APST-Flow: A Reversible Network-Based Artistic Painting Style Transfer Method

In recent years,deep generative models have been successfully applied to perform artistic painting style transfer(APST).The difficulties might lie in the loss of reconstructing spatial details and the inefficiency of model convergence caused by the irreversible en-decoder methodology of the existing models.Aiming to this,this paper proposes a Flow-based architecture with both the en-decoder sharing a reversible network configuration.The proposed APST-Flow can efficiently reduce model uncertainty via a compact analysis-synthesis methodology,thereby the generalization performance and the convergence stability are improved.For the generator,a Flow-based network using Wavelet additive coupling(WAC)layers is implemented to extract multi-scale content features.Also,a style checker is used to enhance the global style consistency by minimizing the error between the reconstructed and the input images.To enhance the generated salient details,a loss of adaptive stroke edge is applied in both the global and local model training.The experimental results show that the proposed method improves PSNR by 5%,SSIM by 6.2%,and decreases Style Error by 29.4%over the existing models on the ChipPhi set.The competitive results verify that APST-Flow achieves high-quality generation with less content deviation and enhanced generalization,thereby can be further applied to more APST scenes.

AN ENGINEERING MODEL FOR MULTICOMPONENT REVERSIBLE REACTION NETWORK

The treatment of a multicomponent reversible reaction network is extremely complicated because largenumber of rate constants must be precisely determined and because the calculation based on these rateconstants is tedious.In order to reduce the degrees of freedom of the process,the authors propose a methodin which the reactor and the separator are regarded as a whole.Based on this approach,an N-componentreversible reaction system can be dealt with as a two—component system.Consequently,a simple and ac-cessible way of the apparent rate determination is suggested.For fiist-order reactions,an explicit,simplifiedexpression has been derived for both lumped and distributed parameter reaction systems.

Topological Confinement in Reversibly Interlocked Polymer Networks

Recently, we reported a series of reversibly interlocked polymer networks(RILNs), whose mechanical robustness and functionalities improvement was believed to be derived from topological interlocking of two sub-networks, although the direct evidence for the deduction is still lacking. Herein, a specially-designed RILNs system, in which the inter-component hydrogen bonds can be shielded as needed, was prepared and used to study the micro-structures of RILNs, aiming to verify the existence of mechanical interlocking in RILNs. By changing the pH of the swelling solvent, the effect exerted by the inter-component non-covalent bonds was eliminated, so detailed information of the networks structure was exposed. The small angle X-ray scattering(SAXS) and small-angle neutron scattering(SANS) results indicated that swelling-induced structural evolution of the two sub-networks mutually affected each other, even when the inter-component hydrogen bonds were absent, proving the presence of topological interlocking. The findings may help to draw a more accurate physical image and reveal the detailed structureproperty relationship of RILNs.

A Hybrid Set of Complexity Metrics for Large-Scale Object-Oriented Software Systems

Large-scale object-oriented（OO） software systems have recently been found to share global network characteristics such as small world and scale free,which go beyond the scope of traditional software measurement and assessment methodologies.To measure the complexity at various levels of granularity,namely graph,class（and object） and source code,we propose a hierarchical set of metrics in terms of coupling and cohesion-the most important characteristics of software,and analyze a sample of 12 open-source OO software systems to empirically validate the set.Experimental results of the correlations between cross-level metrics indicate that the graph measures of our set complement traditional software metrics well from the viewpoint of network thinking,and provide more effective information about fault-prone classes in practice.