The purpose of this paper is to develop an effective method to identify upper limb motions based on EMG signal for community rehabilitation. The method will be applicable to the control system in the rehabilitation equipment and provide objective data for quantitative assessment. The recognition goal sets of upper limb motion are constructed by decomposing assessment activities of activity of daily living scale (ADL). The recognition feature vector space is established by Variance (VAR), Mean Absolute Value (MAV), the fourth-order Autoregressive (the 4thAR), Zero Crossings (ZC’s), integral EMG (IEMG), and Root Mean Square (RMS), and various feature sets are extracted to get the best classification. Locally linear embedding (LLE) algorithm is used to reduce the computational complexity, and upper limb motions about shoulder, elbow and wrist are quickly classified through extreme leaving machine (ELM), which obtained the average accuracy of 98.14%, 98.61% and 94.77%, respectively. Furthermore, when ELM is compared with Back-propagation (BP) and Support vector machine (SVM), it has performed relatively better than BP and SVM. The results show that the validity of the mixed model for recognition is verified. In addition, the method can also provide a basis for recognition and assessment of the angle of upper limb joint in the next study.

No abstract

Chart datum is a vertical reference of ocean depth, which can give the ocean vertical spatial information for Marine Geodesy. Due to time and resource constraints, it is a practical problem of how to determine the chart datum with high accuracy at the short-term tidal stations. In this paper, based on the least-square fitting model, the transfer algorithm for the chart datum at the short-term tidal stations is further developed. Both the accuracy of chart datum computed by this algorithm and the effect on those are presented. The findings of this paper are summarized as follows: The accuracy computed by the least-square fitting model can achieve the centimeter level. The accuracy values determined by the least-square fitting model can further be improved by using the instantaneous ratio of tidal range and selecting the short-distance permanent tidal station.

No abstract