Forecasting and Trading Currency Volatility: An Application of Recurrent Neural Regression and Model Combination

2005 ◽  
pp. 129-162
Author(s):  
Christian L. Dunis ◽  
Xuehuan Huang
Keyword(s):  
Model Combination

scholarly journals Anticancer effects of the combined Thai noni juice ethanolic extracts and 5-fluorouracil against cholangiocarcinoma cells in vitro and in vivo

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jeerati Prompipak ◽  
Thanaset Senawong ◽  
Banchob Sripa ◽  
Albert J. Ketterman ◽  
Suppawit Utaiwat ◽  
...  
Keyword(s):  
Nude Mice ◽  
Combination Treatment ◽  
Synergistic Effects ◽  
Single Agent ◽  
Xenograft Model ◽  
Ethanolic Extract ◽  
Model Combination ◽  
Mouse Xenograft Model ◽  
Ethanolic Extracts

AbstractApplication of 5-fluorouracil (5-FU) in cholangiocarcinoma (CCA) is limited by adverse side effects and chemoresistance. Therefore, the combination therapy of 5-FU with other substances, especially natural products may provide a new strategy for CCA treatment. The aim of this study was to evaluate the combination effects of 5-FU and two ethanolic extracts of Thai noni juice (TNJ) products on CCA cell lines and nude mice xenografts. The results of antiproliferative assay showed the combination treatment of 5-FU and each TNJ ethanolic extract exerted more cytotoxicity on CCA cells than either single agent treatment. Synergistic effects of drug combinations can enable the dose reduction of 5-FU. The mechanism underlying a combination treatment was apoptosis induction through an activation of p53 and Bax proteins. In the nude mouse xenograft model, combination treatments of 5-FU with each TNJ ethanolic extract suppressed the growth of CCA cells implanted mice more than single agent treatments with no effects on mouse body weight, kidney, and spleen. Moreover, low doses of TNJ ethanolic extracts reduced the hepatotoxicity of 5-FU in nude mice. Taken together, these data suggested that the ethanolic extracts of TNJ products can enhance the anti-CCA effect and reduce toxicity of 5-FU.

scholarly journals The Potential Use of Radiomics with Pre-Radiation Therapy MR Imaging in Predicting Risk of Pseudoprogression in Glioblastoma Patients

2021 ◽  
Vol 7 (2) ◽  
pp. 17
Author(s):  
Michael Baine ◽  
Justin Burr ◽  
Qian Du ◽  
Chi Zhang ◽  
Xiaoying Liang ◽  
...  
Keyword(s):  
Clinical Features ◽  
Dna Methyltransferase ◽  
Predictive Ability ◽  
Post Treatment ◽  
Model Combination ◽  
Methylguanine Dna Methyltransferase ◽  
Mri Scans ◽  
Area Under Roc Curve ◽  
True Progression ◽  
Potential Use

Glioblastoma (GBM) is the most common adult glioma. Differentiating post-treatment effects such as pseudoprogression from true progression is paramount for treatment. Radiomics has been shown to predict overall survival and MGMT (methylguanine-DNA methyltransferase) promoter status in those with GBM. A potential application of radiomics is predicting pseudoprogression on pre-radiotherapy (RT) scans for patients with GBM. A retrospective review was performed with radiomic data analyzed using pre-RT MRI scans. Pseudoprogression was defined as post-treatment findings on imaging that resolved with steroids or spontaneously on subsequent imaging. Of the 72 patients identified for the study, 35 were able to be assessed for pseudoprogression, and 8 (22.9%) had pseudoprogression. A total of 841 radiomic features were examined along with clinical features. Receiver operating characteristic (ROC) analyses were performed to determine the AUC (area under ROC curve) of models of clinical features, radiomic features, and combining clinical and radiomic features. Two radiomic features were identified to be the optimal model combination. The ROC analysis found that the predictive ability of this combination was higher than using clinical features alone (mean AUC: 0.82 vs. 0.62). Additionally, combining the radiomic features with clinical factors did not improve predictive ability. Our results indicate that radiomics is potentially capable of predicting future development of pseudoprogression in patients with GBM using pre-RT MRIs.

Research on non-intrusive load disaggregation method based on multi-model combination

2021 ◽  
Vol 200 ◽  
pp. 107472
Author(s):  
Yi Guo ◽  
Xuejun Xiong ◽  
Qi Fu ◽  
Liang Xu ◽  
Shi Jing
Keyword(s):  
Model Combination ◽  
Load Disaggregation

scholarly journals ỨNG DỤNG DỮ LIỆU MƯA CHIRPS VÀ MÔ HÌNH THỦY VĂN HEC-HMS MÔ PHỎNG DÒNG CHẢY LŨ Ở LƯU VỰC SÔNG LẠI GIANG

2021 ◽  
Vol 5 (1) ◽  
pp. 2252-2261
Author(s):  
Ngô Anh Tú ◽  
Phan Thái Lê ◽  
Nguyễn Hữu Xuân ◽  
Trần Văn Bình
Keyword(s):  
Economic Development ◽  
River Basin ◽  
Hydrological Model ◽  
Flow Data ◽  
Model Combination ◽  
The North ◽  
Socio Economic Development ◽  
Flood Peaks ◽  
Simulation Results ◽  
Flood Flow

Bài báo xác định lưu lượng dòng chảy theo thời đoạn dựa vào mô hình HEC-HMS, số liệu mưa từ ảnh vệ tinh CHIRPS của NASA và Hệ thống thông tin địa lý (GIS) trong mô phỏng dòng chảy lũ tháng 12 năm 2016 tại lưu vực sông Lại Giang, lưu vực lớn thứ hai của tỉnh Bình Định (sau lưu vực sông Kôn) và có vai trò quan trọng về phát triển kinh tế-xã hội ở phía Bắc của tỉnh. Kết quả mô phỏng dòng chảy lũ rất đáng tin cậy, lưu lượng dòng chảy lũ đạt đỉnh 2542,6 m3/s tương ứng với với tần suất lũ 5%. Chỉ số kiểm định mô hình NSE với giá trị là 0,93; hệ số R2 đạt 0,78 sai số PBIAS khoảng 24% và sai số đỉnh lũ PEC = 52,01.  ABSTRACT The paper aimed to introduce the application of the HEC-HMS hydrological model combination with the CHIRPS (Climate Hazards Group Infrared Precipitation with Station) and GIS to restore flood flow data in the Lai Giang river basin in 2016. The Lai Giang river basin is the second largest basin of Binh Dinh province (after the Kon river basin), it plays an important role in socio-economic development in the North of Binh Dinh province. The simulation results of flood peaks reached 2542,6 m3.s-1 (P=5%). Model test indices such as NSE = 0.93, the correlation coefficient reached 0,78; the percentage of PBIAS error was about 24%, and peak error (PEC) was 52,01.

Evaluating the contribution of multi-model combination to streamflow hindcasting by empirical and conceptual models

2017 ◽  
Vol 62 (9) ◽  
pp. 1456-1468 ◽  
Author(s):  
Yen-Ming Chiang ◽  
Ruo-Nan Hao ◽  
Hao-Che Ho ◽  
Tsang-Jung Chang ◽  
Yue-Ping Xu
Keyword(s):  
Conceptual Models ◽  
Model Combination

scholarly journals NIR Hyperspectral Imaging Technology Combined with Multivariate Methods to Study the Residues of Different Concentrations of Omethoate on Wheat Grain Surface

Sensors ◽  
2019 ◽  
Vol 19 (14) ◽  
pp. 3147 ◽  
Author(s):  
Liu Zhang ◽  
Zhenhong Rao ◽  
Haiyan Ji
Keyword(s):  
Feature Extraction ◽  
Hyperspectral Imaging ◽  
Hyperspectral Image ◽  
Imaging System ◽  
Support Vector ◽  
Multivariate Methods ◽  
Model Combination ◽  
Modeling Analysis ◽  
Svm Model ◽  
Wheat Kernels

In this study, a hyperspectral imaging system of 866.4–1701.0 nm was selected and combined with multivariate methods to identify wheat kernels with different concentrations of omethoate on the surface. In order to obtain the optimal model combination, three preprocessing methods (standard normal variate (SNV), Savitzky–Golay first derivative (SG1), and multivariate scatter correction (MSC)), three feature extraction algorithms (successive projections algorithm (SPA), random frog (RF), and neighborhood component analysis (NCA)), and three classifier models (decision tree (DT), k-nearest neighbor (KNN), and support vector machine (SVM)) were applied to make a comparison. Firstly, based on the full wavelengths modeling analysis, it was found that the spectral data after MSC processing performed best in the three classifier models. Secondly, three feature extraction algorithms were used to extract the feature wavelength of MSC processed data and based on feature wavelengths modeling analysis. As a result, the MSC–NCA–SVM model performed best and was selected as the best model. Finally, in order to verify the reliability of the selected model, the hyperspectral image was substituted into the MSC–NCA–SVM model and the object-wise method was used to visualize the image classification. The overall classification accuracy of the four types of wheat kernels reached 98.75%, which indicates that the selected model is reliable.

Sign in / Sign up

Export Citation Format

Share Document