3 results about "True positive rate" patented technology

A double cross-entropy loss function is a modification of the standard cross-entropy loss function that is tunable to penalize specific error types, i.e., false positives and false positives for binary classification. A prompt classifier is trained using the double cross-entropy loss function to classify prompts as malicious or benign. The double cross-entropy loss function for the prompt classifier is tuned so that false positive classifications are heavily penalized. The resulting trained prompt classifier maintains a high true positive rate while having a classification threshold that keeps the false positive rate very small. The trained prompt classifier is deployed in a high-load environment for prompt classification.

The data compression analyzer can quickly make a binary decision to compress or not compress an input data block, or it can use a relatively slow neural network to predict the compression ratio of the data block through a regression model. The concentration (CV) and the number of zero-value (NZ) symbols are calculated based on the sum of squared frequencies from an unsorted symbol frequency table. A compression decision is made quickly when their product, CV*NZ, exceeds a level threshold THH. During training, CV*NZ is plotted as a function of the compression ratio C% for multiple training data blocks. Different THH test values ​​are applied to this plot to determine the true positive rate and false positive rate, and are plotted as a receiver operating characteristic (ROC) curve. The point on the ROC curve with the highest Yoden index is selected as the optimal THH for future binary decisions.

The invention discloses a medical examination data anomaly detection system and method based on multi-algorithm fusion and dynamic early warning, and relates to the technical field of medical big data processing. The method comprises the following steps: acquiring patient inspection data through a data interface layer, and converting unstructured data into a standardized entity object by utilizing an ORM mapping technology; constructing a multi-algorithm service pool, and integrating a plurality of detection service classes including threshold statistics, time sequence prediction (ARIMA / Prophet) and machine learning (SVM / random forest); dynamically loading algorithm parameters through an early warning rule configuration service, and calling a selected algorithm service in parallel by using a strategy mode to obtain a preliminary anomaly judgment result; a weighted voting mechanism is adopted to fuse multi-source results, and an early warning threshold value is dynamically calculated in combination with historical data statistical characteristics based on a sliding window; and finally, the abnormal level and attribution analysis are displayed through a visual module. According to the method, the problem of a single model detection blind area is solved through a software engineering algorithm fusion architecture, and the sensitivity and the specificity of data anomaly detection are remarkably improved by utilizing dynamic threshold calculation realized by code logic.