Tsymbal, A., Puuronen, S., Terziyan, V.: Advanced dynamic selection of diagnostic methods, Proc. 11 IEEE Symposium on Computer-Based Medical Systems Lubbock TX, USA, IEEE CS Press, 1998, 50--54. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Local Feature Selection with Dynamic Integration of Classifiers - Puuronen, Tsymbal (2001) Self-citation (Tsymbal Puuronen) (Correct)
No context found.
Tsymbal, A., Puuronen, S., Terziyan, V.: Advanced dynamic selection of diagnostic methods, Proc. 11 IEEE Symposium on Computer-Based Medical Systems Lubbock TX, USA, IEEE CS Press, 1998, 50--54.
Bagging and Boosting with Dynamic Integration of Classifiers - Tsymbal, Puuronen (2000) Self-citation (Tsymbal Puuronen) (Correct)
....approach. Using the collected error information first about half of classifiers (the better half) is selected and then the final classification is derived using weighted voting among them. Previously an application of the dynamic classifier integration in medical diagnostics was considered in [19,20,22]. A number of experiments comparing the dynamic integration with such widely used integration approaches as CVM, and weighted voting were also conducted [13,14,22,23] The comparison results show that the dynamic integration technique outperforms often weighted voting and CVM. In [21] the dynamic ....
....weighted voting among them. Previously an application of the dynamic classifier integration in medical diagnostics was considered in [19,20,22] A number of experiments comparing the dynamic integration with such widely used integration approaches as CVM, and weighted voting were also conducted [13,14,22,23]. The comparison results show that the dynamic integration technique outperforms often weighted voting and CVM. In [21] the dynamic classifier integration was applied to decision committee learning, combining the generated classifiers in a more sophisticated manner than voting. This paper ....
Tsymbal, A., Puuronen, S., Terziyan, V.: Advanced Dynamic Selection of Diagnostic Methods. In: Proceedings 11 th IEEE Symp. on Computer-Based Medical Systems CBMS'98, IEEE CS Press, Lubbock, Texas, June (1998) 50-54.
Decision Committee Learning with Dynamic Integration of Classifiers - Tsymbal (2000) Self-citation (Tsymbal) (Correct)
....classifier C receives a weight W that depends on the local classifier s performance and the final classification is conducted by voting classifier predictions C (x) with their weights W . Previously an application of the dynamic classifier integration in medical diagnostics was considered in [21 23]. A number of experiments comparing the dynamic integration with such widely used integration approaches as CVM, and weighted voting were also conducted [15,16,23,24] The comparison results show that the dynamic integration technique outperforms often weighted voting and CVM. In this paper, the ....
....C (x) with their weights W . Previously an application of the dynamic classifier integration in medical diagnostics was considered in [21 23] A number of experiments comparing the dynamic integration with such widely used integration approaches as CVM, and weighted voting were also conducted [15,16,23,24]. The comparison results show that the dynamic integration technique outperforms often weighted voting and CVM. In this paper, the goal is to apply the dynamic classifier integration to decision committee learning, combining the generated classifiers in a more sophisticated manner than voting. ....
Tsymbal, A., Puuronen, S., Terziyan, V.: Advanced Dynamic Selection of Diagnostic Methods. In: Proceedings 11th IEEE Symp. on Computer-Based Medical Systems CBMS' 98, IEEE CS Press, Lubbock, Texas, June (1998) 50-54.
Arbiter Meta-Learning with Dynamic Selection of.. - Tsymbal, Puuronen.. (1999) Self-citation (Tsymbal Puuronen Terziyan) (Correct)
....of this multi level arbiter tree approach over the one level techniques, which generally could not maintain the accuracy of the global classifier trained on the whole data set. 3 Dynamic Selection of Classifiers In [9, 10] we proposed a technique for the dynamic integration of classifiers. In [14,15,17] we considered some medical applications of this technique. This technique is based on the assumption that each base classifier gives the best prediction inside certain subdomains of the whole application domain, i.e. inside its competence areas. The main problem in the technique is to estimate ....
Tsymbal, A., Puuronen, S., Terziyan, V.: Advanced Dynamic Selection of Diagnostic Methods. In: Proceedings 11 th IEEE Symp. on Computer-Based Medical Systems CBMS' 98, IEEE CS Press, Lubbock, Texas, June (1998) 50-54
Arbiter Meta-Learning with Dynamic Selection of Multiple.. - Tsymbal, Puuronen Self-citation (Tsymbal Puuronen) (Correct)
....cannot maintain the accuracy obtained from the whole data set. 3. Dynamic Selection of Classifiers In [11] we proposed a technique for the dynamic integration of multiple classifiers. The goal was to obtain a more accurate prediction than can be obtained from any single classifier alone. In [8 10] we considered some medical applications of this technique. This technique is based on the assumption that each component classifier gives the best predictions inside certain subdomains of the whole application domain, i.e. inside its competence area. The main problem of the technique is to ....
A. Tsymbal, S. Puuronen, and V. Terziyan. An advanced dynamic selection of diagnostic methods. In Proc. 11th IEEE Symp. on Computer-Based Medical Systems CBMS'98, 1998. To appear.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC