Search

This article investigates the constrained nonsmooth distributed optimization problems (DOPs) of general linear multiagent systems. Our problem involves the general linear dynamics of agents, and the cost functions are nondifferentiable. Moreover, the decisions of agents are constrained by both local and coupled inequalities. Without considering the general linear dynamics, the nonsmooth cost functions, and/or the inequality constraints, existing distributed algorithms are ineffective for our problem. Besides, due to the general linear dynamics, the decisions of agents cannot be determined directly by their control inputs, while the optimal solution must satisfy the constraints. Therefore, it is not easy to design algorithms for our problem. In addition, noteworthily, the global Lipschitz continuity of gradients is an indispensable condition for existing results of DOPs with physical systems. However, the subgradients of nonsmooth cost functions are not Lipschitz continuous, which consequently puts up barriers to algorithm analysis. Based on state/output feedback, subgradient descents, and primal-dual methods, we develop two distributed algorithms. Compared with existing algorithms for DOPs with physical systems, our algorithms are fully distributed. By set-valued Lasalle invariance principle and convex analysis, we analyze the two algorithms rigorously. The first algorithm can solve strictly convex DOPs, in contrast to most results of DOPs with physical systems. The second algorithm only depends on the output information, different from many related algorithms. Finally, the proposed methods are applied to smart grids. With the methods, doubly-fed induction generators can achieve the optimal economic dispatch autonomously.

Age estimation is a significant and active research field in radiological medicine. Recently, researchers have turned their attention to magnetic resonance imaging (MRI) for age estimation, primarily due to concerns regarding ionizing radiation in traditional imaging techniques. In this article, based on the knee MRI dataset, we present a novel end-to-end network that combines convolutional neural network (CNN) and visual transformer network to extract complementary features. In addition, we introduce a feature aggregation module (FAM) that aggregates features from different local knee MRI slices. Our proposed method integrates the feature maps from CNN with the patch embeddings of visual transformer branches, allowing for the acquisition of both local and global information necessary for extracting age-related features. Moreover, we introduce an FAM utilizing the graph attention network (GAT) to achieve interaction between multiple slice features at the feature level. Through extensive experiments conducted on a dataset of 80 knee MRI samples spanning ages 12.0–25.9 years, our method has demonstrated state-of-the-art performance in knee MRI age estimation. Specifically, in a fivefold cross-validation setup, we achieved a mean absolute error (MAE) of 1.52 ± 1.27 years in age regression.

In this work, a novel semisupervised framework is proposed to tackle the small-sample problem of dental-based human identification (DHI), achieving enhanced performance via a “classifying while generating” paradigm. A generative adversarial network (GAN), called the DHI-GAN, is presented to implement this idea, in which an extra classifier is also dedicatedly proposed to achieve an efficient training procedure. Considering the complex specificities of this problem, except for the noise input of the generator, an identity embedding-guided architecture is proposed to retain informative features for each individual. A parallel spatial and channel fusion attention block is innovatively designed to encourage the model to learn discriminative and informative features by focusing on different regional details and abstract concepts. The attention block is also widely applied to the overall classifier to learn identity-dependent information. A loss combination of the ArcFace and focal loss is utilized to address the small-sample problem. Two parameters are proposed to control the generated samples that are fed into the classifier during the optimization procedure. The proposed DHI-GAN framework is finally validated on a real-world dataset, and the experimental results demonstrate that it outperforms other baselines, achieving a 92.5% top-one accuracy rate. Most importantly, the proposed GAN-based semisupervised training strategy is able to reduce the required number of training samples (individuals) and can also be incorporated into other classification models. Our code will be available at https://github.com/sculyi/MedicalImages/.