Combined Support Vector Machine (SVM) and Principal Component Analysis (PCA) was used to recognize the infant cries with asphyxia. SVM classifier based on features selected by the PCA was trained to differentiate between pathological and healthy cries. The PCA was applied to reduce dimensionality of the vectors that serve as inputs to the SVM. The performance of the SVM utilizing linear and RBF kernel was examined. Experimental results showed that SVM with RBF kernel yields good performance. The classification accuracy in classifying infant cry with asphyxia using the SVM-PCA is 95.86%.

No abstract

No abstract

No abstract

Previous works on the effects of salivary alpha amylase in respond to various stressors report encouraging findings on it being a good indicator of stress. Ellestad protocol is a clinical procedure to screen for coronary artery disease by introducing exercise induced physical stress. If a salivary based biomarker profile in accordance to a stress test protocol could be established, the critical stress state which disable rational decision making could be ascertained in a standardized procedure. This technique would serve to aid human resource management in times of critical events such as rescue, firefighting or even military, that would potentially prevent unnecessary sacrifice of human lives. In this pilot study with five healthy volunteers performing the Ellestad protocol treadmill, a measurement profile with physiologic and salivary based biomarker is obtained. It is found that the alpha amylase levels or the changes in it as workload changes from resting-walking-running at ease-exhaustive running, is relatively more significant in reflecting the stress state than heart rate and blood pressure. Moreover, it is strongly associated with mood state with correlation coefficient of 0.8 and significance of 0.01.