In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring...In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.展开更多
The productivity and flavor quality of soy sauce are partly determined by the proteolytic enzymes secreted by the industrial microbe Aspergillus oryzae,which break down proteins into peptides and amino acids.Because o...The productivity and flavor quality of soy sauce are partly determined by the proteolytic enzymes secreted by the industrial microbe Aspergillus oryzae,which break down proteins into peptides and amino acids.Because of how complicated it is to classify proteolytic enzymes and understand how they work,not much is known about what is in the profiles of proteolytic enzymes and which enzymes are most important to A.oryzae during solid-state fermentation.In this study,we collected industrial A.oryzae from Chinese and Japanese soy sauce production,both of which have excellent protein hydrolysis capability but have numerous genetic differences.We systematically analyzed the in vitro enzyme profiles of two industrial A.oryzae based on 4D label-free proteome sequencing technology.In addition,we constructed a local database of proteolytic enzymes from the Aspergillus genus,which helps us analyze the proteomics data more precisely.We found that 96 proteolytic enzymes are excreted by industrial A.oryzae,of which 27 are endopeptidases and 39 are exopeptidases.Based on the relative protein expression and transcription quantity,as well as the catalytic characteristics,we identified 27 potential key proteolytic enzymes associated with high protein breakdown efficiency at solid-state fermentation.Meanwhile,we proposed eight proteolytic enzymes with potential hydrolytic activity.This study deepens our understanding of the proteolytic enzyme profiles excreted by A.oryzae at solid state and provides our knowledge of the candidate key proteolytic enzymes during koji fermentation.展开更多
基金Supported by the National Natural Science Foundation of China(61273160)the Fundamental Research Funds for the Central Universities(14CX06067A,13CX05021A)
文摘In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.
基金financially supported by National Key R&D Program of China(2022YFD2101203).
文摘The productivity and flavor quality of soy sauce are partly determined by the proteolytic enzymes secreted by the industrial microbe Aspergillus oryzae,which break down proteins into peptides and amino acids.Because of how complicated it is to classify proteolytic enzymes and understand how they work,not much is known about what is in the profiles of proteolytic enzymes and which enzymes are most important to A.oryzae during solid-state fermentation.In this study,we collected industrial A.oryzae from Chinese and Japanese soy sauce production,both of which have excellent protein hydrolysis capability but have numerous genetic differences.We systematically analyzed the in vitro enzyme profiles of two industrial A.oryzae based on 4D label-free proteome sequencing technology.In addition,we constructed a local database of proteolytic enzymes from the Aspergillus genus,which helps us analyze the proteomics data more precisely.We found that 96 proteolytic enzymes are excreted by industrial A.oryzae,of which 27 are endopeptidases and 39 are exopeptidases.Based on the relative protein expression and transcription quantity,as well as the catalytic characteristics,we identified 27 potential key proteolytic enzymes associated with high protein breakdown efficiency at solid-state fermentation.Meanwhile,we proposed eight proteolytic enzymes with potential hydrolytic activity.This study deepens our understanding of the proteolytic enzyme profiles excreted by A.oryzae at solid state and provides our knowledge of the candidate key proteolytic enzymes during koji fermentation.
