thereof. The method comprises the following steps: respectively extracting features of an original image I and a corresponding LiDAR point cloud L; carrying out point and pixel feature fusion on the features of the original image I and the corresponding LiDAR point cloud L to form LiDAR point cloud features, taking the features of the original image I as image features, and respectively generating a 3D region proposal and a 2D region proposal; extracting features from the 3D area proposal and the 2D area proposal respectively and fusing, and generating a final 3D target detection result. Meanwhile, the invention provides a corresponding terminal and a medium. According to the method, target detection is completed by using a geometric constraint relationship and feature relevance between modals; a 3D target detection task is completed through feature fusion of a point-pixel level of a first stage and a region proposal level of a second stage; and a high-quality regional proposal is generated by using geometric constraints between the image and the LiDAR point cloud.

The invention provides a screening method of individualized medicine. The method includes: building a disease-related pathogenic protein molecule database, building a paint individual clinical disease course symptom-protein pathogenic factor response feature relevance database, building a disease model target medicine-protein response relevance database, and acquiring a medicine screen result. The screening method has the advantages that the method is brand new and pioneering and used for individualized precise medical treatment, genetic and environment pathogenic factors and patient disease course features can be accurately and comprehensively reflected in the detecting and analyzing result of protein molecules, and objective, precise and individualized treatment medicine applicable to different patient disease course features is screened according to the target medicine's correction of the pathogenic protein molecules.

The invention discloses a recommendation system-oriented privacy sensitive parameter identification and accurate deletion method, and relates to the technical field of recommendation system model optimization and privacy protection. In order to solve the problems that privacy sensitive parameters in an existing recommendation system model are difficult to accurately position and the model performance loss is too large after deletion, according to the evaluation thought of parameter importance and data feature relevance, importance scores of model parameters on two types of data sets are calculated respectively by dividing a forgetting set and a reservation set, and the privacy sensitive parameters are obtained. The privacy sensitive parameters with the forgetting set importance higher than the reserved set importance are screened out, and mask zero setting processing is carried out. According to the method, the model does not need to be retrained or subjected to weight updating, sensitive parameter recognition and deletion can be completed only through single-time forward propagation, and the original recommendation performance of the model is reserved to the maximum extent while the privacy security of a recommendation system is guaranteed. According to the method, accurate identification of privacy sensitive parameters is realized on a mainstream recommendation model, the reduction range of model recommendation accuracy after deletion is controlled within an acceptable range, and the privacy leakage risk is remarkably reduced.

A control valve conditioning method in an electrohydraulic pressure control unit comprising at least one electrically triggered solenoid valve that is controlled in an analog manner. The solenoid valve is operated at a specific operating current according to a functional correlation or characteristic diagram between the valve current and the differential pressure characteristic curve when the pressure is controlled, said functional correlation or characteristic diagram being stored in the pressure control unit. The method comprises the following steps: a) temporarily applying at least one anti-hysteresis pulse to the solenoid valve during which a current is set far below or far above the operating current in the valve; b) applying the anti-hysteresis pulse at the desired operating current before or during controlled operation, and c) applying the anti-hysteresis pulse wherein the duration is limited in such a way that the anti-hysteresis pulse has largely no influence on the brake pressure.

The invention relates to the technical field of automobile electronic intelligent fault diagnosis, and discloses a multi-modal data fusion automobile air conditioner controller abnormal state monitoring method, which comprises the following steps: deploying five types of intelligent sensor nodes at key positions of an automobile air conditioner system to realize hardware-level time synchronization and adaptive sampling; a fast ICA algorithm is combined with sliding window processing to realize signal separation, a self-adaptive wavelet basis selection mechanism is designed to carry out time-frequency analysis, and principal component analysis is used to carry out feature dimension reduction; constructing a lightweight attention fusion network, dynamically adjusting different modal feature weights, and mining feature relevance through a cross-modal interaction module; a hierarchical progressive anomaly detection architecture is designed, a statistical method and a neural network detection result are fused, a time consistency constraint mechanism is established, and multi-time scale anomaly prediction is realized; and fault type identification and severity evaluation are carried out in combination with an expert knowledge base, and a multi-priority protection strategy and an emergency plan are formulated.

A control valve conditioning method in an electrohydraulic pressure control unit comprising at least one electrically triggered solenoid valve that is controlled in an analog manner. The solenoid valve is operated at a specific operating current according to a functional correlation or characteristic diagram between the valve current and the differential pressure characteristic curve when the pressure is controlled, said functional correlation or characteristic diagram being stored in the pressure control unit. The method comprises the following steps: a) temporarily applying at least one anti-hysteresis pulse to the solenoid valve during which a current is set far below or far above the operating current in the valve; b) applying the anti-hysteresis pulse at the desired operating current before or during controlled operation, and c) applying the anti-hysteresis pulse wherein the duration is limited in such a way that the anti-hysteresis pulse has largely no influence on the brake pressure.

The invention provides an airport terminal building heating, ventilation and air conditioning load prediction system and method based on a micro-service architecture. The method comprises the following steps: collecting multi-source heterogeneous original data and extracting a key feature set; mining space-time relevance between people flow and equipment operation, and outputting a space-time characteristic matrix; and constructing a multi-algorithm fusion framework, carrying out cross-terminal distributed cooperative training and dynamic weight aggregation through federal learning, introducing a lion group optimization algorithm to optimize global parameters, and outputting an airport terminal heating ventilation air conditioning load prediction result. Fusion data are standardized, key features are extracted in combination with automatic feature engineering, and the data utilization rate and feature relevance are improved; then capturing a space-time association mode by using a space-time diagram convolutional network, constructing a multi-algorithm fusion framework and dynamically allocating weights; then realizing distributed cooperative training by adopting federal learning, and optimizing parameters in combination with a lion group optimization algorithm to enhance the generalization ability of the model; and finally, through incremental learning dynamic iterative optimization, the prediction precision is continuously improved.

The invention solves the problems such as feature extraction, asynchronization and synchronization, feature relevance and data difference value to fuse visual data and laser radar data so as to generate three-dimensional color depth image data, namely a three-dimensional color laser data point cloud, thereby providing precise distance information and rich environment information, effectively overcoming the defects of the traditional laser radar and the visual sensor in the aspects of robustness, information amount, precision and cost. The invention integrates a two-dimensional laser radar, a monocular vision sensor, an inertial navigation data measuring unit, a driving motor and the like into an information fusion-based three-dimensional color laser radar integral unit with universal applicability and high precision, and utilizes inertial navigation data and visual data to perform secondary alignment on laser radar data, the structure is simple, equipment does not need to be subjected to precise calibration, the performance is reliable and stable, the practicability is strong, and the method and the device can be widely used in various indoor and outdoor environments under the motion condition, and have certain universal applicability.

The invention discloses a Grad-CAM improvement method based on gradient flow direction correction and feature contribution degree redistribution, and relates to the technical field of deep learning model interpretation. Aiming at the defects that in a traditional Grad-CAM algorithm, gradient averaging causes positioning fuzziness, feature relevance is not considered in channel weight calculation, and the channel weight calculation only depends on single-level features, optimization is achieved through three key improvement steps that firstly, gradient flow direction tracking is adopted to replace global averaging to calculate channel weight, and gradient space distribution information is reserved; secondly, feature contribution degree redistribution is carried out based on channel cosine similarity, and weight superposition of redundant features is avoided; and finally, fusing the features of the intermediate layer to perform detail compensation, and enhancing the positioning precision of the thermodynamic diagram. The accuracy and robustness of model explanation are remarkably improved while the lightweight characteristic of an original algorithm is kept, and the method is particularly suitable for scenes needing high-precision explanation, such as model explanation analysis in the deep learning field.