RSVM

AcronymDefinition
RSVMReduced Support Vector Machine (information engineering)
RSVMRat Seminal Vesicle Mesenchyme
RSVMRam Seminal Vesicle Microsomal (biochemistry)
RSVMReduced Vertical Seperation Minima
Copyright 1988-2018 AcronymFinder.com, All rights reserved.
References in periodicals archive ?
The black line is LASSO-LDA, while red and blue ones correspond to LSVM and RSVM, respectively.
Method Number of subjects Linear regression [15] 15 RSVM based [16] 65 Proposed method 72 Table 4: Performance results of the linear regression, SVRM-based method, and ANN-based method with different feature extraction technique on the test database.
RSVM gives 97.75% classification accuracy in the row of SAE 9-7.
From this table, it can be found that the classification performance of RSVM is apparently differential.
And LSVM, RSVM, and CART show much more stability in classification accuracy.
With the principle of RSVM, the interval nonlinear regression model is listed as follows:
Q is a positive semidefinite matrix in RSVM. K(*) is a nonlinear kernel.
Data Raw data NECGT-mRMR mRMR NECGT-RS RS Lymphography 79.74 76.88 74.74 76.43 76.88 Crx 85.51 85.51 85.51 85.51 85.51 Cardiotocography 84.60 85.80 84.87 82.60 80.56 Spectf 84.65 84.63 84.23 79.41 79.41 Hepatitis 82.33 84.33 81.00 79.50 79.50 Average 83.36 83.43 82.07 80.69 80.37 TABLE 6: Classification accuracies based on RSVM (%).
Dataset MLP SVM RMLP Cleveland 79.2079 82.8383 93.72 Statlog 77.4074 84.07 86.6667 Spect 79.4 81.65 88.38 Spectf 76.03 79.40 90.2622 Eric 77.99 78.95 88.51 WBC 95.28 96.85 97.1388 Hepatitis 81.94 85.16 90.3226 Thyroid 96.28 89.77 98.1395 Parkinson 91.28 86.15 96.4103 Pima Indian 75.13 77.47 79.2969 diabetics BUPA liver 71.59 70.14 68.1159 Dataset RSVM ADA-MLP ADA-SVM Cleveland 85.0886 76.23 82.5083 Statlog 83.7037 77.777 84.07 Spect 88.764 79.4007 80.8989 Spectf 82.397 76.03 77.9026 Eric 83.73 77.9904 77.9904 WBC 96.5665 95.5651 96.7096 Hepatitis 85.8065 78.7097 78.9097 Thyroid 78.6047 97.2093 85.1163 Parkinson 90.2564 92.3077 87.6923 Pima Indian 76.0417 73.9583 77.3438 diabetics BUPA liver 54.4928 71.3043 62.029 R: filter-based supervised instance resampling; ADA: ADABOOST.
[9] have proposed a host-based anomaly detection method using RSVM. Kim et al.