Bummo Koo

TL;DR: A threshold-based preimpact fall detection algorithm was developed for wearable airbags that minimize the impact of falls on the user’s body and achieved a high accuracy using the experimental data, which included some highly dynamic motions that had not been tested previously.

TL;DR: The algorithm was successfully applied to provide seven different hand postures in a 5-finger myoelectric hand prosthesis and showed that the major misclassifications were lateral pinch versus palmar pinch, and index versus thumb-up, however, with the classification training for seven or more sessions, the probability of misclassification significantly decreased.

TL;DR: In this article, an sEMG-based hand posture recognition algorithm was developed, considering three main problems: electrode shift, feature vectors, and posture groups, and the results indicated that the classification performance improved with the number of training sessions of the electrode shift.

TL;DR: In this paper , the accuracy and practicality of three different types of algorithms for pre-impact fall detection using both young and old subjects were comprehensively compared, and it was shown that ConvLSTM had an accuracy of 99.16 % and an averaged lead time of 403 ms on young subjects, which outperformed SVM (97.16 percent, 385 ms) and much superior to the threshold-based algorithm (89.06 %, 333 ms).