In this study, a novel approach of the landslide numerical risk factor(LNRF) bivariate model was used in ensemble with linear multivariate regression(LMR) and boosted regression tree(BRT) models, coupled with radar re...In this study, a novel approach of the landslide numerical risk factor(LNRF) bivariate model was used in ensemble with linear multivariate regression(LMR) and boosted regression tree(BRT) models, coupled with radar remote sensing data and geographic information system(GIS), for landslide susceptibility mapping(LSM) in the Gorganroud watershed, Iran. Fifteen topographic, hydrological, geological and environmental conditioning factors and a landslide inventory(70%, or 298 landslides) were used in mapping. Phased array-type L-band synthetic aperture radar data were used to extract topographic parameters. Coefficients of tolerance and variance inflation factor were used to determine the coherence among conditioning factors. Data for the landslide inventory map were obtained from various resources, such as Iranian Landslide Working Party(ILWP), Forestry, Rangeland and Watershed Organisation(FRWO), extensive field surveys, interpretation of aerial photos and satellite images, and radar data. Of the total data, 30% were used to validate LSMs, using area under the curve(AUC), frequency ratio(FR) and seed cell area index(SCAI).Normalised difference vegetation index, land use/land cover and slope degree in BRT model elevation, rainfall and distance from stream were found to be important factors and were given the highest weightage in modelling. Validation results using AUC showed that the ensemble LNRF-BRT and LNRFLMR models(AUC = 0.912(91.2%) and 0.907(90.7%), respectively) had high predictive accuracy than the LNRF model alone(AUC = 0.855(85.5%)). The FR and SCAI analyses showed that all models divided the parameter classes with high precision. Overall, our novel approach of combining multivariate and machine learning methods with bivariate models, radar remote sensing data and GIS proved to be a powerful tool for landslide susceptibility mapping.展开更多
AIM The purpose of this study was to evaluate the diagnostic value of trefoil factor family 3(TFF3) for the early detection of colorectal cancer(CC). METHODS Serum TFF3 and carcino-embryonic antigen(CEA) were detected...AIM The purpose of this study was to evaluate the diagnostic value of trefoil factor family 3(TFF3) for the early detection of colorectal cancer(CC). METHODS Serum TFF3 and carcino-embryonic antigen(CEA) were detected in 527 individuals, including 115 healthy control(HC), 198 colorectal adenoma(CA), and 214 CC individuals in the training group. RESULTS Serum TFF3 showed no significant correlation with age, gender, or tumor location but showed significant correlation with the tumor stage. Serum TFF3 in the CC group was significantly higher than in the HC or CA group. The AUC values of TFF3 for discriminating between HC and CC and between CA and CC were 0.930(0.903, 0.958) and 0.834(0.796, 0.873). A multivariate model combining TFF3 and CEA was built. Compared to TFF3 or CEA alone, the multivariate model showed significant improvement(P < 0.001). For discriminating between HC and CC, HC and early stage CC, HC and advanced stage CC, CA and CC, CA and early stage CC, and CA and advanced stage CC in the training group, the sensitivities were 92.99%, 91.46%, 93.18%, 73.83%, 76.83%, and 81.82%, and the specificities were 91.30%, 91.30%, 93.91%, 88.38%, 77.27%, and 88.38%, respectively. After validation, the sensitivities were 89.39%, 85.71%, 90.79%, 72.73%, 71.43%, and 78.95%, and the specificities were 87.85%, 87.85%, 2.52%, 87.85%, 80.77%, and 87.50%, respectively. CONCLUSION The multivariate diagnostic model that included TFF3 and CEA showed significant improvement over the conventional biomarker CEA and might provide a potential method for the early detection of CC.展开更多
基金supported by the Centre for Advanced Modelling and Geospatial Information Systems(CAMGIS),UTS under grant numbers 321740.2232335,323930,and 321740.2232357
文摘In this study, a novel approach of the landslide numerical risk factor(LNRF) bivariate model was used in ensemble with linear multivariate regression(LMR) and boosted regression tree(BRT) models, coupled with radar remote sensing data and geographic information system(GIS), for landslide susceptibility mapping(LSM) in the Gorganroud watershed, Iran. Fifteen topographic, hydrological, geological and environmental conditioning factors and a landslide inventory(70%, or 298 landslides) were used in mapping. Phased array-type L-band synthetic aperture radar data were used to extract topographic parameters. Coefficients of tolerance and variance inflation factor were used to determine the coherence among conditioning factors. Data for the landslide inventory map were obtained from various resources, such as Iranian Landslide Working Party(ILWP), Forestry, Rangeland and Watershed Organisation(FRWO), extensive field surveys, interpretation of aerial photos and satellite images, and radar data. Of the total data, 30% were used to validate LSMs, using area under the curve(AUC), frequency ratio(FR) and seed cell area index(SCAI).Normalised difference vegetation index, land use/land cover and slope degree in BRT model elevation, rainfall and distance from stream were found to be important factors and were given the highest weightage in modelling. Validation results using AUC showed that the ensemble LNRF-BRT and LNRFLMR models(AUC = 0.912(91.2%) and 0.907(90.7%), respectively) had high predictive accuracy than the LNRF model alone(AUC = 0.855(85.5%)). The FR and SCAI analyses showed that all models divided the parameter classes with high precision. Overall, our novel approach of combining multivariate and machine learning methods with bivariate models, radar remote sensing data and GIS proved to be a powerful tool for landslide susceptibility mapping.
基金Supported by The Capital Health Development Special Scientific Research Projects,No.2014-2-2154National Natural Science Foundation of China,No.81471761 and No.81501568
文摘AIM The purpose of this study was to evaluate the diagnostic value of trefoil factor family 3(TFF3) for the early detection of colorectal cancer(CC). METHODS Serum TFF3 and carcino-embryonic antigen(CEA) were detected in 527 individuals, including 115 healthy control(HC), 198 colorectal adenoma(CA), and 214 CC individuals in the training group. RESULTS Serum TFF3 showed no significant correlation with age, gender, or tumor location but showed significant correlation with the tumor stage. Serum TFF3 in the CC group was significantly higher than in the HC or CA group. The AUC values of TFF3 for discriminating between HC and CC and between CA and CC were 0.930(0.903, 0.958) and 0.834(0.796, 0.873). A multivariate model combining TFF3 and CEA was built. Compared to TFF3 or CEA alone, the multivariate model showed significant improvement(P < 0.001). For discriminating between HC and CC, HC and early stage CC, HC and advanced stage CC, CA and CC, CA and early stage CC, and CA and advanced stage CC in the training group, the sensitivities were 92.99%, 91.46%, 93.18%, 73.83%, 76.83%, and 81.82%, and the specificities were 91.30%, 91.30%, 93.91%, 88.38%, 77.27%, and 88.38%, respectively. After validation, the sensitivities were 89.39%, 85.71%, 90.79%, 72.73%, 71.43%, and 78.95%, and the specificities were 87.85%, 87.85%, 2.52%, 87.85%, 80.77%, and 87.50%, respectively. CONCLUSION The multivariate diagnostic model that included TFF3 and CEA showed significant improvement over the conventional biomarker CEA and might provide a potential method for the early detection of CC.
