Improved Sterrett Algorithm Analysis For Group Detection

In the process of disease detection,it would waste a lot of time,manpower and material resources to detect the diseased individuals from the sample group.Therefore,how to improve the detection efficiency has become the focus of group detection research.Sterrett proposed a Sterrett grouping detection algorithm to improve the detection efficiency of the sample group,while the Sterrett algorithm mainly detects the sample group composed of small probability individuals.In this paper,we propose two new scenarios: the detection of individuals with high probability in small sample group and the detection of individuals with low probability in large sample group.In these two cases,we improve the Sterrett algorithm and establish the algorithm model.In the first chapter,the research background of grouping detection,Sterrett algorithm and some research results of grouping detection are introduced.In the second chapter,an improved Sterrett algorithm is proposed without detection error,and an improved algorithm model without detection error is established.In the third part,an improved Sterrett algorithm with detection sensitivity and specificity is proposed,and an improved algorithm model with detection error is established.In the two cases proposed in this paper,according to the actual detection experience,the probability of positive individuals appearing in the sample group is higher,but the number of positive individuals will not be much,so when we detect the second positive in the sample group,we will do so.The remaining samples were packaged and tested.Chapter 4: Data simulation and result analysis.Under the same conditions,the improved algorithm and the Sterrett algorithm are simulated,and the results of the two algorithms are compared and analyzed to judge the advantages and disadvantages of the improved Sterrett algorithm.The fifth chapter summarizes the research results of this paper and puts forward the prospects for future research.