Online content generation enables automatic and adaptive creation of diverse and playable game content for maximizing player experience or testing Artificial Intelligence (AI) algorithms. Multiple diversity metrics have been formulated on different content facets in the literature, while some of them conflict with one another. Existing work addresses this multi-dimensional diversity nature by converting those metrics into one term that is further used to direct the training of content generators. However, each generator is trained to meet the preference specified by the weights and fails to fully interpret the relationships among these metrics or provide different trade-offs. This paper proposes a multi-objective procedural content generation via reinforcement learning to train a set of generators that create diverse game content in an online manner while balancing the trade-off between multiple diversity metrics with playability as a constraint. Our framework is compared with state-of-the-art approaches on the commonly used Mario-AI benchmark. Results show that our framework is capable of increasing the diversity of the generator distribution while accelerating the convergence during the early stages of model training. Our approach enables researchers, designers, and practitioners to gain a better understanding of the relationship among conflicting diversity metrics, allowing them to generate content more efficiently and accurately tailored to specific needs.

Cervical cancer is a common gynecological cancer, and its common treatment method radiotherapy depends on target area delineation. The manual delineation work takes a long time and has low accuracy, so automating such delineation is important. At present, some traditional image segmentation algorithms for target area delineation have low accuracy rates. Deep learning algorithms also face some difficulties, such as insufficient data and long training time. As the popular network used in medical image segmentation, U-net still has several disadvantages when handling small targets with unclear boundaries. According to the characteristics of the clinical target volume target segmentation task of cervical cancer, this study modified the U-net structure and optimized the training loss to improve the accuracy of small target detection. The modified structure could handle target boundaries well with operations such as bilinear upsampling. Finally, the proposed algorithm was evaluated on the dataset and compared with several deep learning-based algorithms. Results indicate that the proposed approach has certain superiority.

Dynamic heterogeneous graphs comprise different types of events with temporal labels. In many real-world scenarios, the temporal order of different types of events possibly implies causal relationships between these event types. However, existing methods designed to model dynamic heterogeneous graphs neglect the underlying causal relationships between event types. For instance, the determination of the occurrence of a new event is misled by irrelevant historical events considering the type and could lead to performance degradation. First, this paper explicitly defines the causality of event types by the heterogeneous causality graph to utilize such causality from the perspective of the graph structure to tackle the aforementioned issue. Second, this paper proposes the event type causality based continuous-time heterogeneous attention network (ECHN) to model dynamic heterogeneous graphs. ECHN aggregates features based on the strength of different causal relationships between event types in the prediction process to utilize the causality of event types from the perspective of the modeling algorithm. The utilities of event type causality weaken the negative effect of irrelevant events. Experimental results demonstrate that ECHN outperforms state-of-the-arts in the link prediction task. The authors believe that this paper is the first study to model the causality of event types in dynamic heterogeneous graphs explicitly.