Fuzzy Support Vector Machine based Fall Detection Method for Traumatic Brain Injuries

Falling is a major health issue that can lead to both physical and mental injuries. Detecting falls accurately reduce the severe effects improve quality of life for disabled people. Therefore, it critical develop smart fall detection system. Many approaches have been proposed in wearable-based systems. In these approaches, machine learning techniques conducted provide automatic classification accuracy. One most commonly used algorithms Support Vector Machine (SVM). However, classical SVM neither use prior knowledge process accurate classifications nor solve problems characterized by ambiguity. More specifically, some values are inaccurate similar features normal activities, which also greatly impact performance ability SVMs. Hence, became necessary look an effective method based on combination Fuzzy Logic (FL) so as false positive alarms this paper, various training data assigned corresponding membership degrees. Some points with high chance falling degree membership, yielding contribution decision-making. This does not only achieve detection, but reduces hesitation labeling outcomes improves heuristic transparency SVM. The experimental results achieved 100% specificity precision, overall accuracy 99.96%. Consequently, experiment proved be yielded better than conventional approaches.