43results about How to "Prediction is accurate and reliable" patented technology

A device is provided for compression of objects such as parts of the body. The device has the form of a band that can be shaped like a sleeve, wrap or garment that is sized to encircle the body part or other compressible object and having a component or components made of an elastic material. Indicia such as tick marks or scales are printed on the device. The stretch of the elastic material as the device is tensioned around the body part causes increased separation of the indicia or movement of a free end of the band with respect to the indicia. A system measures the separation of the indicia and converts it to compression as a function of the circumference of the body part. The system may be a card having edges with measurement scales or the scales may be printed on the device and the displacement of a free end of a band or sub-band of the device with respect to the scales indicates the compression for particular circumferences of the body part. The device may have additional scales printed on it for measuring the circumference of the body part.

The disclosure is related to a medical device, a system, a method and a storage medium for prediction of a value related to a medical condition. More particularly the invention relates to prediction of glucose in the blood or prediction of blood pressure. The disclosure enables improved control of glucose in the blood or of blood pressure, since prediction can be made with higher accuracy, even when switching between dynamic modes, corresponding to different states, such as exercising. In one embodiment a medical device (1) is provided, which comprises: a predicting unit (2) for prediction of a value related to a medical condition of a patient at a future point in time, based on at least a measured present value related to the medical condition of the patient; wherein the predicting unit (2) comprises an ensemble predictor (3), for predicting the value at a future point in time, continuously adaptable to different predictor modes based on different states of the patient.

In a method for course prediction in driver assistance systems for motor vehicles, a dynamic course hypothesis is created on the basis of vehicle-dynamics data of the vehicle, which method includes the following steps:

• • creating an infrastructure course hypothesis on the basis of data from at least one information source that describe the traffic infrastructure;
  • calculating, on the basis of features of the information source, a weighting factor that describes the reliability of the infrastructure course hypothesis; and
  • fusing the infrastructure course hypothesis with the dynamic course hypothesis, with weighting in accordance with the calculated weighting factor, to produce a definitive course hypothesis.

A system and method for monitoring the operating condition of a wheelset on a railcar comprising a sealed unit mounted on or near a wheelset of the railcar for collecting data from the wheelset and performing AI analyses on the collected data to determine the operational condition and predict failure modes for the wheelset. Results are communicated off-railcar wirelessly via one or more of several different methods.

The invention provides an urban traffic abnormality identification method based on a complex network theory. The method comprises the following steps: step 1, constructing an urban traffic network based on traffic data; step 2, carrying out feature extraction and screening based on a complex network theory; step 3, carrying out the abnormality recognition and prediction of a traffic system; and step 4, evaluating and verifying a model. According to the invention, the scientific and reliable technical support and theoretical support can be provided for the recognition and prediction of the urban traffic congestion abnormality based on the complex network theory and a machine learning method. Therefore, the congestion abnormality of the urban traffic system can be efficiently and accuratelyidentified and predicted, and the method has important significance in ensuring the healthy and stable operation of the urban traffic system and improving the reliability of the urban traffic system;and the method is scientific and good in manufacturability and has the great application and popularization value.

An iced conductor sleet jump simulation testing method is disclosed, where after an initial tension of a conductor and an initial displacement of the conductor in a static state are obtained by using a combination of a given meteorological condition and a typical meteorological condition, displacement and tension states of the conductor in a dynamic state at each discrete moment can be accurately and reliably predicted until a specific time arrives.

The invention discloses a welding fatigue analyzing method based on a rough set theory. The method comprises the following steps of S100, according to a plurality of sets of welded joint fatigue tests, establishing a fatigue database at least containing load attributes, maximum structural stress and number of cycle times; S200, calculating a structural stress change range delta (sigma s) for the maximum structural stress in the fatigue database; constructing attributes for the delta (sigma s) and the number of cycle times; generating decision attribute values in the rough set database, and writing into the rough set database; S300, using the welded joint basic parameters in the fatigue database as conditional attribute values in the rough set database, and writing into the rough set database; and S400, carrying out conditional attribute reduction and conditional attribute value reduction on the obtained rough set database containing the decision attribute values and the conditional attribute values by an united entropy reduction algorithm, so as to obtain a rough set decision rule model; and applying the rule model to analyze the welding fatigue data to obtain the rough set judging results, and then completing the fatigue welding analysis.

A method and system of predicting market information includes the steps of receiving first data, forecasting further data based on the first data, receiving second data and comparing the further data with the second data, and creating an adjustment factor to account for any difference between the further data and the second data.

In various embodiments, an encoder comparison application compares the performance of different configured encoders. In operation, the encoder comparison application generates a first global convex hull of video encode points based on a first configured encoder and a set of subsequences included in a source video sequence. Each video encode point is associated with a different encoded version of the source video sequence. The encoder comparison application also generates a second global convex hull of video encode points based on a second configured encoder and the subsequences. Subsequently, the encoder configuration application computes a performance value for an encoding comparison metric based on the first global convex hull and the second global convex hull. Notably, the first performance value estimates a difference in performance between the first configured encoder and the second configured encoder.

The invention discloses a power load forecasting method suitable for multiple scenes, which comprises the following steps of: selecting a region to be forecasted; obtaining and sorting the influencingfactors of load forecasting in the region to be forecasted; acquiring historical data of influence factors of load forecasting in the area to be forecasted; selecting a load forecasting model of thearea to be forecasted; establishing a load forecasting model of the area to be forecasted; forecasting the electric load of the area to be forecasted. The method of the invention considers each influence factor which affects the electric power load forecasting, and builts load forecasting models in multiple scenes, so that the load forecasting method realizes load forecasting under the condition of multiple influencing factors, and simultaneously the method adopts different load forecasting models to forecast and combine multiple types of scenes, so that the method of the invention can more accurately and reliably forecast the future load, and the method of the invention is simple, reliable, scientific and practical.

The invention discloses a method for predicting volume shrinkage of a cavern in a salt-cavern underground gas storage, and belongs to the technical field of underground space. The method comprises: obtaining actual volume shrinkage of the cavern for n consecutive years; establishing a GM(1,1) prediction model group in combination with a grey theory according to the actual volume shrinkage of the cavern for n consecutive years, wherein the GM(1,1) prediction model group comprises m GM(1,1) prediction models; determining volume shrinkage of the cavern for n consecutive years by adopting a first GM(1,1) prediction model, obtaining n prediction results, establishing a Markov prediction model, and predicting a state of volume shrinkage in next year; determining an average value of volume shrinkage prediction values of the GM(1,1) prediction model group in the next year; and according to the average value and the state of the volume shrinkage, determining the volume shrinkage in the next year. According to the method, the volume shrinkage in the next year is predicted, so that the frequency of measurement by using a cavern sonar is reduced and the leakage risk due to sonar detection under pressure is lowered.

The invention discloses an agricultural product price prediction method based on SHD-ELM. The method comprises the following steps: firstly, collecting agricultural product price time series data; decomposing the original agricultural product price time sequence into a plurality of intrinsic mode functions (IMF) and remainders by utilizing empirical mode decomposition; secondly, performing secondary hybrid decomposition on the influence of the irregularity of the IMF1 component with the strongest fluctuation on prediction, namely performing wavelet transform on IMF1 to decompose the IMF1 intoan approximate sequence and a detail sequence; predicting all components obtained after decomposition by using an extreme learning machine; and finally, combining the prediction results of the components to obtain a prediction value of the original agricultural product price time sequence. The agricultural product price is accurately predicted, and the prediction error is very small. Compared withprediction methods such as a BP neural network, the prediction method combining empirical mode decomposition, wavelet transform and an extreme learning machine has good agricultural product price prediction performance and can be suitable for prediction of agricultural product price fluctuation rules.

The invention discloses a method for predicting viscosity characteristics of cellulose bio-ink. The method comprises the following steps: S1, carrying out a shear scanning test on the cellulose bio-ink by using a rotational rheometer to obtain shear rate-viscosity data; s2, obtaining viscosity characteristics of the cellulose bio-ink according to the shear rate-viscosity curve obtained in the step S1, and providing a candidate viscosity model; s3, by defining optimization variables and determining constraints and optimization targets of an optimization problem, converting a candidate viscosity model parameter determination problem into a multi-target optimization problem so as to determine parameters of each candidate viscosity model; s4, solving the transformed multi-objective optimization problem by using an improved non-dominated sorting genetic algorithm to obtain a Pareto optimal solution; and s5, selecting a single optimal solution from the Pareto optimal solution by using an approximate ideal solution sorting method so as to determine the most suitable viscosity model and viscosity model parameters. Compared with the prior art, the prediction method can accurately and reliably predict the viscosity characteristic of the cellulose bio-ink.

The invention discloses a method and a system for predicting plane distribution of different reservoirs. The method comprises the following steps of S1, acquiring a normalized seismic attribute data volume by using seismic data; S2, processing the normalized seismic attribute data volume to obtain similarity coefficient data of different reservoir types; and S3, performing reservoir probability data calculation on the attribute data of each CDP point on the plane by using the appearance boundaries of different reservoirs and the similarity coefficient data, performing color component normalization and assignment on the data subjected to reservoir probability data calculation, performing color fusion, and displaying. and obtaining a planar graph for reservoir prediction and evaluation. According to the method, a problem that different types of reservoirs, reservoirs and non-reservoirs cannot be accurately predicted and distinguished in the prior art is solved.

The invention relates to an automobile part demand dynamic prediction method, solving the problem of inaccurate spare part prediction in the prior art. The automobile part demand dynamic prediction method comprises the following steps: obtaining historical data of motor vehicle ownership in a target area, and establishing Poisson distribution of the motor vehicle ownership; acquiring the traveledmileage of each motor vehicle in the target area and the fault probability of the target part corresponding to each traveled mileage, and establishing Weibull distribution of the fault rate of the target part based on the traveled mileage of the motor vehicle; determining an expected value of the demand of a random motor vehicle for the target part based on the Weibull distribution; and determining the demand quantity of the target part in the target area in unit time based on the Poisson distribution of the motor vehicle ownership and the expected value. The automobile part demand dynamic prediction method has the advantages that the problem that fitting of the demand quantity of the accessories is inaccurate due to the fact that the failure rates of the accessories are different in the use period is solved, and the demand quantity can be dynamically predicted according to the use conditions of the parts, so that prediction of the demand quantity of the parts is more accurate.

The present invention provides a package comprising an aortoiliac artery graft and a record of a measured pressurized diameter of the aortoiliac artery graft, which measurement has been determined ex vivo under a pressure. A method of processing an aortoiliac artery graft is also provided. The processing method comprises subjecting an aortoiliac artery to a pressure ex vivo, and determining a measured pressurized diameter of the aortoiliac artery under the pressure. A method of treating abdominal aortic aneurysm, infected aortoiliac endograft or a traumatically damaged abdominal aorta or an iliac artery in a patient is further provided. The treatment method comprises anastomosing a processed aortoiliac artery graft with an aorta of the patient on the proximal end and the iliac or femoral arteries on the distal end, wherein a measured pressurized diameter of the processed aortoiliac artery graft has been determined ex vivo under a pressure.

The invention discloses an electric power spot service system fault prediction method and device, computer equipment and a storage medium, and the method comprises the steps: receiving real-time equipment parameter time sequence data of hardware equipment in an electric power spot service system, inputting a first type of deep neural network to obtain the fault probability of the hardware equipment, wherein the first-class deep neural network is obtained through pre-construction, and comprises the steps of receiving equipment parameter time sequence data of hardware equipment in an electric power spot service system before a fault, and constructing an equipment parameter dictionary according to the equipment parameter time sequence data; performing vectorization processing on the equipment parameters by using the equipment parameter dictionary to obtain vectorized equipment parameter time sequence data and training data; and carrying out fine-tuning transfer learning on the training data by using the deep neural network to obtain the first-class deep neural network. According to the invention, safe operation and reliable operation of an electric power spot market and a business system are guaranteed.