Primary and recency effects based on loading path in classical plasticity

We have established an elastoplastic analysis model to explore the effect of loading path in an incompressible thin-walled tube under the combined action of axial force and torque based on Mises yield condition and isotropic linear hardening assumption.Further,four stress areas(σx,τx)are divided according to the characteristics of the final stress,and the plastic stress-strain relationship of twelve stress paths in different stress areas is derived.The"primary effect"of the stress path on plastic strain is demonstrated,namely,the plastic strain caused by the pre-loaded stress in path A(tensile stress is initially applied,followed by shear stress)is always greater than that caused by the post-loaded stress in path C(shear stress is initially applied,followed by tensile stress)irrespective of the value of final stress.The"recency effect"of the strain path on the stress is also established,which indicates that the stress caused by the post-loaded strain in path A is always greater than that caused by the pre-loaded strain in path C irrespective of the value of final strain.From the perspective of deformation,the"primary effect"of the stress path on the plastic strain and the"recency effect"of the strain path on the stress are unified.These effects are succinct and universal,and they provide useful insights on the plastic stress-strain relationship under different loading paths.Furthermore,they can serve as a useful reference for optimizing the processing technologies and construction procedures.

Improvising Personalized Travel Recommendation System with Recency Effects

A travel recommendation system based on social media activity provides a customized place of interest to accommodate user-specific needs and preferences. In general, the user’s inclination towards travel destinations is subject to change over time. In this project, we have analyzed users’ twitter data, as well as their friends and followers in a timely fashion to understand recent travel interest. A machine learning classifier identifies tweets relevant to travel. The travel tweets are then used to obtain personalized travel recommendations. Unlike most of the personalized recommendation systems, our proposed model takes into account a user’s most recent interest by incorporating time-sensitive recency weight into the model. Our proposed model has outperformed the existing personalized place of interest recommendation model, and the overall accuracy is 75.23%.