With the rapid increase in the use of mobile devices in people's daily lives, mobile data traffic is exploding in recent years. In the edge computing environment where edge servers are deployed in close proximity to mobile users, caching popular data on edge servers can ensure mobile users' low-latency access to those data and reduce the data traffic between mobile users and the centralized cloud. Existing studies consider the data caching problem on the reduction of network delay and the improvement of mobile devices' energy efficiency. In this paper, we tackle this data caching problem in the edge computing environment from a service provider's perspective to maximize its data caching revenue. This problem is challenging because there is a trade-off between the benefit produced and the cost incurred by caching data on edge servers. In the meantime, the constraint for data access latency must also be fulfilled. We formulate the data caching problem in the edge computing environment as an integer programming (IP) problem and prove its NP-completeness. To solve this problem effectively and efficiently in large-scale scenarios, we propose an approximation approach to find near-optimal solutions. Experiments are conducted on a real-world dataset to evaluate our approaches.

In cervical cancer screening, accurate segmentation of cervical nucleus is a key part in the early diagnosis of cervical cancer. However, the cervical nucleus segmentation faces many great challenges owing to the overlapping cervical cells, uneven staining and poor contrast of cervical cytology smear images. In this paper, a tree domain structure and screening algorithm based on depth-first searching strategy are proposed to obtain candidate nucleus regions according to the annular clustering characteristics of nucleus depth information in cervical cytology images. Then, the candidate nucleus regions are finely segmented with an iterative level set algorithm based on adaptive radius morphological dilation. Experimental results are evaluated on the ISBI2015 public dataset. The performance of the proposed nucleus segmentation algorithm is higher than that of the state-of-the-art methods in terms of positive predictive value, negative predictive value, precision, recall of the cervical nucleus segmentation.

To enhance the health and stability of livestock product supply chains, it is imperative to augment product sustainability and satisfy food safety requirements through collaborative green innovation. Digital traceability technology amalgamates information and resources from stakeholders in the supply chain, facilitating knowledge sharing and product tracking throughout the entire process to purify the supply chain environment. Augmenting communication and trust among supply chains paves the way for green innovation, thereby yielding value-added benefits. Consequently, this paper formulates a simulation model for manufacturers, retailers, and consumers—three pivotal stakeholders in the traceability process of livestock products—from a value co-creation standpoint. It also incorporates a contract penalty mechanism to probe the collaborative green innovation process among various entities involved in the livestock product supply chain. System simulation is employed to emulate the evolution path of collaborative green innovation in the livestock product supply chain under the value co-creation perspective. Subsequently, a stepwise penalty mechanism, green incentive mechanism, and fair distribution mechanism are proposed for stakeholders to actualize collaborative green innovation and value creation. The findings reveal that: (1) the collaborative green behavior between suppliers, retailers, and consumers is influenced by factors such as value co-creation excess returns, innovative technology costs like traceability, cost sharing among stakeholders, and a certain threshold of government penalties. (2) A balanced distribution of excess returns and cost-sharing among stakeholders fosters the evolution of a green collaborative state in the supply chain, thereby achieving sustainable development with value chain enhancement and ecological optimization.

Currently, in the field of biomedical named entity recognition, CharCNN (Character-level Convolutional Neural Networks) or CharRNN (Character-level Recurrent Neural Network) is typically used independently to extract character features. However, this approach does not consider the complementary capabilities between them and only concatenates word features, ignoring the feature information during the process of word integration. Based on this, this paper proposes a method of multi-cross attention feature fusion. First, DistilBioBERT and CharCNN and CharLSTM are used to perform cross-attention word-char (word features and character features) fusion separately. Then, the two feature vectors obtained from cross-attention fusion are fused again through cross-attention to obtain the final feature vector. Subsequently, a BiLSTM is introduced with a multi-head attention mechanism to enhance the model’s ability to focus on key information features and further improve model performance. Finally, the output layer is used to output the final result. Experimental results show that the proposed model achieves the best F1 values of 90.76%, 89.79%, 94.98%, 80.27% and 88.84% on NCBI-Disease, BC5CDR-Disease, BC5CDR-Chem, JNLPBA and BC2GM biomedical datasets respectively. This indicates that our model can capture richer semantic features and improve the ability to recognize entities.

To examine how digitally empowered rural e-commerce affects the market-oriented allocation of urban–rural factors at the county level and the underlying mechanism, this study treats the National E-commerce into Rural Counties Demonstration Program as a quasi-natural experiment. Using a panel of 1898 Chinese counties from 2000 to 2022, we conduct multi-period DID with staggered adoption and mediation analyses. The results show that rural e-commerce significantly raises the marketization level of factor allocation; the effect grows stronger over time and is most pronounced during the rapid-expansion phase, in agriculture-oriented e-commerce counties, in poverty-stricken counties, and in the Central and Western regions. The impact operates mainly through three channels: enlarging market size, upgrading industrial structure, and deepening digital financial usage. Notably, the digital finance channel exhibits a suppression effect, suggesting a complex role of financial digitalization in the early stages of rural development. To further ensure the robustness of our findings, we also conduct rigorous checks using the CSDID method and alternative proxy variables, consistently reaffirming the policy’s significant positive impact. These findings offer actionable evidence for deepening county-level factor-market reforms and advancing common prosperity, leading to policy recommendations on strengthening county digital infrastructure, tailoring e-commerce support systems, and improving the institutional environment for factor mobility.