Fuzzy Shapley values are developed based on classical Shapley values and used to allocate profit among partners in virtual enterprises （VE）. Axioms of the classical Shapley value are extended to Shapley values with ...Fuzzy Shapley values are developed based on classical Shapley values and used to allocate profit among partners in virtual enterprises （VE）. Axioms of the classical Shapley value are extended to Shapley values with fuzzy payoffs by using fuzzy sets theory. Fuzzy Shapley function is defined based on these extended axioms. From the viewpoint the allocation for each partner should be a crisp value rather a fuzzy membership function at the end of cooperation, a crisp allocation scheme based on fuzzy Shapley values is proposed.展开更多
Opportunistic mobile crowdsensing(MCS)non-intrusively exploits human mobility trajectories,and the participants’smart devices as sensors have become promising paradigms for various urban data acquisition tasks.Howeve...Opportunistic mobile crowdsensing(MCS)non-intrusively exploits human mobility trajectories,and the participants’smart devices as sensors have become promising paradigms for various urban data acquisition tasks.However,in practice,opportunistic MCS has several challenges from both the perspectives of MCS participants and the data platform.On the one hand,participants face uncertainties in conducting MCS tasks,including their mobility and implicit interactions among participants,and participants’economic returns given by the MCS data platform are determined by not only their own actions but also other participants’strategic actions.On the other hand,the platform can only observe the participants’uploaded sensing data that depends on the unknown effort/action exerted by participants to the platform,while,for optimizing its overall objective,the platform needs to properly reward certain participants for incentivizing them to provide high-quality data.To address the challenge of balancing individual incentives and platform objectives in MCS,this paper proposes MARCS,an online sensing policy based on multi-agent deep reinforcement learning(MADRL)with centralized training and decentralized execution(CTDE).Specifically,the interactions between MCS participants and the data platform are modeled as a partially observable Markov game,where participants,acting as agents,use DRL-based policies to make decisions based on local observations,such as task trajectories and platform payments.To align individual and platform goals effectively,the platform leverages Shapley value to estimate the contribution of each participant’s sensed data,using these estimates as immediate rewards to guide agent training.The experimental results on real mobility trajectory datasets indicate that the revenue of MARCS reaches almost 35%,53%,and 100%higher than DDPG,Actor-Critic,and model predictive control(MPC)respectively on the participant side and similar results on the platform side,which show superior performance compared to baselines.展开更多
Under the current long-term electricity market mechanism,new energy and thermal power face issues such as deviation assessment and compression of generation space.The profitability of market players is limited.Simulta...Under the current long-term electricity market mechanism,new energy and thermal power face issues such as deviation assessment and compression of generation space.The profitability of market players is limited.Simultaneously,the cooperation model among various energy sources will have a direct impact on the alliance’s revenue and the equity of income distribution within the alliance.Therefore,integrating new energy with thermal power units into an integrated multi-energy complementary system to participate in the long-term electricity market holds significant potential.To simulate and evaluate the benefits and internal distribution methods of a multi-energy complementary system participating in long-term market transactions,this paper first constructs a multi-energy complementary system integrated with new energy and thermal power generation units at the same connection point,and participates in the annual bilateral game as a unified market entity to obtain the revenue value under the annual bilateral market.Secondly,based on the entropy weight method,improvements are made to the traditional Shapley value distribution model,and an internal distribution model for multi-energy complementary systems with multiple participants is constructed.Finally,a Markov Decision Process(MDP)evaluation system is constructed for practical case verification.The research results show that the improved Shapley value distribution model achieves higher satisfaction,providing a reasonable allocation scheme for multi-energy complementary cooperation models.展开更多
The Shapley value of fuzzy bi-eooperative game is developed based on the conventional Shapley value of bi-cooperative game. From the viewpoint that the players can participate in the coalitions to a certain extent and...The Shapley value of fuzzy bi-eooperative game is developed based on the conventional Shapley value of bi-cooperative game. From the viewpoint that the players can participate in the coalitions to a certain extent and there are at least two independent cooperative projects for every player to choose, Shapley value which is introduced by Grabisch is extended to the case of fuzzy bi-cooperative game by Choquet integral. Moreover, the explicit fuzzy Shapley value is given. The explicit fuzzy Shapley function can be used to allocate the profits among players in supply-chain under the competitive and uncertain environment.展开更多
Shapley value is one of the most fundamental concepts in cooperative games.This paper investigates the calculation of the Shapley value for cooperative games and establishes a new formula via carrier.Firstly,a necessa...Shapley value is one of the most fundamental concepts in cooperative games.This paper investigates the calculation of the Shapley value for cooperative games and establishes a new formula via carrier.Firstly,a necessary and sufficient condition is presented for the verification of carrier,based on which an algorithm is worked out to find the unique minimum carrier.Secondly,by virtue of the properties of minimum carrier,it is proved that the profit allocated to dummy players(players which do not belong to the minimum carrier)is zero,and the profit allocated to players in minimum carrier is only determined by the minimum carrier.Then,a new formula of the Shapley value is presented,which greatly reduces the computational complexity of the original formula,and shows that the Shapley value only depends on the minimum carrier.Finally,based on the semi-tensor product(STP)of matrices,the obtained new formula is converted into an equivalent algebraic form,which makes the new formula convenient for calculation via MATLAB.展开更多
Fuzzy Shapley values are developed based on conventional Shapley value. This kind of fuzzy cooperative games admit the representation of rates of players＇ participation to each coalition. And they can be applicable t...Fuzzy Shapley values are developed based on conventional Shapley value. This kind of fuzzy cooperative games admit the representation of rates of players＇ participation to each coalition. And they can be applicable to both supperadditive and subadditvie cooperative games while other kinds of fuzzy cooperative games can only be superadditive. An explicit form of the Shapley function on fuzzy games with λ-fuzzy measure was also proposed.展开更多
Under green supply chain mode, how to Carry out the distribution of profits between subjects is an important problem. Through the comparison of the green supply chain benefit allocation of non-cooperative game and coo...Under green supply chain mode, how to Carry out the distribution of profits between subjects is an important problem. Through the comparison of the green supply chain benefit allocation of non-cooperative game and cooperative game the payoffmatrix, it is clearly that the necessity of interest distribution cooperative game. Put general manufacturing enterprises of green supply chain as the research object, using Shapley value method for theory analysis and example verification, vertifys that enterprise synergy gains more than their own separate management, and puts forward a feasible path of supply chain collaboration through the construction of the distribution of interests coordination model.展开更多
Rural sewage treatment is in need of more capital investment,in which the financing model of PPP(public-private partnership)is able to encourage the investment of social capital in this sector.Risk sharing is one of t...Rural sewage treatment is in need of more capital investment,in which the financing model of PPP(public-private partnership)is able to encourage the investment of social capital in this sector.Risk sharing is one of the core features in the PPP model.In view that the risk loss of projects cannot be accurately estimated,this article describes the uncertainty of risk loss with fuzzy numbers and allocates the distribution of risk loss among the participants of rural sewage treatment PPP projects with interval fuzzy Shapley value to ensure a more reasonable and effective risk distribution.展开更多
A park hydrogen-doped integrated energy system(PHIES)can maximize energy utilization as a system with multiple supplies.To realize win-win cooperation between the PHIES and active distribution network(ADN),the coopera...A park hydrogen-doped integrated energy system(PHIES)can maximize energy utilization as a system with multiple supplies.To realize win-win cooperation between the PHIES and active distribution network(ADN),the cooperative operation problem of multi-PHIES connected to the same ADN is studied.A low-carbon hybrid game coordination strategy for multi-PHIES accessing ADN based on dynamic carbon base price is proposed in the paper.Firstly,multi-PHIES are constructed to form a PHIES alliance,including a hydrogen-doped gas turbine(HGT),hydrogen-doped gas boiler(HGB),power to gas and carbon capture system(P2G-CCS),and other equipment.Secondly,a hybrid game system model of the ADN and PHIES alliance is constructed,in which the ADN and PHIES alliance constitute a master-slave game,and the members of the PHIES alliance constitute a cooperative game.An improved Shapley value is proposed to deal with the problem of cost share among members in the alliance.Thirdly,an improved stepped carbon trading based on dynamic carbon baseline price is proposed.Thecarbon emissions at each moment and the total carbon emissions in a cycle are set as the dynamic adjustment factors of the carbon baseline price.The pricing mechanism of carbon baseline price increases with carbon emissions is constructed so that carbon emissions decrease.Finally,the quadratic interpolation optimization(QIO)algorithm is combined with Gurobi to solve the model.The results of the example analysis show that the cost of ADN is reduced by 4.47%,the cost of PHIES 1 is reduced by 3.67%,the cost of PHIES 2 is reduced by 0.97%,and the cost of PHIES 3 is reduced by 4.91%respectively.The total carbon emissions of the PHIES alliance are reduced by 7.08%.The low-carbon and economical operation of the multi-PHIES accessing ADN is achieved.展开更多
Coking at the fractionating tower bottom and the decant oil circulation system disrupts the heat balance,leading to unplanned shutdown and destroying the long period stable operation of the Fluid Catalytic Cracking Un...Coking at the fractionating tower bottom and the decant oil circulation system disrupts the heat balance,leading to unplanned shutdown and destroying the long period stable operation of the Fluid Catalytic Cracking Unit(FCCU).The FCCU operates through interconnected subsystems,generating high-dimensional,nonlinear,and non-stationary data characterized by spatiotemporally correlated.The decant oil solid content is the crucial indicator for monitoring catalyst loss from the reactor-regenerator system and coking risk tendency at the fractionating tower bottom that relies on sampling and laboratory testing,which is lagging responsiveness and labor-intensive.Developing the online decant oil solid content soft sensor using industrial data to support operators in conducting predictive maintenance is essential.Therefore,this paper proposes a hybrid deep learning framework for soft sensor development that combines spatiotemporal pattern extraction with interpretability,enabling accurate risk identification in dynamic operational conditions.This framework employs a Filter-Wrapper method for dimensionality reduction,followed by a 2D Convolutional Neural Network(2DCNN)for extracting spatial patterns,and a Bidirectional Gated Recurrent Unit(BiGRU)for capturing long-term temporal dependencies,with an Attention Mechanism(AM)to highlight critical features adaptively.The integration of SHapley Additive exPlanations(SHAP),Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),2DCNN,and expert knowledge precisely quantifies feature contributions and decomposes signals,significantly enhancing the practicality of risk identification.Applied to a China refinery with processing capacity of 2.80×10^(6) t/a,the soft sensor achieved the R^(2) value of 0.93 and five-level risk identification accuracy of 96.42%.These results demonstrate the framework's accuracy,robustness,and suitability for complex industrial scenarios,advancing risk visualization and management.展开更多
Accurate prediction of pure component physiochemical properties is crucial for process integration, multiscale modelling, and optimization. In this work, an enhanced framework for pure component property prediction by...Accurate prediction of pure component physiochemical properties is crucial for process integration, multiscale modelling, and optimization. In this work, an enhanced framework for pure component property prediction by using explainable machine learning methods is proposed. In this framework, the molecular representation method based on the connectivity matrix effectively considers atomic bonding relationships to automatically generate features. The supervised machine learning model random forest is applied for feature ranking and pooling. The adjusted R^(2) is introduced to penalize the inclusion of additional features, providing an assessment of the true contribution of features. The prediction results for normal boiling point (T_(b)), liquid molar volume (L_(mv)), critical temperature (T_(c)) and critical pressure (P_(c)) obtained using Artificial Neural Network and Gaussian Process Regression models confirm the accuracy of the molecular representation method. Comparison with GC based models shows that the root-mean-square error on the test set can be reduced by up to 83.8%. To enhance the interpretability of the model, a feature analysis method based on Shapley values is employed to determine the contribution of each feature to the property predictions. The results indicate that using the feature pooling method reduces the number of features from 13316 to 100 without compromising model accuracy. The feature analysis results for Tb, Lmv, Tc, and Pc confirms that different molecular properties are influenced by different structural features, aligning with mechanistic interpretations. In conclusion, the proposed framework is demonstrated to be feasible and provides a solid foundation for mixture component reconstruction and process integration modelling.展开更多
Floor heave is a common defect in mountainous tunnels.It is critical but challenging to predict the risk of floor heave,as traditional methods often fail to characterize this phenomenon effectively.This study proposes...Floor heave is a common defect in mountainous tunnels.It is critical but challenging to predict the risk of floor heave,as traditional methods often fail to characterize this phenomenon effectively.This study proposes a data-driven approach utilizing a support vector machine(SVM)optimized by the sparrow search algorithm(SSA)to address the issue.The model was developed and validated using a dataset collected from 100 tunnels.Shapley value analysis was conducted to identify the key features influencing floor heave defects.Moreover,a committee-based uncertainty quantification method is presented to evaluate the reliability of each prediction.The results show that:(1)Data feature engineering and SSA play pivotal roles in expediting the convergence of the SVM model.(2)Groundwater and high in situ stress are key factors contributing to tunnel floor heave.(3)In comparison to backpropagation(BP)neural networks,the SSA-SVM demonstrates superior robustness in handling imperfect and limited data.(4)The committee-based uncertainty quantification method is proven effective to evaluate the trustworthiness of each prediction.This data-driven surrogate model offers an effective strategy for understanding the factors that impact tunnel floor defects and accurately predicting tunnel floor heave deformation.展开更多
Background The geo-traceability of cotton is crucial for ensuring the quality and integrity of cotton brands. However, effective methods for achieving this traceability are currently lacking. This study investigates t...Background The geo-traceability of cotton is crucial for ensuring the quality and integrity of cotton brands. However, effective methods for achieving this traceability are currently lacking. This study investigates the potential of explainable machine learning for the geo-traceability of raw cotton.Results The findings indicate that principal component analysis(PCA) exhibits limited effectiveness in tracing cotton origins. In contrast, partial least squares discriminant analysis(PLS-DA) demonstrates superior classification performance, identifying seven discriminating variables: Na, Mn, Ba, Rb, Al, As, and Pb. The use of decision tree(DT), support vector machine(SVM), and random forest(RF) models for origin discrimination yielded accuracies of 90%, 87%, and 97%, respectively. Notably, the light gradient boosting machine(Light GBM) model achieved perfect performance metrics, with accuracy, precision, and recall rate all reaching 100% on the test set. The output of the Light GBM model was further evaluated using the SHapley Additive ex Planation(SHAP) technique, which highlighted differences in the elemental composition of raw cotton from various countries. Specifically, the elements Pb, Ni, Na, Al, As, Ba, and Rb significantly influenced the model's predictions.Conclusion These findings suggest that explainable machine learning techniques can provide insights into the complex relationships between geographic information and raw cotton. Consequently, these methodologies enhances the precision and reliability of geographic traceability for raw cotton.展开更多
During the transitional period of electricity market reforms in China,scheduling simulations of technical virtual power plants(TVPPs)are crucial owing to the lack of operational experience.This study proposes a model ...During the transitional period of electricity market reforms in China,scheduling simulations of technical virtual power plants(TVPPs)are crucial owing to the lack of operational experience.This study proposes a model for TVPPs participating in the current multi-market;that is,TVPP coordinate bidding in the day-ahead energy and ramping ancillary market while purchasing unbalanced power and pro-viding frequency regulation service in the real-time market.A multi-scenario optimization approach was employed in the day-ahead stage to manage uncertainty,and an improved Shapley value was utilized for revenue allocation.By employing linearization techniques,the model is transformed into a mixed-integer second-order cone-programming problem that can be efficiently solved using linear solvers.Numerical simulations based on actual provincial electricity market rules were conducted to validate the effectiveness of a TVPP coalition profitability.展开更多
Background Virtual reality technology has been widely used in surgical simulators,providing new opportunities for assessing and training surgical skills.Machine learning algorithms are commonly used to analyze and eva...Background Virtual reality technology has been widely used in surgical simulators,providing new opportunities for assessing and training surgical skills.Machine learning algorithms are commonly used to analyze and evaluate the performance of participants.However,their interpretability limits the personalization of the training for individual participants.Methods Seventy-nine participants were recruited and divided into three groups based on their skill level in intracranial tumor resection.Data on the use of surgical tools were collected using a surgical simulator.Feature selection was performed using the Minimum Redundancy Maximum Relevance and SVM-RFE algorithms to obtain the final metrics for training the machine learning model.Five machine learning algorithms were trained to predict the skill level,and the support vector machine performed the best,with an accuracy of 92.41%and Area Under Curve value of 0.98253.The machine learning model was interpreted using Shapley values to identify the important factors contributing to the skill level of each participant.Results This study demonstrates the effectiveness of machine learning in differentiating the evaluation and training of virtual reality neurosurgical performances.The use of Shapley values enables targeted training by identifying deficiencies in individual skills.Conclusions This study provides insights into the use of machine learning for personalized training in virtual reality neurosurgery.The interpretability of the machine learning models enables the development of individualized training programs.In addition,this study highlighted the potential of explanatory models in training external skills.展开更多
Cooperative driving around intersections has aroused increasing interest in the last five years.Meanwhile,driving safety in non-signalized intersections has become an issue that has attracted attention globally.In vie...Cooperative driving around intersections has aroused increasing interest in the last five years.Meanwhile,driving safety in non-signalized intersections has become an issue that has attracted attention globally.In view of the potential collision risk when more than three vehicles approach a non-signalized intersection from different directions,we propose a driving model using cooperative game theory.First,the characteristic functions of this model are primarily established on each vehicle’s profit function and include safety,rapidity and comfort indicators.Second,the Shapley theorem is adopted,and its group rationality,individual rationality,and uniqueness are proved to be suitable for the characteristic functions of the model.Following this,different drivers’characteristics are considered.In order to simplify the calculation process,a zero-mean normalization method is introduced.In addition,a genetic algorithm method is adopted to search an optimal strategy set in the constrained multi-objective optimization problem.Finally,the model is confirmed as valid after simulation with a series of initial conditions.展开更多
An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a ne...An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space(i.e.,virtual environment);:the Sharpley value method in inter-pretable machine learning is applied to analyzing the impact of geological and operational parameters in each well(i.e.,single well feature impact analysis):and ensemble randomized maximum likelihood(EnRML)is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost.In the experiment,InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions,and finally achieves an average cost reduction of 9.7%for a case study with 104 wells.展开更多
在网络流分类实践中,网络运营商通常只需要知道网络流所需的服务类别(class of service,CoS),就可对网络流优先级和资源分配做出决定。为了满足用户对体验质量的需求,提出了面向服务等级的网络流多任务分类方法。该方法是直接进行面向Co...在网络流分类实践中,网络运营商通常只需要知道网络流所需的服务类别(class of service,CoS),就可对网络流优先级和资源分配做出决定。为了满足用户对体验质量的需求,提出了面向服务等级的网络流多任务分类方法。该方法是直接进行面向CoS的流分类,而不需要推断应用类型。同时提出多任务框架,利用领域知识定义宏特征组及应用合作博弈中的Shapley Value模型来合理分析特征,并用决策树分箱来解决CoS阈值划分问题。采用真实网络数据集进行实验,通过在少量标记数据的情况下,优化网络参数和调整各网络模型时间损耗和分类准确性的稳定相关系数。结果表明,该方法分类准确度(提高了12.66%)和时间消耗(减少了39.23%)性能优于现有文献方法,同时分析了多分类实验结果并给出有关建议。展开更多
基金the National Natural Science Foundation of China (70471063 , 70171036)the Second Phase of "985"Project of China(107008200400024) the Main/Subject Project of Beijing of China(XK100070534)
文摘Fuzzy Shapley values are developed based on classical Shapley values and used to allocate profit among partners in virtual enterprises （VE）. Axioms of the classical Shapley value are extended to Shapley values with fuzzy payoffs by using fuzzy sets theory. Fuzzy Shapley function is defined based on these extended axioms. From the viewpoint the allocation for each partner should be a crisp value rather a fuzzy membership function at the end of cooperation, a crisp allocation scheme based on fuzzy Shapley values is proposed.
基金sponsored by Qinglan Project of Jiangsu Province,and Jiangsu Provincial Key Research and Development Program(No.BE2020084-1).
文摘Opportunistic mobile crowdsensing(MCS)non-intrusively exploits human mobility trajectories,and the participants’smart devices as sensors have become promising paradigms for various urban data acquisition tasks.However,in practice,opportunistic MCS has several challenges from both the perspectives of MCS participants and the data platform.On the one hand,participants face uncertainties in conducting MCS tasks,including their mobility and implicit interactions among participants,and participants’economic returns given by the MCS data platform are determined by not only their own actions but also other participants’strategic actions.On the other hand,the platform can only observe the participants’uploaded sensing data that depends on the unknown effort/action exerted by participants to the platform,while,for optimizing its overall objective,the platform needs to properly reward certain participants for incentivizing them to provide high-quality data.To address the challenge of balancing individual incentives and platform objectives in MCS,this paper proposes MARCS,an online sensing policy based on multi-agent deep reinforcement learning(MADRL)with centralized training and decentralized execution(CTDE).Specifically,the interactions between MCS participants and the data platform are modeled as a partially observable Markov game,where participants,acting as agents,use DRL-based policies to make decisions based on local observations,such as task trajectories and platform payments.To align individual and platform goals effectively,the platform leverages Shapley value to estimate the contribution of each participant’s sensed data,using these estimates as immediate rewards to guide agent training.The experimental results on real mobility trajectory datasets indicate that the revenue of MARCS reaches almost 35%,53%,and 100%higher than DDPG,Actor-Critic,and model predictive control(MPC)respectively on the participant side and similar results on the platform side,which show superior performance compared to baselines.
文摘Under the current long-term electricity market mechanism,new energy and thermal power face issues such as deviation assessment and compression of generation space.The profitability of market players is limited.Simultaneously,the cooperation model among various energy sources will have a direct impact on the alliance’s revenue and the equity of income distribution within the alliance.Therefore,integrating new energy with thermal power units into an integrated multi-energy complementary system to participate in the long-term electricity market holds significant potential.To simulate and evaluate the benefits and internal distribution methods of a multi-energy complementary system participating in long-term market transactions,this paper first constructs a multi-energy complementary system integrated with new energy and thermal power generation units at the same connection point,and participates in the annual bilateral game as a unified market entity to obtain the revenue value under the annual bilateral market.Secondly,based on the entropy weight method,improvements are made to the traditional Shapley value distribution model,and an internal distribution model for multi-energy complementary systems with multiple participants is constructed.Finally,a Markov Decision Process(MDP)evaluation system is constructed for practical case verification.The research results show that the improved Shapley value distribution model achieves higher satisfaction,providing a reasonable allocation scheme for multi-energy complementary cooperation models.
基金Sponsored by the National Natural Science Foundation of China(70771010)the Second Phase of "985 Project" of China (107008200400024)the Graduate Student’s Science and Technology Innovation Project of Beijing Institute of Technology (GB200818)
文摘The Shapley value of fuzzy bi-eooperative game is developed based on the conventional Shapley value of bi-cooperative game. From the viewpoint that the players can participate in the coalitions to a certain extent and there are at least two independent cooperative projects for every player to choose, Shapley value which is introduced by Grabisch is extended to the case of fuzzy bi-cooperative game by Choquet integral. Moreover, the explicit fuzzy Shapley value is given. The explicit fuzzy Shapley function can be used to allocate the profits among players in supply-chain under the competitive and uncertain environment.
基金supported by the National Natural Science Foundation of China(No.62073202,No.61873150)the Young Experts of Taishan Scholar Project(No.tsqn201909076)the Natural Science Fund for Distinguished Young Scholars of Shandong Province(No.JQ201613).
文摘Shapley value is one of the most fundamental concepts in cooperative games.This paper investigates the calculation of the Shapley value for cooperative games and establishes a new formula via carrier.Firstly,a necessary and sufficient condition is presented for the verification of carrier,based on which an algorithm is worked out to find the unique minimum carrier.Secondly,by virtue of the properties of minimum carrier,it is proved that the profit allocated to dummy players(players which do not belong to the minimum carrier)is zero,and the profit allocated to players in minimum carrier is only determined by the minimum carrier.Then,a new formula of the Shapley value is presented,which greatly reduces the computational complexity of the original formula,and shows that the Shapley value only depends on the minimum carrier.Finally,based on the semi-tensor product(STP)of matrices,the obtained new formula is converted into an equivalent algebraic form,which makes the new formula convenient for calculation via MATLAB.
基金the National Natural Science Foundation of China(70771010)the Second Phase of"985 Project"of China (107008200400024)the Graduate Student s Science and Technology Innovation Project of Beijing Institute of Technology (GB200818)
文摘Fuzzy Shapley values are developed based on conventional Shapley value. This kind of fuzzy cooperative games admit the representation of rates of players＇ participation to each coalition. And they can be applicable to both supperadditive and subadditvie cooperative games while other kinds of fuzzy cooperative games can only be superadditive. An explicit form of the Shapley function on fuzzy games with λ-fuzzy measure was also proposed.
文摘Under green supply chain mode, how to Carry out the distribution of profits between subjects is an important problem. Through the comparison of the green supply chain benefit allocation of non-cooperative game and cooperative game the payoffmatrix, it is clearly that the necessity of interest distribution cooperative game. Put general manufacturing enterprises of green supply chain as the research object, using Shapley value method for theory analysis and example verification, vertifys that enterprise synergy gains more than their own separate management, and puts forward a feasible path of supply chain collaboration through the construction of the distribution of interests coordination model.
文摘Rural sewage treatment is in need of more capital investment,in which the financing model of PPP(public-private partnership)is able to encourage the investment of social capital in this sector.Risk sharing is one of the core features in the PPP model.In view that the risk loss of projects cannot be accurately estimated,this article describes the uncertainty of risk loss with fuzzy numbers and allocates the distribution of risk loss among the participants of rural sewage treatment PPP projects with interval fuzzy Shapley value to ensure a more reasonable and effective risk distribution.
基金supported by the Central Government Guides the Local Science and Technology Development Fund Project(2023ZY0020)Key R&D and Achievement Transformation Project in Inner Mongolia Autonomous Region(2022YFHH0019)+4 种基金the Fundamental Research Funds for Inner Mongolia University of Science and Technology(2022053)Natural Science Foundation of Inner Mongolia Autonomous Region(2022LHQN05002)NationalNatural Science Foundation of China(52067018)Natural Science Foundation of InnerMongoliaAutonomous Region of China(2025MS05052)Control Science and Engineering Quality Improvement and Cultivation Discipline Project in Inner Mongolia University of Science and Technology.
文摘A park hydrogen-doped integrated energy system(PHIES)can maximize energy utilization as a system with multiple supplies.To realize win-win cooperation between the PHIES and active distribution network(ADN),the cooperative operation problem of multi-PHIES connected to the same ADN is studied.A low-carbon hybrid game coordination strategy for multi-PHIES accessing ADN based on dynamic carbon base price is proposed in the paper.Firstly,multi-PHIES are constructed to form a PHIES alliance,including a hydrogen-doped gas turbine(HGT),hydrogen-doped gas boiler(HGB),power to gas and carbon capture system(P2G-CCS),and other equipment.Secondly,a hybrid game system model of the ADN and PHIES alliance is constructed,in which the ADN and PHIES alliance constitute a master-slave game,and the members of the PHIES alliance constitute a cooperative game.An improved Shapley value is proposed to deal with the problem of cost share among members in the alliance.Thirdly,an improved stepped carbon trading based on dynamic carbon baseline price is proposed.Thecarbon emissions at each moment and the total carbon emissions in a cycle are set as the dynamic adjustment factors of the carbon baseline price.The pricing mechanism of carbon baseline price increases with carbon emissions is constructed so that carbon emissions decrease.Finally,the quadratic interpolation optimization(QIO)algorithm is combined with Gurobi to solve the model.The results of the example analysis show that the cost of ADN is reduced by 4.47%,the cost of PHIES 1 is reduced by 3.67%,the cost of PHIES 2 is reduced by 0.97%,and the cost of PHIES 3 is reduced by 4.91%respectively.The total carbon emissions of the PHIES alliance are reduced by 7.08%.The low-carbon and economical operation of the multi-PHIES accessing ADN is achieved.
基金supported by the Innovative Research Group Project of the National Natural Science Foundation of China(22021004)Sinopec Major Science and Technology Projects(321123-1)。
文摘Coking at the fractionating tower bottom and the decant oil circulation system disrupts the heat balance,leading to unplanned shutdown and destroying the long period stable operation of the Fluid Catalytic Cracking Unit(FCCU).The FCCU operates through interconnected subsystems,generating high-dimensional,nonlinear,and non-stationary data characterized by spatiotemporally correlated.The decant oil solid content is the crucial indicator for monitoring catalyst loss from the reactor-regenerator system and coking risk tendency at the fractionating tower bottom that relies on sampling and laboratory testing,which is lagging responsiveness and labor-intensive.Developing the online decant oil solid content soft sensor using industrial data to support operators in conducting predictive maintenance is essential.Therefore,this paper proposes a hybrid deep learning framework for soft sensor development that combines spatiotemporal pattern extraction with interpretability,enabling accurate risk identification in dynamic operational conditions.This framework employs a Filter-Wrapper method for dimensionality reduction,followed by a 2D Convolutional Neural Network(2DCNN)for extracting spatial patterns,and a Bidirectional Gated Recurrent Unit(BiGRU)for capturing long-term temporal dependencies,with an Attention Mechanism(AM)to highlight critical features adaptively.The integration of SHapley Additive exPlanations(SHAP),Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),2DCNN,and expert knowledge precisely quantifies feature contributions and decomposes signals,significantly enhancing the practicality of risk identification.Applied to a China refinery with processing capacity of 2.80×10^(6) t/a,the soft sensor achieved the R^(2) value of 0.93 and five-level risk identification accuracy of 96.42%.These results demonstrate the framework's accuracy,robustness,and suitability for complex industrial scenarios,advancing risk visualization and management.
基金support from China Scholarship Council(CSC)(202406440073).
文摘Accurate prediction of pure component physiochemical properties is crucial for process integration, multiscale modelling, and optimization. In this work, an enhanced framework for pure component property prediction by using explainable machine learning methods is proposed. In this framework, the molecular representation method based on the connectivity matrix effectively considers atomic bonding relationships to automatically generate features. The supervised machine learning model random forest is applied for feature ranking and pooling. The adjusted R^(2) is introduced to penalize the inclusion of additional features, providing an assessment of the true contribution of features. The prediction results for normal boiling point (T_(b)), liquid molar volume (L_(mv)), critical temperature (T_(c)) and critical pressure (P_(c)) obtained using Artificial Neural Network and Gaussian Process Regression models confirm the accuracy of the molecular representation method. Comparison with GC based models shows that the root-mean-square error on the test set can be reduced by up to 83.8%. To enhance the interpretability of the model, a feature analysis method based on Shapley values is employed to determine the contribution of each feature to the property predictions. The results indicate that using the feature pooling method reduces the number of features from 13316 to 100 without compromising model accuracy. The feature analysis results for Tb, Lmv, Tc, and Pc confirms that different molecular properties are influenced by different structural features, aligning with mechanistic interpretations. In conclusion, the proposed framework is demonstrated to be feasible and provides a solid foundation for mixture component reconstruction and process integration modelling.
基金financially supported by the National Natural Science Foundation of China(Grant No.52008039)the Guizhou Provincial Department of Transportation Science and Technology Project(Project No.2024-121-043)the Changsha University of Science and Technology Graduate Research Innovation Project(Grant No.CLSJCX23036).
文摘Floor heave is a common defect in mountainous tunnels.It is critical but challenging to predict the risk of floor heave,as traditional methods often fail to characterize this phenomenon effectively.This study proposes a data-driven approach utilizing a support vector machine(SVM)optimized by the sparrow search algorithm(SSA)to address the issue.The model was developed and validated using a dataset collected from 100 tunnels.Shapley value analysis was conducted to identify the key features influencing floor heave defects.Moreover,a committee-based uncertainty quantification method is presented to evaluate the reliability of each prediction.The results show that:(1)Data feature engineering and SSA play pivotal roles in expediting the convergence of the SVM model.(2)Groundwater and high in situ stress are key factors contributing to tunnel floor heave.(3)In comparison to backpropagation(BP)neural networks,the SSA-SVM demonstrates superior robustness in handling imperfect and limited data.(4)The committee-based uncertainty quantification method is proven effective to evaluate the trustworthiness of each prediction.This data-driven surrogate model offers an effective strategy for understanding the factors that impact tunnel floor defects and accurately predicting tunnel floor heave deformation.
基金supported by Agricultural Science and Technology Innovation Program of Chinese Academy of Agricultural Science。
文摘Background The geo-traceability of cotton is crucial for ensuring the quality and integrity of cotton brands. However, effective methods for achieving this traceability are currently lacking. This study investigates the potential of explainable machine learning for the geo-traceability of raw cotton.Results The findings indicate that principal component analysis(PCA) exhibits limited effectiveness in tracing cotton origins. In contrast, partial least squares discriminant analysis(PLS-DA) demonstrates superior classification performance, identifying seven discriminating variables: Na, Mn, Ba, Rb, Al, As, and Pb. The use of decision tree(DT), support vector machine(SVM), and random forest(RF) models for origin discrimination yielded accuracies of 90%, 87%, and 97%, respectively. Notably, the light gradient boosting machine(Light GBM) model achieved perfect performance metrics, with accuracy, precision, and recall rate all reaching 100% on the test set. The output of the Light GBM model was further evaluated using the SHapley Additive ex Planation(SHAP) technique, which highlighted differences in the elemental composition of raw cotton from various countries. Specifically, the elements Pb, Ni, Na, Al, As, Ba, and Rb significantly influenced the model's predictions.Conclusion These findings suggest that explainable machine learning techniques can provide insights into the complex relationships between geographic information and raw cotton. Consequently, these methodologies enhances the precision and reliability of geographic traceability for raw cotton.
基金supported by Science and Technology Foundation of Global Energy Interconnection Group Co.LTD.(SGGE0000JYJS2310046).
文摘During the transitional period of electricity market reforms in China,scheduling simulations of technical virtual power plants(TVPPs)are crucial owing to the lack of operational experience.This study proposes a model for TVPPs participating in the current multi-market;that is,TVPP coordinate bidding in the day-ahead energy and ramping ancillary market while purchasing unbalanced power and pro-viding frequency regulation service in the real-time market.A multi-scenario optimization approach was employed in the day-ahead stage to manage uncertainty,and an improved Shapley value was utilized for revenue allocation.By employing linearization techniques,the model is transformed into a mixed-integer second-order cone-programming problem that can be efficiently solved using linear solvers.Numerical simulations based on actual provincial electricity market rules were conducted to validate the effectiveness of a TVPP coalition profitability.
基金Supported by the Yunnan Key Laboratory of Opto-Electronic Information Technology,Postgraduate Research Innovation Fund of Yunnan Normal University (YJSJJ22-B79)the National Natural Science Foundation of China (62062069,62062070,62005235)。
文摘Background Virtual reality technology has been widely used in surgical simulators,providing new opportunities for assessing and training surgical skills.Machine learning algorithms are commonly used to analyze and evaluate the performance of participants.However,their interpretability limits the personalization of the training for individual participants.Methods Seventy-nine participants were recruited and divided into three groups based on their skill level in intracranial tumor resection.Data on the use of surgical tools were collected using a surgical simulator.Feature selection was performed using the Minimum Redundancy Maximum Relevance and SVM-RFE algorithms to obtain the final metrics for training the machine learning model.Five machine learning algorithms were trained to predict the skill level,and the support vector machine performed the best,with an accuracy of 92.41%and Area Under Curve value of 0.98253.The machine learning model was interpreted using Shapley values to identify the important factors contributing to the skill level of each participant.Results This study demonstrates the effectiveness of machine learning in differentiating the evaluation and training of virtual reality neurosurgical performances.The use of Shapley values enables targeted training by identifying deficiencies in individual skills.Conclusions This study provides insights into the use of machine learning for personalized training in virtual reality neurosurgery.The interpretability of the machine learning models enables the development of individualized training programs.In addition,this study highlighted the potential of explanatory models in training external skills.
基金Project(61673233)supported by the National Natural Science Foundation of ChinaProject(D171100006417003)supported by Beijing Municipal Science and Technology Program,China
文摘Cooperative driving around intersections has aroused increasing interest in the last five years.Meanwhile,driving safety in non-signalized intersections has become an issue that has attracted attention globally.In view of the potential collision risk when more than three vehicles approach a non-signalized intersection from different directions,we propose a driving model using cooperative game theory.First,the characteristic functions of this model are primarily established on each vehicle’s profit function and include safety,rapidity and comfort indicators.Second,the Shapley theorem is adopted,and its group rationality,individual rationality,and uniqueness are proved to be suitable for the characteristic functions of the model.Following this,different drivers’characteristics are considered.In order to simplify the calculation process,a zero-mean normalization method is introduced.In addition,a genetic algorithm method is adopted to search an optimal strategy set in the constrained multi-objective optimization problem.Finally,the model is confirmed as valid after simulation with a series of initial conditions.
文摘An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space(i.e.,virtual environment);:the Sharpley value method in inter-pretable machine learning is applied to analyzing the impact of geological and operational parameters in each well(i.e.,single well feature impact analysis):and ensemble randomized maximum likelihood(EnRML)is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost.In the experiment,InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions,and finally achieves an average cost reduction of 9.7%for a case study with 104 wells.
文摘在网络流分类实践中,网络运营商通常只需要知道网络流所需的服务类别(class of service,CoS),就可对网络流优先级和资源分配做出决定。为了满足用户对体验质量的需求,提出了面向服务等级的网络流多任务分类方法。该方法是直接进行面向CoS的流分类,而不需要推断应用类型。同时提出多任务框架,利用领域知识定义宏特征组及应用合作博弈中的Shapley Value模型来合理分析特征,并用决策树分箱来解决CoS阈值划分问题。采用真实网络数据集进行实验,通过在少量标记数据的情况下,优化网络参数和调整各网络模型时间损耗和分类准确性的稳定相关系数。结果表明,该方法分类准确度(提高了12.66%)和时间消耗(减少了39.23%)性能优于现有文献方法,同时分析了多分类实验结果并给出有关建议。
