ECG analysis using wavelet transform: application to myocardial ischemia detection

Ranjith, P; Baby, Poornima; Joseph, Paul K.

doi:10.1016/s1297-9562(03)00003-2

Cited by 55 publications

(27 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…f (x,w) = w '(x)+b = ,flw1q(x)+b (2) The margin with (2) between the two classes is proportional to 2 / w As maximizing 2 / w is equivalent to T minimizing W W / 2, After data are mapped into a higher dimensional space, the number of variables (w, b) becomes very large or even infinite. A typical approach to handle this difficulty is solving the dual problem shown in (3 …”

Section: A Determining Support Vectors In Training Phasementioning

confidence: 99%

Electrocardiogram Analysis with Adaptive Feature Selection and Support Vector Machines

Kao

Shen

et al. 2006

APCCAS 2006 - 2006 IEEE Asia Pacific Conference on Circuits and Systems

View full text Add to dashboard Cite

Electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. In this paper, we propose an ECG analysis approach with adaptive feature selection and support vector machines (SVMs). Many wavelet transform-based coefficients are used as candidates, but only a few coefficients are selected for classification problem of each class pair. In addition, the several variation classes are partitioned into two or more subclasses to improve the training efficiency of SVMs. The experimental results show that the proposed ECG analysis approach can obtain high recognition rate and reliable results.

show abstract

Section: A Determining Support Vectors In Training Phasementioning

confidence: 99%

Electrocardiogram Analysis with Adaptive Feature Selection and Support Vector Machines

Kao

Shen

et al. 2006

APCCAS 2006 - 2006 IEEE Asia Pacific Conference on Circuits and Systems

View full text Add to dashboard Cite

show abstract

“…Moreover, these markers drive therapeutic decisions; have prognostic value for patients with hepatitis B virus (HBV) (Lok 2004;Lazo et al 2011;Cui et al 2013;Rehm et al 2013), and hepatitis C virus (HCV) (Wiese et al 2000;Ghany et al 2003;Hui et al 2003;Wiese et al 2014). There were also no reports on the combination of liver lobe volume with albumin to determine the presence of esophageal varices in cirrhotic patients (Ranjith et al 2003;Wiese et al 2014). Many liver proteins are routinely measured in serum to diagnose liver dysfunction.…”

Section: Introductionmentioning

confidence: 99%

“…Many other medical expert systems have been established such as INTERNIST (Miller et al 1982) and CADIAG-2 (Adlassnig et al 1982). However, all of them have been applied to assess the risk factors of cardiac disease (Genest et al 1991;Wung et al 1999;Gamberger et al 2003;Ranjith et al 2003;Chirinos et al 2007;Vaisi-Raygani et al 2010). The fuzzy expert system (FES) has a set of fuzzy rules and functions, i.e., acquisition of knowledge, is considered to be the important issue in the design and establishment of fuzzy expert system.…”

Section: Introductionmentioning

confidence: 99%

Prognosis of Liver Disorders in Dna Positive Hbv Patients Based on Fuzzy Soft Sets

Mohammed¹,

Salih²,

Mirza³

et al. 2017

SJUOZ

View full text Add to dashboard Cite

ABSTRACT:Liver disease and disorders are serious public health burdens because of the high prevalence among populations worldwide and poor long-term clinical outcome. The outcomes of the disease include deaths from liver decompensation, cirrhosis and HCC. Many liver diseases, including chronic HBV and HCV infection, ALD, NAFLD, autoimmune liver disease and drug-induced liver disease (DILI), potentially threaten a large proportion of the global population. The fuzzy soft set principle theory has been used for the developing of a diagnostic system in medicine and devise a prediction system named as fuzzy soft expert system which is a rulebased system uses fuzzy set and fuzzy soft set. There are five main components included in the basic structure, they are: (1) A fuzzication that translates the inputs (real-values) into fuzzy values, (2) obtaining fuzzy sets, (3) changing in to fuzzy soft sets, (4) reduction of normal parameter of fuzzy soft sets, (5) output data by algorithm. Fifty two individuals suspected and managed as HBV patients were involved in this study.All of them were attending liver diseases unit at Azadi teaching hospital in Duhok, Kurdistan Region-Iraq. They were being managed by the herpetology specialist as HBV infected patients. Their parameters (Alanine Aminotransferase (ALT), Aspartate aminotransferase (AST), Total Serum Albumin (Alb.), and Total Serum Bilirubin (T.S.Bil.)), were used as input data and the score of each patient was calculated. The developed fuzzy soft expert system was used to obtain the score for each as prognostic model for liver disorders. The score of 10 of those patients are selected and compared with the clinical status of each base on signs and symptoms of the HBV infection. Score more than 101.844 was considered to be highly linked with HBV infection. Scores less than 101.844 was considered to be not related to HBV infection.

show abstract

“…Research on risk factor analysis [6][7][8][9][10][11] has been done. Studies on 18-lead electro cardiogram (ECG) analysis [11], 12-lead ECG analysis [12][13][14][15], Spectrum analysis [16], wavelet transformed ECG analysis [17], Exercise stress testing analysis [18], Myocardial Infarction analysis [19], heart valve disease analysis [20,28] have been done extensively for detection of cardiovascular diseases. Single lead ECG classification methodology is proposed using time domain principal components [21][22][23] and discrete wavelet transformation domain principal components [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

“…3. The core intervals for low, medium and high risk are[15][16][17][18][19][20][35][36][37][38][39][40][41][42][43][44][45] and P 70 respectively.…”

mentioning

confidence: 99%

Fuzzy expert system approach for coronary artery disease screening using clinical parameters

Pal

Mandana

Pal

et al. 2012

Knowledge-Based Systems

106

View full text Add to dashboard Cite

ECG analysis using wavelet transform: application to myocardial ischemia detection

Cited by 55 publications

References 7 publications

Electrocardiogram Analysis with Adaptive Feature Selection and Support Vector Machines

Electrocardiogram Analysis with Adaptive Feature Selection and Support Vector Machines

Prognosis of Liver Disorders in Dna Positive Hbv Patients Based on Fuzzy Soft Sets

Fuzzy expert system approach for coronary artery disease screening using clinical parameters

Contact Info

Product

Resources

About