Open Access

With the continuous development of economy, consumers pay more attention to the demand for personalization clothing. However, the recommendation quality of the existing clothing recommendation system is not enough to meet the user’s needs. When browsing online clothing, facial expression is the salient information to understand the user’s preference. In this paper, we propose a novel method to automatically personalize clothing recommendation based on user emotional analysis. Firstly, the facial expression is classified by multiclass SVM. Next, the user’s multi-interest value is calculated using expression intensity that is obtained by hybrid RCNN. Finally, the multi-interest value is fused to carry out personalized recommendation. The experimental results show that the proposed method achieves a significant improvement over other algorithms.

To date, special interest has been paid to composite scaffolds based on polymers enriched with hydroxyapatite (HA). However, the role of HA containing different trace elements such as silicate in the structure of a polymer scaffold has not yet been fully explored. Here, we report the potential use of silicate-containing hydroxyapatite (SiHA) microparticles and microparticle aggregates in the predominant range from 2.23 to 12.40 μm in combination with polycaprolactone (PCL) as a hybrid scaffold with randomly oriented and well-aligned microfibers for regeneration of bone tissue. Chemical and mechanical properties of the developed 3D scaffolds were investigated with XRD, FTIR, EDX and tensile testing. Furthermore, the internal structure and surface morphology of the scaffolds were analyzed using synchrotron X-ray μCT and SEM. Upon culturing human mesenchymal stem cells (hMSC) on PCL-SiHA scaffolds, we found that both SiHA inclusion and microfiber orientation affected cell adhesion. The best hMSCs viability was revealed at 10 day for the PCL-SiHA scaffolds with well-aligned structure (~82%). It is expected that novel hybrid scaffolds of PCL will improve tissue ingrowth in vivo due to hydrophilic SiHA microparticles in combination with randomly oriented and well-aligned PCL microfibers, which mimic the structure of extracellular matrix of bone tissue.

Climate change communication efforts grounded in the information deficit model have largely failed to close the gap between scientific and public understanding of the risks posed by climate change. In response, simulations have been proposed to enable people to learn for themselves about this complex and politically charged topic. Here we assess the impact of a widely-used simulation, World Climate, which combines a socially and emotionally engaging role-play with interactive exploration of climate change science through the CROADS climate simulation model. Participants take on the roles of delegates to the UN climate negotiations and are challenged to create an agreement that meets international climate goals. Their decisions are entered into C-ROADS, which provides immediate feedback about expected global climate impacts, enabling them to learn about climate change while experiencing the social dynamics of negotiations. We assess the impact of World Climate by analyzing pre- and post-survey results from >2,000 participants in 39 sessions in eight nations. We find statistically significant gains in three areas: (i) knowledge of climate change causes, dynamics and impacts; (ii) affective engagement including greater feelings of urgency and hope; and (iii) a desire to learn and do more about climate change. Contrary to the deficit model, gains in urgency were associated with gains in participants' desire to learn more and intent to act, while gains in climate knowledge were not. Gains were just as strong among American participants who oppose government regulation of free markets - a political ideology that has been linked to climate change denial in the US - suggesting the simulation's potential to reach across political divides. The results indicate that World Climate offers a climate change communication tool that enables people to learn and feel for themselves, which together have the potential to motivate action informed by science.

Usually financial crises go along with bubbles in asset prices, such as the housing bubble in the US in 2007. This paper attempts to build a mathematical model of financial bubbles from an econophysics, and thus a new perspective. I find that agents identify bubbles only with a time delay. Furthermore, I demonstrate that the detection of bubbles is different on either the individual or collective point of view. Second, I utilize the findings for a new definition of asset bubbles in finance. Finally, I extend the model to the study of asset price dynamics with news. In conclusion, the model provides unique insights into the properties and developments of financial bubbles.