Contour preserving classification for maximal reliability

Tanprasert, Thitipong; Tanprasert, Chularat; Lursinsap, Chidchanok

doi:10.1109/ijcnn.1998.685930

Cited by 8 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Section 3.1 presents the augmentation of the original Contour Preserving Classification [4] to support multi-class data. Section 3.2 introduces an idea to maintain only the input vectors at the decision boundary between consecutive …”

Section: Proposed Methodologymentioning

confidence: 99%

“…al. [4] proposed a technique to improve the robustness and weight fault tolerance of a neural network applied with a linearly separable problem called contour preserving classification. Its major idea is to force non-linear classification on a linearly separable problem to take advantage of the nonlinear contour of the input vector regions to widen the clearance between the classification hyperplane and the input vectors.…”

Section: Related Workmentioning

confidence: 99%

“…Mongkonsirivatana [14] proposed an augmentation on the original Contour Preserving Classification [4] to generate outpost vectors only at the boundary between consecutive classes of data. The technique applies concave detection and edge detection prior to outpost vector generation to determine whether an outpost vector should be generated there.…”

Section: Related Workmentioning

confidence: 99%

“…These work well in most situations. Tanprasert et al [4] demonstrated an alternative to enhance the robustness and fault tolerance of the neural network called contour preserving classification technique. The technique augments the set of training vectors with a set of outpost vectors, which are synthesized from original input vectors of both classes.…”

Section: Introductionmentioning

confidence: 99%

“…To maintain the hyperplane at the middle of the decision boundary between consecutive classes of data, synthesized vectors; called outpost vectors, are inserted into the data set at the decision boundary between consecutive classes of data to assist the FFNN to place the hyperplane at the middle between this decision boundary. Without outpost vectors, the hyperplane; located much closer to the input vectors of one class than the other class, will be sensitive to the weight changes [4].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Reduced Multi-class Contour Preserving Classification

Fuangkhon

Tanprasert

2015

Neural Process Lett

View full text Add to dashboard Cite

This research presents the augmentation of the original contour preserving classification technique to support multi-class data and to reduce the number of synthesized vectors, called multi-class outpost vectors (MCOVs). The technique has been proven to function on both synthetic-problem data sets and real-world data sets correctly. The technique also includes three methods to reduce the number of MCOVs by using minimum vector distance selection between fundamental multi-class outpost vectors and additional multi-class outpost vectors to select only MCOVs located at the decision boundary between consecutive classes of data. The three MCOV reduction methods include the FF-AA reduction method, the FA-AF reduction method, and the FAF-AFA reduction method. An evaluation has been conducted to show the reduction capability, the contour preservation capability, and the levels of classification accuracy of the three MCOV reduction methods on both non-overlapping and highly overlapping synthetic-problem data sets and highly overlapping real-world data sets. For non-overlapping problems, the experimental results present that the FA-AF reduction method can partially reduce the number of MCOVs while preserving the contour of the problem most accurately and obtaining similar levels of classification accuracy as when the whole set of MCOVs is used. For highly overlapping problems, the experimental results present that the FF-AA reduction method can partially reduce the number of MCOVs while preserving the contour of the problem most accurately and obtaining similar levels of classification accuracy as when the whole set of MCOVs is used.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations