A novel bind estimation method for encoder parameters operating over the noisy received signal is proposed in this paper. This scheme can blindly identify the turbo encoder adopted at the transmitter so as to correctl...
详细信息
ISBN:
(纸本)9781467309202
A novel bind estimation method for encoder parameters operating over the noisy received signal is proposed in this paper. This scheme can blindly identify the turbo encoder adopted at the transmitter so as to correctly decode the received signal sequence. An iterative expectation-maximization algorithm is designed to estimate the coding parameters, which are the weighting coefficients in a recursive convolutional encoder. These coefficients are associated with the feedback and forward connections in the encoder. To tackle this blind encoder-parameter estimation, we separate the feedback portion from the forward structure and then convert the recursive systematic convolutional encoder into a non-systematic convolutional encoder preceded by a feedback encoder. Our new encoder structure will be investigated. The effect of the separate feedback encoder on the state sequence resulting from the forward convolutional encoder will be studied. Monte Carlo simulation results will be demonstrated to evaluate the effectiveness of our proposed new scheme.
In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and deconvo...
详细信息
ISBN:
(纸本)9781510838819
In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and deconvolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers act as the feature extractor, which capture the abstraction of image contents while eliminating noises/corruptions. Deconvolutional layers are then used to recover the image details. We propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum. First, the skip connections allow the signal to be back-propagated to bottom layers directly, and thus tackles the problem of gradient vanishing, making training deep networks easier and achieving restoration performance gains consequently. Second, these skip connections pass image details from convolutional layers to deconvolutional layers, which is beneficial in recovering the original image. Significantly, with the large capacity, we can handle different levels of noises using a single model. Experimental results show that our network achieves better performance than recent state-of-the-art methods.
暂无评论