Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Mais filtros

Base de dados
Intervalo de ano de publicação
ACS Appl Mater Interfaces ; 13(33): 39719-39729, 2021 Aug 25.
Artigo em Inglês | MEDLINE | ID: mdl-34392680


In this work, cucurbiturils (CBs), a class of macrocyclic supramolecules, were observed to have an interesting peroxidase-like activity, which is metal-free, substrate-specific, thermophilic, acidophilic, and insensitive to ionic strength. By coating CBs on enzyme-encapsulated zeolitic imidazolate framework-8 (ZIF-8), a composite nanozyme was constructed, which retains the catalytic ability of CBs and enzymes and makes them cascade. On addition of the substrate, i.e., the detection target, a highly efficient cascade catalysis can be launched in all the spatial directions to generate sensitive and visible signals. Convenient detection of glucose and cholesterol as models is thereby achieved. More importantly, we have also successfully constructed a composite nanozyme-based sensor array (6 × 8 wells) and thereby achieved simultaneous colorimetric analysis of multiple samples. The concept and successful practice of the construction of the unique core-shell supramolecule/biomolecule@nanomaterial architecture provide the possibility to fabricate next-generation multifunctional materials and create new applications by integrating their unique functions.

Hidrocarbonetos Aromáticos com Pontes/química , Imidazóis/química , Nanocompostos/química , Peroxidases/química , Zeolitas/química , Técnicas Biossensoriais , Hidrocarbonetos Aromáticos com Pontes/metabolismo , Catálise , Colorimetria , Corantes Fluorescentes/química , Glucose Oxidase/química , Glucose Oxidase/metabolismo , Peróxido de Hidrogênio/química , Imidazóis/metabolismo , Simulação de Acoplamento Molecular , Oxirredução , Peroxidases/metabolismo , Impressão Tridimensional
PLoS One ; 15(6): e0234254, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32502197


Neural networks are widely used in automatic credit scoring systems with high accuracy and outstanding efficiency. However, in the absence of prior knowledge, it is difficult to determine the set of hyper-parameters, which makes its application limited in practice. This paper presents a novel framework of credit-scoring model based on neural networks trained by the optimal swarm intelligence (SI) algorithm. This framework incorporates three procedures. Step 1, pre-processing, including imputation, normalization, and re-ordering of the samples. Step 2, training, where SI algorithms optimize hyper-parameters of back-propagation artificial neural networks (BP-ANN) with the area under curve (AUC) as the evaluation function. Step 3, test, applying the optimized model in Step 2 to predict new samples. The results show that the framework proposed in this paper searches the hyper-parameter space efficiently and finds the optimal set of hyper parameters with appropriate time complexity, which enhances the fitting and generalization ability of BP-ANN. Compared with existing credit-scoring models, the model in this paper predicts with a higher accuracy. Additionally, the model enjoys a greater robustness, for the difference of performance between training and testing phases.

Redes Neurais de Computação , Medição de Risco/economia , Área Sob a Curva , Financiamento de Capital , Modelos Estatísticos