This paper is aimed to study the impact of sEMG feature weight on the recognition of similar grasping gesture, of which the classification performance is hindered by their alike underlying muscle activation pattern. The sEMG were collected from six forearm hand muscles (EPB, EPI, FDS, PL, MB, ED) when subjects conducted a 4-second different grasping gestures. Then empirical mode decomposition (EMD) was employed to represent the sEMG as IMF components, of which the time-domain features (ZC and WAMP) were obtained. Then PCA was used to reduce the dimension of feature set. The optimal training set of similar grasping gestures was determined by adjusting the weight of sEMG feature in the feature space. SVM classifier and Genetic-Algorithm (GA) were used to classify the patterns of the gestures. Experimental results showed that the classification rate of a gesture was improved with the increasing proportion of its sEMG feature in training set, and different gesture exhibited different sensitivity for gesture recognition. The present work suggested that the proportion of candidate gesture should not be equal, and the contribution of different gesture should be considered to optimize the training set.

Several features have been developed to characterize land cover in synthetic aperture radar (SAR) data with speckle noise. Feature extraction has become an essential task for SAR image processing. However, how to preserve the original intrinsic structural information and enhance the discriminant ability to reduce the impact of noise is still a challenge in this area. In this paper, using a clustering method to maintain the nonlocal information in images and tensors with the ability to preserve spatial neighborhood structure information, a new cluster-based tensorial semisupervised discriminant analysis (CTSDA) method is proposed for feature extraction of SAR images. In the CTSDA, the block clustering algorithm is employed to generate several high-order clustering tensors of multifeature SAR images, which preserves the intrinsic nonlocal spatial information and neighborhood structure. In the multiple manifold structures of the cluster tensors, the improved discriminant analysis enhances the feature discrimination by considering the local structure and labeled and unlabeled information through the Laplace matrix, and the fusion of tensor algebraic analysis and improved discriminant analysis produces multiple new projection directions of the cluster tensors. Finally, feature extraction is achieved by rearranging the projected cluster tensors. The experimental results on the simulated SAR data and four real SAR images demonstrate the superiority of the proposed method over several state-of-the-art approaches.