Search

Your search keyword '"Pei, Zhijun"' showing total 105 results
Start Over Author "Pei, Zhijun"
105 results on '"Pei, Zhijun"'

15. Research on Kick Detection Model Based on Machine Learning

Author

Zhaopeng Zhu, Shiming Duan, Xianzhi Song, and Pei Zhijun

Subjects
Support vector machine, Artificial neural network, business.industry, Computer science, Artificial intelligence, business, Machine learning, computer.software_genre, Fuzzy neural nets, computer
Abstract

With the expansion of oil and gas exploration and the development of complex oil and gas resource areas, the probability of risk is increasing. Kick is one of the high-risk risks of drilling, and timely and accurate early warning is increasingly important. Based on the kick generation mechanism, kick characterization parameters are preliminarily selected. According to the characteristics of the data and previous research progress, Random Forest (RF), Support Vector Machine (SVM), Fully Connected Neural Network (FNN), and Long Short-term Memory Neural Network (LSTM) are established using experimental data from Memorial University of Newfoundland. The test results show that the accuracy of the SVM-linear model is 0.952, and the missing alarm, the false alarm rate is only 0.064, 0.035. Also, through the analysis of the kick response time, the lag time of the SVM-linear model is 3.6s, and the comprehensive equivalent time is 23.13, which shows the best performance. This paper lays a good foundation for the establishment of an intelligent kick early warning model.

Published
2021

17. SLC17A9 Is a Novel Prognostic Biomarker Correlated With Immune Infiltrates in Human Lung Adenocarcinoma and Lung Squamous Cell Carcinoma

Author

Gao, Yan, primary, Chen, Yi-Jia, additional, Li, Fuyan, additional, Wu, Ruimin, additional, Zeng, Daobing, additional, Tan, Fan, additional, Liu, Xusheng, additional, Li, Xiaohui, additional, Li, Yang, additional, Su, Shan-Chun, additional, Yang, Jianwei, additional, Zhou, Lumeng, additional, Ke, Changbin, additional, and Pei, Zhijun, additional

Published
2021
Full Text
View/download PDF

18. eIF6 is potential diagnostic and prognostic biomarker that associated with 18F-FDG PET/CT features and immune signatures in esophageal carcinoma.

Author

Gao, Yan, Yuan, Lingling, Zeng, Jing, Li, Fuyan, Li, Xiaohui, Tan, Fan, Liu, Xusheng, Wan, Huabing, Kui, Xueyan, Liu, Xiaoyu, Ke, Changbin, and Pei, Zhijun

Subjects
PROTEINS, CELL physiology, PROGNOSIS, RADIOPHARMACEUTICALS, RESEARCH funding, DEOXY sugars, SQUAMOUS cell carcinoma, EMISSION-computed tomography, CARRIER proteins
Abstract

Background: Although eukaryotic initiation factor 6 (eIF6) is a novel therapeutic target, data on its importance in the development of esophageal carcinoma (ESCA) remains limited. This study evaluated the correlation between eIF6 expression and metabolic analysis using fluorine-18 fluorodeoxyglucose (18F-FDG) -Positron emission tomography (PET) and immune gene signatures in ESCA.Methods: This study employed The Cancer Genome Atlas (TCGA) to analyze the expression and prognostic value of eIF6, as well as its relationship with the immune gene signatures in ESCA patients. The qRT-PCR and Western blot analyses were used to profile the expression of eIF6 in ESCA tissues and different ESCA cell lines. The expression of tumor eIF6 and glucose transporter 1 (GLUT1) was examined using immunohistochemical tools in fifty-two ESCA patients undergoing routine 18F-FDG PET/CT before surgery. In addition, the cellular responses to eIF6 knockdown in human ESCA cells were assessed via the MTS, EdU, flow cytometry and wound healing assays.Results: Our data demonstrated that compared with the normal esophageal tissues, eIF6 expression was upregulated in ESCA tumor tissues and showed a high diagnostic value with an area under curve of 0.825 for predicting ESCA. High eIF6 expression was significantly correlated with shorter overall survival of patients with esophagus adenocarcinoma (p = 0.038), but not in squamous cell carcinoma of the esophagus (p = 0.078). In addition, tumor eIF6 was significantly associated with 18F-FDG PET/CT parameters: maximal and mean standardized uptake values (SUVmax and SUVmean) and total lesion glycolysis (TLG) (rho = 0.458, 0.460, and 0.300, respectively, p < 0.01) as well as GLUT1 expression (rho = 0.453, p < 0.001). A SUVmax cutoff of 18.2 led to prediction of tumor eIF6 expression with an accuracy of 0.755. Functional analysis studies demonstrated that knockdown of eIF6 inhibited ESCA cell growth and migration, and fueled cell apoptosis. Moreover, the Bulk RNA gene analysis revealed a significant inverse association between eIF6 and the tumor-infiltrating immune cells (macrophages, T cells, or Th1 cells) and immunomodulators in the ESCA microenvironment.Conclusion: Our study suggested that eIF6 might serve as a potential prognostic biomarker associated with metabolic variability and immune gene signatures in ESCA tumor microenvironment. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

19. Visual Tracking Using L2 Minimization

Author

Pei Zhijun and Han Lei

Subjects
Engineering (General). Civil engineering (General), TA1-2040
Abstract

Visual tracking has been an active research topic in the computer vision applications. By modeling the target appearance with a sparse approximation over a template set, sparse representation has been applied to the visual tracker, which called L1 tracker. Due to the need to solve the L1 norm related minimization problem for many times, this L1 tracker is very computationally demanding. Although various fast numerical solver is developed to solve the resulting L1 norm related minimization problem, the framework is still a L1 norm related minimization model. Similar to the face recognition problem, sparse approximations may not deliver the desired robustness and a simple L2 approach to the visual tracking problem is not only robust, but also much faster. It may be possible to apply the L2 minimization, instead of L1 minimization, to the visual tracking problems, which has been verified by experiments on challenging sequences in the paper.

Published
2016
Full Text
View/download PDF

27. Pap Smear Images Classification for Early Detection of Cervical Cancer

Author

Pei Zhijun and Ayubu Hassan Mbaga

Subjects
Cervical cancer, Cervical screening, Computer science, business.industry, Pattern recognition, medicine.disease, Cross-validation, Support vector machine, Polynomial kernel, Region of interest, medicine, Radial basis function, Artificial intelligence, business, Classifier (UML)
Abstract

In this presents the analyses of the Pap smear cervical cell images for cervical screening and detection. Initially preprocessed the cell images to remove unwanted noises, Followed by extraction of the cell from the background to obtain the cytoplasm and nucleus of the cell which is the region of interest. It is the only parts of the cell which can be used to differentiate normal cell from abnormal one.20 salient features were extracted for training of support vector machine. SVM-RFE is used for features selection; the RFE algorithm removes unimportant features based on backward sequential selection by iteratively deleting one feature at a time, resulting in suboptimal combination of r(r

Published
2015

28. Leader-member exchange and prohibitive voice in nonprofit organizations in China: The moderating roles of superior-subordinate tenure matching

Author

Pei, Zhijun, Pan, Yingchun, Skitmore, Martin, Feng, Tao, Pei, Zhijun, Pan, Yingchun, Skitmore, Martin, and Feng, Tao

Abstract

The specific purpose of the present research contributes to addressing a gap in the organizational literature by examining how a superior-subordinate relationship may influence the use of prohibitive voice by employees in nonprofit organizations (NPOs). With data collected from 1,798 employees in 103 NPOs in southeastern China, the article investigates the influence of leader-member exchange (LMX) quality on prohibitive voice and explores the moderating effects of superior-subordinate tenure matching on the influence of LMX on prohibitive voice in NPOs. The results indicate that the quality of LMX relationships has a significant, positive influence on employee prohibitive voice behavior in NPOs, and this influence is moderated by superior-subordinate organizational tenure matching and LMX tenure matching. The study offers insight into the use of voice in NPOs since these organizations experience more difficult agency problems than for-profit firms.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results