Evolving decision tree rule based system for audio stego anomalies detection based on Hausdorff distance statistics

Geetha, S.; Ishwarya, N.; Kamaraj, N.

doi:10.1016/j.ins.2010.02.024

Cited by 17 publications

(8 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, each class membership function must be adapted to take into account these temporal changes and to better estimate the current functioning modes characteristics. To realize these changes an adaptive classifier is required (Geetha et al 2010;Bifet and Gavaldà 2009). This adaptive classifier must have a mechanism for adjusting its parameters over time.…”

Section: Evolving Systemsmentioning

confidence: 99%

“…Several classifiers have been developed to consider systems evolutions (Geetha et al 2010;Gil-García and Pons-Porrata 2010;Ilarri et al 2008;Nezhad and Niaki 2010;Yang et al 2010;Bifet and Gavaldà 2009;Sahel et al 2007;Gama and Castillo 2006). In the literature, classifiers are adapted using two approaches (Angstenberger 2000;Angelov 2004;Nakhaeizadeh et al 1997).…”

Section: Adaptive Classifiersmentioning

confidence: 99%

See 1 more Smart Citation

A semi-supervised dynamic version of Fuzzy K-Nearest Neighbours to monitor evolving systems

2010

View full text Add to dashboard Cite

Data issued of most real-world applications are evolving; they change constantly over time. In such applications, it is difficult to induce correctly a model (classifier) using traditional classification methods. Thus, it is important to use an adapted classification method to build a classifier and to update its parameters as new data is available. In this paper, we propose an adaptive classification approach based on the Fuzzy K-Nearest Neighbours (FKNN) method to monitor online evolving systems. The developed method, named semi-supervised Dynamic FKNN, comprises the following phases. In the first phase (detection phase), a class evolution can be detected and confirmed after the classification of each new pattern. Then in the second phase (adaptation phase), the parameters of the evolved class are updated incrementally. In the last phase (validation phase) the adapted classes are validated in order to keep only the representative ones. This approach is illustrated using an example of system which switches between several functioning modes.

show abstract

Section: Evolving Systemsmentioning

confidence: 99%

Section: Adaptive Classifiersmentioning

confidence: 99%

A semi-supervised dynamic version of Fuzzy K-Nearest Neighbours to monitor evolving systems

2010

View full text Add to dashboard Cite

show abstract

“…In [30], the authors proposed a based on lambda multi-diagonal matrix filter method for lowdensity noise removal. Decision tree based denoising (DTBD) method can be found in [31]. The advantage of this method is that it can enhance filtering capability in decreasing impulse noise, while preserving image details.…”

Section: Introductionmentioning

confidence: 99%

A Dynamic Non-Local Means Algorithm for Monochrome Image Denoising

Gao¹,

Nowduri²

2017

Int. J. Appl. Math. Mach. Learning

View full text Add to dashboard Cite

The image denoising is the fundamental problem in the field of image processing. The denoising algorithm of image is most commonly designed for removal of both impulsive noise and Gaussian noise. In image denoising process, impulsive noise (salt and pepper noise and random valued impulsive noise) is a most common noise which affects the image quality during image acquisition, transmission, reception or storage. Many classical denoising techniques have evolved over the years, such as mean filter, median filter, and morphological filter. In this paper, a novel dynamic non-local means algorithm has been proposed for monochrome image processing. The experimental results will confirm that proposed method yields the better performance in terms of peak signal to noise ratio (PSNR).

show abstract

“…The Support Vector Mach ine (SVM ) classifiers [15][16][17][18][19] are mu lti-class classifications which often have superior recognition rates in comparison to other classificat ion methods. In SVM, the mu lti-class classification problems usually decompose into several two-class problems using several Binary Decision Trees (BDTs) [20][21][22][23][24][25]. So we optimize the performance of the packet classification unit with the help of proposed hybrid Binary Decision Tree and Support Vector Machine based classifier, wh ich utilizes a binary tree based architecture that further utilizes SVMs for solving mu lti-class problems [25][26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

Performance Optimization in WBAN Using Hybrid BDT and SVM Classifier

Kathuria¹,

Gambhir²

2016

IJITCS

View full text Add to dashboard Cite

Wireless Body Area Network has attracted significant research interest in various applications due to its self-automaton and advanced sensor technology. The most severe issue in WBAN is to sustain its Quality of Service (QoS) under the dynamic changing environ ment like healthcare, and patient monitoring system. Another critical issue in WBAN is heterogeneous packet handling in such resource-constrained network. In this paper, a new classifier having hybrid Binary Decision Tree and Support Vector Machine classifier is proposed to tackle these important challenges. The proposed hybrid classifier deco mposes the N-class classification problem into N-1 sub-problems, each separating a pair o f subclasses. This protocol dynamically updates the priority of packet and node, adjusts data rate, packet transmission order and time, and resource distribution for the nodes based on node priority. The proposed protocol is implemented and simulated using NS-2 network simu lator. The result generated for proposed approach shows that new protocol can outperform in a dynamic environment, and yields better performance by leveraging advantages of both the Binary Decision Tree in terms of efficient co mputation and Support Vector Mach ine for high classification accuracy. Th is hybrid classifier significantly reduces loss ratio and delay and increase packet delivery ratio and throughput.

show abstract

Evolving decision tree rule based system for audio stego anomalies detection based on Hausdorff distance statistics

Cited by 17 publications

References 65 publications

A semi-supervised dynamic version of Fuzzy K-Nearest Neighbours to monitor evolving systems

A semi-supervised dynamic version of Fuzzy K-Nearest Neighbours to monitor evolving systems

A Dynamic Non-Local Means Algorithm for Monochrome Image Denoising

Performance Optimization in WBAN Using Hybrid BDT and SVM Classifier

Contact Info

Product

Resources

About