A multi-stage approach is presented for thresholding document images, along with its application. The proposed method is based on two stages. Global thresholding is used in first stage to give a preliminary result. A second stage then refines the threshold value based on local spatial characteristics of the regions formed in the first stage. It automatically customizes the thresholding of regio...

This paper presents four different approaches for integrating conventional and AI-based forecasting models to provide a hybridized solution to the continuous river level and flood prediction problem. Individual forecasting models were developed on a stand alone basis using historical time series data from the River Ouse in northern England. These include a hybrid neural network, a simple rule-b...

Project management decisions are made at the strategic, the tactical and the operational level. These decision levels are unarguably interrelated. Uncertainty in project management is primarily dealt with at an operational level by detecting operational risks and deciding on how to respond to them such that the tactical objectives can be met. We stress some major issues regarding the topics of ...

The need to answer quickly to new market opportunities and the high variability of consumer demands tend industrial companies to review their adopted organisation, so to improve their reactivity and to facilitate the coupling with the business enactment. Therefore, these companies require agility in their information systems to allow business needs scalability and design process flexibility. We...

Wireless sensor networks have the problem of lifetime and scalability. To increase lifetime and scalability it is necessary to have control over topology of the network even when dynamically changes are observed. Dynamic clustering with adaptive feature is the best way to achieve the above. In this paper we propose a dynamic multi-level hierarchal clustering (DMH) approach for sensor networks. ...

The Discriminative Generalized Hough Transform (DGHT) is a method for object localization, which combines the standard Generalized Hough Transform (GHT) with a discriminative training technique. In this setup the aim of the discriminative training is to equip the models used in the GHT with individual model point weights such that the localization error in the GHT becomes minimal. In this paper...

Evolutionary Algorithms (EAs) are in this case counter-intuitive since they try to evolve a solution for the entire problem as a whole. EAs may show improvement when they can create more complex evolutionary units through some form of cooperative combination of sub-solutions similar to divide-and-conquer. In other words, instead of trying to evolve a single solution for the problem, solutions m...

Mathematical modeling of an engineering system often leads to such formulations for which one can not obtain a closed form solution/analysis, and thus numerical methods are to be used. In the process, we need to transform the system from an infinite dimensional space to a finite dimensional one(discretization). The result is usually a system of linear equations[5] for which the linear least squ...

We are in the era of multicore processors and it is expected that the number of the processing cores on a chip will steadily increase over the next decade, driven by Moore’s Law. While technology scaling has benefitted high performance, the scaling has a dark side too: a degradation in the reliability of silicon devices. Processors have become highly susceptible to a variety of reliability prob...

Information Extraction (IE) is the process of identifying a set of pre-defined relevant items in text documents. We investigate the application of Machine Learning classification techniques to the problem of Information Extraction. In particular we use Support Vector Machines and several different feature-sets to build a set of classifiers for Information Extraction (IE). We show that this appr...