Recently,deep learning has achieved considerable results in the hyperspectral image(HSI)classification.However,most available deep networks require ample and authentic samples to better train the models,which is expen...Recently,deep learning has achieved considerable results in the hyperspectral image(HSI)classification.However,most available deep networks require ample and authentic samples to better train the models,which is expensive and inefficient in practical tasks.Existing few‐shot learning(FSL)methods generally ignore the potential relationships between non‐local spatial samples that would better represent the underlying features of HSI.To solve the above issues,a novel deep transformer and few‐shot learning(DTFSL)classification framework is proposed,attempting to realize fine‐grained classification of HSI with only a few‐shot instances.Specifically,the spatial attention and spectral query modules are introduced to overcome the constraint of the convolution kernel and consider the information between long‐distance location(non‐local)samples to reduce the uncertainty of classes.Next,the network is trained with episodes and task‐based learning strategies to learn a metric space,which can continuously enhance its modelling capability.Furthermore,the developed approach combines the advantages of domain adaptation to reduce the variation in inter‐domain distribution and realize distribution alignment.On three publicly available HSI data,extensive experiments have indicated that the proposed DT‐FSL yields better results concerning state‐of‐the‐art algorithms.展开更多
In this study,15 strains of Lactic acid bacteria(Allata et al.)and 6 strains of propionic acid bacteria(PAB)were firstly tested for their antifungal activity against three spoilage fungi,Aspergillus niger,Penicillium ...In this study,15 strains of Lactic acid bacteria(Allata et al.)and 6 strains of propionic acid bacteria(PAB)were firstly tested for their antifungal activity against three spoilage fungi,Aspergillus niger,Penicillium crustosum and Aspergillus flavus.Two strains of LAB and PAB were selected and assessed,alone or paired,for their abilities to inhibit the most resistant mold,Aspergillus niger.A mixed culture of P.freudenreichii D6 and L.plantarum L9 was found to be the most active and their optimal inoculum was 1×10^(8) and 1×10^(6) CFU/mL,respectively.Furthermore,the in situ antifungal effect of the mixed culture was evaluated against bakery product spoilage fungi.It was found that the growth of airborne fungi was delayed for up to 7 days.The cell number of L.plantarum L9 was slightly increased by the presence of P.freudenreichii D6.Quantification of three main acids(propionic,lactic and acetic acid)produced by the protective cultures suggested that acetic acid was mainly responsible for the antifungal activity.In conclusion,the mixed culture of P.freudenreichii and L.plantarum may be exploited as biopreservatives in bakery products.展开更多
基金supported by the National Natural Science Foundation of China under Grant 62161160336 and Grant 42030111.
文摘Recently,deep learning has achieved considerable results in the hyperspectral image(HSI)classification.However,most available deep networks require ample and authentic samples to better train the models,which is expensive and inefficient in practical tasks.Existing few‐shot learning(FSL)methods generally ignore the potential relationships between non‐local spatial samples that would better represent the underlying features of HSI.To solve the above issues,a novel deep transformer and few‐shot learning(DTFSL)classification framework is proposed,attempting to realize fine‐grained classification of HSI with only a few‐shot instances.Specifically,the spatial attention and spectral query modules are introduced to overcome the constraint of the convolution kernel and consider the information between long‐distance location(non‐local)samples to reduce the uncertainty of classes.Next,the network is trained with episodes and task‐based learning strategies to learn a metric space,which can continuously enhance its modelling capability.Furthermore,the developed approach combines the advantages of domain adaptation to reduce the variation in inter‐domain distribution and realize distribution alignment.On three publicly available HSI data,extensive experiments have indicated that the proposed DT‐FSL yields better results concerning state‐of‐the‐art algorithms.
文摘In this study,15 strains of Lactic acid bacteria(Allata et al.)and 6 strains of propionic acid bacteria(PAB)were firstly tested for their antifungal activity against three spoilage fungi,Aspergillus niger,Penicillium crustosum and Aspergillus flavus.Two strains of LAB and PAB were selected and assessed,alone or paired,for their abilities to inhibit the most resistant mold,Aspergillus niger.A mixed culture of P.freudenreichii D6 and L.plantarum L9 was found to be the most active and their optimal inoculum was 1×10^(8) and 1×10^(6) CFU/mL,respectively.Furthermore,the in situ antifungal effect of the mixed culture was evaluated against bakery product spoilage fungi.It was found that the growth of airborne fungi was delayed for up to 7 days.The cell number of L.plantarum L9 was slightly increased by the presence of P.freudenreichii D6.Quantification of three main acids(propionic,lactic and acetic acid)produced by the protective cultures suggested that acetic acid was mainly responsible for the antifungal activity.In conclusion,the mixed culture of P.freudenreichii and L.plantarum may be exploited as biopreservatives in bakery products.