No abstract

No abstract

Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to train a new model for a new domain by accessing data. Due to public privacy, the new domain data are not always accessible, leading to a limited applicability of these methods. In this paper, we study the problem of multisource domain generalization in ReID, which aims to learn a model that can perform well on unseen domains with only several labeled source domains. To address this problem, we propose the Memory-based Multi-Source Meta-Learning (M 3 L) framework to train a generalizable model for unseen domains. Specifically, a meta-learning strategy is introduced to simulate the train-test process of domain generalization for learning more generalizable models. To overcome the unstable meta-optimization caused by the parametric classifier, we propose a memory-based identification loss that is non-parametric and harmonizes with meta-learning. We also present a meta batch normalization layer (MetaBN) to diversify meta-test features, further establishing the advantage of meta-learning. Experiments demonstrate that our M 3 L can effectively enhance the generalization ability of the model for unseen domains and can outperform the state-of-the-art methods on four large-scale ReID datasets.

As the proportion of wind power in the world's electricity generation increases, improving wind power prediction accuracy is vital for making full use of wind energy and ensuring the safe and stable operation of the power grid. Given the uncertainty and volatility of wind power and the weak generalization ability of the current wind power prediction models, we propose a wind power prediction model that combines Adaboost algorithm with extreme learning machine optimized by particle swarm optimization (PSO-ELM). First, particle swarm optimization is used to optimize the initial thresholds and input weights of the ELM to obtain the PSO-ELM basic prediction model. Then, combined with the Adaboost algorithm, a series of PSO-ELM weak predictors with input weights and thresholds optimized by PSO and containing different hidden layer nodes are composed. Finally, each weak predictor is weighted and fused into a strong prediction model of wind power, and the final prediction results are output. In this paper, the Adaboost-PSO-ELM model is verified by a wind turbine's measured data in Turkey. The prediction indicators are compared with the current wind power prediction methods including optimized neural networks and ensemble learning models. The results show that the Adaboost-PSO-ELM wind power prediction model has higher accuracy and better generalization ability.

The convergence of AI and IoT enables data to be quickly explored and turned into vital decisions, and however, there are still some challenging issues to be further addressed. For example, lacking of enough data in AI-based decision making (socalled Sparse Decision Making, SDM) will decrease the efficiency dramatically, or even disable the intelligent IoT networks. Taking the intelligent IoT networks as the network infrastructure, the recommendation systems have been facing such SDM problems. A naive solution is to introduce trust information. However, trust information may also face the difficulty of sparse trust evidence (a.k.a sparse trust problem). In our work, an accurate sparse decision-making model with two-way trust recommendation in the AI-enabled IoT systems is proposed, named TT-SVD. Our model incorporates both trust information and rating information more thoroughly, which can efficiently alleviate the abovementioned sparse trust problem and therefore be able to solve the cold start and data sparsity problems. Specifically, we first consider the two-fold trust influences from both trustees and trusters, which can be represented by a factor named trust propensity. To this end, We propose a dual model, including a truster model (TrusterSVD) and a trustee model (TrusteeSVD) based on an existing rating-only recommendation model called SVD++, which are integrated by the weighted average and yield the final model, TT-SVD. The experimental results show that our model outperforms the state-of-the-art including SVD and TrustSVD in both the "all users" and "cold start users" cases, and the accuracy improvement can reach a maximum of 29%. Complexity analysis shows that our model is equally suitable for the case of large sparse datasets. In a summary, our model can effectively solve the sparse decision problem by introducing the two-way trust recommendation, and hence improve the efficiency of the intelligent recommendation systems.