Search

In order to solve the natural images problems of widely types, complex instruction and low classification accuracy, this paper proposed a new classification method for natural images based on feature-weighted K-nearest neighbors. By analyzing the impact of different features on natural images classification, using genetic algorithm to get a set of optimal classification weight vector, weighted textural features and color features based on that data. Finally, it used the adaptive feature-weighted K-nearest neighbors to classify the natural images. The experimental results show that in the constraint of demand classification accuracy and low time complexity that the user given, this algorithm can classify the natural images with high speed and high-precision. The adaptive feature-weighted K-nearest neighbors classification method is generally apply for the variety of natural images, and can improve the classification performance effectively for natural images. [ABSTRACT FROM AUTHOR]

Quantum dots (QDs)/gel composites have sparked tremendous interests due to their great potentials in sensors. However, in most cases, these sensors are focused on single signal detection, suffers from a key hurdle of low signal density. Thus, it is highly desirable to develop multi-signal QDs/gel-based sensors. In this work, we constructed dual-signal QDs/gel assemblies by a microfluidic-assisted method, which shows promising application in dual-signal sensors. Typically, self-healing QDs/gel beads with different fluorescent signals were fabricated via microfluidic techniques. In virtue of the microfluidic-assisted self-assembly, various dual-signal assemblies were constructed controllably in the confined channels, where self-healing QDs/gel beads serve as building blocks. As expected, the assemblies exhibit rapid dual-signal detection capability toward organic amines and pH values. In addition, by using self-healing gels as printable materials, the combination of the self-assembly strategy with 3D microfluidic printing allows the generation of diverse responsive dual-signal patterns and structures. The self-assembly of self-healing building blocks not only offers a promising route toward fluorescent dual-signal architectures for advanced sensors, but will also guide the development of 3D printing for controllable fabrication of functional assemblies. [ABSTRACT FROM AUTHOR]