Considering the random makespans of assembly jobs, this paper develops a mathematical model of stochastic two-sided assembly line balance problem (STALBP) and designs an improved genetic simulated annealing algorithm (IGSAA) based on priority coding. Firstly, a coding method was proposed based on priority value. Then, the job assembly sequence was derived from the chromosome coding sequence, and the job allocation positions were determined, forming a specific allocation plan. After that, the author designed the corresponding decoding method. To enhance the local search ability of the genetic algorithm (GA), the simulated annealing operation was introduced after the mutation, reversing the individuals in the temporary child population. Next, the superiority of the IGSAA was verified by a set of standard examples, and an actual loader assembly line with normally distributed job makespans was balanced by the proposed algorithm. The research findings provide a valuable reference for the balancing of assembly lines.

No abstract

Previous works propose the distance-based sampling for unlabeled datapoints to address the few-shot person re-identification task, however, many selected samples may be assigned with wrong labels due to poor feature quality in these works, which negatively affects the learning procedure. In this article, we propose a novel sampling strategy to improve the quality of assigned pseudo-labels, thus promoting the final performance. To illustrate, we first propose the concept of variance confidence to measure the credibility of pseudo-labels, then we apply a novel variance subsampling algorithm to improve the accuracy of the selected sample labels. Our method combines distance confidence and variance confidence as a two-round sampling criterion. Meanwhile, a variation decay strategy is used in our sampling process in combination with the actual distribution of features. We evaluate our approach on two publicly available datasets, MARS and DukeMTMC-VideoReID, and achieve state-of-the-art one-shot performance.

No abstract

No abstract