Multi-source Heterogeneous Information Research Articles

Drug repositioning based on tripartite cross-network embedding and graph convolutional network

Drug-disease association prediction is an important part of drug discovery, which can help researchers uncover potential drug candidates and disease targets more accurately to deal with the drawbacks of inefficiency and high cost of traditional methods. In contrast, past drug-disease prediction processes often overlooked the associations between drugs and side effects and the impact of proteins on diseases. These issues hindered models from fully learning the potential information within the network. Hence, a method capable of comprehensively learning from multi-source heterogeneous information and extracting high-level features of biological associations is needed. To overcome these challenges, proposes a drug repositioning method based on a tripartite cross-network embedding graph convolutional network, called TGCNDR, to predict the associations between drugs and diseases. Firstly, we construct a tripartite cross-network of drug-disease associations, drug-protein associations, and drug-side effect associations. TGCNDR employs graph convolutional networks to capture information from different nodes to learn drug embedding. Subsequently, TGCNDR uses anchor links for knowledge transfer, and different networks use the Self-attention mechanism to represent drug importance. Experiments on benchmark datasets demonstrate that TGCNDR exhibits good performance (the average AUROC is 0.922, the average AUPR is 0.916, and the average F1-score is 0.860) compared with state-of-the-art methods. In the case study, we perform molecular docking experiments on the predicted drug candidates and identify newly approved drugs for osteosarcoma, which suggests that TGCNDR is an effective tool for drug repositioning.

Knowledge-based digital twin system: Using a knowlege-driven approach for manufacturing process modeling

The Knowledge-Based Digital Twin System is a digital twin system developed on the foundation of a knowledge graph, aimed at serving the complex manufacturing process. This system embraces a knowledge-driven modeling approach, aspiring to construct a digital twin model for the manufacturing process, thereby enabling precise description, management, prediction, and optimization of the process. The core of this system lies in the comprehensive knowledge graph that encapsulates all pertinent information about the manufacturing process, facilitating dynamic modeling and iteration through knowledge matching and inference within the knowledge, geometry, and decision model. This approach not only ensures consistency across models but also addresses the challenge of coupling multi-source heterogeneous information, creating a holistic and precise information model. As the manufacturing process deepens and knowledge accumulates, the model's understanding of the process progressively enhances, promoting self-evolution and continuous optimization. The developed knowledge-decision-geometry model acts as the ontological layer within the digital twin framework, laying a foundational conceptual framework for the digital twin of the manufacturing process. Validated on an aero-engine blade production line in a factory, the results demonstrate that the knowledge model, as the core driver, enables continuous self-updating of the geometric model for an accurate depiction of the entire manufacturing process, while the decision model provides deep insights for decision-makers based on knowledge. The system not only effectively controls, predicts, and optimizes the manufacturing process but also continually evolves as the process advances. This research offers a new perspective on the realization of the digital twin for the manufacturing process, providing solid theoretical support with a knowledge-driven approach.

Deep factor asset pricing with policy guidance based on multi-source heterogeneous information

We propose a novel latent factor pricing model to extract latent pricing factors and corresponding factor loadings from multi-source heterogeneous information through a deep learning architecture. Notably, we pioneer the extraction of policy pricing factors from China’s national strategies (“Five-Year Plans”, “Government Work Reports”, and “Monetary Policy Reports”) using natural language processing and a dynamic topic model. The proposed mixed-frequency deep factor asset pricing (MIDAS-DF) model learns from mixed-frequency heterogeneous data and captures nonlinear joint patterns between inputs and outputs, providing more nuanced insights into asset pricing. The empirical analyses of the Chinese A-share market from January 1, 2003 to July 31, 2022 show that the MIDAS-DF model outperforms competing models in pricing individual stocks, various test portfolios, and investment portfolios. The results also demonstrate that low-frequency policy information anchors long-term pricing trends, while high-frequency market and sentiment information refine short-term pricing accuracy. They work together to enhance the pricing performance.

Weighted probability kernel multi-granularity three-way decision integrating GRA and its application in medical diagnosis

Three-way decision, an outstanding method to handle decision-making uncertainties, relies on essentially the loss functions derived from the Bayesian risk decision process. Actually, there are plentiful loss functions that depend on the subjective judgment of decision-makers under different decision scenarios, lacking uniform and objective measurement frameworks. This study pays attention to the real clinical diagnosis, and constructs a weighted probability kernel multi-granularity three-way decision method (WKMG-TWD) integrating gray relation analysis (GRA) over a multi-source heterogeneous decision information system (MHDIS). The method establishes a standardized data-driven calculation framework of loss functions. Foremost, the multi-kernel probabilistic similarity is defined and granularity's weights with knowledge consistency are explored. Subsequently, a weighted probability kernel multi-granularity rough set (WKMGRS) is constructed in this paper. Secondly, to introduce the three-way decision, this study proposes the cost-sensitive individual loss functions considering the correlation determined by GRA between decision objects and different decision classes. Ultimately, this study establishes and applies a three-way iterative classification model to hypertension diagnosis. The experimental results confirm the effectiveness and superiority of the model. The main contribution of this paper is twofold. One is to offer a uniform calculation framework for loss functions and granularity's weights. The other is to furnish invaluable guidance for solving complex medical decision-making problems.

Self-Supervised Learning and Multisource Heterogeneous Information Fusion Based Quality Anomaly Detection for Heavy-Plate Shape

Plate shape quality anomaly detection suffers from the problems of less labeled and multisource heterogeneous (MSH) data due to the complex production process with multi-process and multi-equipment. To address these problems, this paper proposes a self-supervised learning framework based on MSH contrastive learning (MSH-CL). In the proposed framework, an encoder is designed to extract the MSH information, which contains an MSH feature extract network (MSH-FEN) and an MSH feature fusion network (MSH-FFN). In MSH-FEN, a two-pathway CNN network is employed to extract the MSH feature. Then, a cross-MSH (CMSH) data fusion strategy based on the attention mechanism is designed to characterize the relationship between the MSH data in the MSH-FFN. The learning process consists of two phases, namely the self-supervised feature learning phase based on the contrastive learning (CL) and the supervised fine-tuning phase. The former phase is responsible for training the encoder with massive unlabeled data. Then, a classifier followed by the encoder is built with less labeled data in the supervised fine-tuning phase, which is applied to plate shape quality anomaly detection. Finally, the experiments are carried out on the real-world data set collected from a heavy-plate production process. The experimental results demonstrate the effectiveness and superiority of the proposed approach. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper focuses on the problem of shape quality anomaly detection for the heavy-plate production process, which is crucial to steel-making. However, the most quality-relevant data-driven modeling approaches suffer from the problem of requiring massive labeled data. In addition, the data generated in the practice heavy-plate production process have the characteristics of multisource heterogeneous (MSH). Motivated by the challenge of the less labeled and MSH data modeling, this paper proposed a self-supervised feature learning approach to learn a feature encoder to model the MSH data. Then, fine-tuning is used to obtain the model to detect the plate shape quality. In the feature encoder, a cross-MSH (CMSH) data fusion strategy is proposed. Finally, the effectiveness of the proposed approach is demonstrated by comparing it with other advanced algorithms. The proposed approach can be extended to other heavy-plate quality anomaly detection problems with less labeled and MSH data.

Garlic Origin Traceability and Identification Based on Fusion of Multi-Source Heterogeneous Spectral Information.

The chemical composition and nutritional content of garlic are greatly impacted by its production location, leading to distinct flavor profiles and functional properties among garlic varieties from diverse origins. Consequently, these variations determine the preference and acceptance among diverse consumer groups. In this study, purple-skinned garlic samples were collected from five regions in China: Yunnan, Shandong, Henan, Anhui, and Jiangsu Provinces. Mid-infrared spectroscopy and ultraviolet spectroscopy were utilized to analyze the components of garlic cells. Three preprocessing methods, including Multiple Scattering Correction (MSC), Savitzky-Golay Smoothing (SG Smoothing), and Standard Normalized Variate (SNV), were applied to reduce the background noise of spectroscopy data. Following variable feature extraction by Genetic Algorithm (GA), a variety of machine learning algorithms, including XGboost, Support Vector Classification (SVC), Random Forest (RF), and Artificial Neural Network (ANN), were used according to the fusion of spectral data to obtain the best processing results. The results showed that the best-performing model for ultraviolet spectroscopy data was SNV-GA-ANN, with an accuracy of 99.73%. The best-performing model for mid-infrared spectroscopy data was SNV-GA-RF, with an accuracy of 97.34%. After the fusion of ultraviolet and mid-infrared spectroscopy data, the SNV-GA-SVC, SNV-GA-RF, SNV-GA-ANN, and SNV-GA-XGboost models achieved 100% accuracy in both training and test sets. Although there were some differences in the accuracy of the four models under different preprocessing methods, the fusion of ultraviolet and mid-infrared spectroscopy data yielded the best outcomes, with an accuracy of 100%. Overall, the combination of ultraviolet and mid-infrared spectroscopy data fusion and chemometrics established in this study provides a theoretical foundation for identifying the origin of garlic, as well as that of other agricultural products.

MHIF-MSEA: a novel model of miRNA set enrichment analysis based on multi-source heterogeneous information fusion.

Introduction: MicroRNAs (miRNAs) are a class of non-coding RNA molecules that play a crucial role in the regulation of diverse biological processes across various organisms. Despite not encoding proteins, miRNAs have been found to have significant implications in the onset and progression of complex human diseases. Methods: Conventional methods for miRNA functional enrichment analysis have certain limitations, and we proposed a novel method called MiRNA Set Enrichment Analysis based on Multi-source Heterogeneous Information Fusion (MHIF-MSEA). Three miRNA similarity networks (miRSN-DA, miRSN-GOA, and miRSN-PPI) were constructed in MHIF-MSEA. These networks were built based on miRNA-disease association, gene ontology (GO) annotation of target genes, and protein-protein interaction of target genes, respectively. These miRNA similarity networks were fused into a single similarity network with the averaging method. This fused network served as the input for the random walk with restart algorithm, which expanded the original miRNA list. Finally, MHIF-MSEA performed enrichment analysis on the expanded list. Results and Discussion: To determine the optimal network fusion approach, three case studies were introduced: colon cancer, breast cancer, and hepatocellular carcinoma. The experimental results revealed that the miRNA-miRNA association network constructed using miRSN-DA and miRSN-GOA exhibited superior performance as the input network. Furthermore, the MHIF-MSEA model performed enrichment analysis on differentially expressed miRNAs in breast cancer and hepatocellular carcinoma. The achieved p-values were 2.17e(-75) and 1.50e(-77), and the hit rates improved by 39.01% and 44.68% compared to traditional enrichment analysis methods, respectively. These results confirm that the MHIF-MSEA method enhances the identification of enriched miRNA sets by leveraging multiple sources of heterogeneous information, leading to improved insights into the functional implications of miRNAs in complex diseases.

Multi-source heterogeneous information fusion fault diagnosis method based on deep neural networks under limited datasets

Intelligent fault diagnosis of critical components of rotating machinery is essential for enhancing production efficiency and reducing maintenance costs. However, the scarce labeled samples and the single monitoring data hinder the engineering application and generalization of diagnostic models to some extent. To this end, a novel multi-source heterogeneous information fusion (MSHIF) network is proposed in this paper to identify the health status of rotating machinery more comprehensively and robustly under limited datasets. Specifically, the data enhanced deep belief network (DEDBN) and data enhanced one-dimension convolutional neural network (DE-1DCNN) are firstly designed by repeatedly appending raw data to the hierarchy of conventional deep belief network (DBN) and one-dimension convolutional neural network (1DCNN). DEDBN and DE-1DCNN improve the diagnostic performance of the model under limited datasets while effectively mitigating the loss of potentially valuable information during layer-by-layer feature extraction and compression of DBN and CNN. Then, the MSHIF is further constructed with the designed DEDBN and DE-1DCNN as structural branches. MSHIF aims to alleviate the limitations of scarce labeled samples and single monitoring data on diagnostic performance within a unified framework by mining the rich and complementary device status information in multi-source heterogeneous monitoring data. Extensive comparative experiments and detailed discussions are constructed on both publicly available datasets and rolling mill experimental dataset to verify the feasibility and effectiveness of MSHIF. The experimental results demonstrate that the proposed MSHIF outperforms other comparative methods in terms of diagnostic accuracy, stability, and robustness against noise, achieving 99.491%, 99.143%, and 99.037% average identification accuracy on three cases, respectively.

Optimization of Innovative Paths of Physical Education Teaching in Primary and Secondary Schools under Information Integration Technology

Abstract This article utilizes information fusion technology to provide a more diversified and hierarchical teaching process for physical education, making the content of physical education classroom richer and more vivid. The article firstly discusses the multi-source heterogeneous information fusion technology. It proposes a mass function that combines the output results of the cumulative layer of probabilistic neural network to construct the D-S evidence theory. The D-S evidence theory realizes the decision-level information fusion of the primary results of probabilistic neural networks. In the study, the TPACK knowledge framework was combined with the informationization platform to establish an intelligent classroom for physical education teaching applicable to primary and secondary schools, and a teaching experiment was designed for the selected research subjects. The experiment was conducted to analyze the data mainly from three dimensions: teachers’ and students’ behaviors in the smart classroom, teaching effectiveness and teaching evaluation. The results of data analysis showed that the average time of each learning node of students at the school was more than 50 seconds. At the same time, the coding coverage of teachers’ teaching behaviors was 41.85% lower than the mean value of coding coverage of students’ learning behaviors. In the experimental group, students’ jump rope scores improved by about 9.05% to 20.44% after one month of learning. These findings suggest that an intelligent classroom for physical education teaching relying on information fusion technology can effectively integrate multi-source data, thus providing strong support for improving the effectiveness of physical education teaching in primary and secondary schools.

On-line defect recognition of MIG lap welding for stainless steel sheet based on weld image and CMT voltage: Feature fusion and attention weights visualization

At present, sensor recognition technology has become a research hotspot in welding process monitoring. However, most of the existing defect recognition methods are based on single-sensor information, which hinders the further improvement of recognition accuracy and weakens the anti-interference ability under complex conditions. To overcome the shortcomings of single-sensor recognition technology, multi-source information fusion technology can exploit the advantages of different types of sensors to achieve more comprehensive and accurate monitoring of the welding process. However, given the process of fusion of different information, the feature mining mechanism of the deep learning model is still under-explained, and the direct complementarity of the different information remains unclear. In this paper, we propose a hybrid model that uses the fusion of molten pool image and voltage signals to quickly and accurately identify three types of defects in lap MIG welding: burn-through, weld bias, and uneven width. Firstly, a synchronized trigger device is used to acquire molten pool images and weld voltage information, and the voltage data is sliced and matched with the molten pool image data. Secondly, the Short-Time Fourier Transform (STFT) is applied to explore the frequency variation components in the voltage data, and the resulting time-frequency matrix is transformed into a time spectrogram. Finally, the molten pool image and the time spectrogram are simultaneously fed into the hybrid CNN model for online monitoring of welding defect states. The test results show that the average accuracy of the hybrid CNN model in detecting five different welding states reaches 98.87 %, which is significantly higher than three other models based on single sensor information. The visualization of the confusion matrix and Grad-CAM shows that the hybrid CNN model based on multi-source heterogeneous information has a higher accuracy for detecting the transition states that are difficult to detect in welding, and has a more reasonable mechanism for allocating attention, so it can achieve a more accurate and balanced recognition effect in the whole welding manufacturing process. These studies can provide guidance for quality monitoring of welding processes based on multi-source sensor technology, which can be extended to the field of arc additive monitoring.

An approach to co-medication mechanism mining of Chinese Materia Medica and western medicines based on complex networks with the multi-source heterogeneous information

The co-medication strategy of Chinese Materia Medica (CMM) and western medicines under the holistic integrative medicine (HIM) model offers the advantages of increased efficacy and reduced toxicity, particularly in clinical practice for treating complex and challenging diseases. However, due to the mutual fragmentation of basic theories and principles of medication decision-making between traditional Chinese medicine (TCM) and western medicine, research on the mechanisms for the combined use of CMM and western medicines has become a challenging problem in modern clinical medicine research. Traditional drug combination mining models encounter numerous bottlenecks when dealing with this complex decision-making problem with multi-source information characteristics. This paper aims to mine the optimal drug combination strategy from a real-life decision-making scenario of co-medication between CMM and western medicines. It abstracts this realistic problem as a class of complex network optimal overlapping community detection problem, focusing on solving key difficulties such as the inability of existing drug complex network models to handle the multi-source information of drugs and the randomness in the community detection process. We integrate co-medication prescription information with attribute information to construct the speaker-listener label propagation algorithm based on semantic attribute features (SA-SLPA) and develop a new medicine combination identification strategy based on weighted complex networks. Using 6671 clinically real prescriptions, we conclude that the detection quality of the SA-SLPA method proposed in this paper is improved by up to 78% compared to existing methods. This improvement illustrates the scientificity and effectiveness of the model in this paper and provides new ideas for the application of theoretical models and methods of interdisciplinary disciplines such as decision science, data science, and computational science in the field of modern medicine.

MHANER: A Multi-source Heterogeneous Graph Attention Network for Explainable Recommendation in Online Games

Recommender system helps address information overload problem and satisfy consumers’ personalized requirement in many applications such as e-commerce, social networks and in-game store. However, existing approaches mainly focus on improving the accuracy of recommendation tasks, but usually ignore to improve the interpretability of recommendation, which is still a challenging and crucial task, especially for some complicated scenarios such as large-scale online games. Some few previous attempts on explainable recommendation mostly depend on a large amount of a priori knowledge or user-provided review corpus, which is labor-consuming as well as often suffers from data deficiency. To relieve this issue, we propose a Multi-source Heterogeneous Graph Attention Network for Explainable Recommendation (MHANER) for the case without enough a priori knowledge or corpus of user comments. Specifically, MHANER employs the attention mechanism to model players’ preference to in-game store items as the support for the explanation of recommendation. Then a graph neural network based method is designed to model players’ multi-source heterogeneous information, including the players’ historical behavior data, historical purchase data, and attributes of the player-controlled character, which is leveraged to recommend possible items for players to buy. Finally, the multi-level subgraph pattern mining is adopted to combine the characteristics of a recommendation list to generate corresponding explanations of items. Extensive experiments on three real-world datasets, two collected from JD and one from NetEase game, demonstrate that the proposed model MHANER outperforms state-of-the-art baselines. Moreover, the generated explanations are verified by human encoding comprised of hard-core game players and endorsed by experts from game developers.

HetDDI: a pre-trained heterogeneous graph neural network model for drug-drug interaction prediction.

The simultaneous use of two or more drugs due to multi-disease comorbidity continues to increase, which may cause adverse reactions between drugs that seriously threaten public health. Therefore, the prediction of drug-drug interaction (DDI) has become a hot topic not only in clinics but also in bioinformatics. In this study, we propose a novel pre-trained heterogeneous graph neural network (HGNN) model named HetDDI, which aggregates the structural information in drug molecule graphs and rich semantic information in biomedical knowledge graph to predict DDIs. In HetDDI, we first initialize the parameters of the model with different pre-training methods. Then we apply the pre-trained HGNN to learn the feature representation of drugs from multi-source heterogeneous information, which can more effectively utilize drugs' internal structure and abundant external biomedical knowledge, thus leading to better DDI prediction. We evaluate our model on three DDI prediction tasks (binary-class, multi-class and multi-label) with three datasets and further assess its performance on three scenarios (S1, S2 and S3). The results show that the accuracy of HetDDI can achieve 98.82% in the binary-class task, 98.13% in the multi-class task and 96.66% in the multi-label one on S1, which outperforms the state-of-the-art methods by at least 2%. On S2 and S3, our method also achieves exciting performance. Furthermore, the case studies confirm that our model performs well in predicting unknown DDIs. Source codes are available at https://github.com/LinsLab/HetDDI.

Fault diagnosis strategy of industrial process based on multi-source heterogeneous information and deep learning

With the progress of technology, modern industrial monitoring data not only includes traditional process data but also includes video data. In order to make full use of these multi-source heterogeneous data to achieve better accuracy of fault classification, feature extraction and feature fusion of different modalities is vital important. For feature extraction, because the contribution rate of process data at different times is different to fault classification, in order to obtain the temporal features that have a great impact on fault classification, the Batch Normalization Long Short-Term Memory based on Self-Attention mechanism (BN-LSTM-SA) is used for feature extraction of process data. Since temporal and spatial features are important indicators of video classification, the Two Stream Shifted Windows 3D Convolution Transformer (TSSCT) model is used to extract temporal and spatial features. Cross Multi-head Self-Attention(CMSA) model is designed for feature fusion, which fully utilize the correlation and complementarity of multi-source heterogeneous information and can reasonably allocate the weight of different modalities. Experiments show that our proposed method is superior to the unimodal model or the existing multimodal fusion model and prove the effectiveness of the proposed method.

Inventory Management With Multisource Heterogeneous Information: Roles of Representation Learning and Information Fusion

Inventory Management With Multisource Heterogeneous Information: Roles of Representation Learning and Information Fusion

A Job Recommendation Method Based on Attention Layer Scoring Characteristics and Tensor Decomposition

In the field of job recruitment, a classic recommendation system consists of users, positions, and user ratings on positions. Its key task is to predict the unknown rating data of users on positions and then recommend positions that users are interested in. However, traditional recommendation methods only rely on user rating data for jobs and provide recommendation services for recruiters and candidates through simple information matching. This simple recommendation strategy not only causes a lot of information waste but also cannot effectively utilize the multi-source heterogeneous data information in the field of job recruitment. Therefore, this paper proposes a job recommendation model based on users’ attention levels and tensor decomposition for specific recruitment positions. This model puts forward assumptions based on browsing time for the special behaviors and habits of users in the field of job recruitment, defines corresponding label values for different interactive behaviors, and establishes a grading method based on the attention of job seekers, thus constructing a three-dimensional tensor of “job seeker user-position-attention layered”. Then, a recommendation model is constructed by decomposing the three-dimensional tensor. The effectiveness of the model is verified by comparative experiments with other recommendation algorithms.

Source-Aware Embedding Training on Heterogeneous Information Networks

ABSTRACT Heterogeneous information networks (HINs) have been extensively applied to real-world tasks, such as recommendation systems, social networks, and citation networks. While existing HIN representation learning methods can effectively learn the semantic and structural features in the network, little awareness was given to the distribution discrepancy of subgraphs within a single HIN. However, we find that ignoring such distribution discrepancy among subgraphs from multiple sources would hinder the effectiveness of graph embedding learning algorithms. This motivates us to propose SUMSHINE (Scalable Unsupervised Multi-Source Heterogeneous Information Network Embedding)—a scalable unsupervised framework to align the embedding distributions among multiple sources of an HIN. Experimental results on real-world datasets in a variety of downstream tasks validate the performance of our method over the state-of-the-art heterogeneous information network embedding algorithms.

Thermal deformation prediction for spindle system of machining center based on multi-source heterogeneous information fusion

Thermal deformation prediction for spindle system of machining center based on multi-source heterogeneous information fusion

Identifying the Production–Living–Ecological Functional Structure of Haikou City by Integrating Empirical Knowledge with Multi-Source Data

The inefficient use of urban resources and the imbalance of spatial structures make optimizing land use management a top priority in urban environmental management. Traditional land use classification systems that prioritize only natural features while disregarding human activity can result in redundancy and conflicts in urban planning. The Production–Living–Ecological Space (PLES) approach was developed as an integrated method for territorial spatial classification. However, most existing studies on PLES are conducted at provincial scales, largely overlooking fine-scale usage within cities. In addition, the existing concept of PLES has been vaguely defined, resulting in linear and simple identification methods that are not applicable to complex urban environments. To address these issues, this study proposes a method to identify urban PLES based on supervised classification using random forest models, which integrate empirical knowledge and multi-source heterogeneous information. The experiments conducted in Haikou reveal the regional aggregation of living and production spaces and the scarcity of ecological space in the city. Our study proposes a concrete concept of PLES and a method for identifying PLES that can be applied to multiple regions, providing an effective tool for the coordinated management of urban production, living, and ecological environments.

Real-time comprehensive health status assessment of hydropower units based on multi-source heterogeneous uncertainty information

An effective health status assessment (HSA) method of hydropower unit (HU) is the key to obtaining the real status of HU and providing technical support for safety operation decisions. Thus, a real-time comprehensive HSA method for HUs is proposed. Firstly, a multi-scale data cleaning method based on Gaussian mixture model and density-based spatial clustering of applications with noise (GMM-DBSCAN) is proposed to eliminate outliers and dense anomalies while considering for the variation of operating conditions. Secondly, the correlation analysis method is used to select important measurement points reflecting HU operation status to create multi-source evaluation indices. Then, a novel health indicator (HI) based on Gaussian cloud model (GCM) is proposed to analyze HU condition changes, considering the uncertainty of monitoring signal changes. Further, a hybrid weighting calculation method is proposed to establish a real-time comprehensive health index (RCHI) for assessing HU status. Finally, the proposed approach is verified by a case study using data from a hydropower station in China. The results show that the method improved the stability and smoothness of the state assessment curve compared to other studies.