No abstract

This study reports the effect of polydopamine bionic coating and γ-methacryloxypropyltrimethoxysilane (KH570) composite modified polyacrylonitrile (PAN) fiber as a secondary modifier on the performance of styrenebutadiene-styrene (SBS) modified asphalt. Dynamic shear rheometer test indicated the complex shear modulu, storage modulus, and loss modulus of modified PAN (KD-PAN) incorporated SBS modified asphalt was increased by 12.4, 20.5, and 11.2%, respectively compared with PAN/SBS modified asphalt. The master curve of G * of fiber/SBS composite modified asphalt shows that the deformation resistance of KD-PAN/SBS modified asphalt is greater than that of PAN/SBS modified asphalt in the entire loading frequency range. The cone penetration test showed significantly enhanced shear strength of KD-PAN/SBS modified asphalt. The adhesion work test results and SEM images of interface between fiber and SBS modified asphalt revealed that the adhesion effect of KD-PAN and SBS modified asphalt is better than that of PAN and SBS modified asphalt. SEM and AFM images of fiber further showed that the fiber surface becomes rough after modification. The increased surface

No abstract

Gene Expression Programming (GEP), a variant of Genetic Programming (GP), is a well established technique for automatic generation of computer programs. Due to the flexible representation, GEP has long been concerned as a classification algorithm for various applications. Whereas, GEP cannot be extended to multi-classification directly, and thus is only capable of treating an M-classification task as M separate binary classifications without considering the interrelationship among classes. Consequently, GEP-based multi-classifier may suffer from output conflict of various class labels, and the underlying conflict can probably lead to the degraded performance in multi-classification. This paper employs evolutionary multitasking optimization paradigm in an existing GEP-based multi-classification framework, so as to alleviate the output conflict of each separate binary GEP classifier. Therefore, several knowledge transfer strategies are implemented to enable the interation among the population of each separate binary task. Experimental results on 10 high-dimensional datasets indicate that knowledge transfer among separate binary classifiers can enhance multi-classification performance within the same computational budget.

No abstract