Smart Fashion: A Review of AI Applications in Virtual Try-On & Fashion Synthesis

The rapid progress of computer vision, machine learning, and artificial intelligence combined with the current growing urge for online shopping systems opened an excellent opportunity for the fashion industry. As a result, many studies worldwide are dedicated to modern fashion-related applications such as virtual try-on and fashion synthesis. However, the accelerated evolution speed of the field makes it hard to track these many research branches in a structured framework. This paper presents an overview of the matter, categorizing 110 relevant articles into multiple sub-categories and varieties of these tasks. An easy-to-use yet informative tabular format is used for this purpose. Such hierarchical application-based multi-label classification of studies increases the visibility of current research, promotes the field, provides research directions, and facilitates access to related studies.

Study on the effect of the fastener support structure on rail corrugation in metros based on the friction-induce vibration

Rail corrugation is very serious in Cologne egg fastener track; effective control measures are still lacking. The cause of the corrugation wear on a curved metro track is analyzed based on the friction-induced vibration theory. A finite element model is established to study the frequency domain and time domain features of the friction-induced oscillation of this system. The influences of the fastener spacing and the fastener support length on the corrugation wear are investigated to develop countermeasures. The simulation results show that the friction-induced vibration of the wheel-track system is the wavelength-fixed mechanism of the corrugation wear of rail of the curved Cologne egg fastener track. There are two reasons why the low rail corrugation wear is more serious. The contact resultant force between the low rail and the wheel is obviously bigger than that between the wheel and the high rail, resulting in a higher wear rate of the low rail. The contact force fluctuation of the low rail caused by the friction-induced vibration is more severe, resulting in a higher corrugation wear evolution speed on the low rail. The friction-induced oscillation cannot be eliminated only by adjusting the fastener support length and spacing. However, the long-wavelength corrugation wear instead of the more harmful short-wavelength corrugation wear can be produced by adjusting the fastener support length and the fastener spacing to alleviate the influence of corrugation wear on the vehicle-track system.

Exploration Enhanced RPSO for Collaborative Multitarget Searching of Robotic Swarms

Particle Swarm Optimization (PSO) is an excellent population-based optimization algorithm. Meanwhile, because of its inspiration source and the velocity update feature, it is also widely used in the collaborative searching tasks for swarm robotics. One of the PSO-based models for robotic swarm searching tasks is Robotic PSO (RPSO). It adds additional items for obstacle avoidance into standard PSO and has been applied to many single-target search tasks. However, due to PSO’s global optimization characteristics, it is easy to converge to a specific position in the search space and lose the ability to explore further. When faced with the problem of multitarget searching, it may become inefficient or even invalid. This paper proposes an Exploration Enhanced Robotic PSO (E2RPSO) method for multitarget searching problems for robotic swarms. The proposed method modifies the third item in the RPSO as an additional attraction term. This item not only enables the robot to avoid collisions but also guides the swarm to search unexplored regions as much as possible. This operation increases the swarm’s task-specific (top-down) diversity, making the system cover a broader search area and avoid falling into local optimums. Besides, the aggregation degree and evolution speed factors are also included in determining the inertia weight of the proposed method, which adjusts the swarm’s internal (bottom-up) diversity dynamically. The comparison results show that this method can balance the relationship between exploration and exploitation well, which has the potential to be applied to multitarget searching scenarios.

Research on Self-Organizing Evolution Level of China’s Photovoltaic Industry Chain System

According to the self-organizing theory, we first constructed an index system of the self-organizing evolution level of China’s photovoltaic (PV) industry chain system from two aspects: of development level and synergy level. Furthermore, according to the relevant data of China’s PV industry, the self-organizing evolution level of the system from 2008 to 2017 was measured and evaluated by using the system evolution level measurement model and cloud model. Finally, the GM (1, 1) model was used to predict the self-organizing evolution level of the system from 2018 to 2022. The results show that the overall self-organizing evolution level of China’s PV industry chain system shows a rising trend in the ten years from 2008 to 2017, gradually transitioning from a low evolution level to a relatively low evolution level, with the evolution level declining in 2012 and 2015. It is expected that the self-organizing evolution level will continue to maintain a stable and orderly growth trend in the next five years, entering a medium evolution level stage from 2021. If the current evolution speed can be maintained, it is expected to reach a self-organizing evolution state in the next 20 years or so.

Protein evolution speed depends on its stability and abundance and on chaperone concentrations

Proteins evolve at different rates. What drives the speed of protein sequence changes? Two main factors are a protein’s folding stability and aggregation propensity. By combining the hydrophobic–polar (HP) model with the Zwanzig–Szabo–Bagchi rate theory, we find that: (i) Adaptation is strongly accelerated by selection pressure, explaining the broad variation from days to thousands of years over which organisms adapt to new environments. (ii) The proteins that adapt fastest are those that are not very stably folded, because their fitness landscapes are steepest. And because heating destabilizes folded proteins, we predict that cells should adapt faster when put into warmer rather than cooler environments. (iii) Increasing protein abundance slows down evolution (the substitution rate of the sequence) because a typical protein is not perfectly fit, so increasing its number of copies reduces the cell’s fitness. (iv) However, chaperones can mitigate this abundance effect and accelerate evolution (also called evolutionary capacitance) by effectively enhancing protein stability. This model explains key observations about protein evolution rates.