Wrocław University of Technology

About: Wrocław University of Technology is a education organization based out in Wrocław, Poland. It is known for research contribution in the topics: Laser & Computer science. The organization has 13115 authors who have published 31279 publications receiving 338694 citations.

Evolutionary undersampling boosting for imbalanced classification of breast cancer malignancy

Abstract: Graphical abstractDisplay Omitted HighlightsAutomatic clinical decision support system for breast cancer malignancy grading.Different methodologies for segmentation and feature extraction from FNA slides.An efficient classifier ensemble for imbalanced problems with difficult data.Ensemble combines boosting with evolutionary undersampling.Extensive computational experiments on a large database collected by authors. In this paper, we propose a complete, fully automatic and efficient clinical decision support system for breast cancer malignancy grading. The estimation of the level of a cancer malignancy is important to assess the degree of its progress and to elaborate a personalized therapy. Our system makes use of both Image Processing and Machine Learning techniques to perform the analysis of biopsy slides. Three different image segmentation methods (fuzzy c-means color segmentation, level set active contours technique and grey-level quantization method) are considered to extract the features used by the proposed classification system. In this classification problem, the highest malignancy grade is the most important to be detected early even though it occurs in the lowest number of cases, and hence the malignancy grading is an imbalanced classification problem. In order to overcome this difficulty, we propose the usage of an efficient ensemble classifier named EUSBoost, which combines a boosting scheme with evolutionary undersampling for producing balanced training sets for each one of the base classifiers in the final ensemble. The usage of the evolutionary approach allows us to select the most significant samples for the classifier learning step (in terms of accuracy and a new diversity term included in the fitness function), thus alleviating the problems produced by the imbalanced scenario in a guided and effective way. Experiments, carried on a large dataset collected by the authors, confirm the high efficiency of the proposed system, shows that level set active contours technique leads to an extraction of features with the highest discriminative power, and prove that EUSBoost is able to outperform state-of-the-art ensemble classifiers in a real-life imbalanced medical problem.

ABE fermentation products recovery methods—A review

Abstract: Butanol has a great potential as a biofuel and to date a lot of research has been done both in terms of more efficient butanol production as well as in developing product recovery methods. Many of them deal with separation techniques which can be used for selective recovery of acetone, n-butanol and ethanol from model solutions and fermentation broths. This work is a review of techniques used for ABE recovery, such as distillation, adsorption, gas stripping, liquid–liquid extraction, pertraction, membrane distillation, sweeping gas pervaporation, thermopervaporation and vacuum pervaporation. Advantages and disadvantages of using particular methods, examples of applications and integrated processes are also described.

What do metals tell us about wine

Abstract: This article focuses on analysis of metals in wine in the literature devoted to analytical atomic spectrometry in the past decade. It emphasizes the role of metals in wine and processes involved in winemaking. It covers endogenous and exogenous sources of metals in wine, changes in metal composition during vinification, methods of wine analysis, techniques of wine classification corresponding to distinctive metal patterns, and, finally, approaches to operationally-defined fractionation analysis of metals carried out to understand their nutritional value and bioavailability in wine.

The effect of isopropyl alcohol on etching rate and roughness of (1 0 0) Si surface etched in KOH and TMAH solutions

Abstract: The etching process of (1 0 0) silicon wafers in KOH and TMAH solutions with isopropyl alcohol (IPA) has been studied. The etching rates of different crystallographic planes in the wide range of solutions concentration have been estimated. The mutual relations of the etching rates of these planes have been analysed. Special emphasis was put on the roughness of silicon surface obtained in effect of etching. It was proved that IPA added to the solution improves the morphology of resulted surface. Detailed indications about the solution composition, ensuring satisfactory surface quality have been given. On the basis of experimental results and theoretical considerations, some attempts were made to explain the etching behaviour of silicon in KOH and TMAH solutions with IPA addition. It was suggested that TMA+ ions play similar role in the solution to IPA particles and participate in smoothening of the etched surface.