Metapath-Based Deep Convolutional Neural Network for Predicting miRNA-Target Association on Heterogeneous Network

Characterization Method of Damage Information Based on Heterogeneous Network

Damage is the main form of conflict, and the characterization of damage information is an important component of conflict evaluation. In the existing research, damage mainly refers to the damage effect of a damage load on the target structure. However, in the actual conflict environment, damage is a complex process that includes the entire process from the initial introduction of the damage load to the target function. Therefore, in this paper, the transfer logic of the damage process is analyzed, and the damage process is sequentially divided into being discovered, being attacked, being hit, and being destroyed in succession. Specifically, first considering the multiple types of each process, the transmission of damage is likened to the flow of damage, a network model to characterize damage information based on heterogeneous network meta-path and network flow theory (HF-MCDI) is established. Then, the characteristics of damage information are analyzed based on the capacity of the damage network, the correlation of the damage path, and the importance of the damage node. In addition, HF-MCDI can not only represent the complete damage information and the transmission characteristics of the damage load but also the structural characteristics of the target. Finally, the feasibility and effectiveness of the established HF-MCDI method are fully demonstrated by the example analysis of the launch platform.

A dual-attention based coupling network for diabetes classification with heterogeneous data

Diabetes Mellitus (DM) is a group of metabolic disorders characterized by hyperglycaemia in the absence of treatment. Classification of DM is essential as it corresponds to the respective diagnosis and treatment. In this paper, we propose a new coupling network with hierarchical dual-attention that utilizes heterogeneous data, including Flash Glucose Monitoring (FGM) data and biomarkers in electronic medical records. The long short-term memory-based FGM sub-network extracts the time-dependent features of dynamic FGM sequences, while the biomarkers sub-network learns the features of static biomarkers. The convolutional block attention module (CBAM) for dispersing the feature weights of the spatial and channel dimensions is implemented into the FGM sub-network to endure the variability of FGM and allows us to extract high-level discriminative features more accurately. To better adjust the importance weights of the characteristics of the two sub-networks, self-attention is introduced to integrate the characteristics of heterogeneous data. Based on the dataset provided by Peking University People's Hospital, the proposed method is evaluated through factorial experiments of multi-source heterogeneous data, ablation studies of various attention strategies, time consumption evaluation and quantitative evaluation. The benchmark tests reveal the proposed network achieves a type 1 and 2 diabetes classification accuracy of 95.835% and the comprehensive performance metrics, including Matthews correlation coefficient, F1-score and G-mean, are 91.333%, 94.939% and 94.937% respectively. In the factorial experiments, the proposed method reaches the maximum area under the receiver operating characteristic curve of 0.9428, which indicates the effectiveness of the coupling between the nominated sub-networks. The coupling network with a dual-attention strategy performs better than the one without or only with a single-attention strategy in the ablation study as well. In addition, the model is also tested on another data set, and the accuracy of the test reaches 94.286%, reflecting that the model is robust when it is transferred to untrained diabetes data. The experimental results show that the proposed method is feasible in the classification of diabetes types. The code is available at https://github.com/bitDalei/Diabetes-Classification-with-Heterogeneous-Data.