Handwritten Digit Recognition Based on a DSmT-SVM Parallel Combination

Abbas, Nassim; Chibani, Youcef; Nemmour, Hassiba

doi:10.1109/icfhr.2012.208

Cited by 5 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where x denotes the number of multiple focal elements in the results, y denotes the number of the same multiple focal elements generated in the procedure of mass assignments combination product. Computation complexity comparison of two methods obtained from Equation (29) and Equation (30) shows that the computation complexity of DSmT is almost proportion to (n + c) 2 and the computation complexity of the method in this paper is almost proportion to (n + c). Analysis of computation complexity shows that the computational complexity of the proposed method increases linearly instead of exponentially when the elements number of the discernment framework increases linearly.…”

Section: Analysis Of Computation Complexitymentioning

confidence: 83%

“…DSmT [29] overcomes the exclusiveness limitation in Shafer's model. In many fusion problems, the hypotheses can be vague in reality and the elements are not precisely separated which don't satisfy Shafer's model.…”

Section: Dezert-smarandache Theory (Dsmt)mentioning

confidence: 99%

“…But these methods cannot satisfy the small amount of computational complexity and less loss of information requirements at the same time. In recent years, there are some important articles [27][28][29][30][31][32][33][34] computational complexity of the combination algorithms formulated in DSmT framework in different ways. Djiknavorian [27] has proposed a novel method and a Matlab program to reduce the DSmT hybrid rule complexity.…”

Section: Introductionmentioning

confidence: 99%

“…However, the DSmT (belief function theory) complexity can be reduced by using this practical Martin's codification and only considering the reduced hyper-power set D r after integrating the constraints in the codification at the beginning of the general belief function framework proposed in [28]. Abbas [29,30] has proposed a DSmT based combination scheme for multi-class classification which also reduces the number of focal elements. Li [31] has proposed a method for reducing the information fusion complexity, which is different from the above methods by reducing the combined sources numbers instead of reducing the number of focal elements.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An evidence clustering DSmT approximate reasoning method based on convex functions analysis

Guo

Guan

et al. 2015

Digital Signal Processing

View full text Add to dashboard Cite

The computational complexity of Dezert-Smarandache Theory (DSmT) increases exponentially with the linear increment of element number in the discernment frame, and it limits the wide applications and development of DSmT. In order to efficiently reduce the computational complexity and remain high accuracy, a new Evidence Clustering DSmT Approximate Reasoning Method for two sources of information is proposed based on convex function analysis. This new method consists of three steps. First, the belief masses of focal elements in each evidence are clustered by the Evidence Clustering method. Second, the un-normalized approximate fusion results are obtained using the DSmT approximate convex function formula, which is acquired based on the mathematical analysis of Proportional Conflict Redistribution 5 (PCR5) rule in DSmT. Finally, the normalization step is applied. The computational complexity of this new method increases linearly rather than exponentially with the linear growth of the elements. The simulations show that the approximate fusion results of the new method have higher Euclidean similarity to the exact fusion results of PCR5 based information fusion rule in DSmT framework (DSmT + PCR5), and it requires lower computational complexity as well than the existing approximate methods, especially for the case of large data and complex fusion problems with big number of focal elements.

show abstract

Section: Analysis Of Computation Complexitymentioning

confidence: 83%

Section: Dezert-smarandache Theory (Dsmt)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An evidence clustering DSmT approximate reasoning method based on convex functions analysis

Guo

Guan

et al. 2015

Digital Signal Processing

View full text Add to dashboard Cite

show abstract

“…There were some important methods for reducing the computation complexity of the combination algorithms in DSmT framework since this problem can be treated in different ways: 1) reducing the number of focal elements [33][34][35][36], 2) reducing the number of combined sources [37], 3) reducing both the number of focal elements and the number of combined sources [38]. Applied mathematics has drawn attention by many scholars [39,40].…”

Section: Introductionmentioning

confidence: 99%

An evidence clustering DSmT approximate reasoning method for more than two sources

Guo

Jian

et al. 2016

Digital Signal Processing

View full text Add to dashboard Cite

Due to the huge computation complexity of Dezert-Smarandache Theory (DSmT), its applications especially for multi-source (more than two sources) complex fusion problems have been limited. To get high similar approximate reasoning results with Proportional Conflict Redistribution 6 (PCR6) rule in DSmT framework (DSmT + PCR6) and remain less computation complexity, an Evidence Clustering DSmT approximate reasoning method for more than two sources is proposed. Firstly, the focal elements of multi evidences are clustered to two sets by their mass assignments respectively. Secondly, the convex approximate fusion results are obtained by the new DSmT approximate formula for more than two sources. Thirdly, the final approximate fusion results by the method in this paper are obtained by the normalization step. Analysis of computation complexity show that the method in this paper cost much less computation complexity than DSmT + PCR6. The simulation experiments show that the method in this paper can get very similar approximate fusion results and need much less computing time than DSmT + PCR6, especially, when the numbers of sources and focal elements are large, the superiorities of the method are remarkable.

show abstract

SVM Kernel Configuration and Optimization for the Handwritten Digit Recognition

Drewnik

Pasternak-Winiarski

2017

Computer Information Systems and Industrial Management

View full text Add to dashboard Cite

Part 2: Biometrics and Pattern Recognition ApplicationsInternational audienceThe paper presents optimization of kernel methods in the task of handwritten digits identification. Because such digits can be written in various ways (depending on the person’s individual characteristics), the task is difficult (subsequent categories often overlap). Therefore, the application of kernel methods, such as SVM (Support Vector Machines), is justified. Experiments consist in implementing multiple kernels and optimizing their parameters. The Monte Carlo method was used to optimize kernel parameters. It turned out to be a simple and fast method, compared to other optimization algorithms. Presented results cover the dependency between the classification accuracy and the type and parameters of selected kernel

show abstract

Handwritten Digit Recognition Based on a DSmT-SVM Parallel Combination

Cited by 5 publications

References 16 publications

An evidence clustering DSmT approximate reasoning method based on convex functions analysis

An evidence clustering DSmT approximate reasoning method based on convex functions analysis

An evidence clustering DSmT approximate reasoning method for more than two sources

SVM Kernel Configuration and Optimization for the Handwritten Digit Recognition

Contact Info

Product

Resources

About