In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.
Chinese Sign Language (CSL) subword recognition based on surface electromyography (sEMG), accelerometer (ACC), and gyroscope (GYRO) sensors was explored in this paper. In order to fuse effectively the information of these three kinds of sensors, the classification abilities of sEMG, ACC, GYRO, and their combinations in three common sign components (one or two handed, hand orientation, and hand amplitude) were evaluated first and then an optimized tree-structure classification framework was proposed for CSL subword recognition. Eight subjects participated in this study and recognition experiments under different testing conditions were implemented on a target set consisting of 150 CSL subwords. The proposed optimized tree-structure classification framework based on sEMG, ACC, and GYRO obtained the best performance among seven different testing conditions with single sensor, paired-sensor fusion, and three-sensor fusion, and the overall recognition accuracies of 94.31% and 87.02% were obtained for 150 CSL subwords in a user-specific test and user-independent test, respectively. Our study could lay a basis for the implementation of large-vocabulary sign language recognition system based on sEMG, ACC, and GYRO sensors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.