Optimal Infomation-based Classification [electronic resource] / Baro Hyun

Hyun, Baro.
Bib ID
vtls000456673
出版項
Ann Arbor, Mich. : ProQuest Information and learning
稽核項
147 p.
電子版
附註項
數位化論文典藏聯盟
預約人數:0
全部評等: 0
沒有紀錄。
 
 
 
03530nam a2200361 a 4500
001
 
 
vtls000456673
003
 
 
VRT
005
 
 
20120507093300.0
006
 
 
m        d 
008
 
 
120507s2011    miu     sm    000 0 eng d
020
$a 9781124911373
035
$a (UMI)AAI3476556
039
9
$y 201205070933 $z VLOAD
040
$a UMI $b eng $c UMI $d TKU
100
1
$a Hyun, Baro.
245
1
0
$a Optimal Infomation-based Classification $h [electronic resource] / $c Baro Hyun
260
$a Ann Arbor, Mich. : $b ProQuest Information and learning
300
$a 147 p.
500
$a Source: Dissertation Abstracts International, Volume: 72-12, Section: B, page: .
500
$a Advisers:  Anouck R. Girard; Pierre T. Kabamba.
502
$a Thesis (Ph.D.)--University of Michigan, 2011.
520
$a Classification is the allocation of an object to an existing category among several based on uncertain measurements. Since information is used to quantify uncertainty, it is natural to consider classification and information as complementary subjects. This dissertation touches upon several topics that relate to the problem of classification, such as information, classification, and team classification. Motivated by the U.S. Air Force Intelligence, Surveillance, and Reconnaissance missions, we investigate the aforementioned topics for classifiers that follow two models: classifiers with workload-independent and workload-dependent performance. We adopt workload-independence and dependence as "first-order" models to capture the features of machines and humans, respectively.
520
$a We first investigate the relationship between information in the sense of Shannon and classification performance, which is defined as the probability of misclassification. We show that while there is a predominant congruence between them, there are cases when such congruence is violated. We show the phenomenon for both workload-independent and workload-dependent classifiers and investigate the cause of such phenomena analytically.
520
$a One way of making classification decisions is by setting a threshold on a measured quantity. For instance, if a measurement falls on one side of the threshold, the object that provided the measurement is classified as one type, otherwise, it is of another type. Exploiting thresholding, we formalize a classifier with dichotomous decisions (i.e., with two options, such as true or false) given a single variable measurement. We further extend the formalization to classifiers with trichotomy (i.e., with three options, such as true, false or unknown) and with multivariate measurements.
520
$a When a team of classifiers is considered, issues on how to exploit redundant numbers of classifiers arise. We analyze these classifiers under different architectures, such as parallel or nested. First, we consider a team of homogeneous (identical) classifiers and provide a fusion-rule, supervisor-based strategy using a parallel architecture. Then, we consider a team of heterogeneous classifiers and provide a strategy using a nested architecture. We show results that confirm that both strategies outperform a single classifier.
591
$a 數位化論文典藏聯盟 $b PQDT $c 淡江大學(2012)
653
$a Engineering, Aerospace.
653
$a Engineering, Robotics.
653
$a Computer Science.
710
2
$a University of Michigan.
830
0
$a Dissertation Abstracts International ; $v 72-12B
856
4
0
$u http://info.lib.tku.edu.tw/ebook/redirect.asp?bibid=456673
999
$a VIRTUA00
沒有評論
叢書名
Dissertation Abstracts International ; 72-12B
摘要
Classification is the allocation of an object to an existing category among several based on uncertain measurements. Since information is used to quantify uncertainty, it is natural to consider classification and information as complementary subjects. This dissertation touches upon several topics that relate to the problem of classification, such as information, classification, and team classification. Motivated by the U.S. Air Force Intelligence, Surveillance, and Reconnaissance missions, we investigate the aforementioned topics for classifiers that follow two models: classifiers with workload-independent and workload-dependent performance. We adopt workload-independence and dependence as "first-order" models to capture the features of machines and humans, respectively.
We first investigate the relationship between information in the sense of Shannon and classification performance, which is defined as the probability of misclassification. We show that while there is a predominant congruence between them, there are cases when such congruence is violated. We show the phenomenon for both workload-independent and workload-dependent classifiers and investigate the cause of such phenomena analytically.
One way of making classification decisions is by setting a threshold on a measured quantity. For instance, if a measurement falls on one side of the threshold, the object that provided the measurement is classified as one type, otherwise, it is of another type. Exploiting thresholding, we formalize a classifier with dichotomous decisions (i.e., with two options, such as true or false) given a single variable measurement. We further extend the formalization to classifiers with trichotomy (i.e., with three options, such as true, false or unknown) and with multivariate measurements.
When a team of classifiers is considered, issues on how to exploit redundant numbers of classifiers arise. We analyze these classifiers under different architectures, such as parallel or nested. First, we consider a team of homogeneous (identical) classifiers and provide a fusion-rule, supervisor-based strategy using a parallel architecture. Then, we consider a team of heterogeneous classifiers and provide a strategy using a nested architecture. We show results that confirm that both strategies outperform a single classifier.
附註
Source: Dissertation Abstracts International, Volume: 72-12, Section: B, page: .
Advisers: Anouck R. Girard; Pierre T. Kabamba.
Thesis (Ph.D.)--University of Michigan, 2011.
數位化論文典藏聯盟
合著者
ISBN/ISSN
9781124911373