Memory and computation efficient deep learning architectures are crucial to continued proliferation of machine learning capabilities to new platforms and systems. Binarization of operations in convolutional neural networks has shown promising results in reducing model size and computing efficiency. In this paper, we tackle the problem using a strategy different from the existing literature by p...

This paper describes the Local Serialization pattern which decouples object concurrency control policies from objectspecific algorithm semantics and concurrency generation policies. The pattern was designed in the context of a development process for distributed applications which considers concerns and abstractions. Concerns are the distribution issues that should be solved during the developm...

Novel preventive link maintenance scheme based on directional antennas has been proposed to extend the life of the link for multihop infrastructureless networks such as Mobile Ad Hoc Networks (MANET). We use the ability of directional antennas to orientate radio signals into the desired directions. We investigate preventive link maintenance scheme to on-demand routing algorithms. The scheme of ...

The unavoidable speckle in SAR images seriously interferes with image quality and has a negative effect on subsequent interpretation. existing filters still need to be strengthened terms of both noise suppression edge preservation. Based this, novel non-local means filter by multi-directional local plane inclination angle (MDLPIA) is proposed. proposed uses the MDLPIA reconstruct new weight fun...

This project will involve the exploration of a directional extension of multidimensional wavelet transforms, called “contourlets”, to perform pattern recognition. First, the general concept of a directional extension vs. a regular multidimensional wavelet transform will be discussed and explain the reasoning behind the directional extension. Then, a comparison will be done using sample images b...

This project will involve the exploration of a directional extension of multidimensional wavelet transforms, called “contourlets”, to perform pattern recognition. First, the general concept of a directional extension vs. a regular multidimensional wavelet transform will be discussed and explain the reasoning behind the directional extension. Then, an objective comparison will be done using samp...

Vortex-induced vibrations (VIVs) of a flexible cylinder subjected to multi-directional flows have been studied based on wake oscillator model. The flow comprises two slabs in different directions, with each slab having uniform uni-directional profile. dynamics the is described linear Euler–Bernoulli beam theory, and model uniformly distributed along hydrodynamic force acting it. coupled system ...

There has been a considerable interest in the development of human-like image perception systems. Although a number of algorithms have been proposed so far, it is still a challenging task to achieve a human-like robustness in image perception under various circumstances. For robust image perception, the feature representation algorithm which extracts essential features from an image and represe...

In this study, we suggest a new approach to the detection of edge orientation in order to guide a choice of the appropriate directional filter. This approach aims at analysing variograms properties such as the directionality, the renewal period of texture pattern and size of objet. The use of variograms enable to define directional MAP and to determine the edge orientation of the object in orde...

In this work we addresses the issue of deafness and hidden terminal problem in Mobile Ad Hoc Networks (MANETs) using directional antennas. To minimize these effects, we propose a MAC protocol for directional Antennas (MDA) which employs a novel Enhanced Directional Network Allocation Vector (EDNAV) scheme and, and an efficient technique of Diametrically Opposite Directions (DOD) transmission of...