METHODS: These models utilized experimental data of wavelengths and hemoglobin concentrations in building highly accurate Genetic Algorithm/Support Vector Regression model (GA-SVR).
RESULTS: The developed methodology showed high accuracy as indicated by the low root mean square error values of 4.65 × 10-4 and 4.62 × 10-4 for oxygenated and deoxygenated hemoglobin, respectively. In addition, the models exhibited 99.85 and 99.84% correlation coefficients (r) for the oxygenated and deoxygenated hemoglobin, thus, validating the strong agreement between the predicted and the experimental results CONCLUSIONS: Due to the accuracy and relative simplicity of the proposed models, we envisage that these models would serve as important references for future studies on optical properties of blood.
METHODS: In this work, we present a bit-plane slicing (BPS) and local binary pattern (LBP) based novel approach for glaucoma diagnosis. Firstly, our approach separates the red (R), green (G), and blue (B) channels from the input color fundus image and splits the channels into bit planes. Secondly, we extract LBP based statistical features from each of the bit planes of the individual channels. Thirdly, these features from the individual channels are fed separately to three different support vector machines (SVMs) for classification. Finally, the decisions from the individual SVMs are fused at the decision level to classify the input fundus image into normal or glaucoma class.
RESULTS: Our experimental results suggest that the proposed approach is effective in discriminating normal and glaucoma cases with an accuracy of 99.30% using 10-fold cross validation.
CONCLUSIONS: The developed system is ready to be tested on large and diverse databases and can assist the ophthalmologists in their daily screening to confirm their diagnosis, thereby increasing accuracy of diagnosis.
OBJECTIVE: This paper presents a machine learning-based approach for the automatic classification of regular and irregular capnogram segments.
METHODS: Herein, we proposed four time- and two frequency-domain features experimented with the support vector machine classifier through ten-fold cross-validation. MATLAB simulation was conducted on 100 regular and 100 irregular 15 s capnogram segments. Analysis of variance was performed to investigate the significance of the proposed features. Pearson's correlation was utilized to select the relatively most substantial ones, namely variance and the area under normalized magnitude spectrum. Classification performance, using these features, was evaluated against two feature sets in which either time- or frequency-domain features only were employed.
RESULTS: Results showed a classification accuracy of 86.5%, which outperformed the other cases by an average of 5.5%. The achieved specificity, sensitivity, and precision were 84%, 89% and 86.51%, respectively. The average execution time for feature extraction and classification per segment is only 36 ms.
CONCLUSION: The proposed approach can be integrated with capnography devices for real-time capnogram-based respiratory assessment. However, further research is recommended to enhance the classification performance.