Development of a semi-automatic self learning pattern recognition system for the control of electronic boards

This project was funded under the Applied Research Grants Scheme administered by Enterprise Ireland. The project was a partnership between Galway - Mayo Institute of Technology and an industrial company, Tyco/Mallinckrodt Galway. The project aimed to develop a semi - automatic, self - learning pattern recognition system capable of detecting defects on the printed circuits boards such as component vacancy, component misalignment, component orientation, component error, and component weld. The research was conducted in three directions: image acquisition, image filtering/recognition and software development. Image acquisition studied the process of forming and digitizing images and some fundamental aspects regarding the human visual perception. The importance of choosing the right camera and illumination system for a certain type of problem has been highlighted. Probably the most important step towards image recognition is image filtering, The filters are used to correct and enhance images in order to prepare them for recognition. Convolution, histogram equalisation, filters based on Boolean mathematics, noise reduction, edge detection, geometrical filters, cross-correlation filters and image compression are some examples of the filters that have been studied and successfully implemented in the software application. The software application developed during the research is customized in order to meet the requirements of the industrial partner. The application is able to analyze pictures, perform the filtering, build libraries, process images and generate log files. It incorporates most of the filters studied and together with the illumination system and the camera it provides a fully integrated framework able to analyze defects on printed circuit boards.

The Word Brain - A Short Guide to Fast Language Learning

How long does it take to learn another language? How many words do you need to learn? Are languages within the reach of everybody? Which teachers would you choose and which teachers should you avoid? These are some of the questions you ask yourself when you start learning a new language.The Word Brain provides the answers. If you have learned foreign languages in the past, consider reading it. If you or your children need to learn languages in the future, you must read it. What you will discover in two hours will change for ever the way you see languages and language learning. The principles of The Word Brain are timeless. Our children’s grandchildren will follow them when they discover the people of our planet.

On the role of temporal context in human reinforcement learning

Magdeburg, Univ., Fak. für Naturwiss., Diss., 2011

Partially supervised learning of fuzzy classification rules

Fuzzy classification, semi-supervised learning, data mining

Search improvements in multirelational learning

Machine learning, inductive logic programming, search

contribution of horizontal. intracortical connections to learning-induced gamma oscillations

Magdeburg, Univ., Fak. für Naturwiss., Diss., 2011

role of the anterior cingulate cortex in extinction learning of avoidance behavior and in the retrieval of its extinction memory

Magdeburg, Univ., Fak. für Naturwiss., Diss., 2012

Value of the Qrs-T Angle in Predicting the Induction of Ventricular Tachyarrhythmias in Patients with Chagas Disease

Background:The QRS-T angle correlates with prognosis in patients with heart failure and coronary artery disease, reflected by an increase in mortality proportional to an increase in the difference between the axes of the QRS complex and T wave in the frontal plane. The value of this correlation in patients with Chagas heart disease is currently unknown.Objective:Determine the correlation of the QRS-T angle and the risk of induction of ventricular tachycardia / ventricular fibrillation (VT / VF) during electrophysiological study (EPS) in patients with Chagas disease.Methods:Case-control study at a tertiary center. Patients without induction of VT / VF on EPS were used as controls. The QRS-T angle was categorized as normal (0-105º), borderline (105-135º) or abnormal (135-180º). Differences between groups for continuous variables were analyzed with the t test or Mann-Whitney test, and for categorical variables with Fisher's exact test. P values < 0.05 were considered significant.Results:Of 116 patients undergoing EPS, 37.9% were excluded due to incomplete information / inactive records or due to the impossibility to correctly calculate the QRS-T angle (presence of left bundle branch block and atrial fibrillation). Of 72 patients included in the study, 31 induced VT / VF on EPS. Of these, the QRS-T angle was normal in 41.9%, borderline in 12.9% and abnormal in 45.2%. Among patients without induction of VT / VF on EPS, the QRS-T angle was normal in 63.4%, borderline in 14.6% and abnormal in 17.1% (p = 0.04). When compared with patients with normal QRS-T angle, those with abnormal angle had a fourfold higher risk of inducing ventricular tachycardia / ventricular fibrillation on EPS [odds ratio (OR) 4; confidence interval (CI) 1.298-12.325; p = 0.028]. After adjustment for other variables such as age, ejection fraction (EF) and QRS size, there was a trend for the abnormal QRS-T angle to identify patients with increased risk of inducing VT / VF during EPS (OR 3.95; CI 0.99-15.82; p = 0.052). The EF also emerged as a predictor of induction of VT / VF: for each point increase in EF, there was a 4% reduction in the rate of sustained ventricular arrhythmia on EPS.Conclusions:Changes in the QRS-T angle and decreases in EF were associated with an increased risk of induction of VT / VF on EPS.

Neural dynamics and their relationship to learning behavior in response tot stimulation with a cortical neuroprosthesis

Sensory cortex, neuroprosthetics, brain-machine-interfaces, neurodynamics, learning, perception, embodied cognition

Möglichkeiten und Grenzen des Distance Learning am Beispiel des Alberta Distance Learning Centre in Kanada : Analyse und Transfer auf den Schulkontext Sachsen-Anhalts

Distance learning, Canadian educational system, institution, medial learning, school system Saxony-Anhalt, system theory, qualitative research

Reduced Progression of Cardiac Allograft Vasculopathy with Routine Use of Induction Therapy with Basiliximab

AbstractIntroduction:Cardiac allograft vasculopathy (CAV) is a major limitation for long-term survival of patients undergoing heart transplantation (HT). Some immunosuppressants can reduce the risk of CAV.Objectives:The primary objective was to evaluate the variation in the volumetric growth of the intimal layer measured by intracoronary ultrasound (IVUS) after 1 year in patients who received basiliximab compared with that in a control group.Methods:Thirteen patients treated at a single center between 2007 and 2009 were analyzed retrospectively. Evaluations were performed with IVUS, measuring the volume of a coronary segment within the first 30 days and 1 year after HT. Vasculopathy was characterized by the volume of the intima of the vessel.Results:Thirteen patients included (7 in the basiliximab group and 6 in the control group). On IVUS assessment, the control group was found to have greater vessel volume (120–185.43 mm3 vs. 127.77–131.32 mm3; p = 0.051). Intimal layer growth (i.e., CAV) was also higher in the control group (27.30–49.15 mm3 [∆80%] vs. 20.23–26.69 mm3[∆33%]; p = 0.015). Univariate regression analysis revealed that plaque volume and prior atherosclerosis of the donor were not related to intima growth (r = 0.15, p = 0.96), whereas positive remodeling was directly proportional to the volumetric growth of the intima (r = 0.85, p < 0.001).Conclusion:Routine induction therapy with basiliximab was associated with reduced growth of the intima of the vessel during the first year after HT.

Proactive ontology-based content provision in the context of e-learning

Magdeburg, Univ., Fak. für Informatik, Diss., 2008

Document-oriented e-learning components

Magdeburg, Univ., Fak. für Informatik, Diss., 2009

Robust learning in safety-related domains : machine learning methods for solving safety-related application problems

Magdeburg, Univ., Fak. für Informatik, Diss., 2009