Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles,surface radiation balance,weather and climate changes,and vegetation photosynthesis.Accurate solar radiation pred...Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles,surface radiation balance,weather and climate changes,and vegetation photosynthesis.Accurate solar radiation prediction is of paramount importance for both climate research and the solar industry.This prediction includes forecasting techniques and advanced modeling to evaluate the amount of solar energy available at a specific location during a given period.Solar energy is the cheapest form of clean energy,and due to the intermittent nature of the energy,accurate forecasting across multiple timeframes is necessary for efficient generation and demand management.Solar radiation prediction using deep learning(DL)includes the applications of neural network methods,namely Convolutional Neural Network(CNN)or Long Short-Term Memory(LSTM)models,to forecast and model solar irradiance patterns.By leveraging meteorological variables and historical solar radiation data,DL algorithms can capture complex spatial and temporal dependencies,resulting in accurate predictions.This article presents a novel Solar Radiation Prediction model utilizing a Boosted Coyote Optimization Algorithm with Deep Learning(SRP-BCOADL).The SRP-BCOADL model initially normalizes the input data using a min-max normalization approach to improve the robust nature under different scales.Besides,the SRP-BCOADL technique uses a Deep Long Short-Term Memory Autoencoder(DLSTM-AE)system for precisely forecasting solar radiation levels.The model’s accuracy is further improved through hyperparameter optimization using the BCOA.The performance analysis of the SRP-BCOADL technique is tested using solar radiation data.Extensive experimental outcomes prove that the SRP-BCOADL method obtains better results over other techniques.The Mean Squared Error(MSE)is just 0.13 kWh/m^(2),is much lower when compared to other models.The Root Mean Squared Error(RMSE)is also reduced to 0.36 kWh/m^(2),and the Mean Absolute Error(MAE)reaches a minimal level of 0.276 kWh/m^(2).展开更多
Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern clas...Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern classification include directly learning the image through a convolution neural network and applying the ensemble method after extracting image features.This study aims to classify wafer map defects more effectively and derive robust algorithms even for datasets with insufficient defect patterns.First,the number of defects during the actual process may be limited.Therefore,insufficient data are generated using convolutional auto-encoder(CAE),and the expanded data are verified using the evaluation technique of structural similarity index measure(SSIM).After extracting handcrafted features,a boosted stacking ensemble model that integrates the four base-level classifiers with the extreme gradient boosting classifier as a meta-level classifier is designed and built for training the model based on the expanded data for final prediction.Since the proposed algorithm shows better performance than those of existing ensemble classifiers even for insufficient defect patterns,the results of this study will contribute to improving the product quality and yield of the actual semiconductor manufacturing process.展开更多
We present a study about the flavor changing coupling of the top quark with the Higgs boson through the channe■at LHC.The final states considered for the such process are■.We focus on the boosted region in the phase...We present a study about the flavor changing coupling of the top quark with the Higgs boson through the channe■at LHC.The final states considered for the such process are■.We focus on the boosted region in the phase space of the Higgs boson.The backgrounds and events are simulated and analyzed.The sensitivities for the FCNH couplings are estimated.It is found that it is more sensitive for ytu than ytq at LHC.The upper limits of the FCNH couplings can be set at LHC with 3000 fb-1integrated luminosity as■95%C.L.展开更多
Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Re...Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address Big Data challenges to drive decision making. The challenge of this study is lack of interoperability since the data, a collection of GIS shapefiles, remotely sensed imagery, and aggregated and interpolated spatio-temporal information, are stored in monolithic hardware components. For the modelling process, it was necessary to create one common input file. By merging the data sources together, a structured but noisy input file, showing inconsistencies and redundancies, was created. Here, it is shown that BRT can process different data granularities, heterogeneous data and missingness. In particular, BRT has the advantage of dealing with missing data by default by allowing a split on whether or not a value is missing as well as what the value is. Most importantly, the BRT offers a wide range of possibilities regarding the interpretation of results and variable selection is automatically performed by considering how frequently a variable is used to define a split in the tree. A comparison with two similar regression models (Random Forests and Least Absolute Shrinkage and Selection Operator, LASSO) shows that BRT outperforms these in this instance. BRT can also be a starting point for sophisticated hierarchical modelling in real world scenarios. For example, a single or ensemble approach of BRT could be tested with existing models in order to improve results for a wide range of data-driven decisions and applications.展开更多
This study introduces and evaluates a novel artificial hummingbird algorithm-optimised boosted tree(AHAboosted)model for predicting the dynamic modulus(E*)of hot mix asphalt concrete.Using a substantial dataset from N...This study introduces and evaluates a novel artificial hummingbird algorithm-optimised boosted tree(AHAboosted)model for predicting the dynamic modulus(E*)of hot mix asphalt concrete.Using a substantial dataset from NCHRP Report-547,the model was trained and rigorously tested.Performance metrics,specifically RMSE,MAE,and R2,were employed to assess the model's predictive accuracy,robustness,and generalisability.When benchmarked against well-established models like support vector machines(SVM)and gaussian process regression(GPR),the AHA-boosted model demonstrated enhanced performance.It achieved R2 values of 0.997 in training and 0.974 in testing,using the traditional Witczak NCHRP 1-40D model inputs.Incorporating features such as test temperature,frequency,and asphalt content led to a 1.23%increase in the test R2,signifying an improvement in the model's accuracy.The study also explored feature importance and sensitivity through SHAP and permutation importance plots,highlighting binder complex modulus|G*|as a key predictor.Although the AHA-boosted model shows promise,a slight decrease in R2 from training to testing indicates a need for further validation.Overall,this study confirms the AHA-boosted model as a highly accurate and robust tool for predicting the dynamic modulus of hot mix asphalt concrete,making it a valuable asset for pavement engineering.展开更多
This paper presents new trading models for the stock market and test whether they are able to consistently generate excess returns from the Singapore Exchange (SGX). Instead of conventional ways of modeling stock pric...This paper presents new trading models for the stock market and test whether they are able to consistently generate excess returns from the Singapore Exchange (SGX). Instead of conventional ways of modeling stock prices, we construct models which relate the market indicators to a trading decision directly. Furthermore, unlike a reversal trading system or a binary system of buy and sell, we allow three modes of trades, namely, buy, sell or stand by, and the stand-by case is important as it caters to the market conditions where a model does not produce a strong signal of buy or sell. Linear trading models are firstly developed with the scoring technique which weights higher on successful indicators, as well as with the Least Squares technique which tries to match the past perfect trades with its weights. The linear models are then made adaptive by using the forgetting factor to address market changes. Because stock markets could be highly nonlinear sometimes, the Random Forest is adopted as a nonlinear trading model, and improved with Gradient Boosting to form a new technique—Gradient Boosted Random Forest. All the models are trained and evaluated on nine stocks and one index, and statistical tests such as randomness, linear and nonlinear correlations are conducted on the data to check the statistical significance of the inputs and their relation with the output before a model is trained. Our empirical results show that the proposed trading methods are able to generate excess returns compared with the buy-and-hold strategy.展开更多
Mobile Ad Hoc Network(MANET)is an infrastructure-less network that is comprised of a set of nodes that move randomly.In MANET,the overall performance is improved through multipath multicast routing to achieve the qual...Mobile Ad Hoc Network(MANET)is an infrastructure-less network that is comprised of a set of nodes that move randomly.In MANET,the overall performance is improved through multipath multicast routing to achieve the quality of service(quality of service).In this,different nodes are involved in the information data collection and transmission to the destination nodes in the network.The different nodes are combined and presented to achieve energy-efficient data transmission and classification of the nodes.The route identification and routing are established based on the data broadcast by the network nodes.In transmitting the data packet,evaluating the data delivery ratio is necessary to achieve optimal data transmission in the network.Furthermore,energy consumption and overhead are considered essential factors for the effective data transmission rate and better data delivery rate.In this paper,a Gradient-Based Energy Optimization model(GBEOM)for the route in MANET is proposed to achieve an improved data delivery rate.Initially,the Weighted Multi-objective Cluster-based Spider Monkey Load Balancing(WMC-SMLB)technique is utilized for obtaining energy efficiency and load balancing routing.The WMC algorithm is applied to perform an efficient node clustering process from the considered mobile nodes in MANET.Load balancing efficiency is improved with a higher data delivery ratio and minimum routing overhead based on the residual energy and bandwidth estimation.Next,the Gradient Boosted Multinomial ID3 Classification algorithm is applied to improve the performance of multipath multicast routing in MANET with minimal energy consumption and higher load balancing efficiency.The proposed GBEOM exhibits∼4%improved performance in MANET routing.展开更多
Dry streams filled with sand,and sun-baked soil and drought resistant mopane trees characterize vast expanse of land in the rural Chiredzi District,more than 600 km southeast of Zimbabwe’s capital Harare.Topless and ...Dry streams filled with sand,and sun-baked soil and drought resistant mopane trees characterize vast expanse of land in the rural Chiredzi District,more than 600 km southeast of Zimbabwe’s capital Harare.Topless and barefooted children make a beeline waving at modern non-governmental organization vehicles which frequent the district.展开更多
Introducing a metal sulfide-based co-catalyst is an effective strategy to substantially enhance the Fenton reaction.Manipulation of the co-catalyst’s structure is expected to further boost the co-catalytic capability...Introducing a metal sulfide-based co-catalyst is an effective strategy to substantially enhance the Fenton reaction.Manipulation of the co-catalyst’s structure is expected to further boost the co-catalytic capability.Herein,we demonstrate that the intrinsic high-defect surface of a natural molybdenite material contributes to the enhancement of catalytic performance of the Fenton reaction.The defective surface not only exposes more Mo(IV)active sites for rapid Fe^(3+)/Fe^(2+)conversion but also promotes cooperation with H_(2)O_(2)molecules for reactivation.This synergistic effect brings about enhanced reaction kinetics and boosts the decomposition of H_(2)O_(2),which causes the molybdenite co-catalytic system to display an efficient removal rate for various organic pollutants.This work unveils the defects’contribution for catalyzing the Fenton reaction and sheds light on the potential large-scale water treatment use cases for abundant high-defect molybdenite materials.展开更多
Constructing heterostructures could endow materials with exceptional properties in gas sensing applications owing to boosted interfacial charge transfer.The rational design and controllable synthesis of heterostructur...Constructing heterostructures could endow materials with exceptional properties in gas sensing applications owing to boosted interfacial charge transfer.The rational design and controllable synthesis of heterostructures with a high-quality interface,however,still remains a challenge.Herein,novel Sn atom cosharing SnO_(2)/SnSe_(2) heterostructures with an intimate-contact interface and tunable composition were fabricated via a facile in situ oxidation method.An efficient increase in charge transfer can be achieved at the heterointerface through density functional theory calculations.The gas sensor based on SnO_(2)/SnSe_(2) exhibited an ultrahigh response toward 10 ppm H_(2)S at room temperature (resistance ratio = 32),roughly 4.5 and 16 times higher than that of pure SnO_(2) and SnSe_(2),respectively.Moreover,the sensor exhibited an ultralow detection limit of 10 ppb,superior sensing selectivity,and reliable long-term stability.This enhancement is primarily attributed to the numerous n–n heterojunctions,the boosted interfacial charge transfer,and the increased active sites of SnO_(2)/SnSe_(2) heterostructures.The obtained results prove that SnO_(2)/SnSe_(2) is a promising candidate material for room-temperature H_(2)S gas sensing and offer guidance for rational material design to develop heterostructure-based sensors.展开更多
Transition metal chalcogenides(TMCs)are extensively employed as cathode materials for rechargeable aluminum batteries(RABs)due to their high theoretical specific capacity and voltage plateau.Although promising,practic...Transition metal chalcogenides(TMCs)are extensively employed as cathode materials for rechargeable aluminum batteries(RABs)due to their high theoretical specific capacity and voltage plateau.Although promising,practical applications are hindered by challenges such as inferior structural stability,slow reaction kinetics,and inadequate electronic conductivity.Herein,Mn-ion doping engineering and g-C_(3)N_(4) etched porous carbon frameworks(Mn-ZnSe@CNPC)were integrated to synergistically enhance the electrochemical properties of ZnSe.Through modulating the d-and p-band centers and regulating electronic interactions,Mn-ion doping enhances adsorption for solvent groups and reduces electron transfer energy barriers,resulting in Mn-ZnSe@CNPC cathodes with high redox activity and fast reaction kinetics.In addition,the porous carbon nanocages act as support frameworks,preventing the agglomeration of ZnSe nanoparticles and providing ample ion transport channels,thus addressing issues related to poor cyclability and slow electrochemical kinetics in RABs.Benefiting from the d–p orbital modulation strategy and structural advantages,the tailored Mn-ZnSe@CNPC cathode exhibits boosted electrochemical performance and excellent stability.展开更多
Anomaly detection is crucial for data-driven applications in integrated energy systems.Traditional anomaly detection methods primarily focus on one single energy load,often neglecting potential spatial correlations be...Anomaly detection is crucial for data-driven applications in integrated energy systems.Traditional anomaly detection methods primarily focus on one single energy load,often neglecting potential spatial correlations between multivariate energy time series.Meanwhile,addressing the imbalanced nature of user-level multi-en-ergy load data remains a significant challenge.In this paper,we propose EGBAD,an Ensemble Graph-Boosted Anomaly Detection framework for user-level multi-energy load that leverages the advantages of graph relational analysis and ensemble learning.First,a dynamic graph construction method based on multidimensional scaling(MDS)is proposed to transform multi-energy load data into graph representations.These graphs are subse-quently processed using graph convolutional network(GCN)to capture the spatiotemporal correlations between multi-energy load time series.In addition,to improve detection robustness under class imbalance,the entire training process is embedded within a Boosting ensemble learning framework,where the weight assigned to the minority class is progressively increased at each boosting stage.Experimental results on publicly real-world datasets demonstrate that the proposed model achieves superior anomaly detection accuracy compared to most baseline methods.Notably,it performs especially well in scenarios characterized by extreme data imbal-ance,achieving the highest recall and F1-score for anomaly detection.展开更多
Correction to:Signal Transduction and Targeted Therapy https://doi.org/10.1038/s41392-021-00474-x,published online 29 January 2021 In the process of collating the raw data,the authors noticed an inadvertent mistakes o...Correction to:Signal Transduction and Targeted Therapy https://doi.org/10.1038/s41392-021-00474-x,published online 29 January 2021 In the process of collating the raw data,the authors noticed an inadvertent mistakes occurred in Supplementary Fig.11c that need to be corrected after online publication of the article.1 Due to our negligence in extracting and processing a large amount of experimental data,duplicate images were inadvertently used for the MPTP group and the MPTP+lovastatin group of mice with dopaminergic neurons deficient in SHP2(SHP2TH-/-).The correct data are provided as follows.The keyfindings of the article are not affected by these corrections.展开更多
针对Boost变换器存在多种干扰和电子元件具有非整数阶特性的问题,提出了一种分数阶PID(fractional order PID,FOPID)电压外环-分数阶滑模控制器(fractional order sliding mode control,FOSMC)电流内环双闭环控制系统。首先,利用Oustal...针对Boost变换器存在多种干扰和电子元件具有非整数阶特性的问题,提出了一种分数阶PID(fractional order PID,FOPID)电压外环-分数阶滑模控制器(fractional order sliding mode control,FOSMC)电流内环双闭环控制系统。首先,利用Oustaloup算法对电感和电容进行7阶拟合,得到分数阶电路模型;其次,设计了微积分阶次可调的FOPID,并将其作为电压外环的控制器;然后,设计扩张状态观测器(extended state observer,ESO)对系统状态、负载扰动和输入扰动进行估计;最后,基于ESO的估计值,用FOPID作为滑模面构建了FOSMC。结果表明,与其他控制算法相比,FOPID-FOSMC双闭环控制策略结合了电压外环的稳态调节能力和电流内环的快速响应能力,实现了对Boost变换器输出电压和电流的双重优化控制,具有更快的响应速度、更小的超调量、更短的恢复时间和更好的稳定性与鲁棒性。展开更多
为了进一步解决基于电容-二极管(capacitance-diode,CD)升压单元的两相交错并联Boost高增益变换器存在的开关管数量多、输入输出不共地问题,提出了一种基于CD单元的新型3L型两相交错并联Boost变换器拓扑的构建方法,并根据在第3个升压电...为了进一步解决基于电容-二极管(capacitance-diode,CD)升压单元的两相交错并联Boost高增益变换器存在的开关管数量多、输入输出不共地问题,提出了一种基于CD单元的新型3L型两相交错并联Boost变换器拓扑的构建方法,并根据在第3个升压电感前级和后级引入CD单元数量的不同,推演出基于FN-BMCD单元的3L型高增益Boost变换器的演化规律;以F2-B1CD单元的3L型Boost变换器为例,详细分析了5个开关模态的工作原理,揭示了各电感及电容寄生参数对电压增益的影响机理;搭建由数字信号处理(digital signal processing,DSP)芯片和实时仿真机组成的控制在环半实物仿真实验平台,验证了所提新型变换器拓扑理论分析的正确性。展开更多
精确评估电池的荷电状态(state of charge,SOC)是实现高效储能电池管理的前提。当前利用阻抗估计电池SOC多基于非原位电化学阻抗谱,由于此技术要求充分的静置时间,使得通过阻抗动态估计电池SOC困难。考虑到储能电站的实际运行情况,实时...精确评估电池的荷电状态(state of charge,SOC)是实现高效储能电池管理的前提。当前利用阻抗估计电池SOC多基于非原位电化学阻抗谱,由于此技术要求充分的静置时间,使得通过阻抗动态估计电池SOC困难。考虑到储能电站的实际运行情况,实时快速地获取阻抗数据成为关键。然而工况下受到直流偏置影响,电池电压的非线性变化会导致中低频阻抗产生偏移,影响阻抗测量准确性。针对以上问题,该研究采用离散间隔二进制序列设计了一种动态电化学阻抗谱测量方法,结合电池充放电工况下的阻抗特性,引入Categorical Boosting算法构建了电池SOC估计模型。针对4块商用18650锂电池,在不同温度和充放电倍率下每隔1%SOC重复测量了电池在充放电过程中的动态阻抗。实验结果表明,在不同实验条件下,电池充放电工况下SOC估计的最大平均绝对误差和均方根误差分别为2.98%和3.59%,证明了所提方法的可靠性和鲁棒性。展开更多
基金funded by the Deanship of Scientific Research and Libraries,Princess Nourah Bint Abdulrahman University,through the Program of Research Project Funding after Publication,grant No.(RPFAP-79-1445).
文摘Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles,surface radiation balance,weather and climate changes,and vegetation photosynthesis.Accurate solar radiation prediction is of paramount importance for both climate research and the solar industry.This prediction includes forecasting techniques and advanced modeling to evaluate the amount of solar energy available at a specific location during a given period.Solar energy is the cheapest form of clean energy,and due to the intermittent nature of the energy,accurate forecasting across multiple timeframes is necessary for efficient generation and demand management.Solar radiation prediction using deep learning(DL)includes the applications of neural network methods,namely Convolutional Neural Network(CNN)or Long Short-Term Memory(LSTM)models,to forecast and model solar irradiance patterns.By leveraging meteorological variables and historical solar radiation data,DL algorithms can capture complex spatial and temporal dependencies,resulting in accurate predictions.This article presents a novel Solar Radiation Prediction model utilizing a Boosted Coyote Optimization Algorithm with Deep Learning(SRP-BCOADL).The SRP-BCOADL model initially normalizes the input data using a min-max normalization approach to improve the robust nature under different scales.Besides,the SRP-BCOADL technique uses a Deep Long Short-Term Memory Autoencoder(DLSTM-AE)system for precisely forecasting solar radiation levels.The model’s accuracy is further improved through hyperparameter optimization using the BCOA.The performance analysis of the SRP-BCOADL technique is tested using solar radiation data.Extensive experimental outcomes prove that the SRP-BCOADL method obtains better results over other techniques.The Mean Squared Error(MSE)is just 0.13 kWh/m^(2),is much lower when compared to other models.The Root Mean Squared Error(RMSE)is also reduced to 0.36 kWh/m^(2),and the Mean Absolute Error(MAE)reaches a minimal level of 0.276 kWh/m^(2).
基金the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.NRF-2021R1A5A8033165)the“Human Resources Program in Energy Technology”of the Korea Institute of Energy Technology Evaluation and Planning(KETEP)and was granted financial resources from the Ministry of Trade,Industry&Energy,Republic of Korea(No.20214000000200).
文摘Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern classification include directly learning the image through a convolution neural network and applying the ensemble method after extracting image features.This study aims to classify wafer map defects more effectively and derive robust algorithms even for datasets with insufficient defect patterns.First,the number of defects during the actual process may be limited.Therefore,insufficient data are generated using convolutional auto-encoder(CAE),and the expanded data are verified using the evaluation technique of structural similarity index measure(SSIM).After extracting handcrafted features,a boosted stacking ensemble model that integrates the four base-level classifiers with the extreme gradient boosting classifier as a meta-level classifier is designed and built for training the model based on the expanded data for final prediction.Since the proposed algorithm shows better performance than those of existing ensemble classifiers even for insufficient defect patterns,the results of this study will contribute to improving the product quality and yield of the actual semiconductor manufacturing process.
基金Supported by the National Science Foundation of China under Grant No.11405095
文摘We present a study about the flavor changing coupling of the top quark with the Higgs boson through the channe■at LHC.The final states considered for the such process are■.We focus on the boosted region in the phase space of the Higgs boson.The backgrounds and events are simulated and analyzed.The sensitivities for the FCNH couplings are estimated.It is found that it is more sensitive for ytu than ytq at LHC.The upper limits of the FCNH couplings can be set at LHC with 3000 fb-1integrated luminosity as■95%C.L.
文摘Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address Big Data challenges to drive decision making. The challenge of this study is lack of interoperability since the data, a collection of GIS shapefiles, remotely sensed imagery, and aggregated and interpolated spatio-temporal information, are stored in monolithic hardware components. For the modelling process, it was necessary to create one common input file. By merging the data sources together, a structured but noisy input file, showing inconsistencies and redundancies, was created. Here, it is shown that BRT can process different data granularities, heterogeneous data and missingness. In particular, BRT has the advantage of dealing with missing data by default by allowing a split on whether or not a value is missing as well as what the value is. Most importantly, the BRT offers a wide range of possibilities regarding the interpretation of results and variable selection is automatically performed by considering how frequently a variable is used to define a split in the tree. A comparison with two similar regression models (Random Forests and Least Absolute Shrinkage and Selection Operator, LASSO) shows that BRT outperforms these in this instance. BRT can also be a starting point for sophisticated hierarchical modelling in real world scenarios. For example, a single or ensemble approach of BRT could be tested with existing models in order to improve results for a wide range of data-driven decisions and applications.
文摘This study introduces and evaluates a novel artificial hummingbird algorithm-optimised boosted tree(AHAboosted)model for predicting the dynamic modulus(E*)of hot mix asphalt concrete.Using a substantial dataset from NCHRP Report-547,the model was trained and rigorously tested.Performance metrics,specifically RMSE,MAE,and R2,were employed to assess the model's predictive accuracy,robustness,and generalisability.When benchmarked against well-established models like support vector machines(SVM)and gaussian process regression(GPR),the AHA-boosted model demonstrated enhanced performance.It achieved R2 values of 0.997 in training and 0.974 in testing,using the traditional Witczak NCHRP 1-40D model inputs.Incorporating features such as test temperature,frequency,and asphalt content led to a 1.23%increase in the test R2,signifying an improvement in the model's accuracy.The study also explored feature importance and sensitivity through SHAP and permutation importance plots,highlighting binder complex modulus|G*|as a key predictor.Although the AHA-boosted model shows promise,a slight decrease in R2 from training to testing indicates a need for further validation.Overall,this study confirms the AHA-boosted model as a highly accurate and robust tool for predicting the dynamic modulus of hot mix asphalt concrete,making it a valuable asset for pavement engineering.
文摘This paper presents new trading models for the stock market and test whether they are able to consistently generate excess returns from the Singapore Exchange (SGX). Instead of conventional ways of modeling stock prices, we construct models which relate the market indicators to a trading decision directly. Furthermore, unlike a reversal trading system or a binary system of buy and sell, we allow three modes of trades, namely, buy, sell or stand by, and the stand-by case is important as it caters to the market conditions where a model does not produce a strong signal of buy or sell. Linear trading models are firstly developed with the scoring technique which weights higher on successful indicators, as well as with the Least Squares technique which tries to match the past perfect trades with its weights. The linear models are then made adaptive by using the forgetting factor to address market changes. Because stock markets could be highly nonlinear sometimes, the Random Forest is adopted as a nonlinear trading model, and improved with Gradient Boosting to form a new technique—Gradient Boosted Random Forest. All the models are trained and evaluated on nine stocks and one index, and statistical tests such as randomness, linear and nonlinear correlations are conducted on the data to check the statistical significance of the inputs and their relation with the output before a model is trained. Our empirical results show that the proposed trading methods are able to generate excess returns compared with the buy-and-hold strategy.
基金Deanship of Scientific Research at Umm Al-Qura University,Grant Code,funds this research:22UQU4281768DSR08。
文摘Mobile Ad Hoc Network(MANET)is an infrastructure-less network that is comprised of a set of nodes that move randomly.In MANET,the overall performance is improved through multipath multicast routing to achieve the quality of service(quality of service).In this,different nodes are involved in the information data collection and transmission to the destination nodes in the network.The different nodes are combined and presented to achieve energy-efficient data transmission and classification of the nodes.The route identification and routing are established based on the data broadcast by the network nodes.In transmitting the data packet,evaluating the data delivery ratio is necessary to achieve optimal data transmission in the network.Furthermore,energy consumption and overhead are considered essential factors for the effective data transmission rate and better data delivery rate.In this paper,a Gradient-Based Energy Optimization model(GBEOM)for the route in MANET is proposed to achieve an improved data delivery rate.Initially,the Weighted Multi-objective Cluster-based Spider Monkey Load Balancing(WMC-SMLB)technique is utilized for obtaining energy efficiency and load balancing routing.The WMC algorithm is applied to perform an efficient node clustering process from the considered mobile nodes in MANET.Load balancing efficiency is improved with a higher data delivery ratio and minimum routing overhead based on the residual energy and bandwidth estimation.Next,the Gradient Boosted Multinomial ID3 Classification algorithm is applied to improve the performance of multipath multicast routing in MANET with minimal energy consumption and higher load balancing efficiency.The proposed GBEOM exhibits∼4%improved performance in MANET routing.
文摘Dry streams filled with sand,and sun-baked soil and drought resistant mopane trees characterize vast expanse of land in the rural Chiredzi District,more than 600 km southeast of Zimbabwe’s capital Harare.Topless and barefooted children make a beeline waving at modern non-governmental organization vehicles which frequent the district.
基金supported by the National Key Research and Development Program of China(2019YFC0408300,2019YFC0408303,and 2019YFC0408305)the National 111 Project(B14034)+3 种基金Collaborative Innovation Center for Clean and Efficient Utilization of Strategic Metal Mineral Resources,State Key Laboratory of Mineral Processing(BGRIMM-KJSKL-2017-13)Fundamental Research Funds for the Central Universities of Central South University.J.C.acknowledges the support from the National Natural Science Foundation of China(51901147)Collaborative Innovation Center of Suzhou Nano Science,Technology(NANO-CIC)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD).
文摘Introducing a metal sulfide-based co-catalyst is an effective strategy to substantially enhance the Fenton reaction.Manipulation of the co-catalyst’s structure is expected to further boost the co-catalytic capability.Herein,we demonstrate that the intrinsic high-defect surface of a natural molybdenite material contributes to the enhancement of catalytic performance of the Fenton reaction.The defective surface not only exposes more Mo(IV)active sites for rapid Fe^(3+)/Fe^(2+)conversion but also promotes cooperation with H_(2)O_(2)molecules for reactivation.This synergistic effect brings about enhanced reaction kinetics and boosts the decomposition of H_(2)O_(2),which causes the molybdenite co-catalytic system to display an efficient removal rate for various organic pollutants.This work unveils the defects’contribution for catalyzing the Fenton reaction and sheds light on the potential large-scale water treatment use cases for abundant high-defect molybdenite materials.
基金supported by The National Key Research and Development Program of China(2019YFA0705200)the National Natural Science Foundation of China(No.52072093,51802058,and 11504040)+1 种基金the Applied Technology Research and Development Program of Heilongjiang Province(No.GY2018ZB0046)the China Postdoctoral Science Foundation funded project.
文摘Constructing heterostructures could endow materials with exceptional properties in gas sensing applications owing to boosted interfacial charge transfer.The rational design and controllable synthesis of heterostructures with a high-quality interface,however,still remains a challenge.Herein,novel Sn atom cosharing SnO_(2)/SnSe_(2) heterostructures with an intimate-contact interface and tunable composition were fabricated via a facile in situ oxidation method.An efficient increase in charge transfer can be achieved at the heterointerface through density functional theory calculations.The gas sensor based on SnO_(2)/SnSe_(2) exhibited an ultrahigh response toward 10 ppm H_(2)S at room temperature (resistance ratio = 32),roughly 4.5 and 16 times higher than that of pure SnO_(2) and SnSe_(2),respectively.Moreover,the sensor exhibited an ultralow detection limit of 10 ppb,superior sensing selectivity,and reliable long-term stability.This enhancement is primarily attributed to the numerous n–n heterojunctions,the boosted interfacial charge transfer,and the increased active sites of SnO_(2)/SnSe_(2) heterostructures.The obtained results prove that SnO_(2)/SnSe_(2) is a promising candidate material for room-temperature H_(2)S gas sensing and offer guidance for rational material design to develop heterostructure-based sensors.
基金supported by the National Natural Science Foundation of China(No.51971118,51771102 and 52371114).
文摘Transition metal chalcogenides(TMCs)are extensively employed as cathode materials for rechargeable aluminum batteries(RABs)due to their high theoretical specific capacity and voltage plateau.Although promising,practical applications are hindered by challenges such as inferior structural stability,slow reaction kinetics,and inadequate electronic conductivity.Herein,Mn-ion doping engineering and g-C_(3)N_(4) etched porous carbon frameworks(Mn-ZnSe@CNPC)were integrated to synergistically enhance the electrochemical properties of ZnSe.Through modulating the d-and p-band centers and regulating electronic interactions,Mn-ion doping enhances adsorption for solvent groups and reduces electron transfer energy barriers,resulting in Mn-ZnSe@CNPC cathodes with high redox activity and fast reaction kinetics.In addition,the porous carbon nanocages act as support frameworks,preventing the agglomeration of ZnSe nanoparticles and providing ample ion transport channels,thus addressing issues related to poor cyclability and slow electrochemical kinetics in RABs.Benefiting from the d–p orbital modulation strategy and structural advantages,the tailored Mn-ZnSe@CNPC cathode exhibits boosted electrochemical performance and excellent stability.
基金supported by National Natural Science Foundation of China(U24B6010).
文摘Anomaly detection is crucial for data-driven applications in integrated energy systems.Traditional anomaly detection methods primarily focus on one single energy load,often neglecting potential spatial correlations between multivariate energy time series.Meanwhile,addressing the imbalanced nature of user-level multi-en-ergy load data remains a significant challenge.In this paper,we propose EGBAD,an Ensemble Graph-Boosted Anomaly Detection framework for user-level multi-energy load that leverages the advantages of graph relational analysis and ensemble learning.First,a dynamic graph construction method based on multidimensional scaling(MDS)is proposed to transform multi-energy load data into graph representations.These graphs are subse-quently processed using graph convolutional network(GCN)to capture the spatiotemporal correlations between multi-energy load time series.In addition,to improve detection robustness under class imbalance,the entire training process is embedded within a Boosting ensemble learning framework,where the weight assigned to the minority class is progressively increased at each boosting stage.Experimental results on publicly real-world datasets demonstrate that the proposed model achieves superior anomaly detection accuracy compared to most baseline methods.Notably,it performs especially well in scenarios characterized by extreme data imbal-ance,achieving the highest recall and F1-score for anomaly detection.
文摘Correction to:Signal Transduction and Targeted Therapy https://doi.org/10.1038/s41392-021-00474-x,published online 29 January 2021 In the process of collating the raw data,the authors noticed an inadvertent mistakes occurred in Supplementary Fig.11c that need to be corrected after online publication of the article.1 Due to our negligence in extracting and processing a large amount of experimental data,duplicate images were inadvertently used for the MPTP group and the MPTP+lovastatin group of mice with dopaminergic neurons deficient in SHP2(SHP2TH-/-).The correct data are provided as follows.The keyfindings of the article are not affected by these corrections.
文摘针对Boost变换器存在多种干扰和电子元件具有非整数阶特性的问题,提出了一种分数阶PID(fractional order PID,FOPID)电压外环-分数阶滑模控制器(fractional order sliding mode control,FOSMC)电流内环双闭环控制系统。首先,利用Oustaloup算法对电感和电容进行7阶拟合,得到分数阶电路模型;其次,设计了微积分阶次可调的FOPID,并将其作为电压外环的控制器;然后,设计扩张状态观测器(extended state observer,ESO)对系统状态、负载扰动和输入扰动进行估计;最后,基于ESO的估计值,用FOPID作为滑模面构建了FOSMC。结果表明,与其他控制算法相比,FOPID-FOSMC双闭环控制策略结合了电压外环的稳态调节能力和电流内环的快速响应能力,实现了对Boost变换器输出电压和电流的双重优化控制,具有更快的响应速度、更小的超调量、更短的恢复时间和更好的稳定性与鲁棒性。
文摘为了进一步解决基于电容-二极管(capacitance-diode,CD)升压单元的两相交错并联Boost高增益变换器存在的开关管数量多、输入输出不共地问题,提出了一种基于CD单元的新型3L型两相交错并联Boost变换器拓扑的构建方法,并根据在第3个升压电感前级和后级引入CD单元数量的不同,推演出基于FN-BMCD单元的3L型高增益Boost变换器的演化规律;以F2-B1CD单元的3L型Boost变换器为例,详细分析了5个开关模态的工作原理,揭示了各电感及电容寄生参数对电压增益的影响机理;搭建由数字信号处理(digital signal processing,DSP)芯片和实时仿真机组成的控制在环半实物仿真实验平台,验证了所提新型变换器拓扑理论分析的正确性。
文摘精确评估电池的荷电状态(state of charge,SOC)是实现高效储能电池管理的前提。当前利用阻抗估计电池SOC多基于非原位电化学阻抗谱,由于此技术要求充分的静置时间,使得通过阻抗动态估计电池SOC困难。考虑到储能电站的实际运行情况,实时快速地获取阻抗数据成为关键。然而工况下受到直流偏置影响,电池电压的非线性变化会导致中低频阻抗产生偏移,影响阻抗测量准确性。针对以上问题,该研究采用离散间隔二进制序列设计了一种动态电化学阻抗谱测量方法,结合电池充放电工况下的阻抗特性,引入Categorical Boosting算法构建了电池SOC估计模型。针对4块商用18650锂电池,在不同温度和充放电倍率下每隔1%SOC重复测量了电池在充放电过程中的动态阻抗。实验结果表明,在不同实验条件下,电池充放电工况下SOC估计的最大平均绝对误差和均方根误差分别为2.98%和3.59%,证明了所提方法的可靠性和鲁棒性。
