{"responseHeader":{"status":0,"QTime":7,"params":{"q":"{!q.op=AND}id:\"102816\"","hl":"true","hl.simple.post":"","hl.fragsize":"5000","fq":"!embargo_tdt:[NOW TO *]","hl.fl":"ocr_t","hl.method":"unified","wt":"json","hl.simple.pre":""}},"response":{"numFound":1,"start":0,"docs":[{"file_name_t":"Soller-Automated_Detection.pdf","thumb_s":"/0f/60/0f608af4ccd68c3a471d9c057e4939cbdd058763.jpg","oldid_t":"compsci 10929","setname_s":"ir_computersa","restricted_i":0,"format_t":"application/pdf","modified_tdt":"2016-05-26T00:00:00Z","file_s":"/22/f9/22f9cb7e295effbe56ed7efd72e081f00b1e6f74.pdf","title_t":"Page 59","ocr_t":"44 (8.19) where X is from the ith population. The variance 82 is the Mahalanobis squared distance [110] between two multivariate normal populations. The current formulation does not use a priori probabilities of the two groups and does not give preference to a group selection. A more general formulation including a priori probabilities and losses, the cost of misclassification, is defined below [5]. Let the loss, Cij, be the cost of associating an observation from the jth population as one from the ith population. Let the a priori probabilities for populations a and b be h and 1 - h, respectively: ) I 1 1 ( )' 1 ( ) (1 - h) Cab (~La - /-lb :E- X - - /-la - /-lb ~- /-la + /-lb > ln hC · 2 ba (8.20) 8.6.2 Sample Formulation In most cases, statistical modellers do not know the distribution parameters for a given problem. Therefore, this dissertation presents a sample formulation of the linear discriminant classifier. Let Xa be the multidimensional sample mean vector for observations of patients not diagnosed as delirious and Xb be the sample mean vector for observations of patients diagnosed as delirious. After factor analysis, subsequent analysis assumes a Gaussian distribution with similar covariance structure due to the central limit theorem [143] . Let a= S-1X(-a- -Xb) (8.21) and the linear discriminant function is y = (-Xa- -X)b' s-1 X. (8.22) Substitution of x by each of the group means produces","id":102816,"created_tdt":"2016-05-26T00:00:00Z","parent_i":102961,"_version_":1642982670125236226}]},"highlighting":{"102816":{"ocr_t":[]}}}