Multi-source relational data fusion

GeoAI in terrain analysis: Enabling multi-source deep learning and data fusion for natural feature detection

Traditional QA systems often rely on shallow semantic retrieval and single-source knowledge, making them insufficient for handling cross-domain queries and multi-hop reasoning. To address these limitations, this study proposes a novel QA framework that integrates multi-source heterogeneous data fusion with knowledge graph-based reasoning. The framework first introduces a multi-channel alignment and fusion module that unifies heterogeneous knowledge sources through entity alignment, relation extraction, and confidence-weighted attribute fusion, constructing a coherent knowledge graph. On this basis, a graph augmentation strategy enhances structural connectivity and semantic completeness. A deep reasoning module, combining relation-aware graph neural networks with query-conditioned multi-hop attention, enables both accurate inference and interpretable reasoning paths. Finally, a joint decoder simultaneously outputs natural language answers and supporting reasoning chains, improving explainability. Extensive experiments conducted on WikiHop, HotpotQA, and ComplexWebQuestions demonstrate the superiority of our model. Compared to strong baselines such as GRAFT-Net, HGN, and KG-QA-Base, our framework achieves consistent improvements of 4–6% in Exact Match (EM) and 5–7% in F1 score. More importantly, Path-Precision improves by 10–12 percentage points, highlighting the ability to generate reliable reasoning evidence. This research not only provides a feasible technical pathway for building interpretable QA systems with deep understanding, but also carries important theoretical and practical implications for advancing the cognitive capabilities of general artificial intelligence.

The application of mobile intelligent terminal in the environment is very complex, and its own computing capacity is also very limited, so it is vulnerable to malicious attacks. The security classification of mobile intelligent terminals can effectively ensure the security of their use. Therefore, a security classification method for mobile intelligent terminals based on multi-source data fusion is proposed. The Boolean value is used to count the multi-source data of the mobile intelligent terminal, and the word frequency method is used to calculate the weight of the multi-source data of the mobile intelligent terminal. The D-S evidence theory is used to complete the multi-source data fusion of the mobile intelligent terminal and implement the multi-source data fusion processing of the mobile intelligent terminal. On this basis, the security level permission value of mobile intelligent terminal is calculated to achieve the security level division of mobile intelligent terminal based on multi-source data fusion. The experimental results show that the accuracy of mobile intelligent terminal security classification is higher than 96% and the classification time is less than 3.8 ms after the application of the proposed method. Therefore, the security level of mobile intelligent terminals after the application of this method is high, and the security performance of mobile intelligent terminals is strong, which can effectively improve the accuracy of security classification and shorten the time of security classification.

To improve the effect of college English teaching, combines multi-source data (MSD) fusion technology to build a college English blended teaching system. Moreover, through the research on the functions of smarter classrooms and the analysis and exploration of blended teaching, this paper designs a college English blended teaching system based on MSD fusion. In addition, this paper analyzes the bandwidth-tunable optical routing module of the interference-coupled series double-ring involved in multi-data fusion. Finally, this paper studies the working principle and structural design of the module, and constructs a college English blended teaching system structure based on MSD fusion. From the evaluation results, it can be seen that the college English blended teaching system based on MSD fusion proposed in this paper can effectively improve the quality of English teaching.

With the rapid development of smart grid technology, a large amount of multi-source heterogeneous data has been generated in the power system, and its effective utilization is crucial for the optimization operation, demand prediction, and anomaly detection of the power system. However, the fusion processing of multi-source heterogeneous data faces many challenges, such as inconsistent data format, granularity, and quality, and direct fusion can easily lead to information redundancy and contradictions. A multi-source heterogeneous data fusion technology based on big data mining has been proposed to address the above issues. This method combines the advantages of convolutional neural networks and gated recurrent units to automatically extract features from image and sequence data and handle long-term dependency issues in time series data. Meanwhile, the K-means clustering algorithm is used to preprocess the data and train a specialized ConvGRU model. The results showed that in short-term load forecasting and abnormal electricity consumption behaviour detection tasks, the accuracy of this method reached 96.3% and 98.7%, respectively, with AUC values of 0.994 and 0.996. Compared to models that use only CNN or GRU, the performance is significantly improved. This method effectively solves the problem of integrating and processing multi-source heterogeneous power data, improves the accuracy and efficiency of power system data analysis, and provides strong support for the optimized operation of smart grids.

In recent years, the tourism field related websites are increasing day by day, the network has produced massive tourist generation data. Based on the semi-structured data of scenic spots, hotels and caterings on tourist websites and the travel notes published by tourists, this paper constructed the tourism knowledge graph. The extraction of entities from travel notes was faced with the problems of named entity recognition and entity alignment. In order to improve the accuracy of extracting entities from travel notes, in this paper, the named entity recognition model based on BiLSTM-CRF and the entity alignment model based on siamese network were proposed. F values can reach 90.8% and 93.0%, respectively.

Focusing on the problems of fragmented video data, variable camera angles and low pixel quality of the existing public aircraft carrier surface support operations, we propose a multi-source video data-driven 3D reconstruction method for ship surface support operations. Firstly, we predict the trajectory direction of the objects in the videos. Then we use the methods of similarity correlation, feature trajectory segmentation,and trajectory clustering to extract/correlate/fuse features in multi-source data. Finally, we integrate the above and realize a realistic three-dimensional reconstruction. The results of experiments and user study on the MOT20 dataset and the public video data of ship surface support operations show that the proposed method can obtain credible 3D reconstruction effects of ship surface support operations.

Successful health risk prediction demands accuracy and reliability of the model. Existing predictive models mainly depend on mining electronic health records (EHR) with advanced deep learning techniques to improve model accuracy. However, they all ignore the importance of publicly available online health data, especially socioeconomic status, environmental factors, and detailed demographic information for each location, which are all strong predictive signals and can definitely augment precision medicine. To achieve model reliability, the model needs to provide accurate prediction and uncertainty score of the prediction. However, existing uncertainty estimation approaches often failed in handling high-dimensional data, which are present in multi-sourced data.

In this paper, the sensor is applied to the collection of rock parameter data. Aiming at the classification and evaluation of stability (i.e. rock quality), an attribute recognition model for the classification and evaluation of surrounding rock quality of underground engineering is established. Using multi-source data fusion and orthogonal numerical simulation test methods, the effects of rock mechanics parameters on the horizontal convergence of the tunnel, the settlement of the vault and the plastic zone coefficient are studied. Six factors (elastic modulus, Poisson’s ratio, internal friction angle, tensile strength, cohesion and density) and three levels of orthogonal experimental solutions were selected. The method of defining similar weight by using similar number to determine the weight of evaluation index, so as to calculate the comprehensive attribute measure, and apply confidence criteria to identify the stability of rock samples. Through the analysis and evaluation of rock mass quality classification of underground engineering, the application of the model and the evaluation method of rock mass quality classification are explained. The test results match the orthogonal test results; Considering the stability of tunnel envelope, the horizontal convergence, vault settlement and plastic zone coefficient after excavation should be comprehensively considered.

With the development of science and technology, various kinds of data become more and more, it is increasingly important to obtain knowledge from data. The field of environmental monitoring is in the same situation. How to quickly and effectively dig out the useful information in large-scale multi-source data has become the biggest problem facing the environmental field. This paper focuses on multi-source data fusion methods, data Mining methods and existing cases, and proposed a multi-source data fusion framework for atmospheric environmental monitoring. The proposed framework effectively enhances the knowledge acquisition ability of environmental monitoring big data.

This paper proposes an optimization algorithm for constructing education knowledge graphs based on multi-source heterogeneous data fusion (MEGO). The algorithm first cleans and extracts features from multi-source education data, and uses deep learning models to mine deep features of different types of data, then dynamically adjusts the weights of each data source through the attention mechanism to achieve efficient fusion of multi-source data, finally, the graph structure is optimized with the help of graph convolutional networks to remove noise and redundant information. The experiment selects <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 0 0, 0 0 0}$</tex> multi-source heterogeneous education data from 10 universities in a certain region within 5 years, and compares them with the traditional TransE algorithm and the KG-Basic algorithm based on a single data source. The results show that the accuracy of the MEGO algorithm is 92.3%, which is 8.7% higher than the TransE algorithm and 12.5% higher than the KG -Basic algorithm, the recall rate is 89.6%, which is 7.2% and 10.8% higher than the two comparison algorithms respectively, the F1 value is 90.9%, which is 7.9% and 11.6% higher respectively, the graph construction time is only 12.5 minutes, which is 35.2% shorter than TransE and 42.8% shorter than KG-Basic. In summary, the MEGO algorithm can effectively improve the quality and construction efficiency of the education knowledge graph, and provide solid technical support for multi-dimensional and precise education quality evaluation.

This study proposes a joint identification algorithm based on multi-source data fusion and Graph Neural Networks (GNN) to simultaneously detect adolescent internet addiction and psychological disorders. With the rapid development of internet technology, adolescent internet addiction has become increasingly prominent, and there exists a complex bidirectional relationship between internet addiction and psychological abnormalities. Traditional single-source data modeling methods struggle to accurately capture these intricate psychological and behavioral patterns. To address this, the study integrates multi-source heterogeneous data, including online behavior logs, psychological assessment data, physiological signals, and social relationships, to construct a Heterogeneous Graph Neural Network (H-GNN) model. Through a multi-task learning mechanism, the model simultaneously predicts the risks of internet addiction and psychological disorders. Experimental results demonstrate that the model outperforms traditional machine learning and deep learning models in terms of accuracy and AUC, effectively capturing the complex interactions between adolescent behaviors, psychological states, and social relationships. Ablation studies further validate the critical role of psychological features in prediction, and the model's potential in real-world applications is highlighted.

In order to solve the problem that the target is easily lost in the process of multisource target data fusion tracking, a multisource target data fusion tracking method based on data mining is proposed. Multisource target data fusion tracking belongs to location level fusion. Firstly, a hybrid heterogeneous network fusion model is established, and then, data features are extracted, and a fusion source big data acquisition algorithm is designed based on compressed sensing to complete data preprocessing to reduce the amount of data acquisition. Based on data mining association multisource fusion target, get the relationship between each measurement and target, and build multisource target data fusion tracking model to ensure the stable state of fusion results. It shows that the proposed method can save the tracking time and improve the tracking accuracy compared with the methods based on NNDA and PDA, which is more conducive to the real-time tracking of multisource targets.

Functional urban land use recognition integrating multi-source geospatial data and cross-correlations

With the booming tourism industry, tourists are increasingly demanding personalized and accurate recommendations for scenic spots. This study focuses on integrating multi-source data to construct and optimize an intelligent scenic spot recommendation model. By integrating multi-source information such as user behavior data, scenic spot attribute data, and spatiotemporal data, and performing pre-processing operations such as cleaning and standardization, the innovative dynamic spatiotemporal attention fusion algorithm (DSTAF) is employed to effectively integrate these multi-source data. Regarding model construction, an overall architecture is designed, comprising a multi-source data input layer, a feature fusion layer, a DSTAF-based core processing layer, and a recommendation output layer. Experimental simulations are conducted using a large-scale tourism dataset and compared with traditional collaborative filtering, contentbased recommendation algorithms, and other advanced algorithms. Experimental results show that the proposed model achieves an accuracy of 85 %, a 20 percentage point improvement over traditional collaborative filtering algorithms; a recall of 80 %, a significant improvement over other compared algorithms; an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F 1$</tex> score of 82.5 %, and an average accuracy of 83 %. These data clearly demonstrate that the intelligent attraction recommendation model based on multi-source data fusion and the DSTAF algorithm has significant performance advantages, enabling users to provide more accurate and personalized attraction recommendations, and providing strong support for the intelligent development of the tourism industry.