Numerical Metrics Research Articles

COMPREHENSION OF THE DESCRIPTIVE QUALITATIVE RESEARCH METHOD: A CRITICAL ASSESSMENT OF THE LITERATURE

When a researcher comprehends the research, they can develop research methods because the research needs to adhere to scientific principles. Because of this matter, a methodical scientific approach is required to guarantee that the study can be reaffirmed by other researchers. Moreover, the descriptive qualitative method has become popular due to its less reliance on numerical values or metrics for variable measurement. The aim of this research is to provide a general review of the literature on descriptive qualitative research methods. The researcher can determine that qualitative descriptive research is a descriptively described research method that employs qualitative data based on the findings of the research. Analyzing events, phenomena, or social conditions is a common use for this kind of descriptive qualitative research. Furthermore, qualitative research does not rely on numerical measurements for its research object, nor does it employ statistical methods to test elaborative characteristics. Its application allows for the combination of different data collection techniques, data analysis, instrument creation, and other research stages commonly used in qualitative and descriptive research methodologies.

Enhancing image-based facial expression recognition through muscle activation-based facial feature extraction

This article introduces a non-intrusive method to estimate facial muscle activity from images, diverging from conventional electrode-based approaches. Our methodology capitalizes on an inclusive set of features encompassing a diverse range of facial muscles, often overlooked in research, thus significantly expanding the scope of analyzing muscle activity within facial expressions. Our method is based on the standard 68-point face landmark and extends it by identifying the interactions of these muscles when a person performs a specific facial expression. These interactions are recorded in a feature vector, which is used by three classifiers, Linear Discriminant (LD), Support Vector Machine (SVM) and Multi-layer Perceptron (MLP) to classify six facial expressions (anger, disgust, fear, happiness, neutrality, and sadness). The method’s validation is conducted with three databases: FACES, KDEF, and JAFFE. These databases present different challenges; the first contains faces of individuals from three age ranges and both genders displaying facial expressions. On one hand, the KDEF database contains images of both genders but only within the range of young adults, whereas JAFFE comprises solely female faces. Additionally, JAFFE presents another drawback, representing only 10% of the images contained in FACES. In all these cases, our method yields excellent results, occasionally achieving 100% classification, especially in the young category. It is also noteworthy that the best results were obtained in the classification of facial expressions in female faces, suggesting that women tend to be more expressive. The method was thoroughly evaluated, and the results demonstrate the robustness of the approach, showcasing its good performance across three different databases and also for faces of individuals across various age groups. Numerical metrics, including accuracy, precision, recall, and F1 score, are presented along with confusion matrices.

Quantitative MRI-based radiomics analysis identifies blood flow feature associated to overall survival for rectal cancer patients.

Radiomics objectively quantifies image information through numerical metrics known as features. In this study, we investigated the stability of magnetic resonance imaging (MRI)-based radiomics features in rectal cancer using both anatomical MRI and quantitative MRI (qMRI), when different methods to define the tumor volume were used. Second, we evaluated the prognostic value of stable features associated to 5-year progression-free survival (PFS) and overall survival (OS). On a 1.5T MRI scanner, 81 patients underwent diagnostic MRI, an extended diffusion-weighted sequence with calculation of the apparent diffusion coefficient (ADC) and a multiecho dynamic contrast sequence generating both dynamic contrast-enhanced and dynamic susceptibility contrast (DSC) MR, allowing quantification of Ktrans, blood flow (BF) and area under the DSC curve (AUC). Radiomic features were extracted from T2w images and from ADC, Ktrans, BF and AUC maps. Tumor volumes were defined with three methods; machine learning, deep learning and manual delineations. The interclass correlation coefficient (ICC) assessed the stability of features. Internal validation was performed on 1000 bootstrap resamples in terms of discrimination, calibration and decisional benefit. For each combination of image and volume definition, 94 features were extracted. Features from qMRI contained higher prognostic potential than features from anatomical MRI. When stable features (> 90% ICC) were compared with clinical parameters, qMRI features demonstrated the best prognostic potential. A feature extracted from the DSC MRI parameter BF was associated with both PFS (p = 0.004) and OS (p = 0.004). In summary, stable qMRI-based radiomics features was identified, in particular, a feature based on BF from DSC MRI was associated with both PFS and OS.

Anomaly Detection in Data Center IT & Physical Infrastructure

Anomaly detection in data center IT and physical infrastructure is challenging due to the amount of heterogeneous data to be analyzed. Defining a solution that early identifies unexpected anomalies is particularly important to prevent data losses, breakdown of the system, and any other event considered to be critical for the activity of the data center. In the context of the INFN CNAF data center, one of the WLCG Tier-1s, we have performed a study based on monitored cooling, electrical, and IT hardware and software metrics to identify anomalies. In the present work, we aim to explore statistical approaches and machine learning solutions in the anomaly detection field for time series numerical metrics related to IT and physical infrastructure sensors. With the usage of statistical Z-score and percentile approaches and clustering DBSCAN technique, we have been able to group and identify anomalous events. Using the presented approach, different relevance can be attributed to the likely anomalies.

Indexing high-noise electron backscatter diffraction patterns using convolutional neural network and transfer learning

The crystal orientation indexing method based on Hough transform has many “zero solution” points when indexing the crystal orientation of materials, especially those with large strains. We propose an efficient and migratable indexing method for fast and autonomous crystal orientations indexing of experimental electron backscatter diffraction (EBSD) patterns of various crystal structures by transfer learning. To better evaluate the performance of the model, the performance of the model was assessed both quantitatively based on the numerical metrics and qualitatively through the Inverse Pole Figure (IPF). The results of indexing high-noise nickel EBSD patterns show that the CNN-based indexing method could not only obtain an acceptable indexing accuracy (a mean disorientation error of 1.77° for retraining and 2.31° for transfer learning), but also reasonably index the “zero solution” points remained in the Hough transform-based indexing method. And the results of indexing other materials by transfer learning show that the CNN has strong knowledge migration capability. In addition, the interpretability of the CNN was investigated by visualizing feature maps of each convolutional layer, and the sensitivity analysis of the CNN was realized by testing masked images.

A benchmarking protocol for SAR colorization: From regression to deep learning approaches

Synthetic aperture radar (SAR) images are widely used in remote sensing. Interpreting SAR images can be challenging due to their intrinsic speckle noise and grayscale nature. To address this issue, SAR colorization has emerged as a research direction to colorize gray scale SAR images while preserving the original spatial information and radiometric information. However, this research field is still in its early stages, and many limitations can be highlighted. In this paper, we propose a full research line for supervised learning-based approaches to SAR colorization. Our approach includes a protocol for generating synthetic color SAR images, several baselines, and an effective method based on the conditional generative adversarial network (cGAN) for SAR colorization. We also propose numerical assessment metrics for the problem at hand. To our knowledge, this is the first attempt to propose a research line for SAR colorization that includes a protocol, a benchmark, and a complete performance evaluation. Our extensive tests demonstrate the effectiveness of our proposed cGAN-based network for SAR colorization. The code is available at https://github.com/shenkqtx/SAR-Colorization-Benchmarking-Protocol.

Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework.

With the fast-growing number of classification models being produced every day, numerous model interpretation and comparison solutions have also been introduced. For example, LIME and SHAP can interpret what input features contribute more to a classifier's output predictions. Different numerical metrics (e.g., accuracy) can be used to easily compare two classifiers. However, few works can interpret the contribution of a data feature to a classifier in comparison with its contribution to another classifier. This comparative interpretation can help to disclose the fundamental difference between two classifiers, select classifiers in different feature conditions, and better ensemble two classifiers. To accomplish it, we propose a learning-from-disagreement (LFD) framework to visually compare two classification models. Specifically, LFD identifies data instances with disagreed predictions from two compared classifiers and trains a discriminator to learn from the disagreed instances. As the two classifiers' training features may not be available, we train the discriminator through a set of meta-features proposed based on certain hypotheses of the classifiers to probe their behaviors. Interpreting the trained discriminator with the SHAP values of different meta-features, we provide actionable insights into the compared classifiers. Also, we introduce multiple metrics to profile the importance of meta-features from different perspectives. With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers. We focus on binary classification models in the financial services and advertising industry to demonstrate the efficacy of our proposed framework and visualizations.

Precision medicine for traumatic cervical spinal cord injuries: accessible and interpretable machine learning models to predict individualized in-hospital outcomes

BACKGROUND CONTEXTA traumatic spinal cord injury (SCI) can cause temporary or permanent motor and sensory impairment, leading to serious short and long-term consequences that can result in significant morbidity and mortality. The cervical spine is the most commonly affected area, accounting for about 60% of all traumatic SCI cases. PURPOSEThis study aims to employ machine learning (ML) algorithms to predict various outcomes, such as in-hospital mortality, nonhome discharges, extended length of stay (LOS), extended length of intensive care unit stay (ICU-LOS), and major complications in patients diagnosed with cervical SCI (cSCI). STUDY DESIGNOur study was a retrospective machine learning classification study aiming to predict the outcomes of interest, which were binary categorical variables, in patients diagnosed with cSCI. PATIENT SAMPLEThe data for this study were obtained from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database, which was queried to identify patients who suffered from cSCI between 2019 and 2021. OUTCOME MEASURESThe outcomes of interest of our study were in-hospital mortality, nonhome discharges, prolonged LOS, prolonged ICU-LOS, and major complications. The study evaluated the models' performance using both graphical and numerical methods. The receiver operating characteristic (ROC) and precision-recall curves (PRC) were used to assess model performance graphically. Numerical evaluation metrics included AUROC, balanced accuracy, weighted area under PRC (AUPRC), weighted precision, and weighted recall. METHODSThe study employed data from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database to identify patients with cSCI. Four ML algorithms, namely XGBoost, LightGBM, CatBoost, and Random Forest, were utilized to develop predictive models. The most effective models were then incorporated into a publicly available web application designed to forecast the outcomes of interest. RESULTSThere were 71,661 patients included in the analysis for the outcome mortality, 67,331 for the outcome nonhome discharges, 76,782 for the outcome prolonged LOS, 26,615 for the outcome prolonged ICU-LOS, and 72,132 for the outcome major complications. The algorithms exhibited an AUROC value range of 0.78 to 0.839 for in-hospital mortality, 0.806 to 0.815 for nonhome discharges, 0.679 to 0.742 for prolonged LOS, 0.666 to 0.682 for prolonged ICU-LOS, and 0.637 to 0.704 for major complications. An open access web application was developed as part of the study, which can generate predictions for individual patients based on their characteristics. CONCLUSIONSOur study suggests that ML models can be valuable in assessing risk for patients with cervical cSCI and may have considerable potential for predicting outcomes during hospitalization. ML models demonstrated good predictive ability for in-hospital mortality and nonhome discharges, fair predictive ability for prolonged LOS, but poor predictive ability for prolonged ICU-LOS and major complications. Along with these promising results, the development of a user-friendly web application that facilitates the integration of these models into clinical practice is a significant contribution of this study. The product of this study may have significant implications in clinical settings to personalize care, anticipate outcomes, facilitate shared decision making and informed consent processes for cSCI patients.

A Comprehensive Approach to Image Protection in Digital Environments

Protecting the integrity of images has become a growing concern due to the ease of manipulation and unauthorized dissemination of visual content. This article presents a comprehensive approach to safeguarding images’ authenticity and reliability through watermarking techniques. The main goal is to develop effective strategies that preserve the visual quality of images and are resistant to various attacks. The work focuses on developing a watermarking algorithm in Python, implemented with embedding in the spatial domain, transformation in the frequency domain, and pixel modification techniques. A thorough evaluation of efficiency, accuracy, and robustness is performed using numerical metrics and visual assessment to validate the embedded watermarks. The results demonstrate the algorithm’s effectiveness in protecting the integrity of the images, although some attacks may cause visible degradation. Likewise, a comparison with related works is made to highlight the relevance and effectiveness of the proposed techniques. It is concluded that watermarks are presented as an additional layer of protection in applications where the authenticity and integrity of the image are essential. In addition, the importance of future research that addresses perspectives for improvement and new applications to strengthen the protection of the goodness of pictures and other digital media is highlighted.

Generative Adversarial Networks applied to synthetic financial scenarios generation

In this paper, we introduce Jinkou, a GAN-based algorithm that allows for the conditional generation of synthetic multivariate time series. The set of variables whose distribution is to be replicated include specific variables taking different values for different objects, as well state variables describing the state of the world, common to all objects at a given date and potentially influential on the specific features. The conditioning process is specified at inference time, and only involves state variables; it simply consists in setting lower and/or upper bounds on their values. The generative model is trained as an un-conditioned generator and is agnostic of any scenario the user might set at inference time. The use case considered in this pilot study is of interest for the financial industry: the generator produces random samples of the instrument-specific features over time (e.g their price, size or the risk for securities). Such generation is conditioned on user-defined macroeconomic assumptions/scenarios involving global variables, such as inflation, oil prices or interest rates. We introduce numerical metrics to assess the statistical closeness between the two multivariate distributions of historical and artificial data. As proof of concept, we test the proposed algorithm by reproducing the value variation for two possible portfolios, Energy and Financial, conditioned on scenarios for which a consensus is present in the community. Jinkou allows us to recover some classical stylized facts about the financial markets, this ability constituting a proof of its efficiency.

SpineTool is an open-source software for analysis of morphology of dendritic spines

Dendritic spines form most excitatory synaptic inputs in neurons and these spines are altered in many neurodevelopmental and neurodegenerative disorders. Reliable methods to assess and quantify dendritic spines morphology are needed, but most existing methods are subjective and labor intensive. To solve this problem, we developed an open-source software that allows segmentation of dendritic spines from 3D images, extraction of their key morphological features, and their classification and clustering. Instead of commonly used spine descriptors based on numerical metrics we used chord length distribution histogram (CLDH) approach. CLDH method depends on distribution of lengths of chords randomly generated within dendritic spines volume. To achieve less biased analysis, we developed a classification procedure that uses machine-learning algorithm based on experts’ consensus and machine-guided clustering tool. These approaches to unbiased and automated measurements, classification and clustering of synaptic spines that we developed should provide a useful resource for a variety of neuroscience and neurodegenerative research applications.

Optimization of Traffic Network Signal Durations with Heuristic Algorithm and the Effect of Number of Individuals

In the traffic network that we frequently use in our daily life, the primary demand of people has been to reduce the time they spend in traffic and to travel to the points they want to reach as quickly as possible. Developing countries want to meet this demand with the least cost in order to meet this demand. This study aims to manage the traffic network with the best times by optimizing the traffic signal durations in order to minimize the travel time for a road network chosen as a benchmark. For the optimization process, it is aimed to run a population-based heuristic algorithm with different numbers of individuals and obtain the best travel time. With the help of an open-source code traffic simulation program, which was run by modeling the benchmark road network, the received traffic data was also visually analyzed and compared. The effects of the heuristic algorithms applied with different numbers of individuals on the travel times according to the starting-destination points were examined before and after the optimization. As a result of the study, it has been observed that travel times and traffic signal times can be reduced with heuristic algorithms. Based on both numerical metrics and visual results, it has been determined that optimized traffic light durations give better results than non-optimized ones.

Relationship between Transformational Leadership and Church Health: A Survey of Selected Denominational Churches in Nairobi City County, Kenya

The subject of church health and its deteriorating condition has taken center-stage in leadership discourse across the world. A decline in the health of a church has negative implications not only on the sustainability of the church but also on the wider society owing to the role of the church as the moral custodian of society. An argument has been advanced in extant scholarship that transformational leadership is suitable for guiding religious organizations. However, most studies on this front take focus almost exclusively on the numerical health aspect of the organizations. The aim of the present study was to estimate the differential effect of transformational leadership on spiritual health and economic health in addition to the numerical health of selected churches in Nairobi City County, Kenya. The target population comprised members of selected denominational churches from which a sample size of 330 members was drawn. The participants filled out the Multifactor Leadership Questionnaire and the Natural Church Development tools. Data analysis was done using SPSS. Results showed that the four transformational leadership dimensions explained 40% of numerical health metrics, 56.9% of economic health metrics, and 50.2% of spiritual health metrics. The conclusion was drawn that transformational leadership had a positive but differential effect on church health dimensions. The study has affirmed the relevance of transformational leadership in enhancing the numeric, economic, and spiritual health of the church in Kenya. However, in as much as the effect sizes were large, a substantial share of church health metrics still remained unexplained, thereby providing grounds for continued empirical inquiry.

Integrating BLUP, AMMI, and GGE Models to Explore GE Interactions for Adaptability and Stability of Winter Lentils (Lens culinaris Medik.).

Lentil yield is a complicated quantitative trait; it is significantly influenced by the environment. It is crucial for improving human health and nutritional security in the country as well as for a sustainable agricultural system. The study was laid out to determine the stable genotype through the collaboration of G × E by AMMI and GGE biplot and to identify the superior genotypes using 33 parametric and non-parametric stability statistics of 10 genotypes across four different conditions. The total G × E effect was divided into two primary components by the AMMI model. For days to flowering, days to maturity, plant height, pods per plant, and hundred seed weight, IPCA1 was significant and accounted for 83%, 75%, 100%, and 62%, respectively. Both IPCA1 and IPCA2 were non-significant for yield per plant and accounted for 62% of the overall G × E interaction. An estimated set of eight stability parameters showed strong positive correlations with mean seed yield, and these measurements can be utilized to choose stable genotypes. The productivity of lentils has varied greatly in the environment, ranging from 786 kg per ha in the MYM environment to 1658 kg per ha in the ISD environment, according to the AMMI biplot. Three genotypes (G8, G7, and G2) were shown to be the most stable based on non-parametric stability scores for grain yield. G8, G7, G2, and G5 were determined as the top lentil genotypes based on grain production using numerical stability metrics such as Francis's coefficient of variation, Shukla stability value (σi2), and Wrick's ecovalence (Wi). Genotypes G7, G10, and G4 were the most stable with the highest yield, according to BLUP-based simultaneous selection stability characteristics. The findings of graphic stability methods such as AMMI and GGE for identifying the high-yielding and stable lentil genotypes were very similar. While the GGE biplot indicated G2, G10, and G7 as the most stable and high-producing genotypes, AMMI analysis identified G2, G9, G10, and G7. These selected genotypes would be used to release a new variety. Considering all the stability models, such as Eberhart and Russell's regression and deviation from regression, additive main effects, multiplicative interactions (AMMI) analysis, and GGE, the genotypes G2, G9, and G7 could be used as well-adapted genotypes with moderate grain yield in all tested environments.

Fractional-Order Variational Image Fusion and Denoising Based on Data-Driven Tight Frame

Multi-modal image fusion can provide more image information, which improves the image quality for subsequent image processing tasks. Because the images acquired using photon counting devices always suffer from Poisson noise, this paper proposes a new three-step method based on the fractional-order variational method and data-driven tight frame to solve the problem of multi-modal image fusion for images corrupted by Poisson noise. Thus, this article obtains fused high-quality images while removing Poisson noise. The proposed image fusion model can be solved by the split Bregman algorithm which has significant stability and fast convergence. The numerical results on various modal images show the excellent performance of the proposed three-step method in terms of numerical evaluation metrics and visual quality. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on image fusion with Poisson noise.

Probabilistic coherence, logical consistency, and Bayesian learning: Neural language models as epistemic agents.

It is argued that suitably trained neural language models exhibit key properties of epistemic agency: they hold probabilistically coherent and logically consistent degrees of belief, which they can rationally revise in the face of novel evidence. To this purpose, we conduct computational experiments with rankers: T5 models [Raffel et al. 2020] that are pretrained on carefully designed synthetic corpora. Moreover, we introduce a procedure for eliciting a model's degrees of belief, and define numerical metrics that measure the extent to which given degrees of belief violate (probabilistic, logical, and Bayesian) rationality constraints. While pretrained rankers are found to suffer from global inconsistency (in agreement with, e.g., [Jang et al. 2021]), we observe that subsequent self-training on auto-generated texts allows rankers to gradually obtain a probabilistically coherent belief system that is aligned with logical constraints. In addition, such self-training is found to have a pivotal role in rational evidential learning, too, for it seems to enable rankers to propagate a novel evidence item through their belief systems, successively re-adjusting individual degrees of belief. All this, we conclude, confirms the Rationality Hypothesis, i.e., the claim that suitable trained NLMs may exhibit advanced rational skills. We suggest that this hypothesis has empirical, yet also normative and conceptual ramifications far beyond the practical linguistic problems NLMs have originally been designed to solve.

Leveraging Deep Neural Networks for Massive MIMO Data Detection

Massive multiple-input multiple-output (MIMO) is a key technology for emerging next-generation wireless systems. Utilizing large antenna arrays at base-stations, massive MIMO enables substantial spatial multiplexing gains by simultaneously serving a large number of users. However, the complexity in massive MIMO signal processing (e.g., data detection) increases rapidly with the number of users, making conventional hand-engineered algorithms less computationally efficient. Lowcomplexity massive MIMO detection algorithms, especially those inspired or aided by deep learning, have emerged as a promising solution. While there exist many MIMO detection algorithms, the aim of this magazine paper is to provide insight into how to leverage deep neural networks (DNN) for massive MIMO detection. We review recent developments in DNN-based MIMO detection that incorporate the domain knowledge of established MIMO detection algorithms with the learning capability of DNNs. We then present a comparison of the key numerical performance metrics of these works. We conclude by describing future research areas and applications of DNNs in massive MIMO receivers.

Reducing high-risk glucose forecasting errors by evolving interpretable models for Type 1 diabetes

Diabetes mellitus is a metabolic disease involving high blood glucose levels that can lead to serious medical consequences. Hence, for diabetic patients the prediction of future glucose levels is essential in the management of the disease. Most of the forecasting approaches in the literature evaluate the effectiveness of glucose predictors only with numerical metrics. These approaches are limited because they evenly treat all the errors without considering their different clinical impact that could involve lethal effects in dangerous situations such as hypo- or hyperglycemia.To overcome such a limitation, this paper aims to devise models for reducing high-risk glucose forecasting errors for Type 1 diabetic patients. For this purpose, we exploit a Grammatical Evolution algorithm to induce personalized and interpretable forecasting glucose models assessed with a novel, composite metric to satisfy both clinical and numerical requirements of the estimated predictions.To assess the effectiveness of the proposed approach, a real-world data set widely used in literature, consisting of data from several patients suffering from Type 1 diabetes, has been adopted. The experimental findings show that the induced models are interpretable and capable of assuring predictions with a good tradeoff between medical quality and numerical accuracy and with remarkable performance in reducing high-risk glucose forecasting errors. Furthermore, their performance is better than or comparable to that of other state-of-the-art methods.

Transversal Survey of Emergency Medicine Policy and Quality Metrics in Japan's Regional Health Care Plans.

It is essential to establish appropriate medical quality metrics and make improvements to safely and efficiently deliver optimum emergency medical services. The Ministry of Health, Labor and Welfare (MHLW) recommends prefectures to establish numerical quality metrics in their regional healthcare plans (RHCP). The 7th RHCP was issued by the MHLW in 2017 along with a notice of planning in covering the six-year period from 2018 to 2023. In this descriptive study, the emergency medicine policies in the 7th RHCP of each prefecture were analyzed from a quality improvement perspective. The authors examined the chapters on emergency medicine in the RHCPs of 47 prefectural governments for the overall structure, cost-benefits, and connection to community-based integrated care systems. The type and number of clinical measures listed as numerical metrics and their classification methods were emphasized. Regarding the overall plan structure, 40 prefectural governments began their description with an analysis of current surroundings. In total, 24 prefectural governments mentioned community-based integrated care systems but none mentioned cost-benefit analysis. Altogether, only 43 of 47 prefectural governments (91%) indicated numerical metrics. The maximum number of numerical targets for quality measures by prefecture was 19, the minimum was 0, and the median was 4 (IQR: 3-6.5); there were 220 metrics in total, with 82 structural, 96 process, and 42 outcome measures. Additionally, 13 prefectures (28%) classified quality measures according to the MHLW's guidance, 6 (13%) used their own classification manner, while the others did not classify their measures. There were significant differences in emergency medicine policies and quality metrics among the prefectural governments. Further research is needed to develop and establish more comprehensive and appropriate metrics based on a common methodology to improve the quality of emergency medicine.

Approach to text data clustering based on molecular chemical reactions in agricultural and food industries

We propose an algorithm for clustering short text fragments such as lists of ingredients in food products using the k-means algorithm in combination with the molecular chemical reactions algorithm. The solution obtained with k-means is used as an initial molecular structure solution to optimize chemical reactions in combination with k-means by generating new solutions using the four main types of chemical reactions. The computational experiment showed the comparative efficiency of new algorithm, taking into account numerical metrics: accuracy, precision, recall, and F-measure.