132 results about "Interval Sequence" patented technology

A method and apparatus for trainning a fraud detection model and a method and apparatus for fraud detection are provided, includes acquiring target history operation behavior information of a plurality of sample users at a sampling time when the target history operation behavior occurs and in a preset history period before the sampling time, and label information indicating whether or not a fraudbehavior occurs at the sampling time for each sample user, and obtaining the target history operation behavior information of the sample users at the sampling time. According to the acquired historical operation behavior information of the target, the behavior feature vector sequence and the time interval sequence under each operation type are generated. Based on the sample user's behavior eigenvector sequence, time interval sequence and label information, the fraud detection model is trained to obtain the fraud detection model. The present application can analyze the current target operationbehavior of the user when using the electronic bank according to the target historical operation behavior and the current time target operation behavior, and improve the accuracy of judging whether the current target operation behavior of the user is a fraudulent behavior or not.

The invention provides a signal processing method and device for frequency-agile radar based on a variable repetition frequency technology. The method includes the following steps: designing a frequency point sequence of random hopping according to a random number and the carrier frequency related parameters of radar, and designing a pulse time interval sequence according to the frequency point sequence and the distance range of a target to be detected; emitting a radar pulse signal according to the designed frequency point sequence and the designed pulse time interval sequence, receiving an echo signal of the radar pulse signal, and sampling and preprocessing the echo signal to obtain a baseband echo sampling signal; processing the baseband echo sampling signal by a single pulse to obtaina time-domain echo signal after pulse compression; and coherently accumulating the time-domain echo signal after pulse compression in the two dimensions of frequency point and pulse number, and obtaining the fine resolution distance and Doppler velocity values of the target to be detected through threshold decision. Accurate detection of the distance and velocity of a moving target by coherent frequency-agile radar is realized, and the amount of computation for the processing of coherent frequency-agile signals can be reduced.

The invention discloses a data parallel sequencing method and system. The system comprises a data source, a plurality of parallel processing units connected with the data source through a network and a communication interface. The method comprises the steps that data to be sequenced are divided into a plurality of data blocks, and the parallel processing units respectively obtain the data blocks and conduct sampling; a first parallel processing unit summarizes and sequences sampled data of the parallel processing units, the global sequencing interval sequence is determined according to the parallel processing units, and data intervals in the global sequencing interval sequence sequentially correspond to the parallel processing units; the parallel processing units judge the data intervals to which the data in the data blocks obtained by the parallel processing units belong, and the data are distributed to corresponding parallel processing units; the parallel processing units receive the data and conduct global sequencing; global sequencing results of the parallel processing units are combined in a sequencing mode. The data parallel sequencing method and system improve sequencing speed of large-scale data and meanwhile have high expansibility to data volume.

The invention discloses a sleep state determination system based on motions and HRV measurement. The system comprises a triaxial acceleration sensor module, a limb motion counting module, an optical sensor module, a pulse wave signal calculation module, a heart rate and heartbeat interval calculation module, a heart rate variability index calculation module and a sleep state calculation module which are connected in sequence. Human body limb three-dimensional acceleration data within a set period of time is collected; the number of limb motions within the set period of time is counted; skin surface light intensity change information caused by blood flow volume changes in blood vessels of a user is detected; pulse wave signals are obtained; the heart rate and the each-beat heartbeat interval time are calculated; the heart rate or heartbeat time interval sequence is analyzed, and heart rate variability related indexes are obtained; a sleep state stage-by-stage algorithm model is used for calculating the human body sleep state. According to the sleep state determination system, the human body sleep state monitoring accuracy and convenience are greatly improved, people can be effectively guided to improve the sleep state and arrange the reasonable sleep time to adjust the body state.

The invention relates to a system and a method for implementing detection on a pulse and a heart rate and monitoring on an emotion and a fatigue degree. The system comprises an optical detection module, a pulse wave signal calculation module, a heart rate and heartbeat interval calculation module, a heart rate variation index calculation module and an emotion and fatigue degree estimation module, wherein the optical detection module is used for detecting information about skin surface light intensity variation caused by variation of a blood-flow volume in blood vessels of a user after light of at least one LED (Light-Emitting Diode) irradiates the surface of skin; the pulse wave signal calculation module is used for acquiring a pulse wave signal according to the light intensity variation information; the heart rate and heartbeat interval calculation module is used for calculating the heart rate and interval time of each stroke of heartbeat; the heart rate variation index calculation module is used for carrying out analysis on a heart rate or heartbeat time interval sequence to obtain related indexes of heart rate variation; the emotion and fatigue degree estimation module is used for estimating the fatigue degree and the emotion state according to the related indexes of the heart rate variation. The system and method for implementing detection on the pulse and the heart rate and monitoring on the emotion and the fatigue degree, which adopt the structure, are greatly improved in comfort and convenience, are economic and practical and have a wider application range.

The invention discloses a high-speed press slider mechanism size optimization method based on interval constraint violation degrees. The method comprises the following steps: firstly establishing a high-speed press slider mechanism size optimization model based on interval variables; then establishing a polynomial response surface model capable of predicating values of an object function and a constraint function; Solving the slider mechanism size optimization problem based on the interval variables by utilizing two nested genetic algorithms; calculating the upper and lower limits of object and constraint intervals corresponding to all individuals in an outer-layer genetic optimization process by utilizing the inner-layer genetic algorithm and the polynomial response surface model so as to obtain corresponding interval midpoints and radiuses, and calculating the corresponding interval constraint violation degrees; performing good and bad sequencing on all the individuals in an outer-layer genetic optimization population by utilizing preferable relation maxim of an interval sequence, so as to determine the adaptability; when the out-layer optimization achieves maximal evolutionary algebra, outputting the individual with the greatest adaptability value as an optimal solution. The method disclosed by the invention can be used for truly realizing the press slider mechanism size optimization in which the interval uncertainity is considered.

The invention provides a heart failure detection method based on an electrocardio-interval sequence normalized histogram and a device thereof. The detection method comprises the following steps: (1) electrocardiosignals of a testee are collected; (2) the analog-digital conversion is carried out on the electrocardiosignals, and electrocardio-waveform data are stored; (3) R wave peak value points of the electrocardiosignals are extracted to construct an electrocardio-interval sequence RR; (4) the effectiveness of the RR sequence is tested; (5) the RR electrocardio-interval sequence normalized histogram is constructed; (6) two specific indexes of center-edge rate (CER) and cumulative energy (CE) of the normalized histogram are calculated; (7) the heart failure course of the testee is evaluated according to the indexes of CER and CE. The detection device comprises an electrocardiosignal detection module, an analog-digital conversion device and a computer. Based on the two specific indexes of CER and CE of the electrocardio-interval sequence normalized histogram, the heart failure course of the testee is evaluated, the heart failure course of the testee can be detected noninvasively, conveniently and quantitatively, and the discrimination index is high.

The invention discloses a user identity verification method and device based on user operation habits and a contact area. The method comprises the following steps that: obtaining a contact area and areference touch area model corresponding to first business when a user to be verified triggers a first business operation; obtaining the quantization value of a behavior feature, wherein the behaviorfeature comprises one of or a plurality of gyroscope fluctuation behaviors, sliding behavior features, click behavior features and input time interval sequence behavior features; according to behaviorfeature identification and the business identification of the first business, obtaining the quantization value change range of the behavior features corresponding to behavior feature identification and business identification from a behavior feature library; and according to a corresponding relationship between the contact area and the reference contact area model and a relationship between the quantification value of the behavior feature and the obtained quantification value change range, determining the validity of the user to be verified. Therefore, an identity verification method in the prior art is optimized, the safety of the identity verification is improved, the success rate of the malicious attack of lawbreakers is lowered, and the interest of a user is guaranteed.

The invention discloses a quantitative cardiopulmonary system interaction analysis method which includes the steps: acquiring multi-lead physiological signals of a subject in nocturnal sleep; marking sleep stages of the signals and extracting an RR interval sequence, a PP interval sequence, a PTT sequence and an RA interval sequence; synchronously segmenting the four sequences according to 5-minute duration in the same sleep state and then extracting three characteristic parameters: low-frequency Shannon entropy, high-frequency Shannon entropy and transfer entropy; training a neural network, determining neural network parameters and building a neural network cardiopulmonary interaction evaluation model; evaluating the cardiopulmonary function of the subject by the trained neural network and outputting evaluation results. Cardiopulmonary coupling is analyzed by multi-variable time sequence analysis technology, multiple variables such as cardiac cycle, respiration and blood pressure are analyzed by a frequency domain and information analysis method, analysis deficiency of single variable is effectively remedied, so that a complicated regulation mechanism between cardiopulmonary systems is more accurately and comprehensively quantified, the coupling strength of cardiopulmonary interaction is quantified, and the direction of cardiopulmonary interaction can be judged.

The invention provides a salmonella CRISPR (clustered regularlay interspaced short palindromic repeats) sequencing typing method; according to the method, by DNA sequencing of a latest interval sequence between Salmonella CRISPR1 site and CRISPR2 site, CRISPR type of a strain to be detected can be determined, and the Serotype can be predicted. The method is simple, rapid, low-cost and high-resolution, is high in consistency in salmonella serotyping results, and low in requirements on laboratory equipment and software, a new CRISPR type comprises bacterial evolution and regional and other various information, and by combination of a fluorescence probe and other methods, real time and rapid detection can be realized, and the method has popularization and application value.

The invention discloses a time sequence prediction model-based alarm threshold value setting method and device. The method comprises the following steps of: obtaining time sequence monitor data of a to-be-set monitor index; determining a maximum value and a minimum value under each time unit in the time sequence data so as to generate a maximum value sequence and a minimum value sequence; creatinga time sequence prediction model for the maximum value sequence and the minimum value sequence; predicting change conditions of the to-be-set monitor index in q time units in the future by utilizingthe time sequence prediction model for the maximum value sequence and the minimum value sequence so as to obtain a maximum value prediction sequence and a minimum value prediction sequence; and obtaining an alarm interval sequence of an alarm threshold value according to an initial threshold value of an alarm threshold value of the determined to-be-set monitor index, the maximum value prediction sequence and the minimum value prediction sequence. The method and device are capable of realizing self-adaptive setting of monitor data alarm threshold values of data center infrastructures, and are beneficial for improving the operation efficiency of data center infrastructures.

The invention relates to a micro RNA (ribonucleic acid) fluorescence detection probe. The probe has a folding structure, and comprises a tail-end area and an annular area, wherein the tail-end area has a double-chain structure; the annular area has a single-chain structure and comprises a complementary sequence and an interval sequence of a target to be detected; and the interval sequence does not form a secondary structure with other sequences of the probe. By the tail-end area of the probe, the relative stability of the folding structure of the probe can be maintained; the folding structure is opened when a sample containing a detection object is added, a complementary primer of the tail-end area of the detection probe is added, and a deoxyribonucleic acid (DNA) polymerase without excision enzyme activity is added; micro RNA is released by extension of the primer and replacement of corresponding chains to allow the probe to recover and generate a fluorescence signal; the corresponding target micro RNA is detected by the generated detection fluorescence signal; and different fluorescence is marked according to the probes of the different RNAs, so that the simultaneous detection of the different micro RNAs can be realized.

The embodiment of the application provides a method and device for identifying access attacks. The method comprises the following steps: acquiring a first time interval sequence of the adjacent access in each access from the current identification user or IP in a first preset range; implementing spectrum analysis on the first time interval sequence to obtain the weight coefficients of the fundamental frequency and each subharmonic frequency of the first time interval sequence; judging whether the ratio of the weight coefficient of the fundamental frequency of the first time interval sequence to the average value of the weight coefficients of each subharmonic frequency of the first time interval sequence is greater than the preset threshold value; and if the ratio is greater than the preset threshold value, identifying each access from the current identification user or IP in the first preset range as the access attack. According to the method and device provided by the embodiment of the application, the identification is processed based on the time interval sequence of the adjacent access in each access from the same identification user or IP, and thus the diversity of various access can be shielded, the various access can be effectively identified, and relatively good universality can be achieved.

The invention discloses an interval uncertainty optimization method based on BP neural network differentiation and interval analysis. The interval uncertainty optimization method comprises the steps of training a BP neural network agent model of an original model; employing NSGA-II algorithm in an outer-layer optimization solver, calculating an inner layer interval by adopting an interval analysismethod; for each group of design variables, carrying out interval division by adopting a sub-interval technology; inputting the interval median of the subinterval combination into a neural network tocalculate an output response, carrying out a neural network first-order differential operation, carrying out first-order Taylor series expansion on the uncertainty objective function and the constraint function, and calculating the intervals by adopting an interval expansion method and an interval set method; converting the uncertainty optimization model into a multi-objective determinacy optimization model through an interval sequence, an interval possibility and an error economy evaluation index; and using NSGA-II algorithm for performing simulation search to obtain a Pareto optimal solution set. Through the method, the nonlinear interval uncertainty optimization problem, especially the engineering uncertainty optimization problem, can be efficiently solved, and the method has high engineering practical value.

The invention discloses a detection method of a time-sequence type covert channel based on a neural network. The method comprises the steps of obtaining three feature values of a time interval sequence including a variable coefficient, similarity and an entropy value according to a time interval between data packages; taking a four-dimensional feature vector consisting of the variable coefficient, the similarity, the entropy value and a channel type is a training sample of the neural network to train; detecting by the neural network to judge whether the communication channel has the convert channel and the belonged type after the neural network is astringed.

The present invention discloses a parameter optimization design method of a variable parameter high squint satellite-borne beam bunching SAR (Synthetic Aperture Radar) system. The method comprises: obtaining basic parameters of an earth observation task; calculating system parameters derived from the basic parameters; fitting a satellite orbit coordinate polynomial, and estimating the initiation and termination sampling time scales; setting an orientation sampling number, and calculating a sampling time interval and an earth surface drift angle sequence corresponding to a scene center; determining a satellite sampling position sequence, the slope distance sequence of the scene center and a time sampling interval sequence; verifying constraint condition of a point echo interference without transmission pulse shielding and satellite; and calculating the time variant regulation rule of radar platform parameters. According to the invention, a theoretical basis and a realization method are provided for the design requirement of a variable parameter high squint satellite-borne beam bunching SAR system.

The invention relates to an oligonucleotide microarray technique for detecting pathogen contamination in seawater, belonging to the field of seawater contamination monitoring. The technique comprises the main technical schemes that a 16S-23S rRNA gene transcription interval sequence is used as a detection target and is amplified by a one-step polymerase chain reaction, a digoxin mark is obtained simultaneously, and then oligonucleotide hybridization is carried out; and the obtained monitoring result is interpreted in a manner that an enzyme-labeled antibody catalyzes the substrate colour development. Compared with the traditional product for detecting seawater contamination, the invention utilizes microarray detection to obtain the distribution situation of large numbers of pathogens and contamination index bacteria, and has the advantage of high flux; the invention can directly utilize seawater as a sample and truly obtain the contamination situation information of target bacteria under a condition of keeping the natural proportion of the flora number in the seawater; however, most existing detection techniques need the step of enrichment culture, destroy the original proportion of a flora composition, have lower reliability of the result and have longer detection procedure; and the oligonucleotide microarray detection operation has short procedure and is comparatively sensitive and fast.