Selection Methodology Research Articles

Detection and classification of photovoltaic module defects based on artificial intelligence

Photovoltaic (PV) system performance and reliability can be improved through the detection of defects in PV modules and the evaluation of their effects on system operation. In this paper, a novel system is proposed to detect and classify defects based on electroluminescence (EL) images. This system is called Fault Detection and Classification (FDC) and splits into four modules, which are (1) Image Preprocessing Module (IPM), (2) Feature Extraction Module (FEM), (3) Feature Selection Module (FSM), and (4) Classification Module (CM). In the first module (i.e., IPM), the EL images are preprocessed to enhance the quality of the images. Next, the two types of features in these images are extracted and fused together through FEM. Then, during FSM, the most important and informative features are extracted from these features using a new feature selection methodology, namely, Feature Selection-based Chaotic Map (FS-CM). FS-CM consists of two stages: filter stage using chi-square to initially select the most effective features and a modified selection stage using an enhanced version of Butterfly Optimization Algorithm (BOA). In fact, BOA is a popular swarm-based metaheuristic optimization algorithm that has only recently found success. While BOA has many benefits, it also has some drawbacks, including a smaller population and an increased likelihood of getting stuck in a local optimum. In this paper, a new methodology is proposed to improve the performance of BOA, called chaotic-based butterfly optimization algorithm. Finally, these selected features are used to feed the proposed classification model through CM. During CM, Hybrid Classification Model (HCM) is proposed. HCM consists of two stages, which are binary classification stage using Naïve Bayes (NB) and multi-class classification stage using enhanced multi-layer perceptron. According to the experimental results, the proposed system FDC outperforms the most recent methods. FDC introduced 98.2%, 89.23%, 87.2%, 87.9%, 87.55%, and 88.20% in terms of accuracy, precision, sensitivity, specificity, g-mean, and f-measure in the same order.

#328 Non-invasive assessment of urinary exfoliated proximal tubule cells using multispectral autofluorescence imaging features for early detection of CKD

Abstract Background and Aims Early detection of CKD is important to allow for timely intervention which may reduce adverse clinical outcomes and cost of renal replacement therapies. Histopathological diagnosis of CKD remains the gold standard, but routine kidney biopsy is costly and associated with risks such as pain and bleeding. There is a need to develop accurate non-invasive methods for early diagnosis and prognostication of CKD. Kidney cell exfoliation into urine is an active process, which may generate significant information regarding an individual's kidney status. In particular, proximal tubule cells (PTCs) make up majority of the kidney mass and represents the hallmark of CKD in reflecting the degree of tubulointerstitial fibrosis and atrophy. Multispectral assessment of native cell autofluorescence has been specifically shown to be sensitive to metabolic changes and oxidative stress, which are key factors involved in kidney function decline. Hence, we evaluated whether multispectral autofluorescence signals in urinary exfoliated PTCs reflect kidney function as determined by eGFR. Method Individuals aged 18 or above were included and informed consent was obtained from all participants involved in this study. Spot urine samples were collected and stored at -80°C. On assessment, exfoliated PTCs were extracted from thawed urine using a validated specific immunomagnetic separation method based on anti-CD13 and anti-SGLT2 antibodies. Multispectral autofluorescence imaging was performed using a custom-made autofluorescence microscopy system (standard Olympus iX83™ fluorescence microscope and multispectral excitation lamp from Quantitative™, AU). Images were captured by a Nüvü™ EMCCD camera HNü 1024 cooled to -65°C in our laboratory to reduce sensor-induced noise. For the 34 image channels taken per sample, image acquisition times of up to 5 seconds per channel, with multiple averaging (3 times) was applied to optimize image quality. Image analysis was conducted through a workflow encompassing data preprocessing, data normalization and outlier handling, followed by basic model training and evaluation. An entropy-based image feature selection methodology was initially completed by hand, with results subsequently compared to that generated from the AutoGluon machine-learning framework [1]. The models developed from this process were assessed using ROC (Receiver Operating Characteristic) curves and AUC (Area Under the Curve) values. Two discriminative studies were performed – an overall study between exfoliated PTCs of individuals eGFR≥60 and eGFR < 60 ml/min/1.73 m2 and a subgroup study between that of individuals eGFR≥90 and eGFR 60-90 ml/min/1.73 m2. Results 40 individuals were included in our study. 20 individuals had eGFR≥60 and 20 had eGFR < 60 ml/min/1.73 m2. Multispectral assessment of cell autofluorescence features differentiated between exfoliated PTCs of these 2 groups with AUC value of 0.97 (95% CI 0.94-1.00) (Fig. 1), model accuracy being 82%. Subgroup analysis included 20 individuals of which 10 had eGFR≥90 and 10 had eGFR 60-90 ml/min/1.73 m2. Multispectral assessment of cell autofluorescence features differentiated between exfoliated PTCs of these 2 groups with AUC value of 0.99 (95% CI 0.99-1.00) (Fig. 2), model accuracy being 85%. Conclusion An excellent degree of differentiation between urinary PTCs derived from those with normal or high eGFR and mild degrees of CKD is now reliably demonstrated, complementing conclusions from our group's original small pilot study which evaluated between urinary PTCs from CKD and non-CKD cohorts [2]. Further studies are required to determine whether our novel method can be used to non-invasively predict individuals at risk of progressive kidney disease and to monitor whether intervention is effective.

Influence of wildfire emissions to carbon dioxide (CO2) observed at the Mt. Cimone station (Italy, 2165 m asl): A multi-year investigation

This work aimed at investigating on a multi-year framework (2015–2021) the contributions of wildfire emissions to atmospheric CO2 observed at the ICOS atmospheric class-2 station Mt. Cimone (CMN, 2165 m a.s.l. - Italy). Based on the analysis of a case study occurred in March 2020, a methodology providing indications about the possible presence of wildfire plumes from different European source regions was implemented. The methodology used observed CO at CMN, active fire detection by MODIS and air mass back-trajectories. An alternative detection method based on the use of a reanalysis dataset (CAMS) providing information about the amount of PM10 tagged to wildfires was also used.The results suggested that CMN could be affected by wildfire plumes for a fraction of time ranging from 1% to 10% (as a function of the adopted methodology setting). Over the studied period, we found a potentially important contribution of plumes from eastern Europe during October–April, while during May–September there was a prevalence from the Mediterranean sectors.Looking at the possible impact of these events to the observed CO2, we detected a notable increase of CO2 residuals with respect to periods not affected by fire perturbations during October–April (from +1.8 to +3.9 ppm, on average). We did not find evident impacts during the summer months, possibly due to a contribution by biospheric uptake during air mass transport to CMN (at least for a fraction of selected events).We discussed the sensitivity of results as a function of the selection methodology settings, suggesting that the strictest set-up based on the detection of large CO excesses could trace “major” events. A medium level of agreement was found when comparing the results of our selection methodology with CAMS reanalysis (fraction of PM10 emitted by wildfires).Even if it is still preliminary, our study indicated that the observations from CMN can represent, if supported by adequate diagnostic tools, a powerful dataset to evaluate the impact of wildfires to the atmospheric CO2 variability.

Interfacial characteristics and foam stability: A microscopic perspective from molecular dynamics simulation

Foams play a pivotal role in diverse industrial and academic applications, yet their stability, particularly in relation to surfactants, remains inadequately understood at the microscopic level. This study undertakes a comprehensive modeling of water films stabilized by 15 surfactants, spanning 4 ion types of hydrophilic groups. We conducted a systematic comparison and correlation of key interfacial characteristics at different stages of rupture. Our findings reveal that the critical film thickness and interface tension are integral in characterizing foam stabilities near equilibrium (metastable state) and near rupture (critical state), respectively. Furthermore, we observed a positive correlation between the hydrophilicity of surfactant head groups and both the thickness of Gibbs dividing surface and the orderliness of interfacial surfactant molecules. These factors are crucial in maintaining film stability in both metastable and critical states. This work presents a quantitative framework to generalize various interfacial characteristics commonly employed in describing foam stability, which is poised to enhance the data-driven methodology for surfactant selection and design.

A Standard Pipeline for Analyzing the Endometrial Microbiome.

The endometrial microbiome is a rapidly advancing field of research, particularly in obstetrics and gynecology, as it has been found to be linked with obstetric complications and potential impacts on fertility. The diversity of microorganisms presents in the endometrium, along with their metabolites, can influence reproductive outcomes by modulating the local immune environment of the uterus. However, a major challenge in advancing our understanding of the endometrial microbiota lies in the heterogeneity of available studies, which vary in terms of patient selection, control groups, collection methods and analysis methodologies. In this study, we propose a detailed pipeline for endometrial microbiome analysis, based on the most comprehensive prospective of 64 studies that have investigated the endometrial microbiome up to the present. Additionally, our review suggests that a dominance of Lactobacilli in the endometrium may be associated with improved reproductive prognosis, including higher implantation rates and lower miscarriage rates. By establishing a standardized pipeline, we aim to facilitate future research, enabling better comparison and correlation of bacterial communities with the health status of patients, including fertility-related issues.

Validation and Evaluation of 5 Scoring Systems for Predicting Metastatic Risk in Pheochromocytoma and Paraganglioma.

Currently, 5 scoring systems have been proposed in the literature for predicting metastatic risk in pheochromocytoma and paraganglioma (PPGL): Pheochromocytoma of the Adrenal Gland Scaled Score (PASS), Grading System for Adrenal Pheochromocytoma and Paraganglioma (GAPP), Composite Pheochromocytoma/paraganglioma Prognostic Score (COPPS), Age, Size, Extra-adrenal location, Secretion type (ASES) score, and Size, Genetic, Age, and PASS (SGAP) model. To validate and evaluate these 5 scoring systems, we conducted a retrospective review of cases diagnosed as PPGL at the Department of Pathology, West China Hospital of Sichuan University, between January 2012 and December 2019. A total of 185 PPGL cases were included, comprising 35 cases with metastasis and 150 cases remained metastasis-free for over 8 years after surgery. The criteria of the 5 scoring systems were used for scoring and risk classification. The predictive performance of the 5 scoring systems was validated, compared, and evaluated using concordance index (C-index) and decision curve analysis (DCA). The C-indices for PASS, GAPP, and SGAP were 0.600, 0.547, and 0.547, respectively, indicating low discriminative ability. In contrast, COPPS and ASES had C-indices of 0.740 and 0.706, respectively, indicating better discriminative performance. DCA also showed that the predictive capability of COPPS was superior to that of ASES, with both outperformed PASS, while PASS had better predictive ability than GAPP and SGAP. Our analysis indicated that pathology-based scoring systems cannot accurately predict metastatic risk of PPGL. Establishing a precise prediction system requires integrating clinical, pathologic, and molecular information, using a scientific methodology for predictive factor selection and weight assessment.

Acute lymphocytic leukemia detection and subtype classification via extended wavelet pooling based-CNNs and statistical-texture features

Acute lymphoblastic leukemia (ALL) is considered the most fatal form of leukemia (also known as blood cancer). It propagates quickly among adults and children and could lead to their death. Early detection of ALL and ALL subtypes is the key factor in selecting effective treatment types and improving survival rates. However, routine diagnostic approaches have several drawbacks. Computer-assisted diagnosis (CAD) is the perfect solution to avoid these challenges and achieve a fast and accurate diagnosis. Current CAD models require enhancement/segmentation processing. Besides, they are either dependent on deep learning (DL) models or handcrafted features along with machine learning. Those CADs that employed DL approaches relied solely on spatial information during the training procedure. However, learning them with spectral temporal and temporal representations could improve performance. Furthermore, integrating deep features from DL models along with handcrafted features can increase the discrimination ability of attributes in medical image classification. This study aims to propose a novel CAD for ALL detection and subtype classification without pre-segmentation or enhancement steps. The proposed CAD extends the conventional DL models of convolutional neural networks by introducing an additional wavelet pooling, accompanied by a dense layer or a long-short-term memory (LSTM) layer, and then a SoftMax layer, acquiring spectral-temporal information along with temporal information. To further improve the framework's ability to discriminate, the introduced CAD then combines the wavelet-based deep features of every CNN with numerous handcrafted attributes. Afterward, a feature selection methodology is utilized to create a model with limited features and improved accuracy. The performance results show that the novel CAD is capable of achieving 100% ALL detection accuracy, as well as 100% ALL-subtype classification accuracy with just 88 and 146 features. Thus, this CAD can be employed to assist pathologists in the rapid and precise ALL identification and subcategories recognition.

A methodology for the selection of low friction/anti-seize coating in applying bolted joints of ITER blanket modules

The application of bolted joints with the Spiralock®/Selflock® technology for remote handling system in fusion machines leads to develop a methodology for selection a low friction/anti-seize coating in applying sliding surfaces of high-loaded threaded fasteners. This study discusses the analytical engineering method for calculation the maximum/minimum allowable friction coefficients in the thread and on the bearing surface during the tightening/untightening procedure. Calculations were made to determine the maximum/minimum allowable coefficient of friction in threaded pairs used for the ITER Blanket Module Connections and enhanced flux First Wall Panel fasteners (bolts with a regular metric thread/nuts with a self-locking thread, Spiralock®/Selflock® technology) of the ITER fusion experimental reactor under maximum torque conditions of the robot manipulator (remote handling system) and tensile load (preload) generated in the bolt during the tightening/untightening procedure. Design features of the Spiralock® technology were derived for calculation the working ranges of thread friction coefficient in the threaded pairs of the Blanket Module Connection and enhanced Heat Flux First Wall Panels fasteners at different coefficient of thread proportionality values (ζ=0.45–1.00). The lowest thread friction coefficients were obtained by the coefficient of thread proportionality ζ=1.00: 0.022≤μth≤0.171 for the M24 × 3 SB Electrical strap central bolts, 0.013≤μth≤0.047 for the М52 × 4 Outboard Flexible Cartridge central bolts, 0.010≤μth≤0.055 for the M64 × 4 Inboard Flexible Cartridge central bolts. The new method of determining the total tightening torque of the M24 × 3, M52 × 4, M64 × 4 bolted joints fastened to the Spiralock® female thread under conditions of elastoplastic, plastic deformation was applied to assess the suitability the solid lubricating coating MoS2 (VNIINP-212) under preload force Fa=10–1200 kN. The performed design verification indicated the significant differences in the calculated tightening torque obtained according to the standard and proposed method for the Spiralock® female thread by the plastic deformation of the tip of bolt thread and change of sliding friction coefficient depending on the contact pressure.

IVPF-AHP integrated VIKOR methodology in supplier selection of three-dimensional (3D) printers

Complex geometries, fine details, and various designs that are difficult to create using traditional methods can easily be turned into a tangible object with Three-Dimensional (3D) printers. 3D printers have advantages such as providing design flexibility, obtaining prototypes in the shortest possible time, allowing for personalization, and reducing waste through the use of advanced technology. These advantages emphasize the significance of 3D printers in a sustainable production model. The widespread usage of 3D printers leads to increased efficiency and cost reduction in production. When the literature is examined, it is observed that there are limited studies on the evaluation of supplier performances for company using 3D printers. The aim of this study is to address 3D printers, which are highly significant for sustainable production, and to reveal the criteria that companies utilizing these printers need to consider for determining their suppliers. As a result of the literature review and expert interviews, a model has been developed that gathers the criteria to be considered for supplier selection, which is an important cost factor for companies involved in designing and producing 3D printers under five main and 18 sub-criteria. The importance weights of the criteria have been determined using the Interval Valued Pythagorean Fuzzy Analytic Hierarchy Process (IVPF-AHP) method, and the most suitable supplier among alternative suppliers has been selected using the Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method. Finally, the supplier scores have been statistically analyzed to show the validation of the results of the proposed method. According to the results, it has been concluded that for company using 3D printers, quality and technical service criteria are more important in the supplier selection. Additionally, cost of the material/equipment, product price and easy maintenance criteria also play a critical role in the supplier selection of 3D printer.

From whole genomes to probiotic candidates: A study of potential lactobacilli strains selection for vaginitis treatment

Vaginitis, characterized by pathogenic invasion and a deficiency in beneficial lactobacilli, has recognized lactobacilli supplementation as a novel therapeutic strategy. However, due to individual differences in vaginal microbiota, identifying universally effective Lactobacillus strains is challenging. Traditional methodologies for probiotic selection, which heavily depend on extensive in vitro experiments, are both time-intensive and laborious. The aim of this study was to pinpoint possible vaginal probiotic candidates based on whole-genome screening. We sequenced the genomes of 98 previously isolated Lactobacillus strains, annotating their genes involved in probiotic metabolite biosynthesis, adherence, acid/bile tolerance, and antibiotic resistance. A scoring system was used to assess the strains based on their genomic profiles. The highest-scoring strains underwent further in vitro evaluation. Consequently, two strains, Lactobacillus crispatus LG55-27 and Lactobacillus gasseri TM13-16, displayed an outstanding ability to produce d-lactate and adhere to human vaginal epithelial cells. They also showed higher antimicrobial activity against Gardnerella vaginalis, Escherichia coli, Candida albicans, Staphylococcus aureus, and Pseudomonas aeruginosa compared to reference Lactobacillus strains. Their resilience to acid and bile environments highlights the potential for oral supplementation. Oral and vaginal administration of these two strains were tested in a bacterial vaginosis (BV) rat model at various doses. Results indicated that combined vaginal administration of these strains at 1 × 106 CFU/day significantly mitigated BV in rats. This research offers a probiotic dosage guideline for vaginitis therapy, underscoring an efficient screening process for probiotics using genome sequencing, in vitro testing, and in vivo BV model experimentation.

Формирование плана диверсификации в инвестиционной и операционной сфе-рах деятельности АО «Пластик»

The comprehensive approach to the diversification of the chemical enterprise activity is suggested, it’s system repulse in the investment and operating budgets is justified. The au-thor developed the activity selection methodology of the diversification plan forming, re-ceived approval at the JSC “Plastic” and realized in the scientific productional and professional educational enterprise programs.

Enhancing gastric cancer early detection: A multi-verse optimized feature selection model with crossover-information feedback

Gastric cancer (GC), an acknowledged malignant neoplasm, threatens life and digestive system functionality if not detected and addressed promptly in its nascent stages. The indispensability of early detection for GC to augment treatment efficacy and survival prospects forms the crux of this investigation. Our study introduces an innovative wrapper-based feature selection methodology, referred to as bCIFMVO-FKNN-FS, which integrates a crossover-information feedback multi-verse optimizer (CIFMVO) with the fuzzy k-nearest neighbors (FKNN) classifier. The primary goal of this initiative is to develop an advanced screening model designed to accelerate the identification of patients with early-stage GC. Initially, the capability of CIFMVO is validated through its application to the IEEE CEC benchmark functions, during which its optimization efficiency is measured against eleven cutting-edge algorithms across various dimensionalities—10, 30, 50, and 100. Subsequent application of the bCIFMVO-FKNN-FS model to the clinical data of 1632 individuals from Wenzhou Central Hospital—diagnosed with either early-stage GC or chronic gastritis—demonstrates the model's formidable predictive accuracy (83.395%) and sensitivity (87.538%). Concurrently, this investigation delineates age, gender, serum gastrin-17, serum pepsinogen I, and the serum pepsinogen I to serum pepsinogen II ratio as parameters significantly associated with early-stage GC. These insights not only validate the efficacy of our proposed model in the early screening of GC but also contribute substantively to the corpus of knowledge facilitating early diagnosis.

Using Feature Selection Enhancement to Evaluate Attack Detection in the Internet of Things Environment

The rapid evolution of technology has given rise to a connected world where billions of devices interact seamlessly, forming what is known as the Internet of Things (IoT). While the IoT offers incredible convenience and efficiency, it presents a significant challenge to cybersecurity and is characterized by various power, capacity, and computational process limitations. Machine learning techniques, particularly those encompassing supervised classification techniques, offer a systematic approach to training models using labeled datasets. These techniques enable intrusion detection systems (IDSs) to discern patterns indicative of potential attacks amidst the vast amounts of IoT data. Our investigation delves into various aspects of supervised classification, including feature selection, model training, and evaluation methodologies, to comprehensively evaluate their impact on attack detection effectiveness. The key features selected to improve IDS efficiency and reduce dataset size, thereby decreasing the time required for attack detection, are drawn from the extensive network dataset. This paper introduces an enhanced feature selection method designed to reduce the computational overhead on IoT resources while simultaneously strengthening intrusion detection capabilities within the IoT environment. The experimental results based on the InSDN dataset demonstrate that our proposed methodology achieves the highest accuracy with the fewest number of features and has a low computational cost. Specifically, we attain a 99.99% accuracy with 11 features and a computational time of 0.8599 s.

A novel two-stage wrapper feature selection approach based on greedy search for text sentiment classification

Sentiment analysis is a crucial step in obtaining subjective data from online text sources. Nevertheless, the substantial challenge of high dimensionality prevails within text classification. Addressing this, dimension reduction emerges as a valuable approach to enhance the efficacy of classification in the domain of machine learning. The discerning removal of redundant features not only expedites training processes but also bolsters the achievement of accurate classifications. It is worth noting that the effectiveness of distinct feature selection methodologies can be contingent upon the unique attributes inherent in diverse datasets. Within the purview of this investigation, a novel two-stage approach is introduced, characterized by a greedy search-based wrapper feature selection algorithm. The underpinning of this algorithm involves leveraging the outcomes yielded by filter-based feature selection techniques to establish a prioritized sequence for the scrutiny of features within the proposed framework. This strategic sequencing harnesses the cumulative insights from a series of filter-based methodologies, thereby facilitating the curation of feature subsets that underscore pivotal attributes. Nonetheless, it is acknowledged that the greedy selection approach primarily favors features with high-ranking scores, and thus, it may not adequately evaluate the potential of feature combinations that involve low-scoring elements. An extensive experimental inquiry was conducted across widely recognized sentiment analysis datasets to assess the performance of the introduced methodology. The computational findings eloquently demonstrate that the proposed algorithm attains an average accuracy of 96.88% for nine public sentiment datasets and 94.43% for the Humir datasets when coupled with the multinomial Naive Bayes classifier. Furthermore, the experimental outcomes conspicuously establish the superiority of the proposed technique in state-of-the-art studies across the same set of nine sentiment datasets and the Humir datasets.

A comprehensive review on the integration of geographic information systems and artificial intelligence for landfill site selection: A systematic mapping perspective.

Properly selecting landfill sites for waste disposal is crucial for mitigating environmental and public health risks. Geographic Information Systems (GISs) and Artificial Intelligence (AI) techniques have emerged as valuable tools for identifying suitable landfill locations. This study presents a systematic mapping study (SMS) that investigates the usage of GIS and AI in landfill site selection. We searched six databases (IEEE Xplore, ACM Digital Library, Science Direct, Emerald Insight, Taylor & Francis Online and Web of Science) using predefined keywords related to landfills, GIS and AI. From 858 initially retrieved articles, we selected 48 relevant articles for in-depth analysis. Our research aimed to answer various questions, such as publication trends, the geographic distribution of case studies, criteria for assessing landfill suitability, tools and techniques employed, preliminary site screening methods, decision-making processes, limitations and future research directions. We used bubble charts, bar charts and tables to visualize the results. The findings of our study highlight the growing interest in using GIS and AI for landfill site selection and emphasize the importance of incorporating multi-criteria decision-making techniques. Furthermore, the results reveal the need for developing more advanced AI models, addressing the limitations of current approaches and exploring novel visualization techniques for enhancing landfill site selection processes. This study provides valuable insights for researchers and practitioners in waste management, environmental science and geoinformatics. It sets the groundwork for future research on improving GIS- and AI-based landfill site selection methodologies.

Thermal Energy Storage Using Phase Change Materials in High-Temperature Industrial Applications: Multi-Criteria Selection of the Adequate Material.

Thermal energy storage (TES) plays an important role in industrial applications with intermittent generation of thermal energy. In particular, the implementation of latent heat thermal energy storage (LHTES) technology in industrial thermal processes has shown promising results, significantly reducing sensible heat losses. However, in order to implement this technology, a proper selection of materials is important. In this study, a new multi-criteria phase change material (PCM) selection methodology is presented, which considers relevant factors from an application and material handling point of view, such as hygroscopicity, metal compatibility (corrosion), level hazard, cost, and thermal and atmospheric stability. The methodology starts after setting up the system requirements where the PCM will be used, then a material screening is able to find all possible candidates that are listed with all available properties as listed before. Then, a color map is produced, with a qualitative assessment of material properties drawbacks, hazard level, melting enthalpy, and price. The experimentation starts with a preliminary set of tests on hygroscopicity and one-week corrosion test, which allows disregarding PCMs and selecting a short list of potential PCMs that would need further characterization before the final selection.

Expected credit loss modeling

This article proposes a method for modeling the probability of default, describes the statistical evaluation of the model, and presents a model of the software implementation algorithm. The algorithm automatically selects from the group of regression models where the models are both linear regression and various modifications of semi-logarithmic models and lag models for macro factors Xi,t,Xi,t-1, ...,Xi,t-TStatistical analysis is carried out using the coefficient of determination R-squared, p-value, VIF (variance inflation factor).The relevance of this topic is determined by the need for banking organizations to comply with international standards, such as International Financial Reporting Standards (IFRS 9) and the Agreement on Banking Supervision and Capital (Basel 3). These standards define credit risk assessment requirements and capital requirements. Adherence to these standards is important not only for ensuring the stability and reliability of the financial system, but also for maintaining the trust of clients and investors. Compliance with international standards also makes banks competitive in the global market and promotes investment inflows and the development of the financial sector.IFRS 9 can be presented in various mathematical models. The article proposes an approach to choosing the appropriate model for forecasting the probability of default. The described model selection method allows banks to choose the optimal default forecast assessment model within the framework of the given standard. This contributes to a more accurate and reliable assessment of credit risk, in accordance with regulatory requirements, which will provide banks with the means for better forecasting and management of financial resources, as well as risk reduction.The model selection methodology saves a significant amount of time and resources, since the search for the optimal model occurs automatically. This allows us to react more quickly to changes in the economic environment, improve decision-making strategies and manage credit risks, which is of great importance for financial institutions in a competitive environment.There is currently a war going on in Ukraine, and forecasting using current methods becomes a difficult task due to unpredictable stressful situations for the economy. In such conditions, standard models may not be sufficiently adapted to account for increased risk and volatility. The proposed approach allows finding more conservative forecasting models that can be useful in unstable periods and war.

A Computational Approach for the Discovery of Novel DNA Methyltransferase Inhibitors.

Nowadays, the explosion of knowledge in the field of epigenetics has revealed new pathways toward the treatment of multifactorial diseases, rendering the key players of the epigenetic machinery the focus of today's pharmaceutical landscape. Among epigenetic enzymes, DNA methyltransferases (DNMTs) are first studied as inhibition targets for cancer treatment. The increasing clinical interest in DNMTs has led to advanced experimental and computational strategies in the search for novel DNMT inhibitors. Considering the importance of epigenetic targets as a novel and promising pharmaceutical trend, the present study attempted to discover novel inhibitors of natural origin against DNMTs using a combination of structure and ligand-based computational approaches. Particularly, a pharmacophore-based virtual screening was performed, followed by molecular docking and molecular dynamics simulations in order to establish an accurate and robust selection methodology. Our screening protocol prioritized five natural-derived compounds, derivatives of coumarins, flavones, chalcones, benzoic acids, and phenazine, bearing completely diverse chemical scaffolds from FDA-approved "Epi-drugs". Their total DNMT inhibitory activity was evaluated, revealing promising results for the derived hits with an inhibitory activity ranging within 30-45% at 100 µM of the tested compounds.

A revised interpretation of signal-to-noise ratio paradox and its application to constrain regional climate projections

The signal-to-noise ratio paradox is interpreted as the climate model’s ability to predict observations better than the model itself. This view is counterintuitive, given that climate models are simplified numerical representations of complex earth system dynamics. A revised interpretation is provided here: the signal-to-noise ratio paradox represents excessive noise in climate predictions and projections. Noise is potentially reducible, providing a scientific basis for improving the signal in regional climate projections. The signal-to-noise ratio paradox was assessed in long-term climate projections using single-model and multi-model large ensemble climate data. A null hypothesis was constructed by performing bootstrap resampling of climate model ensembles to test its ability to predict the 20th-century temperature and precipitation trends locally and compare it with the observations. The rejection of the null hypothesis indicates the existence of a paradox. The multi-model large ensemble does not reject the null hypothesis in most places globally. The rejection rate in the single-model large ensemble is related to the model’s fidelity to simulate internal climate variability rather than its ensemble size. For regions where the null hypothesis is rejected in the multi-model large ensemble, for example, India, the paradox is caused by a smaller signal strength in the climate model’s ensemble. The signal strength was improved by 100% through ensemble selection and based on past performance, which reduced uncertainty in India’s 30-year temperature projections by 25%. Consistent with previous studies, precipitation projections are noisier, leading to a paradox metric value 2–3 times higher than that of the temperature projections. The application of ensemble selection methodology significantly decreased uncertainty in precipitation projections for the United Kingdom, Western Australia, and Northeastern America by 47%, 36%, and 20%, respectively. Overall, this study makes a unique contribution by reducing uncertainty at the temporal scale, specifically in estimating trends using the signal-to-noise ratio paradox metric.

Wi-CHAR: A WiFi Sensing Approach with Focus on Both Scenes and Restricted Data.

Significant strides have been made in the field of WiFi-based human activity recognition, yet recent wireless sensing methodologies still grapple with the reliance on copious amounts of data. When assessed in unfamiliar domains, the majority of models experience a decline in accuracy. To address this challenge, this study introduces Wi-CHAR, a novel few-shot learning-based cross-domain activity recognition system. Wi-CHAR is meticulously designed to tackle both the intricacies of specific sensing environments and pertinent data-related issues. Initially, Wi-CHAR employs a dynamic selection methodology for sensing devices, tailored to mitigate the diminished sensing capabilities observed in specific regions within a multi-WiFi sensor device ecosystem, thereby augmenting the fidelity of sensing data. Subsequent refinement involves the utilization of the MF-DBSCAN clustering algorithm iteratively, enabling the rectification of anomalies and enhancing the quality of subsequent behavior recognition processes. Furthermore, the Re-PN module is consistently engaged, dynamically adjusting feature prototype weights to facilitate cross-domain activity sensing in scenarios with limited sample data, effectively distinguishing between accurate and noisy data samples, thus streamlining the identification of new users and environments. The experimental results show that the average accuracy is more than 93% (five-shot) in various scenarios. Even in cases where the target domain has fewer data samples, better cross-domain results can be achieved. Notably, evaluation on publicly available datasets, WiAR and Widar 3.0, corroborates Wi-CHAR's robust performance, boasting accuracy rates of 89.7% and 92.5%, respectively. In summary, Wi-CHAR delivers recognition outcomes on par with state-of-the-art methodologies, meticulously tailored to accommodate specific sensing environments and data constraints.