Search

We tackle explicitly constrained black-box continuous optimization problems in which the feasible domain forms a union of disconnected feasible subdomains. The decoder-based constraint-handling technique is a promising approach when the feasible domain is disconnected. However, the design of a reasonable decoder requires deep prior knowledge of the optimization problem to be solved and, hence, human effort. In this study, we investigated the usefulness of a deep neural network as a decoder and developed a training scheme for a deep neural network without prior information, such as a training dataset consisting of feasible and infeasible solutions required by existing decoder approaches. To stabilize the training of the deep generative model as the decoder, we propose decomposing the decoder into sub-models, introducing skip connections to each sub-model, and training the sub-models sequentially with separate loss functions. Numerical experiments using a test problem and a topology optimization problem show that the proposed method can find feasible domains with better objective function values and higher probability than both conventional decoder-based constraint-handling methods and non-decoder-based constraint-handling methods.

This study focuses on the domain generalization task, which aims to learn a model that generalizes to unseen domains by utilizing multiple training domains. More specifically, we follow the idea of adversarial data augmentation, which aims to synthesize and augment training data with “hard” domains to improve the model’s domain generalization ability. However, previous studies augmented training data only with samples similar to the training data, resulting in limited generalization ability. To alleviate this issue, we propose a novel adversarial data augmentation method, termed GADA (generative adversarial domain augmentation), which employs an image-to-image translation model to obtain a distribution of novel domains that are semantically different from the training domains, and, at the same time, hard to classify. Evaluation and further analysis suggest that GADA fits our expectation; adversarial data augmentation with semantically different samples leads to better domain generalization performance.

Simultaneous data gathering is an application that exploits the unique advantages of wireless sensor networks. Because many sensor nodes access a channel, co-channel interference limits the number of nodes who can access it. To suppress co-channel interference, a frequency spectrum (or channel) is required to obtain large diversity and spreading gains. Cognitive radio with transmit power control exploits available channels because, in this approach, the co-channel interference on the primary system is suppressed and spectrum sharing between the primary system and a secondary system is possible. Prolonging a node’s life is also important in wireless sensor networks. However, in simultaneous data gathering, the power consumed by the relay station (cluster head) is quite high. In this article, a method for constructing a cluster head selection and rotation that is optimal for increasing the number of available channels and prolonging the life of the node is proposed. In simultaneous data gathering, the link with the minimum number of available channels is the bottleneck. Our proposed technique achieves the maximum number of available channels and extends the life of the nodes because of the cluster head rotation. In addition, the optimal number of clusters is also determined.