Comparison of SVM and ANFIS for Snore Related Sounds Classification by Using the Largest Lyapunov Exponent and Entropy

Ankishan, Haydar; Yılmaz, Derya

doi:10.1155/2013/238937

Cited by 24 publications

(12 citation statements)

References 45 publications

(95 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Especially in multiple classifications, the ability of SVMs to be high is the reason for selecting the classification and training accuracy in the same conditions to be high compared to some other classifiers [32].…”

Section: Classifier Resultsmentioning

confidence: 99%

A New Approach for Detection of Pathological Voice Disorders with Reduced Parameters

Ankishan¹

2018

IU-JEEE

View full text Add to dashboard Cite

Section: Classifier Resultsmentioning

confidence: 99%

A New Approach for Detection of Pathological Voice Disorders with Reduced Parameters

Ankishan¹

2018

IU-JEEE

View full text Add to dashboard Cite

“…Though neural network based classifiers, like ANFIS, act efficiently, to deal with the uncertainties involved in EEG signals [14]. Another study examines as a object the snore related sounds (SRSs) for detection of sleep apnea / hypopnea syndrome (SAHS), as indicator of specific sleep disorders [15]. Of interest is the application of ANFIS in signal processing systems for energy production from renewable energy sources such as wind turbines and others.…”

Section: ____________________________________________________________mentioning

confidence: 99%

Identification of Sine, Squire, Triangle and Sawtooth Waveforms with Uniform White and Inverse F Noises by Adaptive Neuro - Fuzzy Interface System

Georgiev¹,

Balabanova²,

Kogias³

et al. 2018

JESTR

View full text Add to dashboard Cite

In this paper the structures of Adaptive Neuro-fuzzy interface system (ANFIS) are studied for noise identification. The system's structures are analyzed for different types of membership functions applied for input variables with root mean square errors variation. Hybrid algorithm and back propagation algorithm are applied. The input data are obtained through system simulation based on LabVIEW system design platform and development environment. The choice of ANFIS structure is based on the training results and minimum RMSE for identification of the signals with uniform white and inverse F Noises. Therefore, "gbellmf" membership function for input data variables is chosen. The accuracy classification is obtained at 100 %.

show abstract

“…Therefore wrapper approaches such as Support Vector Machine (SVM) [29,28,8], Artificial Neural Networks (ANN) [30,28] are more significant than the filter approaches. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) [31,32] also can be used for wrapper. However SVM performs better than ANFIS [32] and ANFIS does not provide any feature reduction heuristics [31].…”

Section: Filter and Wrapper Approaches For Malware Detectionmentioning

confidence: 99%

“…Adaptive Neuro-Fuzzy Inference Systems (ANFIS) [31,32] also can be used for wrapper. However SVM performs better than ANFIS [32] and ANFIS does not provide any feature reduction heuristics [31]. Different search strategies [33] such as sequential backward elimination (SBE), sequential forward elimination (SFE) [33] or bidirectional search approaches are used in the subset generation process.…”

Section: Filter and Wrapper Approaches For Malware Detectionmentioning

confidence: 99%

Hybrids of support vector machine wrapper and filter based framework for malware detection

Huda

Abawajy

Alazab

et al. 2016

Future Generation Computer Systems

103

View full text Add to dashboard Cite

h i g h l i g h t s• A signature-free malware detection approach has been proposed. • A hybrid wrapper-Filter based malware feature selection has been proposed. • Proposed hybrid approach can take advantages from both filter and wrapper. • Models have also been validated by statistical model selection criteria such as Chi Square and Akaike information criterion (AIC). a b s t r a c tMalware replicates itself and produces offspring with the same characteristics but different signatures by using code obfuscation techniques. Current generation Anti-Virus (AV) engines employ a signaturetemplate type detection approach where malware can easily evade existing signatures in the database. This reduces the capability of current AV engines in detecting malware. In this paper we propose a hybrid framework for malware detection by using the hybrids of Support Vector Machines Wrapper, MaximumRelevance-Minimum-Redundancy Filter heuristics where Application Program Interface (API) call statistics are used as a malware features. The novelty of our hybrid framework is that it injects the filter's ranking score in the wrapper selection process and combines the properties of both wrapper and filters and API call statistics which can detect malware based on the nature of infectious actions instead of signature. To the best of our knowledge, this kind of hybrid approach has not been explored yet in the literature in the context of feature selection and malware detection. Knowledge about the intrinsic characteristics of malicious activities is determined by the API call statistics which is injected as a filter score into the wrapper's backward elimination process in order to find the most significant APIs. While using the most significant APIs in the wrapper classification on both obfuscated and benign types malware datasets, the results show that the proposed hybrid framework clearly surpasses the existing models including the independent filters and wrappers using only a very compact set of significant APIs. The performances of the proposed and existing models have further been compared using binary logistic regression. Various goodness of fit comparison criteria such as Chi Square, Akaike's Information Criterion (AIC) and Receiver Operating Characteristic Curve ROC are deployed to identify the best performing models. Experimental outcomes based on the above criteria also show that the proposed hybrid framework outperforms other existing models of signature types including independent wrapper and filter approaches to identify malware.

show abstract

Comparison of SVM and ANFIS for Snore Related Sounds Classification by Using the Largest Lyapunov Exponent and Entropy

Cited by 24 publications

References 45 publications

A New Approach for Detection of Pathological Voice Disorders with Reduced Parameters

A New Approach for Detection of Pathological Voice Disorders with Reduced Parameters

Identification of Sine, Squire, Triangle and Sawtooth Waveforms with Uniform White and Inverse F Noises by Adaptive Neuro - Fuzzy Interface System

Hybrids of support vector machine wrapper and filter based framework for malware detection

Contact Info

Product

Resources

About