Numerous studies have shown that in-depth mining of correlations between multi-modal features can help improve the accuracy of cross-modal data analysis tasks. However, the current image description methods based on the encoder-decoder framework only carry out the interaction and fusion of multi-modal features in the encoding stage or the decoding stage, which cannot effectively alleviate the semantic gap. In this paper, we propose a Deep Fusion Transformer (DFT) for image captioning to provide a deep multi-feature and multi-modal information fusion strategy throughout the encoding to decoding process. We propose a novel global cross encoder to align different types of visual features, which can effectively compensate for the differences between features and incorporate each other’s strengths. In the decoder, a novel cross on cross attention is proposed to realize hierarchical cross-modal data analysis, extending complex cross-modal reasoning capabilities through the multi-level interaction of visual and semantic features. Extensive experiments conducted on the MSCOCO dataset prove that our proposed DFT can achieve excellent performance and outperform state-of-the-art methods. The code is available at https://github.com/weimingboya/DFT.

Combined with wireless power transfer (WPT) technology, mobile edge computing can provide continuous energy supply and computing resources for mobile devices, and improve their battery life and business application scenarios. This paper first designs the mobile edge computing (MEC) model of mobile devices with random mobility and hybrid access point (HAP) with data transmission and energy transmission. On this basis, the selection of target server and the amount of data offloading are taken as the learning objectives, and the task offloading strategy based on multi-agent deep reinforcement learning is constructed. Then combined with MADDPG algorithm and SAC algorithm, the problems of multi-agent environment instability and the difficulty of convergence are solved. The final experimental results show that the improved algorithm based on MADDPG and SAC has good stability and convergence. Compared with other algorithms, it has achieved good results in energy consumption, delay and task failure rate.

Aneuploidy compromises genomic stability, often leading to embryo inviability, and is frequently associated with tumorigenesis and aging. Different aneuploid chromosome stoichiometries lead to distinct transcriptomic and phenotypic changes, making it helpful to study aneuploidy in tightly controlled genetic backgrounds. By deploying the engineered SCRaMbLE (synthetic chromosome rearrangement and modification by loxP-mediated evolution) system to the newly synthesized megabase Sc2.0 chromosome VII (synVII), we constructed a synthetic disomic yeast and screened hundreds of SCRaMbLEd derivatives with diverse chromosomal rearrangements. Phenotypic characterization and multi-omics analysis revealed that fitness defects associated with aneuploidy could be restored by (1) removing most of the chromosome content or (2) modifying specific regions in the duplicated chromosome. These findings indicate that both chromosome copy number and specific chromosomal regions contribute to the aneuploidy-related phenotypes, and the synthetic chromosome resource opens new paradigms in studying aneuploidy.

Spatial transcriptomics is an emerging technology that enables the profiling of gene expression in tissues while preserving spatial location information. This innovative approach is anticipated to provide a comprehensive understanding of the spatial distribution of different cells within tissues and facilitate in-depth analysis of tissue structure. To accurately recognize spatial domains from spatial transcriptomics, we have introduced a generalized deep learning method called GAAEST (Graph Attention-based Autoencoder for Spatial Transcriptomics). Our proposed approach effectively integrates both spatial location information and gene expression data from spatial transcriptomics. Specifically, it leverages spatial location details to construct a neighborhood graph and employs a graph attention network-based encoder to embed gene expression information into a spatially informed space. At the same time, to further optimize the learned potential embedding, self-supervised contrastive learning is introduced to capture spatial information at three levels: local, global and contextual feature of spots. Finally, the decoder reconstructs gene expressions, which are then clustered to identify spatial domains with similar expression patterns and spatial proximity. Based on our experiments conducted on multiple datasets, GAAEST consistently outperforms existing state-of-the-art methods. The proposed GAAEST demonstrates excellent capabilities in spatial domain recognition, positioning it as an ideal tool for advancing spatial transcriptomics research.

In mobile edge computing systems, the edge server placement problem is mainly tackled as a multi-objective optimization problem and solved with mixed integer programming, heuristic or meta-heuristic algorithms, etc. These methods, however, have profound defect implications such as poor scalability, local optimal solutions, and parameter tuning difficulties. To overcome these defects, we propose a novel edge server placement algorithm based on deep q-network and reinforcement learning, dubbed DQN-ESPA, which can achieve optimal placements without relying on previous placement experience. In DQN-ESPA, the edge server placement problem is modeled as a Markov decision process, which is formalized with the state space, action space and reward function, and it is subsequently solved using a reinforcement learning algorithm. Experimental results using real datasets from Shanghai Telecom show that DQN-ESPA outperforms state-of-the-art algorithms such as simulated annealing placement algorithm (SAPA), Top-K placement algorithm (TKPA), K-Means placement algorithm (KMPA), and random placement algorithm (RPA). In particular, with a comprehensive consideration of access delay and workload balance, DQN-ESPA achieves up to 13.40% and 15.54% better placement performance for 100 and 300 edge servers respectively.

Task offloading in mobile edge computing (MEC) improves the efficacy of mobile devices in terms of computing performance, data storage, and energy consumption by offloading computational tasks to edge servers. Efficient task offloading can leverage MEC technology to reduce task processing latency and energy consumption. By integrating the reasoning ability and machine intelligence of the cognitive computing architecture, such as SOAR and ACT-R, reinforcement learning (RL) algorithms have been applied to resolve the task offloading in MEC. To solve the problem that conventional Deep RL (DRL) algorithms cannot adapt to dynamic environments, this paper proposed a task offloading scheduling strategy which combined multi-agent reinforcement learning and meta-learning. In order to make the two actions of charging time and offloading strategy fully considered at the same time, we implemented a learning network of two agent on a mobile device. To efficiently train the policy network, we proposed a first order approximation method based on clipped surrogate objective. Finally, the experiments are designed with variety of the number of subtasks, transmission rate, and edge server performance, and the results show that the MRL-based strategy has the overwhelming overall performance and can be quickly applied in various environments with good stability and generalization.