Data Fusion Analysis Research Articles

Outlier detection of monitored data and unsupervised recognition of construction activities during seismic performance enhancement of historic stone monuments

Abstract To enhance the seismic resilience of historical and cultural heritage sites, protective measures were implemented through the installation of advanced heritage protection platform facilities. A structural health monitoring system was developed to safeguard historical relics during construction activities by continuously monitoring the overall condition of the relics and the integrity of critical components. Key parameters, such as settlement differences, tilt, crack width, and acceleration, were meticulously tracked, with predefined warning and alarm thresholds established. Alerts were triggered whenever these parameters exceeded their respective thresholds, ensuring timely interventions. To ensure the reliability and consistency of the collected data, this study proposes an evaluation method that integrates multi-source data fusion with statistical analysis techniques. Building on this foundation, an unsupervised algorithm was employed to identify construction activities impacting the structural health of the relics. The results demonstrate the effectiveness of combining multi-source data and intelligent algorithms for reliable monitoring and early detection of risks during conservation. The developed system offers automated, real-time assessments and can serve as a model for future heritage protection projects. Looking forward, integrating wireless sensors and diverse data sources could improve system accuracy, efficiency, and cost-effectiveness, further enhancing the protection of cultural heritage.

Tandem Raman microscopy: integration of spontaneous and coherent Raman scattering offering data fusion analysis to improve optical biosensing

We provide tandem Raman microscopy (TRAM), a cutting-edge multimodal microscope that integrates the methods of stimulated Raman scattering (SRS), coherent anti-Stokes Raman scattering (CARS), and spontaneous (resonance) Raman scattering [(R)RS]. The device facilitates sequential continuous wave (CW)-driven RS imaging to collect full spectra from every sample location and rapid pulsed-wave-driven SRS-CARS scanning at specific wavenumbers, offering a reliable and efficient analytical tool. The fingerprint spectral region can be included in the spectral imaging capabilities of CARS and SRS. Data collected from a sample area using several techniques can be integrated and analyzed, significantly increasing reliability and predictions. We analyzed the in vitro model of nonadherent leukocytes (LCs) to illustrate the capabilities of this unique system, emphasizing the benefits of measuring the same sample with three different Raman techniques without having to transfer it between microscopes. Data fusion allowed for the correct classification of two subtypes of LCs based on the partial least squares (PLS) discrimination, increasing the prediction accuracy from approximately 83% in the case of textural and morphological data (SRS) to 100% when combined with spectral data (SRS and RS). We also present RRS images of LC labeled with astaxanthin, and reference data from SRS and CARS microscopy. Additionally, polystyrene beads were investigated as a non-biological material. The advantages of each Raman technique are utilized when (R)RS, SRS, and CARS are combined into a single device. This paves the way for dependable chemical characterization in a wide range of scientific and industrial fields.

Intelligent Recognition for Operation States of Hydroelectric Generating Units Based on Data Fusion and Visualization Analysis

This paper proposes a novel recognition approach for operation states of hydroelectric generating units based on data fusion and visualization analysis. First, the principal component analysis (PCA) is employed to simplify signals from multiple channels into a single fused signal, thereby reducing data computation for multiple‐channel signals. To reflect the features of fused signals under different operation states, the Gramian angular field (GAF) method is applied to convert the fused signals into image formats, including Gramian angular differential field (GADF) images and Gramian angular summation field (GASF) images, then a depthwise separable convolution neural network (DSCNN) model is established to achieve the operation state recognition for the unit by GADF and GASF images. Based on the operation data from a Kaplan hydroelectric unit at a hydropower station in Southwest China, an experiment on operation recognition is conducted. The proposed PCA–GAF–DSCNN method achieves an accuracy rate of 95.21% with GADF images and 96.41% with GASF images, which were higher than the results obtained using original signals with the GAF–DSCNN method. The results indicate that the fused signal with PCA demonstrates superior performance in the operation recognition compared to the original signals, and PCA–GAF–DSCNN can be used for hydroelectric units effectively. This approach accurately identifies abnormal states in units, making it suitable for monitoring and fault diagnosis in the daily operations of hydroelectric generating units.

A Quality Prediction Method for Optimizing the Teaching Mode of History Courses Based on Multi-Category Data Fusion Analysis

In the process of predicting the optimization quality of teaching mode, a single convolutional neural network method is affected by multiple sources of data such as students’ behavioral data and teachers’ evaluations, which is prone to causing modal collapse and affecting the prediction quality. For this reason, we propose a method for predicting the optimization quality of history course teaching mode based on the fusion analysis of multi-class data. After collecting the data of optimizing the quality of teaching mode of historical courses, noise reduction is carried out by the noise reduction self-coder network on the data collection, and the combination of historical data and current data is realized by the dynamic slicing method of multi-feature matrix, after fusing the multi-category data, the data are inputted into the convolutional neural network, and an optimized multi-objective genetic algorithm optimizes the convolutional neural network, stabilizes the convolutional neural network model, and avoids the modal collapse caused by multi-source attributes and categories of the data. The optimized convolutional neural network is used to extract the deep features of the optimized quality of history course teaching mode, and the obtained features are input into the multiple linear regression model as independent variables to obtain the predicted scores of the optimized quality of history course teaching mode. Through experimental verification, the method can realize in-depth cleaning and denoising of the data of each feature of history curriculum teaching mode, and there is a large correlation between the features related to the optimization quality of the five history curriculum teaching modes collected by the method and the final score of the optimization quality of the history curriculum teaching modes, the method predicts that the optimization quality of the history curriculum teaching modes scores and the scores of the expert evaluation are basically consistent.

Multimodal HSI Combined with Multiblock Data Fusion: A New Tool for the Study of Time-Dependent Alteration Processes in Dyed Textiles.

The present study describes an innovative approach for the study of time-dependent alteration processes. It combines an advanced hyperspectral imaging (HSI) system, to collect visible reflectance and fluorescence spectral data sets sequentially, with a tailored multiblock data processing method. This enables the modeling of chemical degradation maps and the early, spatially resolved detection of dye alteration in textiles. A chemometric method based on data fusion and principal component analysis was employed to identify spectral features of dye degradation, combining and enhancing information from reflectance and fluorescence HSI data. The most significant spectral profiles extracted were used to develop an asymmetric Gaussian-based pixel-by-pixel fitting model applied to the HSI fluorescence data set, enabling the reconstruction of degradation maps for rapid and intuitive visualization. In particular, changes in intensities and horizontal shift of dye emission peaks were pixel-by-pixel evaluated and fitted for the reconstruction of the degradation maps. Artificially aged wool samples tinted with indigo carmine (IC) dye served as a case study. IC is extensively used in textiles, and it is notable for its light sensitive. The results show that this approach effectively identifies spatial variations and chemical changes in dyed wool fibers, offering potential for sustainable conservation of historical textiles and other types of time-dependent processes. Thus, by amplifying variation in spectral profiles induced over time by aging, even minimal changes at early stages can be easily detected and localized, offering powerful tools for future studies on food and drug shelf life and stability, as well as forensic trace analysis.

Fault diagnosis of inter‐turn short circuits in PMSM based on deep regulated neural network

AbstractPermanent Magnet Synchronous Machine (PMSM) is widely utilised in numerous industrial applications due to its precise control capabilities. However, these motors frequently encounter operational faults, potentially leading to severe safety and performance issues. Consequently, effective health monitoring techniques for early fault detection are essential to maintain optimal performance and extend the lifespan of these systems. This study presents a qualification‐based methodology for diagnosing faults in three‐phase PMSMs through vibration–current data fusion analysis. The stator faults, specifically inter‐turn short circuits (ITSC) induced via bypassing resistances, were investigated using experimental data from a custom‐built test rig. The collected current and vibration signals were transformed into statistical features. Various operating scenarios were diagnosed utilising a deep regulated neural network (RegNet), an improved convolutional neural network based on an enhanced residual architecture. The proposed approach was assessed through various metrics including training efficiency, precision, recall, f1‐score, and accuracy, and compared against several neural network methods. The findings reveal that the proposed RegNet model achieves perfect accuracy, attaining 100%. This research highlights the efficacy of data fusion analysis and deep learning in fault diagnosis, facilitating proactive maintenance strategies and improving the reliability of PMSMs in diverse industrial applications and renewable energy systems.

A Data Fusion Analysis and Random Forest Learning for Enhanced Control and Failure Diagnosis in Rotating Machinery

A Data Fusion Analysis and Random Forest Learning for Enhanced Control and Failure Diagnosis in Rotating Machinery

Large model-driven hyperscale healthcare data fusion analysis in complex multi-sensors

Large model-driven hyperscale healthcare data fusion analysis in complex multi-sensors

Interval state estimation method for distribution networks considering multi-attribute decision making and multi-source measurement data uncertainty

Interval state estimation method for distribution networks considering multi-attribute decision making and multi-source measurement data uncertainty

Large-scale data fusion in astronomy

Large-scale data fusion in astronomy Peter Melchior, Assistant Professor of Statistical Astronomy from Princeton University, provides a compelling analysis of large-scale data fusion in astronomy. Observational astronomy constantly pushes the limits of what can be observed. We seek to peer deeper into the Universe, extend the wavelength range, or increase the spatial, spectral, and temporal resolution. Observing with the premier telescopes and the latest instruments leads to the groundbreaking advances that move astronomy forward. The discipline is defined by its instruments. Because these instruments are expensive to build and operate, significant specialization and increasingly large scientific collaborations are needed to extract the best science from the data.

RESEARCH ON THE STANDARDIZATION AND VISUALIZATION PLATFORM FOR MONITORING AND TESTING DATA OF METRO CIVIL FACILITIES BASED ON BIG DATA

Introduction: With consideration for extensive standardized detection and monitoring data, multi-source data fusion analysis and comparison were implemented at cross-project and inter-regional levels to provide robust data support for the full life-cycle management of metro civil facilities. The purpose of the study was to integrate detection and monitoring data on metro bridges and tunnel structures and address the significant data isolation issue in existing systems and various units. Based on big data and Internet of Things technology, this paper investigates the standardized format of uploading, storage, processing, sharing, and other types of managing detection and monitoring data on metro bridges and tunnel structures. Additionally, a third-party data standardization and visualization platform for bridges and tunnel structures was developed, ensuring integration of detection and monitoring data fusion. In the course of the study, the following methods were used: theoretical analysis and software system development. As a result, the practicability and feasibility of the platform were verified through practical applications.

3DECG-Net: ECG fusion network for multi-label cardiac arrhythmia detection

Cardiovascular diseases represent the leading global cause of death, typically diagnosed and addressed through electrocardiograms (ECG), which record the heart's electrical activity. In recent years, there has been a notable surge in ECG recordings, driven by the widespread use of wearable devices. However, the limited availability of medical experts to analyze these recordings underscores the necessity for automated ECG analysis using computer-aided methods. In this study, we introduced 3DECG-Net, a deep learning model designed to detect and classify seven distinct heart states through the analysis of data fusion from 12-lead ECG in a multi-label framework. Our model leverages a residual architecture with a multi-head attention mechanism, undergoing training within a five-fold cross-validation scheme. By transforming 12-lead ECG signals into 3D data with the help of Recurrent Plot technique, 3DECG-Net achieves a noteworthy micro F1-score of 80.3%, surpassing the performance of other state-of-the-art deep learning models developed for this specific task. Also, we present an ECG preprocessing framework to generate compact, high-quality ECG signals for potential application in future studies within this domain. We conduct an explainable AI experiment using Local Interpretable Model-agnostic Explanations (LIME) to elucidate the significance of each lead in accurately diagnosing specific arrhythmias, ensuring the logical processing of ECG data by 3DECG-Net. The findings of this study suggest that the proposed model is trustworthy and has the potential to be used as an effective diagnostic toolset for identifying heart arrhythmias. Its effectiveness can improve the diagnostic process, facilitate early treatment, and enhance overall efficiency in medical settings.

Convolutional neural networks-based multi-sensor data fusion analysis for transmission lines

Abstract With the development of the power system, accurate assessment and fault diagnosis of the health status of transmission lines have become increasingly important. However, the standard data fusion algorithms do not fully exploit the correlation and weight disparity among multiple sensors. This study proposes a technique for analyzing transmission lines using a convolutional neural network-based approach to address this issue. By fusing data collected from multiple sensors in different directions, it can more accurately capture key information about transmission lines and conduct comprehensive analysis to evaluate their health status.

Electronic Keyboard Performance based multimodal data fusion and noise fluctuation analysis using machine learning

Electronic Keyboard Performance based multimodal data fusion and noise fluctuation analysis using machine learning

Enhancing Forest‐Steppe Ecotone Mapping Accuracy through Synthetic ApertureRadar‐Optical Remote Sensing Data Fusion and Object-based Analysis

In ecologically vulnerable regions with intricate land use dynamics, such as ecotones, frequent and intense land use transitions unfold. Therefore, the precise and timely mapping of land use becomes imperative. With that goal, by using principal component analysis, we integrated Sentinel-1 and Sentinel-2 data, using an object-oriented methodology to craft a 10-meter-resolution land use map for the forest‐grassland ecological zone of the Greater Khingan Mountains spanning the years 2019 to 2021. Our research reveals a substantial enhancement in classification accuracy achieved through the integration of synthetic aperture radar‐optical remote sensing data. Notably, our products outperformed other land use/land cover data sets, excelling particularly in delineating intricate riverine wetlands. The 10-meter land use product stands as a pivotal guide, offering indispensable support for sustainable development, ecological assessment, and conservation endeavors in the Greater Khingan Mountains region.

Co-expression and Data Fusion Analysis of Omics Data for Liver Related Metabolic Diseases

Co-expression and Data Fusion Analysis of Omics Data for Liver Related Metabolic Diseases

A Review of Multi-source Heterogeneous Twin Data Processing Methods in Traffic Scenes

As the complexity of intelligent public transportation systems continues to increase and the degree of interconnection of equipment at all levels gradually deepens, building a digital twin system will generate a large amount of multi-source heterogeneous data. Effective processing and in-depth mining of data can provide real-time and intelligent decision-making optimization for the construction of digital twin systems, thereby efficiently handling complex emergencies. This paper conducts a systematic review on the processing methods and technologies of multi-source heterogeneous twin data in traffic dynamic scenarios. First, the content and classification of multi-source heterogeneous twin data in the operation process of intelligent bus systems are clarified; secondly, the multi-source The data processing methods and technologies applied in each stage of data collection, data storage, data fusion and data analysis in heterogeneous twin data processing are analyzed, and the advantages, disadvantages and applications of various methods and technologies are analyzed; finally, corresponding to the multiple This paper summarizes the methods and technologies for processing multi-source heterogeneous twin data, and points out the challenges and development trends faced by the current multi-source heterogeneous twin data processing methods and technologies.

Research on A Ship Trajectory Classification Method Based on Deep Learning

The unrestricted development and utilization of marine resources have resulted in a series of practical problems, such as the destruction of marine ecology. The wide application of radar, satellites and other detection equipment has gradually led to a large variety of large-capacity marine spatiotemporal trajectory data from a vast number of sources. In the field of marine domain awareness, there is an urgent need to use relevant information technology means to control and monitor ships and accurately classify and identify ship behavior patterns through multisource data fusion analysis. In addition, the increase in the type and quantity of trajectory data has produced a corresponding increase in the complexity and difficulty of data processing that cannot be adequately addressed by traditional data mining algorithms. Therefore, this paper provides a deep learning-based algorithm for the recognition of four main motion types of the ship from automatic identification system (AIS) data: anchoring, mooring, sailing and fishing. A new method for classifying patterns is presented that combines the computer vision and time series domains. Experiments are carried out on a dataset constructed from the open AIS data of ships in the coastal waters of the United States, which show that the method proposed in this paper achieves more than 95\% recognition accuracy. The experimental results confirm that the method proposed in this paper is effective in classifying ship trajectories using AIS data and that it can provide efficient technical support for marine supervision departments.

Occurrence Frequency of Global Atmospheric River (AR) Events: A Data Fusion Analysis of 12 Identification Data Sets

AbstractThe atmospheric river (AR) is a long, narrow, and transient corridor of strong horizontal water vapor transport. Various AR detection methods have been proposed, which have introduced significant uncertainty to the identified AR characteristics. This study has designed a data fusion algorithm to merge 12 data sets of different global and regional AR identification algorithms published by the Atmospheric River Tracking Method Intercomparison Project (ARTMIP) covering the period from 1980 to 2016. It aims to conduct frequency statistics to further research the global distribution, interannual variation, the trends in poleward shifting, and the impacted factors of AR occurrence. The quantitative results indicate an overall increasing trend in interannual variation, with a more pronounced growth trend observed in the oceanic region between 40 and 60ºS. Additionally, the study identifies a poleward shift in the peak latitude of AR occurrence frequency, with speeds of 0.589° and 0.769° per decade in the Northern and Southern Hemispheres, respectively. This shift may be associated with the tropical poleward expansion. Upon examining the relationship between AR frequency and sea surface temperature (SST) as well as zonal wind, the study finds that distinct dominant factors influence AR in different regions. AR events near the 30°N/S ocean are influenced more significantly by zonal wind than by SST. These findings shed light on the global characteristics of AR occurrences and provide insights into the factors governing their variability across different areas.

CM-GAN: A Cross-Modal Generative Adversarial Network for Imputing Completely Missing Data in Digital Industry.

Multimodal data fusion analysis is essential to model the uncertainty of environment awareness in digital industry. However, due to communication failure and cyberattack, the sampled time-series data often have the issue of data missing. In some extreme cases, part of units are unobservable for a long time, which results in complete data missing (CDM). To impute missing data, many models have been proposed. However, they cannot address the CDM issue, because no observation data of the unobservable units can be obtained in this case. Thus, to address the CDM issue, a novel cross-modal generative adversarial network (CM-GAN) is proposed in this article. It combines the cross-modal data fusion technique and the deep adversarial generation technique to construct a cross-modal data generator. This generator can generate long-term time-series data from widely existing spatio-temporal modal data in modern industrial system, and then impute missing value by replacing them with generated data. To test the performance of CM-GAN, extensive experiments are conducted on photovoltaic (PV) power output dataset. Compared with other baseline models, the performance of CM-GAN is generally better and reaches the state-of-the-art level. Moreover, sufficient ablation studies are conducted to present the contribution of the cross-modal data fusion technique and show the reasonability of parameter settings of CM-GAN. Apart from this, some prediction experiments are also conducted. The results show that the PV data recovered by CM-GAN can provide more predictability information for improving the prediction accuracy of deep learning model.