Accurate forecasting of renewable power generation is crucial for grid stability and cost efficiency.Feature se-lection in AI-based forecasting remains challenging due to high data acquisition cost,lack of transparenc...Accurate forecasting of renewable power generation is crucial for grid stability and cost efficiency.Feature se-lection in AI-based forecasting remains challenging due to high data acquisition cost,lack of transparency,and limited user control.We introduce a transparent and cost-sensitive feature selection framework for renewable power forecasting that leverages Explainable Artificial Intelligence(XAI).We integrate SHapley Additive ex-Planations(SHAP)and Explain Like I’m 5(ELI5)to identify dominant and redundant features.This approach enables systematic dataset reduction without compromising model performance.Our case study,based on Photovoltaic(PV)generation data,evaluates the approach across four experimental setups.Experimental results indicate that our XAI-based feature selection reduces the dominance index from 0.37 to 0.17,maintains high predictive accuracy(R^(2)=0.94,drop<0.04),and lowers data acquisition costs.Furthermore,eliminating dominant features improves robustness to noise and reduces performance variance by a factor of three compared to the baseline scenario.The developed framework enhances interpretability,supports human-in-the-loop de-cisionmaking,and introduces a cost-sensitive objective function for feature selection.By combining trans-parency,robustness,and efficiency,we contribute to the development and implementation of Trustworthy AI(TAI)applications in energy forecasting,providing a scalable solution for industrial deployment.展开更多
Novel porous aromatic frameworks（PAF-53 and PAF-54） have been obtained by the polymerization of amino compound（p-phenylenediamine and melamine） and cyanuric chloride. They display a certain amount of CO2 adsorptio...Novel porous aromatic frameworks（PAF-53 and PAF-54） have been obtained by the polymerization of amino compound（p-phenylenediamine and melamine） and cyanuric chloride. They display a certain amount of CO2 adsorption capacity and highly selective separation of CO2/CH4 and CO2/N2 as 18.1 and83 by Henry Law respectively. They may be applied as ideal adsorbents to separate and capture CO2.展开更多
Software defect feature selection has problems of feature space dimensionality reduction and large search space.This research proposes a defect prediction feature selection framework based on improved shuffled frog le...Software defect feature selection has problems of feature space dimensionality reduction and large search space.This research proposes a defect prediction feature selection framework based on improved shuffled frog leaping algorithm(ISFLA).Using the two-level structure of the framework and the improved hybrid leapfrog algorithm's own advantages,the feature values are sorted,and some features with high correlation are selected to avoid other heuristic algorithms in the defect prediction that are easy to produce local The case where the convergence rate of the optimal or parameter optimization process is relatively slow.The framework improves generalization of predictions of unknown data samples and enhances the ability to search for features related to learning tasks.At the same time,this framework further reduces the dimension of the feature space.After the contrast simulation experiment with other common defect prediction methods,we used the actual test data set to verify the framework for multiple iterations on Internet of Things(IoT)system platform.The experimental results show that the software defect prediction feature selection framework based on ISFLA is very effective in defect prediction of IoT communication software.This framework can save the testing time of IoT communication software,effectively improve the performance of software defect prediction,and ensure the software quality.展开更多
Alkane isomers(mainly C5-C7 alkanes),produced via catalytic isomerization reactions during oil refinement,are important raw chemicals in the petrochemical industry[1].They are used in a broad spectrum of chemical proc...Alkane isomers(mainly C5-C7 alkanes),produced via catalytic isomerization reactions during oil refinement,are important raw chemicals in the petrochemical industry[1].They are used in a broad spectrum of chemical processes,depending on their branching.Specifically,normal alkanes and monobranched isomers are premium ethylene feed,and dibranched isomers are desired components for high-rating gasolines[2].Consequently,the isomers must be separated before further use.展开更多
文摘Accurate forecasting of renewable power generation is crucial for grid stability and cost efficiency.Feature se-lection in AI-based forecasting remains challenging due to high data acquisition cost,lack of transparency,and limited user control.We introduce a transparent and cost-sensitive feature selection framework for renewable power forecasting that leverages Explainable Artificial Intelligence(XAI).We integrate SHapley Additive ex-Planations(SHAP)and Explain Like I’m 5(ELI5)to identify dominant and redundant features.This approach enables systematic dataset reduction without compromising model performance.Our case study,based on Photovoltaic(PV)generation data,evaluates the approach across four experimental setups.Experimental results indicate that our XAI-based feature selection reduces the dominance index from 0.37 to 0.17,maintains high predictive accuracy(R^(2)=0.94,drop<0.04),and lowers data acquisition costs.Furthermore,eliminating dominant features improves robustness to noise and reduces performance variance by a factor of three compared to the baseline scenario.The developed framework enhances interpretability,supports human-in-the-loop de-cisionmaking,and introduces a cost-sensitive objective function for feature selection.By combining trans-parency,robustness,and efficiency,we contribute to the development and implementation of Trustworthy AI(TAI)applications in energy forecasting,providing a scalable solution for industrial deployment.
基金support of the National Natural Science Foundation of China(No.0831002)Major International (Regional) Joint Research Project(No.21120102034)
文摘Novel porous aromatic frameworks（PAF-53 and PAF-54） have been obtained by the polymerization of amino compound（p-phenylenediamine and melamine） and cyanuric chloride. They display a certain amount of CO2 adsorption capacity and highly selective separation of CO2/CH4 and CO2/N2 as 18.1 and83 by Henry Law respectively. They may be applied as ideal adsorbents to separate and capture CO2.
基金This work was supported by Liaoning Natural Fund Guidance Plan Project(No.20180550021)Dalian Science and Technology Star Project(No.2017RQ021)2019 Qingdao Binhai University-level Science and Technology Plan Research Project(No.2019KY09).
文摘Software defect feature selection has problems of feature space dimensionality reduction and large search space.This research proposes a defect prediction feature selection framework based on improved shuffled frog leaping algorithm(ISFLA).Using the two-level structure of the framework and the improved hybrid leapfrog algorithm's own advantages,the feature values are sorted,and some features with high correlation are selected to avoid other heuristic algorithms in the defect prediction that are easy to produce local The case where the convergence rate of the optimal or parameter optimization process is relatively slow.The framework improves generalization of predictions of unknown data samples and enhances the ability to search for features related to learning tasks.At the same time,this framework further reduces the dimension of the feature space.After the contrast simulation experiment with other common defect prediction methods,we used the actual test data set to verify the framework for multiple iterations on Internet of Things(IoT)system platform.The experimental results show that the software defect prediction feature selection framework based on ISFLA is very effective in defect prediction of IoT communication software.This framework can save the testing time of IoT communication software,effectively improve the performance of software defect prediction,and ensure the software quality.
基金supported by the Key Program of National Natural Science Foundation of China(22438001)the National Natural Science Foundation of China(22478251,52373212)+1 种基金the Shenzhen Science and Technology Program(KCXFZ20211020163818026)the Shenzhen Polytechnic University Research Fund(6024310024K)。
文摘Alkane isomers(mainly C5-C7 alkanes),produced via catalytic isomerization reactions during oil refinement,are important raw chemicals in the petrochemical industry[1].They are used in a broad spectrum of chemical processes,depending on their branching.Specifically,normal alkanes and monobranched isomers are premium ethylene feed,and dibranched isomers are desired components for high-rating gasolines[2].Consequently,the isomers must be separated before further use.
