Dongfang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Dongfang Wang has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Jingyu Wang
Department of Laboratorial Science and Technology, School of Public Health, Peking University, Beijing 100191, China
3 shared publications Bing Cao
Department of Laboratorial Science and Technology, School of Public Health, Peking University, Beijing 100191, PR China
2 shared publications- Daniel Raftery
University of Washington
2 shared publications - Haiwei Gu
College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA
2 shared publications Jingjing Yan
Department of Laboratorial Science and Technology, School of Public Health, Peking University, Beijing 100191, PR China
2 shared publicationsXiaoyu Sun
Department of Laboratorial Science and Technology, School of Public Health, Peking University, Beijing 100191, PR China
2 shared publications
Latest Publications
- Open Access
- 4 December 2022
- Published by Taylor & Francis in Geocarto International
- Vol. 38 (1)
Evaluation of linear, nonlinear and ensemble machine learning models for landslide susceptibility assessment in southwest China
Machine learning models are gradually replacing traditional techniques used for landslide susceptibility assessment. This study aims to comprehensively compare multiple models, including linear, nonlinear, and ensemble models, based on 5281 historical landslides in southwest China, the area most severely affected by the landslide disaster. Linear models represented by logistic regression (LR), nonlinear models represented by support vector machine (SVM), artificial neural network (ANN) and classification 5.0 decision tree (C5.0 DT), and ensemble models represented by random forest (RF) and categorical boosting (Catboost) were selected. The correlation coefficient, variance inflation factor (VIF), and relative important analysis were used to select the dominate landslide conditioning factors. Using multiple statistical indicators (e.g. Area Under the Receiver Operating Characteristic curve (AUC) and Kappa), cross-validation and qualitative methods to evaluate the models' performance. The findings are: (1) Regarding the model predictive performance, the best predictive performance was demonstrated by the ensemble models Catboost (AUC = 0.823 and Kappa = 0.593) and RF (AUC = 0.821 and Kappa = 0.582), followed by the nonlinear models SVM (AUC = 0.775 and Kappa = 0.520), ANN (AUC = 0.770 and Kappa = 0.486) and C5.0 DT (AUC = 0.751 and Kappa = 0.497), while the linear model LR (AUC = 0.756 and Kappa = 0.456) had a more limited performance. The ensemble model, which uses a tree as its baseline classifier, has a lot of potential for studies into the landslide susceptibility. (2) Regarding the model robustness, the three types of models in nonspatial cross-validation (CV) performed relatively similarly in terms of predictive power, while in spatial cross-validation (SPCV), the linear model LR (median AUC = 0.714) achieved better results than the ensemble and nonlinear models. It implies that when the distribution of landslides is not homogeneous, linear models may be the most robust. It is advisable to consider various evaluation metrics from different perspectives and integrate them with specialist qualitative geomorphological empirical knowledge to determine the best model. (3) The Gini index-based RF model suggests that road density was the dominant factor in the frequency of landslides in the study area.
- 4 December 2022
- Published by Taylor & Francis in Geocarto International
- Vol. 38 (1)
Open AccessEvaluation of linear, nonlinear and ensemble machine learning models for landslide susceptibility assessment in southwest China
Machine learning models are gradually replacing traditional techniques used for landslide susceptibility assessment. This study aims to comprehensively compare multiple models, including linear, nonlinear, and ensemble models, based on 5281 historical landslides in southwest China, the area most severely affected by the landslide disaster. Linear models represented by logistic regression (LR), nonlinear models represented by support vector machine (SVM), artificial neural network (ANN) and classification 5.0 decision tree (C5.0 DT), and ensemble models represented by random forest (RF) and categorical boosting (Catboost) were selected. The correlation coefficient, variance inflation factor (VIF), and relative important analysis were used to select the dominate landslide conditioning factors. Using multiple statistical indicators (e.g. Area Under the Receiver Operating Characteristic curve (AUC) and Kappa), cross-validation and qualitative methods to evaluate the models' performance. The findings are: (1) Regarding the model predictive performance, the best predictive performance was demonstrated by the ensemble models Catboost (AUC = 0.823 and Kappa = 0.593) and RF (AUC = 0.821 and Kappa = 0.582), followed by the nonlinear models SVM (AUC = 0.775 and Kappa = 0.520), ANN (AUC = 0.770 and Kappa = 0.486) and C5.0 DT (AUC = 0.751 and Kappa = 0.497), while the linear model LR (AUC = 0.756 and Kappa = 0.456) had a more limited performance. The ensemble model, which uses a tree as its baseline classifier, has a lot of potential for studies into the landslide susceptibility. (2) Regarding the model robustness, the three types of models in nonspatial cross-validation (CV) performed relatively similarly in terms of predictive power, while in spatial cross-validation (SPCV), the linear model LR (median AUC = 0.714) achieved better results than the ensemble and nonlinear models. It implies that when the distribution of landslides is not homogeneous, linear models may be the most robust. It is advisable to consider various evaluation metrics from different perspectives and integrate them with specialist qualitative geomorphological empirical knowledge to determine the best model. (3) The Gini index-based RF model suggests that road density was the dominant factor in the frequency of landslides in the study area.
- 1 February 2019
- Published by Elsevier in Psychiatry Research
- Vol. 272, 18-29
Metabolic profiling identifies phospholipids as potential serum biomarkers for schizophrenia
- 1 February 2019
- Published by Elsevier in Psychiatry Research
- Vol. 272, 18-29
Metabolic profiling identifies phospholipids as potential serum biomarkers for schizophrenia
- 1 November 2018
- Published by Elsevier in Psychiatry Research
- Vol. 269, 558-564
A comparative study of the typical toxic metals in serum by patients of schizophrenia and healthy controls in China
- 1 November 2018
- Published by Elsevier in Psychiatry Research
- Vol. 269, 558-564
A comparative study of the typical toxic metals in serum by patients of schizophrenia and healthy controls in China
- 1 July 2018
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 102, 168-178
Alterations of eicosanoids and related mediators in patients with schizophrenia
- 1 July 2018
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 102, 168-178
Alterations of eicosanoids and related mediators in patients with schizophrenia
- 24 April 2018
- Published by American Chemical Society (ACS) in Journal of Proteome Research
- Vol. 17 (6) , 2092-2101
Multiplatform Metabolomics Investigation of Antiadipogenic Effects on 3T3-L1 Adipocytes by a Potent Diarylheptanoid
Obesity is fast becoming a serious health problem worldwide. Of the many possible antiobesity strategies, one interesting approach focuses on blocking adipocyte differentiation and lipid accumulation to counteract the rise in fat storage. However, there is currently no drug available for the treatment of obesity that works by inhibiting adipocyte differentiation. Here we use a broad-based metabolomics approach to interrogate and better understand metabolic changes that occur during adipocyte differentiation. In particular, we focus on changes induced by the antiadipogenic diarylheptanoid, which was isolated from a traditional Chinese medicine Dioscorea zingiberensis and identified as (3R,5R)-3,5-dihydroxy-1-(3,4-dihydroxyphenyl)-7-(4-hydroxyphenyl)-heptane (1). Targeted aqueous metabolic profiling indicated that a total of 14 metabolites involved in the TCA cycle, glycolysis, amino acid metabolism, and purine catabolism participate in regulating energy metabolism, lipogenesis, and lipolysis in adipocyte differentiation and can be modulated by diarylheptanoid 1. As indicated by lipidomics analysis, diarylheptanoid 1 restored the quantity and degree of unsaturation of long-chain free fatty acids and restored the levels of 171 lipids mainly from 10 lipid classes in adipocytes. In addition, carbohydrate metabolism in diarylheptanoid-1-treated adipocytes further demonstrated the delayed differentiation process by flux analysis. Our results provide valuable information for further understanding the metabolic adjustment in adipocytes subjected to diarylheptanoid 1 treatment. Moreover, this study offers new insight into developing antiadipogenic leading compounds based on metabolomics.
- 24 April 2018
- Published by American Chemical Society (ACS) in Journal of Proteome Research
- Vol. 17 (6) , 2092-2101
Multiplatform Metabolomics Investigation of Antiadipogenic Effects on 3T3-L1 Adipocytes by a Potent Diarylheptanoid
Obesity is fast becoming a serious health problem worldwide. Of the many possible antiobesity strategies, one interesting approach focuses on blocking adipocyte differentiation and lipid accumulation to counteract the rise in fat storage. However, there is currently no drug available for the treatment of obesity that works by inhibiting adipocyte differentiation. Here we use a broad-based metabolomics approach to interrogate and better understand metabolic changes that occur during adipocyte differentiation. In particular, we focus on changes induced by the antiadipogenic diarylheptanoid, which was isolated from a traditional Chinese medicine Dioscorea zingiberensis and identified as (3R,5R)-3,5-dihydroxy-1-(3,4-dihydroxyphenyl)-7-(4-hydroxyphenyl)-heptane (1). Targeted aqueous metabolic profiling indicated that a total of 14 metabolites involved in the TCA cycle, glycolysis, amino acid metabolism, and purine catabolism participate in regulating energy metabolism, lipogenesis, and lipolysis in adipocyte differentiation and can be modulated by diarylheptanoid 1. As indicated by lipidomics analysis, diarylheptanoid 1 restored the quantity and degree of unsaturation of long-chain free fatty acids and restored the levels of 171 lipids mainly from 10 lipid classes in adipocytes. In addition, carbohydrate metabolism in diarylheptanoid-1-treated adipocytes further demonstrated the delayed differentiation process by flux analysis. Our results provide valuable information for further understanding the metabolic adjustment in adipocytes subjected to diarylheptanoid 1 treatment. Moreover, this study offers new insight into developing antiadipogenic leading compounds based on metabolomics.