Informatica

A method for counterfactual explanation of machine learning survival models is proposed. One of the difficulties of solving the counterfactual explanation problem is that the classes of examples are implicitly defined through outcomes of a machine learning survival model in the form of survival functions. A condition that establishes the difference between survival functions of the original example and the counterfactual is introduced. This condition is based on using a distance between mean times to event. It is shown that the counterfactual explanation problem can be reduced to a standard convex optimization problem with linear constraints when the explained black-box model is the Cox model. For other black-box models, it is proposed to apply the well-known Particle Swarm Optimization algorithm. Numerical experiments with real and synthetic data demonstrate the proposed method.

In order to avoid working in a constrained hazardous environment, manual spray painting operation is gradually being replaced by automated robotic systems in many manufacturing industries. Application of spray painting robots ensures defect-free painting of dissimilar components with higher repeatability, flexibility, productivity, reduced cycle time and minimum wastage of paint. Due to availability of a large number of viable options in the market, selection of a spray painting robot suitable for a given application poses a great problem. Thus, this paper proposes the integrated application of step-wise weight assessment ratio analysis (SWARA) and combined compromise solution (CoCoSo) methods to identify the most apposite spray painting robot for an automobile industry based on seven evaluation criteria (payload, mass, speed, repeatability, reach, cost and power consumption). The SWARA method identifies cost as the most significant criterion based on a set preference order, whereas, Fanuc P-350iA/45 is selected as the best spray painting robot by CoCoSo method. The derived ranking results are also contrasted with other popular multi-criteria decision making (MCDM) techniques (TOPSIS, VIKOR, COPRAS, PROMETHEE and MOORA) and subjective criteria weighting methods (AHP, PIPRECIA, BWM and FUCOM). High degrees of similarity in the ranking patterns between the adopted approach and other MCDM techniques prove its effectiveness in solving complex industrial robot selection problems. This integrated approach is proved to be quite robust being almost unaffected by the changing values of the corresponding tuning parameter in low-dimensional MCDM problems.

The theory of T-spherical fuzzy (T-SF) sets possesses remarkable capability to manage intricate uncertain information. The REGIME method is a well-established technique concerning discrete choice analysis. This paper comes up with a multiple-criteria choice analysis approach supported by the REGIME structure for manipulating T-SF uncertainties. This paper constructs new-created measurements such as superiority identifiers and guide indices for relative attractiveness and fittingness, respectively, between T-SF characteristics. This study evolves the T-SF REGIME I and II prioritization procedures for decision support. The application and comparative studies exhibit the effectiveness and favorable features of the propounded T-SF REGIME methodology in real decisions.

This paper aims to develop a Fermatean fuzzy ELECTRE method for solving multi-criteria group decision-making problems with unknown weights of decision makers and incomplete weights of criteria. First, a new distance measure between Fermatean fuzzy sets is proposed based on the Jensen–Shannon divergence. The cross entropy for Fermatean fuzzy sets is defined. Three kinds of dominance relationships for Fermatean fuzzy sets are proposed. Then, two optimization models are constructed to obtain positive ideal decision-making information and negative ideal decision-making information, respectively. Accordingly, the credibility degree of each decision maker is calculated. Decision makers’ dynamic weights are determined by their credibility degrees. Besides, to obtain the weights of criteria, an optimization model is constructed based on grey relational analysis for Fermatean fuzzy numbers. Finally, the strong, medium and weak Fermatean fuzzy concordance and discordance sets are identified to construct the Fermatean fuzzy concordance and discordance matrices, respectively. A practical case study is carried out to illustrate the feasibility and applicability of the proposed ELECTRE method. Comparative analyses are performed to demonstrate the superiority and effectiveness of the proposed ELECTRE method.

Computed tomography coronary angiography (CTCA) is a non-invasive, powerful image processing technique for assessing coronary artery disease. The aim of the paper is to evaluate the diagnostic role of CTCA using optimal scanning parameters and to investigate the effect of low kilovoltage CTCA on the qualitative and quantitative image parameters and radiation dose in overweight and obese patients. Consolidation of knowledge in medicine and image processing was used to achieve the aim, and performance was evaluated in a clinical setting. Elevated body mass index is one of the factors causing increased radiation dose to patients. This study examined the feasibility of 80-kV and 100-kV CTCA in overweight and obese adult patients, comparing radiation doses and image quality versus standardized 100-kV protocols in the group of overweight patients and 120-kV CTCA in the group of obese patients. Qualitative and quantitative image parameters were determined in proximal and distal segments of the coronary arteries. Quantitative assessment was determined by the contrast-to-noise ratio and signal-to-noise ratio. The results of the study showed that in overweight and obese patients, the low dose protocol affords radiation dose reduction of 35% and 41%, respectively. Image quality was found to be diagnostically acceptable in all cases.

Convolutional neural networks (CNNs) were popular in ImageNet large scale visual recognition competition (ILSVRC 2012) because of their identification ability and computational efficiency. This paper proposes a palm vein recognition method based on CNN. The four main steps of palm vein recognition are image acquisition, image preprocessing, feature extraction, and matching. To reduce the processing steps in the recognition of palm vein images, a palm vein recognition method using a CNN is proposed. CNN is a deep learning network. Palm vein images are acquired using near-infrared light, under which the veins in the palm of the hand are relatively prominent. To obtain a good vein image, many previous methods used preprocessing to further enhance the image before using feature extraction to find feature matches for further comparison. In recent years, CNNs have been shown to have great advantages and have performed well in image classification. To reduce early-stage image processing, a CNN is used to classify and recognize palm vein images. The networks AlexNet and VGG depth CNN were trained to extract image features. The palm vein recognition rates by VGG-19, VGG-16, and AlexNet were 98.5%, 97.5%, and 96%, respectively.

A proper CNC machine selection problem is an important issue for manufacturing companies under competitive market conditions. The selection of an improper machine tool can cause many problems such as production capabilities and productivity indicators considering time and money industrially and practically. In this paper, a comprehensive solution approach is presented for the CNC machine tool selection problem according to the determined criteria. Seven main and thirteen sub-criteria were determined for the evaluation of the seven alternatives. To purify the selection process from subjectivity, instead of a single decision-maker, the opinions of six different experts on the importance of the criteria were taken and evaluated using the Best-Worst method. According to the evaluations, the order of importance of the main criteria has been determined as cost, productivity, flexibility, and dimensions. After the weighting of the criteria, three different ranking methods (GRA, COPRAS, and MULTIMOORA) were preferred due to the high investment costs of the selected alternatives. The findings obtained by solving the problem of selection of the CNC machine are close to those obtained by past researchers. As a result, using the suggested methodology, effective alternative decision-making solutions are obtained.

There exist various types of similarity measures for intuitionistic fuzzy sets in the literature. However, in many studies the interactions among the elements are ignored in the construction of the similarity measure. This paper presents a cosine similarity measure for intuitionistic fuzzy sets by using a Choquet integral model in which the interactions between elements are considered. The proposed similarity measure is applied to some pattern recognition problems and the results are compared with some existing results to demonstrate the effectiveness of this new similarity measure.

This paper is devoted to the problem of class imbalance in machine learning, focusing on the intrusion detection of rare classes in computer networks. The problem of class imbalance occurs when one class heavily outnumbers examples from the other classes. In this paper, we are particularly interested in classifiers, as pattern recognition and anomaly detection could be solved as a classification problem. As still a major part of data network traffic of any organization network is benign, and malignant traffic is rare, researchers therefore have to deal with a class imbalance problem. Substantial research has been undertaken in order to identify these methods or data features that allow to accurately identify these attacks. But the usual tactic to deal with the imbalance class problem is to label all malignant traffic as one class and then solve the binary classification problem. In this paper, however, we choose not to group or to drop rare classes but instead investigate what could be done in order to achieve good multi-class classification efficiency. Rare class records were up-sampled using SMOTE method (Chawla et al., 2002) to a preset ratio targets. Experiments with the 3 network traffic datasets, namely CIC-IDS2017, CSE-CIC-IDS2018 (Sharafaldin et al., 2018) and LITNET-2020 (Damasevicius et al., 2020) were performed aiming to achieve reliable recognition of rare malignant classes available in these datasets.

State of emergency affects many areas of our life, including education. Due to school closure during COVID-19 pandemic as a case of a long-term emergency, education has been moved into a remote mode. In order to determine the factors driving the acceptance of distance learning technologies and ensuring sustainable education, a model based on the Unified Theory of Acceptance and Use of Technology has been proposed and empirically validated with data collected from 550 in-service primary school teachers in Lithuania. Structural equation modelling technique with multi-group analysis was utilized to analyse the data. The results show that performance expectancy, social influence, technology anxiety, effort expectancy, work engagement, and trust are factors that significantly affect teachers’ behavioural intention to use distance learning technologies. The relationships in the model are moderated by pandemic anxiety and age of teachers. The results of this study provide important implications for education institutions, policy makers and designers: the predictors of intention to use distance learning technologies observed during the emergency period may serve as factors that should be strengthened in teachers’ professional development, and the applicability of the findings is expanded beyond the pandemic isolation period.