In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual Attention Network is built by stacking Attention Modules which generate attention-aware features. The attention-aware features from different modules change adaptively as layers going deeper. Inside each Attention Module, bottom-up top-down feedforward structure is used to unfold the feedforward and feedback attention process into a single feedforward process. Importantly, we propose attention residual learning to train very deep Residual Attention Networks which can be easily scaled up to hundreds of layers.Extensive analyses are conducted on CIFAR-10 and CIFAR-100 datasets to verify the effectiveness of every module mentioned above. Our Residual Attention Network achieves state-of-the-art object recognition performance on three benchmark datasets including CIFAR-10 (3.90% error), CIFAR-100 (20.45% error) and ImageNet (4.8% single model and single crop, top-5 error). Note that, our method achieves 0.6% top-1 accuracy improvement with 46% trunk depth and 69% forward FLOPs comparing to ResNet-200. The experiment also demonstrates that our network is robust against noisy labels.

No abstract

In this paper, an identification method of finger motions using the wavelet transform of multi-channel electromyography (EMG) signal is presented. The first step of this method is to analyze surface EMG signal detected from the subject's upper arm using the multi-resolution of wavelet transform, and extract features using the variance, maximum and mean absolute value of the wavelet coefficients. In this way, a new feature space is established by wavelet coefficients. The second step is to import the feature values into an Artificial Neural Network (ANN) to identify the finger motion. Based on the results of experiments, it is concluded that this method is effective in identification of finger motion. Thus, it provides an alternative approach to use the surface EMG in controlling the finger motion of a multi-fingered prosthetic hand.

No abstract

No abstract