•The problem of credit scoring is addressed as a classification and feature subset selection problem.•A novel algorithm “IGDFS” is proposed which uses information gain and SVM, KNN, Naive Bayes ...algorithms for credit scoring.•The prediction results by IGDFS, Genetic Algorithm Wrapper and Baseline classification models are compared for three public credit datasets.•The classification accuracy is sensitive to the type of data, number of samples and the number of positive and negative samples in the dataset.•There is a potential for improvement in the models’ performances if the feature selection method is chosen carefully.
Financial credit scoring is one of the most crucial processes in the finance industry sector to be able to assess the credit-worthiness of individuals and enterprises. Various statistics-based machine learning techniques have been employed for this task. “Curse of Dimensionality” is still a significant challenge in machine learning techniques. Some research has been carried out on Feature Selection (FS) using genetic algorithm as wrapper to improve the performance of credit scoring models. However, the challenge lies in finding an overall best method in credit scoring problems and improving the time-consuming process of feature selection. In this study, the credit scoring problem is investigated through feature selection to improve classification performance. This work proposes a novel approach to feature selection in credit scoring applications, called as Information Gain Directed Feature Selection algorithm (IGDFS), which performs the ranking of features based on information gain, propagates the top m features through the GA wrapper (GAW) algorithm using three classical machine learning algorithms of KNN, Naïve Bayes and Support Vector Machine (SVM) for credit scoring. The first stage of information gain guided feature selection can help reduce the computing complexity of GA wrapper, and the information gain of features selected with the IGDFS can indicate their importance to decision making.
Regarding the classification accuracy, SVM accuracy is always better than KNN and NB for Baseline techniques, GAW and IGDFS. Also, we can conclude that the IGDFS achieved better performance than generic GAW, and GAW obtained better performance than the corresponding single classifiers (baseline) for almost all cases, except for the German Credit dataset, IGDFS + KNN has worse performance than generic GAW and the single classifier KNN. Removing features with low information gain could produce conflict with the original data structure for KNN, and thus affect the performance of IGDFS + KNN.
Regarding the ROC performance, for the German Credit Dataset, the three classic machine learning algorithms, SVM, KNN and Naïve Bayes in the wrapper of IGDFS GA obtained almost the same performance. For the Australian credit dataset and the Taiwan Credit dataset, the IGDFS + Naive Bayes achieved the largest area under ROC curves.
Abnormal expression of long non-coding RNAs (lncRNAs) has been shown to be associated with the pathogenesis of cancers, including colorectal cancer (CRC). It has been reported that LINC00022 is ...highly expressed in some typs of cancer and its overexpression indicates poor prognosis. The function of LINC00022 in CRC progression remains unclear and is mainly investigated in the present study.
LINC00022 expression in CRC tissues was analyzed by using the TNMplot software. LINC00022 expression in CRC cells was measured by quantitative real-time PCR. The effects of LINC00022 on the malignant behaviors of CRC cells were detected by a series of in vitro and in vivo experiments. Dual-luciferase assays were used to verify the targeting relationship between LINC00022 and miR-375-3p and between miR-375-3p and Forkhead box F1 (FOXF1), followed by the rescue experiment.
LINC00022 was highly expressed in CRC tissues compared with paired para-carcinoma tissues (n = 41). CRC cells with LINC00022 knockdown exhibited decreased cell proliferation, migration, and invasion abilities but increased apoptosis accompanied by decreased protein levels of c-Myc, cyclin D1, cleaved caspase 3, cleaved poly(ADP-ribose) polymerase, matrix metalloproteinase (MMP) 2, and MMP9. Additionally, LINC00022 downregulation in CRC cells suppressed the tube formation of human umbilical vein endothelial cells (HUVECs) as evidenced by decreased vascular endothelial growth factor A levels in LINC00022-silenced cells. The inhibitory effect of LINC00022 knockdown on tumor growth was also observed in an in vivo model. Conversely, LINC00022 overexpression showed that opposite effect. We further demonsrtaed that LINC00022 could upregulate FOXF1 expression through sponging miR-375-3p. Moreover, miR-375-3p knockdown reversed the effects of LINC00022 down-regulation.
LINC00022 may up-regulate FOXF1 expression via competitively binding miR-375-3p, thereby promoting the development of CRC.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
A high selectivity toward phosphate and reusability were exhibited by the calcined ZnAl–CO
3 LDHs at different temperatures.
The selective adsorption of phosphate ions was investigated on
CO
3
2
-
, ...Cl
−, and
NO
3
-
-type ZnAl layered double hydroxides (LDHs) and the calcined
CO
3
2
-
-type LDH at 200, 400, 600 and 800
°C, respectively. The calcined LDHs and
NO
3
-
-type LDH showed high selectivity toward phosphate ions, while the Cl
−-type LDH shows selectivity toward both
SO
4
2
-
and phosphate ions. The
NO
3
-
-type LDH selectively adsorbed phosphate ions mainly through ion exchange. The calcined samples possibly proceed through ligand complexation or electrostatic attraction between phosphate ions and hydrated ZnO formed after calcination, although the structural memory effect was observed for the samples calcined below 600
°C with the formation of
CO
3
2
-
-type LDH. Adsorption/desorption behaviors indicated that the calcined samples had good stability and reusability.
To evaluate the efficacy of autologous platelet-rich plasma (PRP) gel in the treatment of refractory pressure injuries and its effect on wound healing time and quality of life of patients.
A random ...number table method was used to group 102 patients with refractory pressure injuries into either a control group (CG) (51 cases) receiving negative pressure wound therapy (NPWT) or a study group (SG) (51 cases) receiving NPWT+PRP gel.
The total efficacy rate in the SG (92.16%) was higher than that in the CG (76.47%) (p<0.05). The SG exhibited lower visual analog scale (VAS) scores and pressure ulcer scale for healing (PUSH) scores, smaller wound sizes and depths, and shorter wound healing times than the CG after 21 days of treatment (p<0.05). After 6 months of treatment, the SG scored higher than the CG on the psychological, physiological, social functions, and daily activity domains on the World Health Organization Quality of Life (WHOQOL-BREF) scale (p<0.05). The incidence of postoperative complications in the SG (13.73%) was not significantly different from that of the CG (7.84%) (p>0.05).
In the treatment of refractory pressure injuries, PRP gel can accelerate wound healing, reduce wound pain, shorten the treatment cycle, regulate tissue inhibitor matrix metalloproteinase-1 (TIMP-1) and matrix metalloproteinase-9 (MMP-9) levels and the expression of specific proteins in granulation tissue, reduce the levels of the inflammatory factors interleukin-1β (IL-1β), IL-8, and tumor necrosis factor-α (TNF-α), and improve the quality of life of patients without increasing complications.
Tissue factor pathway inhibitor 2 (TFPI2) participates in carcinogenesis of various tumors, and is associated with poor survival of breast cancer patients. However, the effect and underlying ...mechanism of TFPI2 on breast cancer progression remains to be investigated.
The expression level of TFPI2 in breast cancer tissues and cell lines was examined via qRT-PCR (quantitative real-time polymerase chain reaction) and immunohistochemistry. CCK8 (Cell Counting Kit-8), colony formation, wound healing or transwell assays were used to detect cell viability, proliferation, migration or invasion, respectively. In vivo subcutaneous xenotransplanted tumor model was established to detect tumorigenic function of TFPI2, and the underlying mechanism was evaluated by immunohistochemistry and western blot.
TFPI2 was down-regulated in breast cancer tissues and cell lines, and was associated with poor prognosis of patients diagnosed with breast cancer. Over-expression of TFPI2 inhibited cell viability, proliferation, migration and invasion of breast cancer cells. Mechanistically, Twist-related protein 1 (TWIST1) was negatively associated with TFPI2 in breast cancer patients, whose expression was decreased by TFPI2 over-expression or increased by TFPI2 knockdown. Moreover, TWIST1 could up-regulate integrin α5 expression. Functional assays indicated that the inhibition abilities of TFPI2 over-expression on breast cancer progression were reversed by TWIST1 over-expression. In vivo subcutaneous xenotransplanted tumor model also revealed that over-expression of TFPI2 could suppress breast tumor growth via down-regulation of TWIST1-mediated integrin α5 expression.
TFPI2 suppressed breast cancer progression through inhibiting TWIST-integrin α5 pathway, providing a new potential therapeutic target for breast cancer treatment.
Aiming at the enhancement of the lightweight formability potential of aluminum alloy, the bulging and tensile properties of a 5052 Aluminum alloy sheet were tested on a microcomputer controlled sheet ...metal forming tester and tensile testing machine. The effects of different blank holder force, punch velocity and lubrication conditions were investigated on bulging properties by the experimental analysis. The cupping values (Erichsen Cupping Index: IE) of sheets with a thickness of 1.2 mm at room temperature were obtained under different process parameters. Meanwhile, the anisotropic property of the material was analyzed in different rolling directions. The results show that the sheet cupping values increase with the increase of blank holder force and punch velocity, and the stress state was changed due to the changing of the blank holder force and strain rate. Moreover, the use of lubricating conditions with a lower coefficient of friction allows the sheet to exhibit a larger cupping value. The effect of rolling direction on the anisotropy of 5052 aluminum alloy sheet is distinct, which means in the aluminum alloy sheet forming process the anisotropy factor should be carefully considered.
Regulating bulk polymeric carbon nitride (PCN) into nanostructured PCN has long been proven effective in enhancing its photocatalytic activity. However, simplifying the synthesis of nanostructured ...PCN remains a considerable challenge and has drawn widespread attention. This work reported the one-step green and sustainable synthesis of nanostructured PCN in the direct thermal polymerization of the guanidine thiocyanate precursor via the judicious introduction of hot water vapor's dual function as gas-bubble templates along with a green etching reagent. By optimizing the temperature of the water vapor and polymerization reaction time, the as-prepared nanostructured PCN exhibited a highly boosted visible-light-driven photocatalytic hydrogen evolution activity. The highest H
evolution rate achieved was 4.81mmol∙g
∙h
, which is over four times larger than that of the bulk PCN (1.19 mmol∙g
∙h
) prepared only by thermal polymerization of the guanidine thiocyanate precursor without the assistance of bifunctional hot water vapor. The enhanced photocatalytic activity might be attributed to the enlarged BET specific surface area, increased active site quantity, and highly accelerated photo-excited charge-carrier transfer and separation. Moreover, the sustainability of this environmentally friendly hot water vapor dual-function mediated method was also shown to be versatile in preparing other nanostructured PCN photocatalysts derived from other precursors such as dicyandiamide and melamine. This work is expected to provide a novel pathway for exploring the rational design of nanostructured PCN for highly efficient solar energy conversion.
A comprehensive assessment of machine learning applications is conducted to identify the developing trends for Artificial Intelligence (AI) applications in the oil and gas sector, specifically ...focusing on geological and geophysical exploration and reservoir characterization. Critical areas, such as seismic data processing, facies and lithofacies classification, and the prediction of essential petrophysical properties (e.g., porosity, permeability, and water saturation), are explored. Despite the vital role of these properties in resource assessment, accurate prediction remains challenging. This paper offers a detailed overview of machine learning's involvement in seismic data processing, facies classification, and reservoir property prediction. It highlights its potential to address various oil and gas exploration challenges, including predictive modelling, classification, and clustering tasks. Furthermore, the review identifies unique barriers hindering the widespread application of machine learning in the exploration, including uncertainties in subsurface parameters, scale discrepancies, and handling temporal and spatial data complexity. It proposes potential solutions, identifies practices contributing to achieving optimal accuracy, and outlines future research directions, providing a nuanced understanding of the field's dynamics. Adopting machine learning and robust data management methods is crucial for enhancing operational efficiency in an era marked by extensive data generation. While acknowledging the inherent limitations of these approaches, they surpass the constraints of traditional empirical and analytical methods, establishing themselves as versatile tools for addressing industrial challenges. This comprehensive review serves as an invaluable resource for researchers venturing into less-charted territories in this evolving field, offering valuable insights and guidance for future research.
With the growing demand for insulation parts in extreme service environments, such as nuclear power, aviation, and other related fields, fiberglass-reinforced silicone resin (FRSR) has become a ...popular choice due to its exceptional physical and chemical properties in high-temperature and electromagnetic working environments. To enhance the performance of FRSR molded parts that can adapt to more demanding extreme environments, the oven postcuring process parameters on thermal stability and mechanical properties of the bobbin were investigated. The curing behavior of FRSR was analyzed by using thermogravimetric analysis (TGA) and the differential scanning calorimetry (DSC) method, and the bobbins were manufactured based on the testing results. Subsequently, the bobbins were oven postcured at different conditions, and the heat resistance and mechanical properties were analyzed by TGA and tensile tests. The results revealed that the tensile strength of the bobbin increased by 122%, and the weight loss decreased by 0.79% at 350 °C after baking at 175 °C for 24 h. The optimal process parameters for producing bobbins to meet the criteria of nuclear installations were determined to be a molding temperature of 120 °C, molding pressure of 50 MPa, pressure holding time of 3 min, oven postcuring temperature of 175 °C, and postcuring time of 24 h. The molded products have passed the thermal aging performance test of nuclear power units.
Cyber-physical systems such as satellite telecommunications networks generate vast amounts of data and currently, very crude data processing is used to extract salient information. Only a small ...subset of data is used reactively by operators for troubleshooting and finding problems. Sometimes, problematic events in the network may go undetected for weeks before they are reported. This becomes even more challenging as the size of the network grows due to the continuous proliferation of Internet of Things type devices. To overcome these challenges, this research proposes a knowledge-based cognitive architecture supported by machine learning algorithms for monitoring satellite network traffic. The architecture is capable of supporting and augmenting infrastructure engineers in finding and understanding the causes of faults in network through the fusion of the results of machine learning models and rules derived from human domain experience. The system is characterised by (1) the flexibility to add new or extend existing machine learning algorithms to meet the user needs, (2) an enhanced pattern recognition and prediction through the support of machine learning algorithms and the expert knowledge on satellite infrastructure, (3) the ability to adapt to changing conditions of the satellite network, and (4) the ability to augment satellite engineers through interpretable results. An industrial real-life satellite case study is provided to demonstrate how the architecture could be used. A single blind experimental methodology was used to validate the results generated by our approach.