|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization显示文摘The present study aims to develop two hybrid models to optimize the factors and enhance the predictive ability of the landslide susceptibility models.For this,a landslide inventory map was created with 406 historical landslides and 2030 non-landslide points,which was randomly divided into two datasets for model training(70%)and model testing(30%).22 factors were initially selected to establish a landslide factor database.We applied the GeoDetector and recursive feature elimination method(RFE)to address factor optimization to reduce information redundancy and collinearity in the data.Thereafter,the frequency ratio method,multicollinearity test,and interactive detector were used to analyze and evaluate the optimized factors.Subsequently,the random forest(RF)model was used to create a landslide susceptibility map with original and optimized factors.The resultant hybrid models GeoDetector-RF and RFE-RF were evaluated and compared by the area under the receiver operating characteristic curve(AUC)and accuracy.The accuracy of the two hybrid models(0.868 for GeoDetector-RF and 0.869 for RFE-RF)were higher than that of the RF model(0.860),indicating that the hybrid models with factor optimization have high reliability and predictability.Both RFE-RF GeoDetector-RF had higher AUC values,respectively 0.863 and 0.860,than RF(0.853).These results confirm the ability of factor optimization methods to improve the performance of landslide susceptibility models. | Xinzhi Zhou Haijia Wen Yalan Zhang Jiahui Xu Wengang Zhang | 2021 | Geoscience Frontiers2021，12，5： | 12 |
| 2 | Predicting TBM penetration rate in hard rock condition:A comparative study among six XGB-based metaheuristic techniques显示文摘A reliable and accurate prediction of the tunnel boring machine(TBM)performance can assist in minimizing the relevant risks of high capital costs and in scheduling tunneling projects.This research aims to develop six hybrid models of extreme gradient boosting(XGB)which are optimized by gray wolf optimization(GWO),particle swarm optimization(PSO),social spider optimization(SSO),sine cosine algorithm(SCA),multi verse optimization(MVO)and moth flame optimization(MFO),for estimation of the TBM penetration rate(PR).To do this,a comprehensive database with 1286 data samples was established where seven parameters including the rock quality designation,the rock mass rating,Brazilian tensile strength(BTS),rock mass weathering,the uniaxial compressive strength(UCS),revolution per minute and trust force per cutter(TFC),were set as inputs and TBM PR was selected as model output.Together with the mentioned six hybrid models,four single models i.e.,artificial neural network,random forest regression,XGB and support vector regression were also built to estimate TBM PR for comparison purposes.These models were designed conducting several parametric studies on their most important parameters and then,their performance capacities were assessed through the use of root mean square error,coefficient of determination,mean absolute percentage error,and a10-index.Results of this study confirmed that the best predictive model of PR goes to the PSO-XGB technique with system error of(0.1453,and 0.1325),R^(2) of(0.951,and 0.951),mean absolute percentage error(4.0689,and 3.8115),and a10-index of(0.9348,and 0.9496)in training and testing phases,respectively.The developed hybrid PSO-XGB can be introduced as an accurate,powerful and applicable technique in the field of TBM performance prediction.By conducting sensitivity analysis,it was found that UCS,BTS and TFC have the deepest impacts on the TBM PR. | Jian Zhou Yingui Qiu Danial Jahed Armaghani Wengang Zhang Chuanqi Li Shuangli Zhu Reza Tarinejad | 2021 | Geoscience Frontiers2021，12，3： | 10 |
| 3 | Active Contours Based on Image Laplacian Fitting Energy显示文摘 | ZHANG Kaihua XU Shoushi ZHOU Wengang LIU Bo | 2009 | Chinese Journal of Electronics2009，18，2： | 7 |
| 4 | Influence of groundwater drawdown on excavation responses e A case history in Bukit Timah granitic residual soils显示文摘Performances of a braced cut-and-cover excavation system for mass rapid transit(MRT) stations of the Downtown Line Stage 2 in Singapore are presented. The excavation was carried out in the Bukit Timah granitic(BTG) residual soils and characterized by significant groundwater drawdown, due to dewatering work in complex site conditions, insufficient effective waterproof measures and more permeable soils. A two-dimensional numerical model was developed for back analysis of retaining wall movement and ground surface settlement. Comparisons of these measured excavation responses with the calculated performances were carried out, upon which the numerical simulation procedures were calibrated. In addition, the influences of groundwater drawdown on the wall deflection and ground surface settlement were numerically investigated and summarized. The performances were also compared with some commonly used empirical charts, and the results indicated that these charts are less applicable for cases with significant groundwater drawdowns. It is expected that these general behaviors will provide useful references and insights for future projects involving excavation in BTG residual soils under significant groundwater drawdowns. | Wengang Zhang Wei Wang Dong Zhou Runhong Zhang A.T.C. Goh Zhongjie Hou | 2018 | Journal of Rock Mechanics and Geotechnical Engineering2018，10，5： | 5 |
| 5 | Genetically modified CD7-targeting allogeneic CAR-T cell therapy with enhanced efficacy for relapsed/refractory CD7-positive hematological malignancies:a phase I clinical study显示文摘Chimeric antigen receptor(CAR)-T cell therapy against T cell malignancies faces major challenges including fratricide between CAR-T cells and product contamination from the blasts.Allogeneic CAR-T cells,generated from healthy donor T cells,can provide ready-to-use,blast-free therapeutic products,but their application could be complicated by graft-versus-host disease(GvHD)and host rejection.Here we developed healthy donor-derived,CD7-targeting CAR-T cells(RD13-01)with genetic modifications to resist fratricide,GvHD and allogeneic rejection,as well as to potentiate antitumor function.A phase I clinical trial(NCT04538599)was conducted with twelve patients recruited(eleven with T cell leukemia/lymphoma,and one with CD7-expressing acute myeloid leukemia).All patients achieved pre-set end points and eleven proceeded to efficacy evaluation.No dose-limiting toxicity,GvHD,immune effector cell-associated neurotoxicity or severe cytokine release syndrome(grade≥3)were observed.28 days post infusion,81.8%of patients(9/11)showed objective responses and the complete response rate was 63.6%(7/11,including the patient with AML).3 of the responding patients were bridged to allogeneic hematopoietic stem cell transplantation.With a median follow-up of 10.5 months,4 patients remained in complete remission.Cytomegalovirus(CMV)and/or Epstein-Barr virus(EBV)reactivation was observed in several patients,and one died from EBV-associated diffuse large B-cell lymphoma(DLBCL).Expansion of CD7-negative normal T cells was detected post infusion.In summary,we present the first report of a Phase I clinical trial using healthy donor-derived CD7-targeting allogeneic CAR-T cells to treat CD7^(+)hematological malignancies.Our results demonstrated the encouraging safety and efficacy profiles of the RD13-01 allogeneic CAR-T cells for CD7^(+)tumors. | Yongxian Hu Yali Zhou Mingming Zhang Houli Zhao Guoqing Wei Wengang Ge Qu Cui Qitian Mu Gong Chen Lu Han Tingting Guo Jiazhen Cui Xiaoyan Jiang Xiujun Zheng Shuhui Yu Xiaolong Li Xingwang Zhang Mingxi Chen Xiuju Li Ming Gao Kang Wang Cheng Zu Hao Zhang Xiaohong He Yanbin Wang Dongrui Wang Jiangtao Ren He Huang | 2022 | Cell Research2022，32，11： | 2 |
| 6 | Active contours with selective local or global segmentation: A new formulation and level set method显示文摘 | Kaihua Zhang Lei Zhang Huihui Song Wengang Zhou | 2009 | Image and Vision Computing2009，，4： | 2 |
| 7 | Expression of RECK and MMP?2 in salivary adenoid cystic carcinoma: Correlationwith tumor progression and patient prognosis显示文摘 | Xiaoqing Zhou Shengyun Huang Licheng Jiang Shizhou Zhang Wengang Li Zhanwei Chen Dongsheng Zhang | 2014 | Oncology Letters2014，，5： | 1 |
| 8 | Neural network and support vector machine models for the prediction of the liquefaction-induced uplift displacement of tunnels显示文摘Tunnels buried in liquefiable deposits are vulnerable to liquefaction-induced uplift damage during earthquakes.This paper presents support vector machine(SVM)and artificial neural network(ANN)models to predict the liquefaction-induced uplift displacement of tunnels based on artificial databases generated by the finite difference method.The performance of the SVM and ANN models was assessed using statistical parameters,including the coefficient of determination R^(2),the mean absolute error,and the root mean squared error.Applications for the above-mentioned approaches are compared and discussed.A relative importance analysis was adopted to quantify the sensitivity of each input variable.The precision of the presented models is demonstrated using centrifuge test results from previous studies. | Gang Zheng Wenbin Zhang Wengang Zhang Haizuo Zhou Pengbo Yang | 2021 | Underground Space2021，6，2： | 1 |
| 9 | Active contours with selective local or global segmentation: A new formulation and level set method显示文摘 | Kaihua Zhang Lei Zhang Huihui Song Wengang Zhou | 2009 | Image and Vision Computing2009，，4： | 1 |
| 10 | Probabilistic stability analysis of Bazimen landslide with monitored rainfall data and water level fluctuations in Three Gorges Reservoir, China显示文摘Landslide is a common geological hazard in reservoir areas and may cause great damage to local residents’life and property.It is widely accepted that rainfall and periodic variation of water level are the two main factors triggering reservoir landslides.In this study,the Bazimen landslide located in the Three Gorges Reservoir(TGR)was back-analyzed as a case study.Based on the statistical features of the last 3-year monitored data and field instrumentations,the landslide susceptibility in an annual cycle and four representative periods was investigated via the deterministic and probabilistic analysis,respectively.The results indicate that the fluctuation of the reservoir water level plays a pivotal role in inducing slope failures,for the minimum stability coefficient occurs at the rapid decline period of water level.The probabilistic analysis results reveal that the initial sliding surface is the most important area influencing the occurrence of landslide,compared with other parts in the landslide.The seepage calculations from probabilistic analysis imply that rainfall is a relatively inferior factor affecting slope stability.This study aims to provide preliminary guidance on risk management and early warning in the TGR area. | Wengang ZHANG Libin TANG Hongrui LI Lin WANG Longfei CHENG Tingqiang ZHOU Xiang CHEN | 2020 | Frontiers of Structural and Civil Engineering2020，14，5： | 1 |
| 11 | BSIFT: toward data- independent codebook for large scale image search 显示文摘 | Zhou Wengang Li Houqiang Lu Yijuan | 2015 | IEEE Tans on Image Processing2015，24，3： | 1 |
| 12 | Correlative Analysis between Contents of Nutrients and Secondary Substances in Damaged Pinus massoniana Needles and Population Parameters of Dendrolimus kikuchii(Lepidoptera:Lasiocampidae)显示文摘In order to explore the effects of chemical substances changes in damaged masson pine(Pinus massoniana) needles on population dynamics of Dendrolimus kikuchii,D. kikuchii larvae were reared with P. massoniana needles with different damage degrees(mild,moderate and severe),and its population parameters and contents of nutrients and secondary substances in damaged P. massoniana needles were measured,and the integrated correlation coefficient was adopted for data analysis. The results showed that with the damage degree aggravating,flavones in needles increased accordingly,while contents of soluble sugars,polysaccharides and proteins decreased. The average developmental duration and mortality of D. kikuchii larvae increased with the damage degree increasing. No significant correlation was found between the changes in contents of tannins or total phenols and the developmental duration or mortality of each instar larvae. There were significant direct and integrated correlations between contents of nutrients and secondary substances of P. massoniana needles and the developmental duration or mortality of each instar larvae except the 6thinstar larvae. With the damage degree increasing,all parameters of D. kikuchii population including body weight of the 7thinstar larvae,average feeding capacity of larvae,pupal weight,pupation rate,female ratio and fecundity decreased. No significant correlation was found between the changes in contents of tannins or total phenols and population parameters of D. kikuchii larvae. The results suggest that the contents of nutrients and secondary substances in P. massoniana needles dramatically influenced the population parameters of D. kikuchii,and the importance from high to low successively was soluble sugars > proteins > polysaccharides > flavones. Contents of tannins and total phenols seemed to have little influence. | Tong Wengang Chen Shunli Zhou Suo Chen Delan | 2014 | Plant Diseases and Pests2014，5，4： | 1 |
| 13 | Image denoising with an optimal threshold and neighbouring window 显示文摘 | Zhou Dengwen Cheng Wengang | 2008 | Pattern Recognition Letters2008，29，： | 1 |
| 14 | BSIFT:Toward data-independent codebook for large scale image search显示文摘 | Zhou Wengang Li Houqiang Lu Yijuan | 2015 | IEEE Transactions on Image Processing2015，24，3： | 1 |
| 15 | Dynamic antimicrobial resistant patterns of Escherichia coli from healthy poultry and swine over 10 years in Chongming Island,Shanghai显示文摘Background:Antimicrobial resistance(AMR)is one of the greatest threats to animal and public health.Here,we conducted a dynamic surveillance of Escherichia coli on Chongming Island in Shanghai during 2009-2021 to identify the characteristics and trends of Chongming’s AMR pandemic.Methods:Rectal(cloaca)swabs from four poultry and nine swine farms(Chongming Island,2009-2021)were collected for E.coli strains acquisition.The micro-broth dilution method was used to test antimicrobial susceptibility of E.coli isolates against 10 antimicrobial classes including 15 antimicrobials.Utilizing generalized linear mixed models(GLMMs)and co-occurrence analyses,we further explored the multiple-drug-resistance(MDR)combinations and dynamic patterns of E.coli over 10 years in two food animals.Results:Total of 863 MDR isolates were found among 945 collected E.coli isolates,337 from poultry and 608 from swine.Both isolates exhibited high resistant rates(>70%)to tetracyclines,phenicols,sulfonamides,penicillins,and aminoglycosides(only in swine).The resistant rates of swine isolates to penicillins,aminoglycosides,tetracyclines,phenicols,and polymyxins were significantly higher than those of poultry isolates,whereas resistance to fluoroquinolones was reversed.Resistance to polymyxins decreased similarly in swine(42.4%in 2009 to 0.0%in 2021)and poultry isolates(from 16.5%to 0.0%).However,resistance to other seven antimicrobial classes(excluding carbapenems and penicillins)declined dramatically in swine isolates,particularly fluoroquinolones(from 80.5%to 14.4%),and tendencies of resistance to the seven classes showed markedly divergent patterns in poultry isolates.Using Poisson GLMMs,the AMR carriage since 2016 was significantly lower than that of 2009(odds ratio<1),indicating a decline in the risk of MDR emergence.Furthermore,despite the highly diverse MDR profiles,co-occurrence analysis identified two prominent MDR clusters of penicillins-phenicols-fluoroquinolones in poultry and aminoglycosides-tetracyclines-sulfonamides-phenicols in swine.Conclusions:Our study uncovered vastly distinct AMR patterns and dynamic tendencies of poultry and swine E.coli isolates from Chongming.Meanwhile,Chongming’s AMR status has ameliorated,as indicated by the decline in antimicrobials prevalence(particularly in swine),lower likelihood of MDR emergence and low carbapenem-,cephalosporin-,and polymyxin resistance.Importantly,this surveillance results are the vital basis for future policy development in Chongming and Shanghai. | Chao Lv Jun Shang Wengang Zhang Bingqing Sun Min Li Chaoyi Guo Nan Zhou Xiaokui Guo Shixin Huang Yongzhang Zhu | 2022 | Infectious Diseases of Poverty2022，11，5： | 0 |
| 16 | User Role Discovery and Optimization Method Based on K-means++ and Reinforcement Learning in Mobile Applications显示文摘With the widespread use of mobile phones,users can share their location and activity anytime,anywhere,as a form of check-in data.These data reflect user features.Long-term stability and a set of user-shared features can be abstracted as user roles.This role is closely related to the users’social background,occupation,and living habits.This study makes four main contributions to the literature.First,user feature models from different views for each user are constructed from the analysis of the check-in data.Second,the K-means algorithm is used to discover user roles from user features.Third,a reinforcement learning algorithm is proposed to strengthen the clustering effect of user roles and improve the stability of the clustering result.Finally,experiments are used to verify the validity of the method.The results show that the method can improve the effect of clustering by 1.5∼2 times,and improve the stability of the cluster results about 2∼3 times of the original.This method is the first time to apply reinforcement learning to the optimization of user roles in mobile applications,which enhances the clustering effect and improves the stability of the automatic method when discovering user roles. | Yuanbang Li Wengang Zhou Chi Xu Yuchun Shi | 2022 | Computer Modeling in Engineering & Sciences2022，，6： | 0 |
| 17 | Highly Enantioselective Reactions of Cyclohexanone and β,γ-Unsaturated α-Keto Ester: The Tuning of Chemoselectivities by Secondary and Primary Amine Catalysts显示文摘A series of of amphiphilic imidazole based secondary and primary amine catalysts were synthesized and shown to be very effective with an acid cocatalyst for the asymmetric reaction of cyclohexanone to β,γ-unsaturated α-keto ester.Interestingly,primary and secondary amine catalysts show different regio-selectivities in this reaction.Under the catalysis of secondary amine 1,excellent enantioselectivities were observed for the products from direct 3+3 reactions of cyclohexanone withβ,γ-unsaturated α-keto esters using water as the solvent.Moreover,the same reactants catalyzed by the primary amines 2 lead to the aldol reactions,affording the corresponding products with high diastereoselectivities and up to 97%ee.Theoretical studies on the transition states by using a model in gas phase revealed that steric effect plays an important role on different chemo-selective induction between the secondary amine 1 and primary amine 2. | Jianwei Wei Wengang Guo Xin Zhou Xin Du Yan Liu Can Li | 2014 | Chinese Journal of Chemistry2014，32，10： | 0 |
| 18 | Characterization of nanoparticle mixed 316L powder for additive manufacturing显示文摘Nanoparticles reinforced steels have many advantaged mechanical properties.Additive manufacturing offers a new method for fabricating nanoparticles reinforced high performance metal components.In this work,we report the application of low energy ball milling in mixing nanoparticles and micron 316 L powder.With this method,0.3 and 1.0 wt% Y2 O3 nanoparticles can be uniformly distributed on the surface of 316 L powder with the parameters of ball-to-powder ratio at 1:1,speed at 90 rpm and 7 h of mixing.The matrix 316 L powders remain spherical in shape after the mixing process.In the meantime,the effect of low energy ball milling and the addition of Y2 O3 nanoparticles on the powder characteristics(flowability,apparent density and tap density) are also studied.Results show that the process of low energy ball milling itself can slightly decrease the flowability and apparent density of the 316 L powder.The addition of 0.3 and 1.0 wt% Y2 O3 nanoparticles can also decrease the flowability,the tap density and the apparent density compared with the original 316 L powder.All of these changes result from the rough surface of the mixed powder produced by ball milling and the addition of Y2 O3 nanoparticles.The powder’s rough surface can increase the coefficient of friction of powders.The mixture of 316 L powder and Y2 O3 nanoparticles can be successfully used for selective laser melting(SLM).The relative density of SLM 316 L-Y2 O3 is measured at 99.5%.However,Y2 O3 agglomerations were observed which is due to the poor wettability between 316 L and Y2 O3. | Wengang Zhai Wei Zhou Sharon Mui Ling Nai Jun Wei | 2020 | Journal of Materials Science & Technology2020，47，12： | 0 |
| 19 | Synthesis of Fluorene Derivatives Via TfOH-catalyzed Intramolecular Friedel-Crafts Alkylation Reactions显示文摘We devoloped an efficient and simple method to synthesize fluorene derivatives via intramolecular Friedel-Crafts alkylation of chalcones.The transform is catalyzed by TfOH in CH_(3)NO_(2)at 80℃and the yield is up to 99%. | ZHOU Ziyang YI Ying ZHANG Fanglin XU Wengang LU Zhi LUO Tian | 2023 | Journal of Wuhan University of Technology(Materials Science)2023，38，5： | 0 |
| 20 | Multi-Agent Hierarchical Graph Attention Reinforcement Learning for Grid-Aware Energy Management显示文摘The increasing adoption of renewable energy has posed challenges for voltage regulation in power distribution networks.Gridaware energy management,which includes the control of smart inverters and energy management systems,is a trending way to mitigate this problem.However,existing multi-agent reinforcement learning methods for grid-aware energy management have not sufficiently considered the importance of agent cooperation and the unique characteristics of the grid,which leads to limited performance.In this study,we propose a new approach named multi-agent hierarchical graph attention reinforcement learning framework(MAHGA)to stabilize the voltage.Specifically,under the paradigm of centralized training and decentralized execution,we model the power distribution network as a novel hierarchical graph containing the agent-level topology and the bus-level topology.Then a hierarchical graph attention model is devised to capture the complex correlation between agents.Moreover,we incorporate graph contrastive learning as an auxiliary task in the reinforcement learning process to improve representation learning from graphs.Experiments on several real-world scenarios reveal that our approach achieves the best performance and can reduce the number of voltage violations remarkably. | FENG Bingyi FENG Mingxiao WANG Minrui ZHOU Wengang LI Houqiang | 2023 | ZTE Communications2023，21，3： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员