The performance optimization of scientific applications usually requires an in-depth knowledge of the hardware and software. A performance tuning mechanism is suggested to automatically tune OpenACC parameters to adapt to the execution environment on a given system. A historic learning based methodology is suggested to prune the parameter search space for a more efficient auto-tuning process. T...

We are developed a modified version of affine projection algorithm for acoustic echo cancellation, which has moderate convergence speed and noiserobust characteristics. The proposed algorithm normalizes the update equation to reduce noise effect of affine projection algorithm, by adding the multiplication of estimation error power and projection order to auto-covariance matrix of input signal. ...

We characterise the relationship between two network based oligopoly markets when local players share the interconnection’s ownership. To that purpose, we analyse the case of the Bacton (UK)-Zeebrugge (Belgium) natural gas pipeline using Vector Auto-regressive Representation techniques. We conclude that there is a threshold of capacity deployment after which the two local markets split. As a re...

The purpose of the paper is to provide a method to quantify the impact of promotions for retailers. Using scanner data aggregated by category of an Italian hypermarkets chain, the authors measure the promotional direct and cross-effectiveness on regular sales, in shortand long-term, by means of a structural vector auto-regressive model. The empirical results suggest that promotions in the heavy...

This paper develops a framework for stress-testing the credit risk of Chinese commercial banks to macroeconomic shocks. Using data over the period 1985-2008, this study establishes a vector auto-regression (VAR) model to describe the links between default rate and macroeconomic factors, and then designs three stress scenarios to implement the stress testing by Monte Carlo simulation. As a resul...

Three different methodologies for automatic speaker identification have been evaluated in the paper, namely the well known Dynamic Time Warping (DTW), the Auto-Regressive Vector Models (ARVM) and an Algebraic Approach (AA). The aim of our study is to examine the effectiveness of these approaches in the fixed-text speaker identification task with short phrases in Bulgarian language collected ove...

Abstract— Electromyography (EMG) signal provides a significant source of information for identification of neuromuscular disorders. This paper presents an application of neural network classifier on classification and identification of different normal and auto aggressive actions of hands and legs. Eight features that are extracted from eight channel EMG signals representing these actions have ...

We present a weighted-LASSO method to infer the parameters of a first-order vector auto-regressive model that describes time course expression data generated by directed gene-to-gene regulation networks. These networks are assumed to own prior internal structures of connectivity which drive the inference method. This prior structure can be either derived from prior biological knowledge or infer...

People detection is an interesting computer vision topic. Locating people in images and videos have many potential applications, such as human computer interaction and auto-focus cameras. There have been much effort on developing people detection algorithms, and among them, the “Dense ScaleInvariant Feature Transform (DSIFT) [1]” algorithms appear to be very effective. To implement our own peop...

This paper presents an Intelligent control based fuzzy logic for Sensorless speed control of induction motor drive. The proposed scheme used indirect vector control with fuzzy logic controller which gives optimal condition for maximum torque both in steady state and transient condition and has ability to plan via decomposition of a complex task into manageable subtasks and it has auto tuning pr...