predicting model
Recently Published Documents


TOTAL DOCUMENTS

233
(FIVE YEARS 79)

H-INDEX

12
(FIVE YEARS 4)

2022 ◽  
Vol 10 ◽  
pp. 1-8
Author(s):  
Saad Al-Ahmadi

Phishing websites have grown more recently than ever, and they become more intelligent, even against well-designed phishing detection techniques. Formerly, we have proposed in the literature a state-of-the-art URL-exclusive phishing detection solution based on Convolutional Neural Network (CNN) model, which we referred as PUCNN model. Phishing detection is adversarial as the phisher may attempt to avoid the detection. This adversarial nature makes standard evaluations less useful in predicting model performance in such adversarial situations. We aim to improve PUCNN by addressing the adversarial nature of phishing detection with a restricted adversarial scenario, as PUCNN has shown that an unrestricted attacker dominates. To evaluate this adversarial scenario, we present a parameterized text-based mutation strategy used for generating adversarial samples. These parameters tune the attacker’s restrictions. We have focused on text-based mutation due to our focus on URL-exclusive models. The PUCNN model generally showed robustness and performed well when the parameters were low, which indicates a more restricted attacker.


2021 ◽  
Author(s):  
Rongxin Chen ◽  
Qing Han ◽  
Huale Zhang ◽  
Jianying Yan

Abstract Background Preeclampsia (PE) is a complex multisystem disease and its etiology remains unclear. The aim of this study was to identify potential immune-related diagnostic genes for PE, analyze the role of immune cell infiltration in PE, and explore the mechanism underlying PE-induced disruption of immune tolerance at the maternal-fetal interface. Methods We used the PE dataset GES25906 from Gene Expression Omnibus and immune-related genes from ImmPort database. The differentially expressed genes (DEGs) were identified using the “limma” package, and the differentially expressed immune-related genes (DEIGs) were extracted from the DEGs and immune-related genes using Venn diagrams. The potential functions of DEIGs were determined by Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses. Furthermore, the protein–protein interaction network was obtained from the STRING database, and it was visualized using Cytoscape software. Least absolute shrinkage and selection operator logistic regression was used to verify the diagnostic markers of PE and build a predicting model. The model was validated using datasets GSE66273 and GSE75010. Finally, CIBERSORT was used to evaluate the infiltration of immune cells in PE tissues. Results Six genes (ACTG1, ENG, IFNGR1, ITGB2, NOD1, and SPP1) enriched in Th17 cell differentiation, cytokine-cytokine receptor interaction, innate immune response, and positive regulation of MAPK cascade pathways were identified, and a predicting model was built. Datasets GSE66273 and GSE75010 were used to validate the model, and the area under the curve was 0.8333 and 0.8107, respectively. Immune cell infiltration analysis revealed an increase in plasma cells and gamma delta T cells and a decrease in resting natural killer cells in the high score group according to the predictive model risk values. Conclusions We developed a risk model to predict PE and proved that immune imbalance at the maternal-fetal interface plays a key role in the pathogenesis of PE.


Author(s):  
Abdus Saboor ◽  
Nimra Yousaf ◽  
Javed Haneef ◽  
Syed Imran Ali ◽  
Shaine Mohammadali Lalji

AbstractAsphaltene Precipitation is a major issue in both upstream and downstream sectors of the Petroleum Industry. This problem could occur at different locations of the hydrocarbon production system i.e., in the reservoir, wellbore, flowlines network, separation and refining facilities, and during transportation process. Asphaltene precipitation begins due to certain factors which include variation in crude oil composition, changes in pressure and temperature, and electrokinetic effects. Asphaltene deposition may offer severe technical and economic challenges to operating Exploration and Production companies with respect to losses in hydrocarbon production, facilities damages, and costly preventive and treatment solutions. Therefore, asphaltene stability monitoring in crude oils is necessary for the prevention of aggravation of problem related to the asphaltene deposition. This study will discuss the performance of eleven different stability parameters or models already developed by researchers for the monitoring of asphaltene stability in crude oils. These stability parameters include Colloidal Instability Index, Stability Index, Colloidal Stability Index, Chamkalani’s stability classifier, Jamaluddin’s method, Modified Jamaluddin’s method, Stankiewicz plot, QQA plots and SCP plots. The advantage of implementing these stability models is that they utilize less input data as compared to other conventional modeling techniques. Moreover, these stability parameters also provide quick crude oils stability outcomes than expensive experimental methods like Heithaus parameter, Toluene equivalence, spot test, and oil compatibility model. This research study will also evaluate the accuracies of stability parameters by their implementation on different stability known crude oil samples present in the published literature. The drawbacks and limitations associated with these applied stability parameters will also be presented and discussed in detail. This research found that CSI performed best as compared to other SARA based stability predicting models. However, considering the limitation of CSI and other predictors, a new predictor, namely ANJIS (Abdus, Nimra, Javed, Imran & Shaine) Asphaltene stability predicting model is proposed. ANJIS when used on oil sample of different conditions show reasonable accuracy. The study helps Petroleum companies, both upstream and downstream sector, to determine the best possible SARA based parameter and its associated risk used for the screening of asphaltene stability in crude oils.


Metals ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1966
Author(s):  
Yang Liu ◽  
Mingxuan Li ◽  
Xiaofeng Lu ◽  
Xiaolei Zhu ◽  
Peng Li

During the process of laser powder bed fusion (LPBF) printing, the energy of heat input have a great influence on the quality of fabricated specimens. In this paper, based on the heat transfer and metallurgical mechanism, a theoretical predicting model of the required laser energy to fabricate high-density LPBF components was established. The theoretical required laser energy density of AlSi10Mg, TC4 and 316L were calculated, which are 51.74 J/mm3, 104.48 J/mm3 and 69.28 J/mm3, respectively. By comparing with the experimental results in the references, it was found that the errors between them are within 10%. In addition, this article discussed the relationship between the VED and the specimen defects, and found that the changing in the VED will alter the types of specimen defects.


2021 ◽  
Vol 8 ◽  
Author(s):  
Rongjia Su ◽  
Yuan Liu ◽  
Xiaomei Wu ◽  
Jiangdong Xiang ◽  
Xiaowei Xi

Background: The homologous recombination (HR) pathway defects in cancers induced abrogation of cell cycle checkpoints, resulting in the accumulation of DNA damage, mitotic catastrophe, and cell death. Cancers with BRCA1/2 loss and other accumulation of similar genomic scars resulting in HRD displayed increased sensitivity to chemotherapy. Our study aimed to explore HRD score genetic mechanisms and subsequent clinical outcomes in human cancers, especially ovarian cancer.Methods: We analyzed TCGA data of HRD score in 33 cancer types and evaluated HRD score distribution and difference among tumor stages and between primary and recurrent tumor tissues. A weighted gene co-expression network analysis (WGCNA) was performed to identify highly correlated genes representing essential modules contributing to the HRD score and distinguish the hub genes and significant pathways. We verified HRD status predicting roles in patients’ overall survival (OS) with univariate and multivariate Cox regression analyses and built the predicting model for patient survival.Results: We found that the HRD score increased with the rise in tumor stage, except for stage IV. The HRD score tended to grow up higher in recurrent tumor tissue than in their primary counterparts (p = 0.083). We constructed 15 co-expression modules with WGCNA, identified co-expressed genes and pathways impacting the HRD score, and concluded that the HRD score was tightly associated with tumor cells replication and proliferation. A combined HRD score ≥42 was associated with shorter OS in 33 cancer types (HR = 1.010, 95% CI: 1.008–1.011, p < 0.001). However, in ovarian cancer, which ranked the highest HRD score among other cancers, HRD ≥42 cohort was significantly associated with longer OS (HR = 0.99, 95% CI: 0.98–0.99, p < 0.0001). We also built a predicting model for 3 and 5 years survival in HGSC patients.Conclusion: A quantitative HRD score representing the accumulated genomic scars was dynamically increasing in proliferating tumor cells since the HRD score was tightly correlated to tumor cell division and replication. We highlighted HRD score biomarker role in prognosis prediction of ovarian cancer.


2021 ◽  
Vol 80 (23) ◽  
Author(s):  
Longxia Qian ◽  
Zhengxin Wang ◽  
Mei Hong ◽  
Hongrui Wang ◽  
Yangjun Wang

Sign in / Sign up

Export Citation Format

Share Document