-Viterbi decoder is a basic and important block in any Code Division Multiple Access (CDMA) and CDMA uses Convolutional encoder to prevent Interference. Convolutional encoding and Viterbi decoding are widely used in various communication systems because of their excellent error control performance. This paper deals with the implementation of Convolutional encoding and Viterbi decoding using SOP...

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 de-convolution 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 ...

In this thesis, a family of low complexity convolutional codes is constructed, by modifying appropriately the trellis diagram of punctured convolutional codes. The goal is to improve performance at the expense of a reasonable low increase of the trellis complexity. Many new convolutional codes of various code rates and values of complexity are provided. In many cases, a small increase in comple...

In the last few years, deep learning has lead to very good performance on a variety of problems, such as object recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Due to the lack of training data and computing power in early days, it is hard to train a large high-capaci...

In this paper, we investigate the performance of serially concatenated convolutional code with super-orthogonal space-time trellis code (SOSTTC) in orthogonal frequency division multiplexing (OFDM) over frequency selective fading channels. We consider both recursive systematic convolutional code (RSC) and non-recursive convolutional code (NRC) as the outer code, and 16-state QPSK SOSTTC as the ...

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse. Examples include penstrokes forming on a piece of paper, or (colored) 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard “dense...

We present in this paper a simple, yet efficient convolutional neural network (CNN) architecture for robust audio event recognition. Opposing to deep CNN architectures with multiple convolutional and pooling layers topped up with multiple fully connected layers, the proposed network consists of only three layers: convolutional, pooling, and softmax layer. Two further features distinguish it fro...

In this paper two-dimensional convolutional codes with finite support are considered, i.e., convolutional codes whose codewords have compact support indexed in N and take values in F, where F is a finite field. The main goal of this work is to analyze the (free) distance properties of this type of codes of rate 1/n and degree δ. We first establish an upper bound on the maximum possible distance...

Convolutional codes over rings behave quite differently from convolutional codes over fields, but they are the ones best suited for phase modulation. This behavior depends strongly on the structure of the underlying ring. Some basic concepts about ring convolutional codes, in particular over Zpr , and their structural properties such as basicity, systematicity, non-catastrophicity and minimalit...

We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional kernel. This allows us to gain the generalisation benefit of a convolutional kernel, together wit...