4 results about "Negative correlation" patented technology

The invention relates to the technical field of cooperative control, in particular to a cooperative optimization control method and system for the expansion degree and strength of flow-state solidified soil, and the method comprises the steps: designing a sample according to all influence factors, measuring performance data, and forming test data; constructing a correlation matrix through preprocessing such as abnormal value elimination, variable standardization and virtual variable conversion; screening significant influence items through a variance analysis model and quantifying weights; constructing a dual-output prediction model based on a random forest algorithm, and performing training verification optimization; taking the prediction model as a constraint, and combining economy and convenience to screen an optimal parameter combination; on-site trial mixing verification is carried out, deviation reaches the standard, parameters are determined, and otherwise, data are complemented to update the model to resolve. According to the method, the single factor and the interaction effect are effectively removed, the problem of collaborative prediction under negative correlation of the expansion degree and the strength is solved, collaborative optimization of the expansion degree and the strength is realized, and the scientificity and efficiency of construction parameter determination are improved.

The invention relates to the field of data processing, in particular to a financial statement abnormal data detection method. The method comprises the following steps: firstly, carrying out standardization processing on collected financial statement data, calculating a Spearman rank correlation coefficient, and generating an incidence matrix; counting all Spearman rank correlation coefficients in the incidence matrix, and dynamically setting positive and negative correlation thresholds; then, based on a Spearman rank correlation coefficient and positive and negative correlation thresholds, classifying the index relations; based on the standardized financial statement data and the index relationship, introducing a positive and negative and uncorrelated fluctuation feature extraction algorithm, and extracting fluctuation features; on the basis of the Spearman rank correlation coefficient and the fluctuation characteristics, an abnormal score is calculated in a segmentation mode; and finally, comparing the abnormal score with an abnormal threshold value, and judging whether the data is abnormal data or not. The technical problems that the influence of abnormal values on a correlation analysis result is too large, the dependency relationship between financial indexes is neglected, and fluctuation feature extraction is insufficient are solved.

The invention relates to the technical field of rehabilitation training, in particular to an evaluation training method and system based on sitting and standing rotation, and the method comprises the steps that data of a patient during evaluation are collected, and the data comprise the rotation angle of the waist of the patient, pressure data of the patient when the patient sits down and pressure data of the patient when the patient stands; and calculating the waist obstacle degree of the patient, and evaluating the training effect according to the waist obstacle degree. According to the method, a multi-parameter evaluation model of the waist obstacle degree is constructed by comprehensively collecting the waist rotation angle and the pressure data during sitting and standing, the three key indexes including the left and right pressure symmetry index, the balance coefficient and the rotation obstacle index are covered, and quantitative evaluation is achieved in combination with a weighted calculation formula. The model can accurately reflect the waist function state of a patient, each index is in negative correlation with the waist obstacle degree, the function degradation trend can be found in time, and the objectivity and accuracy of an evaluation result are guaranteed.

The present application relates to the field of health care information technology, and in particular to a primary liver cancer postoperative micro-metastasis detection method based on multispectral molecular imaging. A high-frequency echo proportion map is constructed by means of an undetected radio frequency signal, and a liver parenchyma region is segmented to exclude scar interference; a pulsation amplitude map is extracted by means of a multispectral photoacoustic time sequence image, and the phase is corrected in speed by means of the high-frequency echo proportion map to eliminate speed distortion caused by the scar; background subtraction is performed based on the average drift trend of the liver parenchyma region to generate a net signal enhancement map; a negative correlation linear model of the pulsation amplitude and the net signal is fitted in the liver parenchyma, and the residual is calculated to represent metabolic clearance abnormalities; the residual and the corrected phase map are weighted and fused to generate a supply and demand imbalance index, and accordingly, an abnormal region is adaptively identified. The method effectively decouples structural artifacts and abnormal regions, and significantly improves detection specificity and positioning accuracy.