The proliferation of delay-sensitive applications in the Internet of Vehicles (IoV) poses significant challenges to conventional vehicular edge computing (VEC), particularly in terms of limited coverage and constrained computing resources. To address these issues, this paper proposes a market-driven air–ground collaborative vehicular edge computing framework that unifies heterogeneous computing services provided by an unmanned aerial vehicle (UAV), roadside unit (RSU), and vehicle platoon (VP) within a common pricing-and-allocation mechanism. The interaction among service providers and the user vehicle (UV) is modeled as a multi-leader single-follower Stackelberg game, where UAV, RSU, and VP act as heterogeneous leaders that announce service prices, and the UV acts as the follower that determines task allocation ratios. The main contribution of this work lies in establishing a unified economic coordination model for heterogeneous air–ground edge services, together with a numerical equilibrium computation framework tailored to the resulting low-dimensional bounded pricing game. We show that the follower-side optimization problem is convex and admits a unique optimal response, and that the upper-level pricing game admits at least one Nash equilibrium. Based on this structure, we develop a coarse-to-fine grid-search-based Stackelberg equilibrium computation method (CFGS-SE), which directly verifies best-response consistency through numerical evaluation and local refinement. Simulation results show that the proposed method achieves high follower utility and low energy consumption while maintaining competitive delay performance and balanced task allocation. These results demonstrate that the proposed framework provides an effective solution for price-guided task allocation in air–ground collaborative vehicular edge computing.

Affordance grounding refers to identifying the interactive regions of an object that enable it to perform a specific function, which is essential for effective robot interaction with complex environments. Current methods face challenges of incomplete localization and unclear distinction of affordance regions. To address these challenges, we propose a novel framework called AffordStruct, which draws on human experiential knowledge to explore affordance structures from the perspectives of spatial configuration and semantic relationships. Specifically, we first compute multi-order spatial interactions from the spatial configuration perspective to enhance long-range pixel dependencies, thereby reinforcing the network’s sensitivity to affordance-relevant regions and suppressing irrelevant areas. Besides, we design a pyramid hierarchical chain-of-thought prompting to guide the large language model in reasoning about affordance structural attributes. An attention-based fusion strategy is then employed to perform multimodal fusion with egocentric images that contain only the target objects, enabling the model to better perceive affordance structures at the semantic level. Finally, based on the local knowledge transfer mechanism, the affordance knowledge extracted from the exocentric view containing human-object interactions is transferred to the multimodal egocentric view. Extensive experiments on public datasets and robotic grasping tasks demonstrate that our method outperforms existing state-of-the-art affordance grounding models.

MOTIVATION: The microbes in human body play a crucial role in influencing the functions of drugs, as they can regulate the activities and toxicities of drugs. Most recent methods for predicting drug-microbe associations are based on graph learning. However, the relationships among multiple drugs and microbes are complex, diverse, and heterogeneous. Existing methods often fail to fully model the relationships. In addition, the attributes of drug-microbe pairs exhibit long-distance spatial correlations, which previous methods have not integrated effectively. RESULTS: We propose a new prediction method named DHDMP which is designed to encode the relationships among multiple drugs and microbes and integrate the attributes of various neighbor nodes along with the pairwise long-distance correlations. First, we construct a hypergraph with dynamic topology, where each hyperedge represents a specific relationship among multiple drug nodes and microbe nodes. Considering the heterogeneity of node attributes across different categories, we developed a node category-sensitive hypergraph convolution network to encode these diverse relationships. Second, we construct homogeneous graphs for drugs and microbes respectively, as well as drug-microbe heterogeneous graph, facilitating the integration of features from both homogeneous and heterogeneous neighbors of each target node. Third, we introduce a graph convolutional network with cross-graph feature propagation ability to transfer node features from homogeneous to heterogeneous graphs for enhanced neighbor feature representation learning. The propagation strategy aids in the deep fusion of features from both types of neighbors. Finally, we design spatial cross-attention to encode the attributes of drug-microbe pairs, revealing long-distance correlations among multiple pairwise attribute patches. The comprehensive comparison experiments showed our method outperformed state-of-the-art methods for drug-microbe association prediction. The ablation studies demonstrated the effectiveness of node category-sensitive hypergraph convolution network, graph convolutional network with cross-graph feature propagation, and spatial cross-attention. Case studies on three drugs further showed DHDMP's potential application in discovering the reliable candidate microbes for the interested drugs. AVAILABILITY AND IMPLEMENTATION: Source codes and supplementary materials are available at https://github.com/pingxuan-hlju/DHDMP.

MOTIVATION: Long noncoding RNAs (lncRNAs) play an important role in the occurrence and development of diseases. Predicting disease-related lncRNAs can help to understand the pathogenesis of diseases deeply. The existing methods mainly rely on multi-source data related to lncRNAs and diseases when predicting the associations between lncRNAs and diseases. There are interdependencies among node attributes in a heterogeneous graph composed of all lncRNAs, diseases and micro RNAs. The meta-paths composed of various connections between them also contain rich semantic information. However, the existing methods neglect to integrate attribute information of intermediate nodes in meta-paths. RESULTS: We propose a novel association prediction model, GSMV, to learn and deeply integrate the global dependencies, semantic information of meta-paths and node-pair multi-view features related to lncRNAs and diseases. We firstly formulate the global representations of the lncRNA and disease nodes by establishing a self-attention mechanism to capture and learn the global dependencies among node attributes. Second, starting from the lncRNA and disease nodes, respectively, multiple meta-pathways are established to reveal different semantic information. Considering that each meta-path contains specific semantics and has multiple meta-path instances which have different contributions to revealing meta-path semantics, we design a graph neural network based module which consists of a meta-path instance encoding strategy and two novel attention mechanisms. The proposed meta-path instance encoding strategy is used to learn the contextual connections between nodes within a meta-path instance. One of the two new attention mechanisms is at the meta-path instance level, which learns rich and informative meta-path instances. The other attention mechanism integrates various semantic information from multiple meta-paths to learn the semantic representation of lncRNA and disease nodes. Finally, a dilated convolution-based learning module with adjustable receptive fields is proposed to learn multi-view features of lncRNA-disease node pairs. The experimental results prove that our method outperforms seven state-of-the-art comparing methods for lncRNA-disease association prediction. Ablation experiments demonstrate the contributions of the proposed global representation learning, semantic information learning, pairwise multi-view feature learning and the meta-path instance encoding strategy. Case studies on three cancers further demonstrate our method's ability to discover potential disease-related lncRNA candidates. CONTACT: [email protected] or [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Briefings in Bioinformatics online.

Dueto its distributed characteristics, the development and deployment of the blockchain framework are able to provide feasible solutions for a wide range of Internet of Things (IoT) applications. While the IoT devices are usually resource-limited, how to make sure the acquisition of computational resources and participation of the devices will be the driving force to realize blockchain at the network edge. In this article, an edge computing-based blockchain framework is considered, where multiple edge service providers (ESPs) can provide computational resources to the devices for mining. We mainly focus on investigating the trading between the devices and ESPs in the computational resource market, where ESPs act as the sellers and devices act as the buyers. Accordingly, a sequential game model is formulated and by exploring the sequential Nash equilibrium (SE), the existence of the optimal solutions of selling and buying strategies can be proved. Then, a deep Q-network-based algorithm with modified experience replay update method is applied to find the optimal strategies. Through theoretical analysis and simulations, we demonstrate the effectiveness of the proposed incentive mechanism on forming the blockchain via the assistance of edge computing.

This paper proposes a small object detection algorithm based on multi-scale feature fusion. By learning shallow features at the shallow level and deep features at the deep level, the proposed multi-scale feature learning scheme focuses on the fusion of concrete features and abstract features. It constructs object detector (MsfNet) based on multi-scale deep feature learning network and considers the relationship between a single object and local environment. Combining global information with local information, the feature pyramid is constructed by fusing different depth feature layers in the network. In addition, this paper also proposes a new feature extraction network (CourNet), through the way of feature visualization compared with the mainstream backbone network, the network can better express the small object feature information. The proposed algorithm is evaluated on MS COCO dataset and achieves the leading performance. This study shows that the combination of global information and local information is helpful to detect the expression of small objects in different illumination. MsfNet uses CourNet as the backbone network, which has high efficiency and a good balance between accuracy and speed.

Abstract Large alphabet languages such as Chinese are very different from English, and therefore present different problems for text compression. In this article, we first examine the characteristics of Chinese, then we introduce a new variant of the Prediction by Partial Match (PPM) model especially for Chinese characters. Unlike the traditional PPM coding schemes, which encodes an escape probability if a novel character occurs in the context, the new coding scheme directly encodes the order first before encoding a symbol, without having to output an escape probability. This scheme achieves excellent compression rates in comparison with other schemes on a variety of Chinese text files.

Summary form only given. We have adapted the PPM model especially for Chinese text and achieve good compression results. We highlighted the importance of pre-processing work for Chinese, as unlike naturally segmented languages such as English, it is not clear what are the most appropriate symbols to use for encoding. We have developed a text compression corpus for Chinese text, and our experiments with this corpus show that the pre-processing work can improve the compression rate significantly. We made several changes in the PPM model to adapt specifically to the Chinese language. Changing the symbol encoding unit to 16 bits captures the structure of the language precisely. Sorting all the characters in context by frequency order improves the program speed significantly and using no exclusions also leads to faster execution speed. This new PPM-Ch model should also achieve similar improvements in other large alphabet size languages such as Japanese, Korean and Thai.