Similarity-based classification of sequences using hidden Markov models
Pattern Recognition
Development of a wireless sensor glove for surgicalskills assessment
IEEE Transactions on Information Technology in Biomedicine - Special section on computational intelligence in medical systems
Proceedings of the 2nd Conference on Wireless Health
| Hi-index | 0.00 |
Laparoscopic surgical training is a challenging task due to the complexity of instrument control and demand on manual dexterity and hand-eye coordination. Currently, training and assessing surgeons for their laparoscopic skills rely mainly on subjective assessment. This paper presents a Body Sensor Network (BSN) sensor glove for laparoscopic gesture recognition and objective assessment of surgical skills. An HMM framework is proposed for the selection of sensors to maximize the sensitivity and specificity of gesture recognition for a given set of laparoscopic tasks. With the proposed framework, the optimal location as well as the number of the sensors can be determined. The sensors used in this study include accelerometers and fiber optic bend sensors. Experimental data is collected by participants wearing the glove while performing simple laparoscopic tasks. By using the proposed HMM framework, sensor correlation and relevance to task recognition can be determined, thus allowing a reduction in the number of sensors used. Results have shown that it is possible to establish the intrinsic correlation of the sensors and determine which sensors are most relevant to specific gestures based on the proposed method.