Determining the similarity degree between process models was very important for their management,reuse,and analysis.Current approaches either focused on process model's structural aspect,or had inefficiency or imp...Determining the similarity degree between process models was very important for their management,reuse,and analysis.Current approaches either focused on process model's structural aspect,or had inefficiency or imprecision in behavioral similarity.Aiming at these problems,a novel similarity measure which extended an existing method named Transition Adjacent Relation(TAR) with improved precision and efficiency named TAR * was proposed.The ability of measuring similarity was extended by eliminating the duplicate tasks without impacting the behaviors.For precision,TARs was classified into repeatable and unrepeatable ones to identify whether a TAR was involved in a loop.Two new kinds of TARs were added,one related to the invisible tasks after the source place and before sink place,and the other representing implicit dependencies.For efficiency,all TARs based on unfolding instead of its reach ability graph of a labeled Petri net were calculated to avoid state space explosion.Experiments on artificial and real-world process models showed the effectiveness and efficiency of the proposed method.展开更多
Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,rese...Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.展开更多
基金Project supported by the National Science Foundation,China(No.61003099)the National Basic Research Program,China(No.2009CB320700)
文摘Determining the similarity degree between process models was very important for their management,reuse,and analysis.Current approaches either focused on process model's structural aspect,or had inefficiency or imprecision in behavioral similarity.Aiming at these problems,a novel similarity measure which extended an existing method named Transition Adjacent Relation(TAR) with improved precision and efficiency named TAR * was proposed.The ability of measuring similarity was extended by eliminating the duplicate tasks without impacting the behaviors.For precision,TARs was classified into repeatable and unrepeatable ones to identify whether a TAR was involved in a loop.Two new kinds of TARs were added,one related to the invisible tasks after the source place and before sink place,and the other representing implicit dependencies.For efficiency,all TARs based on unfolding instead of its reach ability graph of a labeled Petri net were calculated to avoid state space explosion.Experiments on artificial and real-world process models showed the effectiveness and efficiency of the proposed method.
基金supported by the Major Project of the National Natural Science Foundation of China (82090051,81871442)Outstanding Member Project of Youth Innovation Promotion Association of the Chinese Academy of Sciences (Y201930)。
文摘Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.