Informatica

The recent introduction of whole-slide scanning systems enabled accumulation of high-quality pathology images into large collections, thus opening new perspectives in cancer research, as well as new analysis challenges. Automated identification of tumour tissue in the whole-slide image enables further use of developed grading systems that classify tumour cell abnormalities and predict tumour developments. In this article, we describe several possibilities to achieve epithelium-stroma classification of tumour tissues in digital pathology images by employing annotated superpixels to train machine learning algorithms. We emphasize that annotating superpixels rather than manually outlining tissue classes in raw images is less time consuming, and more effective way of producing ground truth for computational pathology pipelines. In our approach feature space for supervised learning is created from tissue class assigned superpixels by extracting colour and texture parameters, and applying dimensionality reduction methods. Alternatively, to train convolutional neural network, labelled superpixels are used to generate square image patches by moving fixed size window around each superpixel centroid. The proposed method simplifies the process of ground truth data collection and should minimize the time spent by a skilled expert to perform manual annotation of whole-slide images. We evaluate our method on a private data set of colorectal cancer images. Obtained results confirm that a method produces accurate reference data suitable for the use of different machine learning based classification algorithms.

The selection of waste lubricant oil regenerative technology regarding the complexity of the technologies and financial issues is a complex problem. Some risk factors exist regarding the ratings of technologies on the effective criteria. The current study tackles the selection of the technology based on fuzzy axiomatic design approach considering risk factors. Shannon entropy significance coefficients are computed for criteria. The problem is first solved by considering all criteria and then supplementary solutions are presented by categorizing the criteria to technical and economic groups. Two types of risk factors are identified for the technologies, i.e. general and specific risk factors.

The heliostat field of Solar Central Receiver Systems takes up to 50% of the initial investment and can cause up to 40% of energetic loss in operation. Hence, it must be carefully optimized. Design procedures usually rely on particular heliostat distribution models. In this work, optimization of the promising biomimetic distribution model is studied. Two stochastic population-based optimizers are applied to maximize the optical efficiency of fields: a genetic algorithm, micraGA, and a memetic one, UEGO. As far as the authors know, they have not been previously applied to this problem. However, they could be a good option according to their structure. Additionally, a Brute-Force Grid is used to estimate the global optimum and a Pure-Random Search is applied as a baseline reference. Our empirical results show that many different configurations of the distribution model lead to very similar solutions. Although micraGA exhibits poor performance, UEGO achieves the best results in a reduced time and seems appropriate for the problem at hand.

Non-programmed decision-making is an activity that requires a number of methods to try to capture the rational behaviour of an aspirant in situations of uncertainty. Thus, there is a varied list of attributes, methods, and mechanisms that are intended to describe the way in which aspirants can be profiled. However, this modelling proves to be complex if it is approached in scenarios based on game mechanics from gamification. For this reason, the following article aims to contribute to the processes of selection of personnel delimited only to the making of non-programmed decisions, through the implementation of game mechanics. In order to model this selection, the purpose of the following study is to carry out the formulation of inference rules based on fuzzy logic in order to capture the tacit transfer of certain types of information in personnel selection processes and to determine aspects that allow the shaping of aspirants. Finally, the results and conclusions obtained are presented.

The aim is to develop simple for industrial use neuro-fuzzy (NF) predictive controllers (NFPCs) that improve the system performance and stability compensating the nonlinear plant inertia and time delay. A NF plant predictor is trained from real time plant control data and validated to supply a main model-free fuzzy logic controller with predicted plant information. A proper prediction horizon is determined via simulation investigations. The NFPC closed loop system stability is validated based on a parallel distributed compensation (PDC) approximation of the NFPC. The PDC can easily be embedded in industrial controllers. The proposed approach is applied for the real time air temperature control in a laboratory dryer. The improvements are reduced overshoot and settling time.

Compared to fuzzy numbers, intuitionistic fuzzy numbers provide greater opportunities for solving complex decision-making problems, especially when they are related to ambiguities, uncertainties and vagueness. However, their use is more complex, especially when it comes to ordinary users. Therefore, in this paper an approach adopted for evaluating alternatives on the basis of a smaller number of some more complex evaluation criteria is proposed. The approach is based on the use of linguistic variables, triangular intuitionistic fuzzy numbers, and the Hamming distance. At the end, a case study of hotels’ websites evaluation is given to demonstrate the practicality and effectiveness of the proposed approach, together with its limitations and weaknesses. Additionally, a new procedure for ranking intuitionistic fuzzy numbers is proposed and its use is verified.

Scalar quantizer selection for processing a signal with a unit variance is a difficult problem, while both selection and quantizer design for the range of variances is even tougher and to the authors’ best knowledge, it is not theoretically solved. Furthermore, performance estimation of various image processing algorithms is unjustifiably neglected and there are only a few analytical models that follow experimental analysis. In this paper, we analyse application of piecewise uniform quantizer with Golomb-Rice coding in modified block truncation coding algorithm for grayscale image compression, propose design improvements and provide a novel analytical model for performance analysis. Besides the nature of input signal, required compression rate and processing delay of the observed system have a strong influence on quantizer design. Consequently, the impact of quantizer range choice is analysed using a discrete designing variance and it was exploited to improve overall quantizer performance, whereas variable-length coding is applied in order to reduce quantizer’s fixed bit-rate. The analytical model for performance analysis is proposed by introducing Inverse Gaussian distribution and it is obtained by discussing a number of images, providing general closed-form solutions for peak-signal-to-noise ratio and the total average bit-rate estimation. The proposed quantizer design ensures better performance in comparison to the other similar methods for grayscale image compression, including linear prediction of pixel intensity and edge-based adaptation, whereas analytical model for performance analysis provides matching with the experimental results within the range of 1 dB for PSQNR and 0.2 bpp for the total average bit-rate.

Information systems contain a lot of data regarding business process execution history. Use of this data, in the form of an event log, can greatly support business process management. The paper presents an approach to construct Bayesian belief network from an event log that could facilitate decision support in business process execution. The approach is evaluated against multiple event logs by inferring data probabilities occurring in the business processes. The results show that the approach is suitable for the task and could be used in decision support with future research focused on prediction and simulation of business processes.

In this paper, with respect to how to express the complex fuzzy information, we proposed the concept of interval-valued linguistic intuitionistic fuzzy numbers (IVLIFNs), whose membership and non-membership are represented by interval-valued linguistic terms, then the Hamming distance is defined, further, we also proposed the interval-valued linguistic intuitionistic fuzzy entropy. Considering that the VIKOR method can achieve the maximum “group utility” and minimum of “individual regret”, we extended the VIKOR method to process the interval-valued linguistic intuitionistic fuzzy information (IVLIFI), and proposed an extended VIKOR method for the multiple attribute decision making (MADM) problems with IVLIFI. And an illustrative example shows the effectiveness of the proposed approach.