Image fusion combines complementary information for several input images. To obtain useful information from two misaligned images, registration is required. A hybrid textural registration-based multi-focus image fusion scheme is proposed. The Gabor filtering with specific frequency and orientation is used to extract different texture features from the image. The resulting Gabor-filtered images are then aligned using existing affine transformation. The proposed registration scheme yields superior performance as compared to affine registration, as Gabor transform extracts all the features. The fusion is performed using undecimated dual-tree complex wavelet transform. The quantitative and qualitative analysis of the proposed scheme outperforms existing image fusion schemes. 相似文献
Yogurt is a health food with notable market production and demand. Because of this, we conducted a study on prominent commercial brands of yogurts in Pakistan for microbial content and the probiotic potential of the contained lactic acid bacteria (LAB), in the context of their label claims. All contained viable LAB, but the numbers (cfu g−1) varied considerably. Three of the products made explicit probiotic claims, but LAB from these displayed no probiotic attributes per WHO-FAO guidelines. The yogurt starter and nonstarter Lactobacillus strains had no gelatinase or hemolytic activity and exhibited significant antibacterial activity against some human pathogens. One brand with a probiotic claim contained an L. acidophilus strain that showed cholesterol assimilation activity in vitro. Some potential human pathogens that were hemolytic and resistance to β-lactam antibiotics were also detected in the products. The findings demonstrate a need for better quality control and regulation to ensure safety and efficacy of yogurt products. 相似文献
Generative adversarial network (GAN) models have been successfully utilized in a wide range of machine learning applications, and tabular data generation domain is not an exception. Notably, some state-of-the-art models of tabular data generation, such as CTGAN, TableGan, MedGAN, etc. are based on GAN models. Even though these models have resulted in superior performance in generating artificial data when trained on a range of datasets, there is a lot of room (and desire) for improvement. Not to mention that existing methods do have some weaknesses other than performance. For example, the current methods focus only on the performance of the model, and limited emphasis is given on the interpretation of the model. Secondly, the current models operate on raw features only, and hence they fail to exploit any prior knowledge on explicit feature interactions that can be utilized during data generation process. To alleviate the two above-mentioned limitations, in this work, we propose a novel tabular data generation model—GenerativeAdversarial Network modelling inspired fromNaiveBayes andLogisticRegression’s relationship (\({ { \texttt {GANBLR} } }\)), which not only address the interpretation limitation of existing tabular GAN-based models but provides capability to handle explicit feature interactions as well. Through extensive evaluations on wide range of datasets, we demonstrate \({ { \texttt {GANBLR} } }\)’s superior performance as well as better interpretable capability (explanation of feature importance in the synthetic generation process) as compared to existing state-of-the-art tabular data generation models.
Silicon - This work investigated the electrical properties in AlGaN/GaN/Si HEMTsgrown by molecular beam epitaxy. The electrical behavior have been investigated using by electric permittivity,... 相似文献
Silicon - This research aims to study the behavior of silica based geopolymeric material (22–28%Si) from granitic waste. Granitic waste in powder form was used as main precursor in... 相似文献