Search

The rapid growth of the tourism industry has spurred extensive research into tourist route planning. However, existing studies primarily focus on route planning for individual tourists, leaving a notable gap in addressing multiple tourists planning scenarios. Traditional methods for multiple tourists planning, derived from single tourist frameworks, often prioritize the interests and benefits of tourists. This has led to problems like popularity-biased route planning, which exacerbates overtourism in favored destinations and under-tourism in lesser-known spots, thereby undermining sustainable tourism. To address these challenges, we introduce a multi-agent reinforcement learning (RL) framework specifically designed for multiple tourists route planning, incorporating consideration of tourists’ distribution. Our approach consists of two key components: firstly, a novel tourism RL environment that enables interaction with multiple tourists; secondly, a dual-congestion model that considers both local congestion at tourist spots and overall city-wide tourist’ distribution. This dual-congestion mechanism formulates the reward system in our multi-agent RL framework. We validate our framework with comprehensive experiments using real-world human mobility data from Kyoto, a globally renowned tourist city. The results show our model’s superiority over existing methods in optimizing route rewards and managing tourists’ distribution. Additionally, we conducted a user study to examine the effect of our method on tourists’ experience, serving as a reference for our future implementation. The findings indicate that our dual-congestion model slightly affects tourists who prefer popular spots. Our discussion highlights the typically non-cooperative relationship between tourism sustainability and tourist self-interest, underscoring the necessity for a trade-off between them in practical applications. Significantly, our model demonstrates the potential to transform this non-cooperative relationship into a cooperative dynamic.

Advances in deep learning have revolutionized medical image segmentation, facilitating the precise delineation of complex anatomical structures. The scarcity of annotated training samples remains a significant bottleneck. To tackle the data limitation, federated learning (FL) offers the promise of pooling data from multiple healthcare institutions. However, as models grow larger, the increase in communication costs restricts FL to fewer nodes, which constrains the volume of data. This situation necessitates the simultaneous achievement of model lightweighting. To address this problem, this study proposes FKD-Med, a novel framework that integrates FL for privacy-sensitive data amalgamation across multiple healthcare institutions, and uses knowledge distillation (KD) to enhance communication efficiency. The “Med” in FKD-Med refers to medical application computational problems. Our principal contributions encompass the design of an open-source framework that seamlessly blends FL and KD, rendering it applicable to a broad spectrum of medical informatics tasks. Our approach substantially augments the computational data volume, thereby boosting both communication efficiency and training throughput. Tested on two datasets of medical image segmentation using TransUNet and ResUNet as teacher models, FKD-Med achieves data privacy, lowers communication costs, and increases accuracy. The parameters of the student models were reduced to 1/127 and 1/1027 of those in the teacher models. Additionally, the models subjected to KD exhibited accuracy improvements of 0.25%, 0.43%, 1.35%, and 1.46% respectively, given the same parameter volume. This positions FKD-Med not only as a pivotal tool for multi-institutional medical research but also as a versatile platform adaptable to a wide array of real-world medical engineering applications. The code is publicly available at https://github.com/SUN-1024/FKD-Med.

Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional U-Net architectures and their transformer-integrated variants excel in automated segmentation tasks. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transformers. However, they lack the ability to harness the image’s intrinsic position and channel features. Research employing Dual Attention mechanisms of position and channel have not been specifically optimized for the high-detail demands of medical images. To address these issues, this study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to integrate the Transformer and dual attention block (DA-Block) into the traditional U-shaped architecture. Also, DA-TransUNet tailored for the high-detail requirements of medical images, optimizes the intermittent channels of Dual Attention (DA) and employs DA in each skip-connection to effectively filter out irrelevant information. This integration significantly enhances the model’s capability to extract features, thereby improving the performance of medical image segmentation. DA-TransUNet is validated in medical image segmentation tasks, consistently outperforming state-of-the-art techniques across 5 datasets. In summary, DA-TransUNet has made significant strides in medical image segmentation, offering new insights into existing techniques. It strengthens model performance from the perspective of image features, thereby advancing the development of high-precision automated medical image diagnosis. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet.

With the further development of knowledge graphs, many weighted knowledge graphs (WKGs) have been published and greatly promote various applications. However, current deterministic knowledge graph embedding algorithms cannot encode weighted knowledge graphs well. This paper gives a promising framework WeExt that can extend deterministic knowledge graph embedding models to enable them to learn weighted knowledge graph embeddings. In addtion, we introduce weighted link prediction to evaluate the weighted knowledge graph embedding models’ performance on completing WKGs. Finally, we give concrete implementation of WeExt based on two translational distance models and two semantic matching models. Our experimental results show the proposed framework achieves promising performance in link prediction, weight prediction, and weighted link prediction.

Data sparsity is one of the challenges for low-resource language pairs in Neural Machine Translation (NMT). Previous works have presented different approaches for data augmentation, but they mostly require additional resources and obtain low-quality dummy data in the low-resource issue. This paper proposes a simple and effective novel for generating synthetic bilingual data without using external resources as in previous approaches. Moreover, some works recently have shown that multilingual translation or transfer learning can boost the translation quality in low-resource situations. However, for logographic languages such as Chinese or Japanese, this approach is still limited due to the differences in translation units in the vocabularies. Although Japanese texts contain Kanji characters that are derived from Chinese characters, and they are quite homologous in sharp and meaning, the word orders in the sentences of these languages have a big divergence. Our study will investigate these impacts in machine translation. In addition, a combined pre-trained model is also leveraged to demonstrate the efficacy of translation tasks in the more high-resource scenario. Our experiments present performance improvements up to +6.2 and +7.8 BLEU scores over bilingual baseline systems on two low-resource translation tasks from Chinese to Vietnamese and Japanese to Vietnamese.

Sclerotium rot on Pulsatilla koreana was observed in the exhibition field of Jinju Agriculture Technology Center in July 2013. The infected plants showed water-soaked, blighted and rotted symptoms. White mycelial mats spread over lesions, and then numerous sclerotia were formed on flower stalk and flower stem near the soil line. The sclerotia were globoid in shape, 1-3 mm in size and white to brown in color. The optimum temperature for mycelial growth and sclerotia formation on PDA was 30°C and the hyphal width was 4-8 μm. The typical clamp connections were observed in the hyphae of the fungus grown on PDA. For molecular identification, the complete ITS rDNA sequence of the causal fungus was sequenced and analyzed. On the basis of mycological characteristics, ITS rDNA sequence analysis, and pathogenicity to host plants, this fungus was identified as Sclerotium rolfsii Saccardo. This is the first report of sclerotium rot on Pulsatilla koreana caused by S. rolfsii in Korea.