Big data analysis is confronted with the obstacle of high dimensionality in data samples.To address this issue,researchers have devised a multitude of intel-ligent optimization algorithms aimed at enhancing big data a...Big data analysis is confronted with the obstacle of high dimensionality in data samples.To address this issue,researchers have devised a multitude of intel-ligent optimization algorithms aimed at enhancing big data analysis techniques.Among these algorithms is the War Strategy Optimization(WSO)proposed in 2022,which distinguishes itself from other intelligence algorithms through its potent optimization capabilities.Nevertheless,the WSO exhibits limitations in its global search capacity and is susceptible to becoming trapped in local optima when dealing with high-dimensional problems.To surmount these shortcomings and improve the performance of WSO in handling the challenges posed by high dimensionality in big data,this paper introduces an enhanced version of the WSO based on the carnivorous plant algorithm(CPA)and shared niche.The grouping concept and update strategy of CPA are incorporated into WSO,and its update strategy is modified through the introduction of a shared small habitat approach combined with an elite strategy to create a novel improved algorithm.Simula-tion experiments were conducted to compare this new War Strategy Optimization(CSWSO)with WSO,RKWSO,I-GWO,NCHHO and FDB-SDO using 16 test functions.Experimental results demonstrate that the proposed enhanced algorithm exhibits superior optimization accuracy and stability,providing a novel approach to addressing the challenges posed by high dimensionality in big data.展开更多
Rapid growth of China’s overall national strength after the end of the ColdWar has attracted worldwide attention. As a consequence, political scien-tists of various countries begin to ponder over a question: whether ...Rapid growth of China’s overall national strength after the end of the ColdWar has attracted worldwide attention. As a consequence, political scien-tists of various countries begin to ponder over a question: whether will Chi-na seek external expansion when it becomes powerful? In 1992, there began to ap-pear a myth of so-called "China threat". In its November 28 issue of that year,展开更多
文摘Big data analysis is confronted with the obstacle of high dimensionality in data samples.To address this issue,researchers have devised a multitude of intel-ligent optimization algorithms aimed at enhancing big data analysis techniques.Among these algorithms is the War Strategy Optimization(WSO)proposed in 2022,which distinguishes itself from other intelligence algorithms through its potent optimization capabilities.Nevertheless,the WSO exhibits limitations in its global search capacity and is susceptible to becoming trapped in local optima when dealing with high-dimensional problems.To surmount these shortcomings and improve the performance of WSO in handling the challenges posed by high dimensionality in big data,this paper introduces an enhanced version of the WSO based on the carnivorous plant algorithm(CPA)and shared niche.The grouping concept and update strategy of CPA are incorporated into WSO,and its update strategy is modified through the introduction of a shared small habitat approach combined with an elite strategy to create a novel improved algorithm.Simula-tion experiments were conducted to compare this new War Strategy Optimization(CSWSO)with WSO,RKWSO,I-GWO,NCHHO and FDB-SDO using 16 test functions.Experimental results demonstrate that the proposed enhanced algorithm exhibits superior optimization accuracy and stability,providing a novel approach to addressing the challenges posed by high dimensionality in big data.
文摘Rapid growth of China’s overall national strength after the end of the ColdWar has attracted worldwide attention. As a consequence, political scien-tists of various countries begin to ponder over a question: whether will Chi-na seek external expansion when it becomes powerful? In 1992, there began to ap-pear a myth of so-called "China threat". In its November 28 issue of that year,
