Search

Patient similarity networks (PSNs), where patients are represented as nodes and their similarities as weighted edges, are being increasingly used in clinical research. These networks provide an insightful summary of the relationships among patients and can be exploited by inductive or transductive learning algorithms for the prediction of patient outcome, phenotype and disease risk. PSNs can also be easily visualized, thus offering a natural way to inspect complex heterogeneous patient data and providing some level of explainability of the predictions obtained by machine learning algorithms. The advent of high-throughput technologies, enabling us to acquire high-dimensional views of the same patients (e.g. omics data, laboratory data, imaging data), calls for the development of data fusion techniques for PSNs in order to leverage this rich heterogeneous information. In this article, we review existing methods for integrating multiple biomedical data views to construct PSNs, together with the different patient similarity measures that have been proposed. We also review methods that have appeared in the machine learning literature but have not yet been applied to PSNs, thus providing a resource to navigate the vast machine learning literature existing on this topic. In particular, we focus on methods that could be used to integrate very heterogeneous datasets, including multi-omics data as well as data derived from clinical information and medical imaging. [ABSTRACT FROM AUTHOR]

The automated capability of generating spatial prediction for a variable of interest is desirable in various science and engineering domains. Take precision medicine of cancer as an example, in which the goal is to match patients with treatments based on molecular markers identified in each patient’s tumor. A substantial challenge, however, is that the molecular markers can vary significantly at different spatial locations of a tumor. If this spatial distribution could be predicted, the precision of cancer treatment could be greatly improved by adapting treatment to the spatial molecular heterogeneity. This is a challenging task because no technology is available to measure the molecular markers at each spatial location within a tumor. Biopsy samples provide direct measurement, but they are scarce/local. Imaging, such as MRI, is global, but it only provides proxy/indirect measurement. Also available are mechanistic models or domain knowledge, which are often approximate or incomplete. This article proposes a novel machine learning framework to fuse the three sources of data/information to generate a spatial prediction, namely, the knowledge-infused global-local (KGL) data fusion model. A novel mathematical formulation is proposed and solved with theoretical study. We present a real-data application of predicting the spatial distribution of tumor cell density (TCD)—an important molecular marker for brain cancer. A total of 82 biopsy samples were acquired from 18 patients with glioblastoma, together with six MRI contrast images from each patient and biological knowledge encoded by a PDE simulator-based mechanistic model called proliferation-invasion (PI). KGL achieved the highest prediction accuracy and minimum prediction uncertainty compared with a variety of competing methods. The result has important implications for providing individualized, spatially optimized treatment for each patient. Note to Practitioners—This article proposes a machine learning framework to fuse local data, global imaging, and domain knowledge to generate a spatial prediction for a variable of interest. This methodology is relevant to multiple application domains. In precision medicine, it will allow for mapping the spatial distribution of important, treatment-informing molecular markers across each tumor by integrating biopsy data, MRI, and biological knowledge. This capability can help resolve the spatial heterogeneity of molecular characteristics and greatly improve the precision of cancer treatment. Other applications include early detection of regional fire risk across a forest by integrating ground/aerial survey data, satellite imagery, and fire simulator output, as well as regional poverty estimation for resource allocation. [ABSTRACT FROM AUTHOR]

Personality analysis is widely used in occupational aptitude tests and entrance psychological tests. However, answering hundreds of questions at once seems to be a burden. Inspired by personality psychology, we propose a multimodal attention network with Category-based mean square error (CBMSE) for personality assessment. With this method, we can obtain information about one’s behaviour from his or her daily videos, including his or her gaze distribution, speech features, and facial expression changes, to accurately determine personality traits. In particular, we propose a new approach to implementing an attention mechanism based on the facial Region of No Interest (RoNI), which can achieve higher accuracy and reduce the number of network parameters. Simultaneously, we use CBMSE, a loss function with a higher penalty for the fuzzy boundary in personality assessment, to help the network distinguish boundary data. After effective data fusion, this method achieves an average prediction accuracy of 92.07%, which is higher than any other state-of-the-art model on the dataset of the ChaLearn Looking at People challenge in association with ECCV 2016. [ABSTRACT FROM AUTHOR]

Metabolomics plays a critical role in deciphering metabolic alterations within individuals, demanding the use of sophisticated analytical methodologies to navigate its intricate complexity. While many studies focus on single biofluid types, simultaneous analysis of multiple matrices enhances understanding of complex biological mechanisms. Consequently, the development of data fusion methods enabling multiblock analysis becomes essential for comprehensive insights into metabolic dynamics. This study introduces a novel guideline for jointly analyzing diverse metabolomic datasets (serum, urine, metadata) with a focus on metabolic differences between groups within a healthy cohort. The guideline presents two fusion strategies, 'Low-Level data fusion' (LLDF) and 'Mid-Level data fusion' (MLDF), employing a sequential application of Multivariate Curve Resolution with Alternating Least Squares (MCR-ALS), linking the outcomes of successive analyses. MCR-ALS is a versatile method for analyzing mixed data, adaptable at various stages of data processing—encompassing resonance integration, data compression, and exploratory analysis. The LLDF and MLDF strategies were applied to 1H NMR spectral data extracted from urine and serum samples, coupled with biochemical metadata sourced from 145 healthy volunteers. Both methodologies effectively integrated and analysed multiblock datasets, unveiling the inherent data structure and variables associated with discernible factors among healthy cohorts. While both approaches successfully detected sex-related differences, the MLDF strategy uniquely revealed components linked to age. By applying this analysis, we aim to enhance the interpretation of intricate biological mechanisms and uncover variations that may not be easily discernible through individual data analysis. [Display omitted] • MCR-ALS was applied for resonance integration, data compression and exploratory data analysis. • A new guideline is proposed for performing the joint analysis of different metabolomic datasets (serum, urine, metadata). • Two data fusion strategies are proposed which use MCR-ALS in a consecutive way. • Both methodologies were able to successfully merge and process the multiblock datasets. [ABSTRACT FROM AUTHOR]

• The relationship between repeatability error and data confidence is established. • The spatial error prediction model based on confidence weighting is derived. • The simulation process based on statistics is designed. • A spatial error measurement scheme based on data fusion is proposed. • The accuracy and reliability are verified on a horizontal machining center prototype. A spatial error prediction method for precision machine tools considering the influence of repeatability errors is proposed in this paper. Firstly, the reciprocal of the repeatability error is used to evaluate the measurement data confidence to distinguish the difference of useful information contained in the measurement data of different positions. Secondly, the proposed confidence index is used to weight the measured values of PDGEs at different positions, so that the data containing more useful information can play a full role in the error prediction, and the predicted error is substituted into the error model to predict the spatial error. Then, the computer simulation based on statistical analysis is designed, the PDGEs and spatial error prediction accuracy of the weighted algorithm are verified by simulation. Finally, a multi-instrument fusion spatial error measurement scheme is proposed, and the accuracy and reliability of the model are verified on a horizontal machining center prototype. [ABSTRACT FROM AUTHOR]

• The time transfer link is a necessary support for Universal Time Coordinated. In order to improve the accuracy of time transfer link, it is imperative to study appropriate data fusion methods. • Before fusing data, time scale matching must typically be finished and interpolated in the time domain due to the varying sample intervals of various time transfer link types. The method showed in this article uses wavelet analysis methods to decompose raw data into many approximation signals at different sampling rates as needed, is very ideal for processing data of time transfer links at different sampling rates. • The fusion method has the capacity to specifically suppress the link's phase modulation and frequency modulation white noise, thereby increasing the accuracy of the links. The stability of the links has also been somewhat enhanced at the same time. • The fusion approach also works well to deal with jumps and data loss brought on by unusual system conditions. To raise the precision and stability of time transfer links, a wavelet-based multi-resolution data fusion technique is offered. This approach fixes the "Day-Boundary discontinuities" in global positioning system (GPS) precise point positioning (PPP) link and lessens the diurnal in Two-way satellite time and frequency transfer (TWSTFT) link by integrating the model-based dynamic system analysis method with the statistically based multi-scale signal transformation method. It can also handle data from GPS PPP links and TWSTFT links at different sampling rates. More specifically, after applying wavelet transformation to the raw data and Kalman filtering estimation on various scales, this method uses the Mallat fast reconstruction algorithm of wavelet transform to achieve the fused results. The National Time Service Center (NTSC) and the Physikalisch-Technische Bundesanstalt (PTB) handle time transfer results using this method. Experiments show that this strategy greatly improves the link's short-term stability and can manage atypical interruptions while also boosting the link's robustness and reliability, which has a wide range of possible applications. [ABSTRACT FROM AUTHOR]

[Display omitted] • To improve the accuracy of the model and reduce the computational effort, three algorithms including UVE, CARS and PCA are used to extract the spectral features from terahertz absorption spectra and refractive index spectra. • Because of the large data volume of terahertz time-domain spectra, temporal features, including maximum value, minimum values, variance, are calculated to subsequent data processing. • To further enhance classification accuracy of classifiers, the data fusion method of feature-level fusion is employed. • The results show that the performance of data fusion model is best than that of the model using single-type spectra. The model with the highest prediction accuracy is the KNN model, with an accuracy of 97.37%, when the refractive index spectra and time-domain spectra are fused as inputs. Rubber, an essential industrial product, plays a crucial role in industry and human life. However, some manufacturers of rubber use inferior, recycled or low-cost rubber materials to replace high-quality rubber products. Therefore, in order to ensure industrial production, protect natural environment and ensure personal safety, it is of great economic and social significance to enable rapid and non-destructive qualitative identification of rubber products. In this paper, eight different types of black rubber, including Nitrile Butadiene Rubber (NBR), Choloroprene Rubber (CR) and Ethylen Propylen Diene Monomer (EPDM), were selected as research objects. Terahertz Time-Domain Spectroscopy (THz-TDS) technology was utilized to get the absorption spectra, refractive index spectra and time-domain spectra of these samples for exploring the differences between different types of rubber in terahertz spectra. To reduce the data volume, three band selection algorithms were employed to extract features from the absorption spectra and refractive index spectra, and temporal features of time-domain spectra were extracted for subsequent data processing. In the selection of classification model algorithms, K-Nearest Neighbor (KNN), Random Forest (RF) and Supervised Kohonen Neural Networks (S-Kohonen) were employed to recognize these spectral data. To fully exploit the latent information within these data and considering the possibility of the loss of partial information in single-type signal, a feature-level data fusion method was applied to different optical parameter signals to obtain more information about terahertz spectra during the process of data modeling. The results of the research indicated that the model with the highest prediction accuracy was the KNN model, with an accuracy of 97.37%, when refractive index spectra and time-domain spectra were fused as inputs, the F1-score reached 99.64. The performance of data fusion was noticeably better than that of a single-type signal. This study validates the feasibility of using terahertz time-domain spectroscopy for qualitative identification of different types of rubber. [ABSTRACT FROM AUTHOR]

• A novel probabilistic model to study process dynamics, data variabilities, and diverse source data fusion. • The model tested on two cases, an enzymatic reaction system and a real-world scenario of pandemic risk forecasting. • The enzymatic reaction system case depicts effectiveness of the proposed model in a closed system with limited data. • The pandemic risk forecasting case illustrates the scope of the proposed model to open system. • Both cases demonstrate data fusion from different sources. This work presents a hierarchical Bayesian network-based model for handling dynamic nature, data variabilities, and information fusion in a dynamical process system. The overall dynamics has been captured by physics-based models while uncertainty and local variabilities in the model parameters have been accounted for by using a hierarchical Bayesian network formalism. The resulting semi-mechanistic model has been investigated in two cases, a simulated case of an enzymatic reaction system and a real-world scenario of pandemic risk forecasting. The first case study on the enzymatic reaction system shows effectiveness of the proposed semi-mechanistic framework in a closed system with limited data from different sources. The second case illustrates scope of the proposed semi-mechanistic framework to open systems by investigating transmission of disease under evolving conditions of the advent of multiple waves of a pandemic outbreak. The findings have been presented in terms of the most probable values and credible intervals that account for data variabilities in different scenarios. The model is benchmarked and validated for the fatality forecast of the Coronavirus Disease of 2019 by the observed data and benchmark models reported by the Center for Disease Prevention and Control of the United States [ https://covid.cdc.gov/covid-data-tracker/#datatracker-home ]. [ABSTRACT FROM AUTHOR]

Experienced firefighters can fuse the flame image, smoke pattern, and varying temperature, sound, and odour in complex and fast-changing fire scenes to foresee flashover and explosion. This study mimics firefighters and proposes a novel transformer algorithm for the fusion of fire images and temperature sensor data to forecast the backdraft explosion in a building fire. The model of backdraft forecast is demonstrated with full-scale fire tests. After training 2674 fire scenarios with various fire intensities and images from various view angles, the Fusion-Transformer model can forecast the risk of backdraft with an overall accuracy of 84%. Moreover, the occurrence time and explosion scale of backdraft can be predicted with the Mean Absolute Error (MAE) of 1.6 s and 0.14 m, respectively. Compared with the single modal model, the fusion of fire images and temperature sensor data improves the accuracy of backdraft forecast by over 50%. This work demonstrates the use of a transformer algorithm in forecasting fire evolution and critical events. It also bridges the gap between data fusion methods and fire forecast, which inspires future universal AI-driven smart firefighting practices. [Display omitted] • Full-scale fire experiments are conducted to establish a real backdraft fire database. • Visual and temperature sensor data are integrated in a data fusion model to forecast backdraft. • The AI model via fusing visual and temperature data predicts backdraft with accuracy of 84%. • The multimodal model demonstrates a prototype of future smart firefighting application. [ABSTRACT FROM AUTHOR]

The fusion of RGB and thermal data for dense prediction tasks has been demonstrated to be an effective and robust approach in autonomous driving. Nevertheless, the challenge lies in fusing features from different modalities, as a simple fusion strategy may lead to redundant or conflicting semantic information. In this paper, we delve into the hierarchical connections between multi-modal features and propose a novel fusion paradigm termed DHFNet, which decouples multi-modal features into similar global long-distance and discrepant local detail features for hierarchical feature fusion. At each fusion stage, a Lightweight Global Self-attention (LGSA) module is designed to decouple the global long-distance features with cheap computational complexity cost, and a Cross Modal Long-distance Feature Fusion (CMLFF) module is designed to eliminate redundant features by facilitating information interaction between different modalities. During the process of decoupling local detail features, a Cross Modal Deformable Convolution (CMDC) module is proposed to dynamically extract effective local features and capture misaligned features between different modalities. Finally, the fused global long-distance and local detail features are recoupled to achieve efficient hierarchical fusion. The results on RGB-T semantic segmentation and object detection tasks demonstrate the effectiveness of proposed method. The code will be available at: https://github.com/donggaomu/DHFNet. [ABSTRACT FROM AUTHOR]

6-DoF grasp estimation methods based on point clouds have long been a challenge in robotics due to the limitations of single data input, which hinder the robot's perception of real-world scenarios, thus reducing its robustness. In this work, we propose a 6-DoF grasp pose estimation method based on RGB-D data, which leverages ResNet to extract color image features, utilizes the PointNet++ network to extract geometric information features, and employs an external attention mechanism to fuse both features. Our method is an end-to-end design, and we validate its performance through benchmark tests on a large-scale dataset and evaluations in a simulated robot environment. Our method outperforms previous state-of-the-art methods on public datasets, achieving 47.75mAP and 40.08mAP for seen and unseen objects, respectively. We also test our grasp pose estimation method on multiple objects in a simulated robot environment, demonstrating that our approach exhibits higher grasp accuracy and robustness than previous methods. [ABSTRACT FROM AUTHOR]

• An experimental variational mode decomposition (VMD)-based data-fusion displacement measurement framework is proposed. • Vision, acceleration, and fusion methods are compared. • A four-story RC structure on a 25-ton table is detailed. Dynamic displacement is a crucial parameter in structural health monitoring (SHM) for assessing the safety, dependability, and suitability of structures under various types of excitations. Computer vision-based methods for dynamic displacement estimation have attracted much interest owing to their cost-effectiveness and convenience. However, these methods are limited by their low sampling rates and high data sensitivity. To compensate for these limitations, methods for combining data obtained from other sensors have been proposed. In this study, an experimental data-fusion framework for displacement estimation based on variational mode decomposition (VMD) was developed to leverage the advantages of vision- and acceleration-based measurements. The measurements were decomposed into ensembles of modes and recomposed to reconstruct the displacement with a higher accuracy and over a wider frequency range. An optimal mode recomposition method was proposed to achieve optimal mode combinations. Furthermore, this study introduced an improved vision-based displacement measurement method and a VMD-based indirect acceleration measurement method. The proposed framework was validated through four-story RC structure tests, which demonstrated that the method could enhance the accuracy of displacement estimation and extend the feasible frequency range compared with single-source displacement measurements. The method provides a promising solution for more effective health monitoring of modern structures subjected to a wide variety of dynamic loads. [ABSTRACT FROM AUTHOR]

The angular vibration sensors must be calibrated regularly to ensure the precise measurement of dynamic angle motion in various engineering applications such as attitude estimation, inertial navigation, and machine automation. Currently, the high-accuracy vibration calibration has been developed in the medium and high-frequency range. However, it is difficult to accomplish such calibration over a wide low-frequency band because the current angular exciter cannot generate the high-dynamic and low-distortion excitation acceleration for the sensors. Aiming at this problem, a complementary filter-based data fusion control method is proposed and successfully applied to an exciter for achieving high-precision calibration in a wide low-frequency range. The results demonstrate that the proposed method has the ability to generate high-dynamic and low-distortion excitation accelerations in the range of 0.01 Hz-150 Hz. The maximum total harmonic distortion of these excitations measured by the commonly used laser interferometry and circular grating ruler method is 0.80 % and 0.42 %, respectively. In addition, the corresponding maximum relative standard deviation is 0.039 % and 0.005 %. The experiment results show that the proposed method can well meet the high-accuracy calibration requirements. [Display omitted] • A broad-band and low-distortion excitation generation method was proposed. • Several amplitude-frequency response and vibration excitation measurements were accomplished. • The working frequency band, THD and RStd comparison experiments were achieved. [ABSTRACT FROM AUTHOR]

The current nondestructive inspection paradigm of mono-modal testing and signal-over-threshold call criteria is insufficient for characterization of microtexture regions in titanium alloys, which exceeds the capabilities of any single, practical sensing technique that could be deployed to a manufacturing environment for quality control. In this work, we develop a data fusion-based solution to microtexture region characterization. The material problem and potential inspection methods are reviewed, and registered datasets are presented. Next, we develop a data fusion algorithm that combines covariance-generalized matching component analysis and a conditionally Gaussian hypermodel to successfully estimate the boundaries and average crystallographic orientations of microtexture regions from scanning electron microscopy electron backscatter diffraction and eddy current testing data. • Ti MTR cannot be characterized in a practical environment for quality control. • Inspection techniques like SAM and ECT are sensitive to key MTR parameters. • A conditionally Gaussian hypermodel enables MTR characterization from fused SEM/ECT. [ABSTRACT FROM AUTHOR]

Accurate forecasting of regional solar photovoltaic power (SPVP) generation is essential for efficient energy management and planning. Existing approaches have shown the effectiveness of decomposing the time series to model the stochastic variability in SPVP data. However, these approaches have limitations in extracting and exploiting both spatial and temporal information from complex and high-dimensional data from multiple sources with intricate relationships, which can impact the accuracy of predictions. In this paper, we propose a novel approach called multilevel data fusion and neural basis expansion analysis (MF-NBEA) for forecasting aggregated regional-level SPVP generation. MF-NBEA integrates exogenous data at multiple levels, uses supervised and unsupervised encoders to provide compact data representation, and enhances model learning from complex data by incorporating spatial information. It also includes a sequence analyser module based on a neural network decomposition mechanism to learn the variability in data and incorporates a residuals learner module to improve overall predictions. We evaluate MF-NBEA using two real-world datasets and find that it outperforms state-of-the-art deep learning methods in terms of forecast accuracy. Furthermore, MF-NBEA facilitates information fusion and knowledge extraction to provide interpretable predictions regarding trend, seasonality, and residual components. The insights gained from our approach inform decision-making for energy management and planning, and can lead to more efficient and sustainable resource utilisation. • MF-NBEA for multivariate solar power time series forecasting. • A 3D autoencoder encodes spatial and temporal information from heterogeneous sources. • Interpretable forecasting in terms of trend, seasonality, and residuals. [ABSTRACT FROM AUTHOR]

Land use changes are analyzed correctly, a series of improvements according to the changes are carried out appropriately, the relationship between land use development and economic and human survival is handled correctly, and the healthy and orderly development of the entire society is promoted. Aiming at the combination of multisource remote sensing data and monitoring changes in land planning, this study uses CBERS data and ASAR data as multisource remote sensing data sources to conduct in-depth research and discussion on the land use change in this area and uses the HPF pixel-level fusion method for data fusion to generate HPF. The data are integrated, and then, the CBERS data and HPF fusion data are used to extract the land use type information of Zhenning County, respectively, and a confusion matrix is built based on the field sample points to verify the accuracy, compare and analyze the relative error of the land use type information extraction before and after data fusion, and evaluate the CBERS data. Regarding the extraction effect of land use type information of fusion data with HPF, the results show that the two kinds of remote sensing data have good effects in extracting water body type information, and the accuracy has reached 100%. Using multisource remote sensing image processing can well summarize and analyze land use changes and make the changes in various indicators in the study area. Accurate statistics is obtained. [ABSTRACT FROM AUTHOR]

The teaching mode of English translation in universities has been changed greatly, so the design of teaching mode is needed to be optimized. Besides, the network teaching mode should be studied. Specifically, in this article, the advantages of English translation teaching in network environment are analyzed. Finally, we focus on the effective countermeasures to solve the problems of translation teaching mode and provide the reference values for teaching staff. This paper summarizes the integration of information technology and interpretation teaching according to the evolutionary route of technology application from three aspects: (1) general field, (2) interpretation professional field, and (3) education field. Furthermore, we propose a correlation analysis method of English translation teaching based on data fusion technology. Considering the time-related characteristics of English translation teaching, a perturbation time period division method based on moving time window is proposed based on the actual data and the development results of cutting-edge technologies. Finally, interpretation teaching is foreseen in four aspects: intelligence, simulation, precision, and collaboration. [ABSTRACT FROM AUTHOR]

In the era of big data, the field of enterprise risk is facing considerable challenges brought by massive multisource heterogeneous information sources. In view of the proliferation of multisource and heterogeneous enterprise risk information, insufficient knowledge fusion capabilities, and the low level of intelligence in risk management, this article explores the application process of enterprise knowledge service models for rapid responses to risk incidents from the perspective of semantic reasoning and data fusion and clarifies the elements of the knowledge service model in the field of risk management. Based on risk data, risk decision making as the standard, risk events as the driving force, and knowledge graph analysis methods as the power, the risk domain knowledge service process is decomposed into three stages: prewarning, in-event response, and postevent summary. These stages are combined with the empirical knowledge of risk event handling to construct a three-level knowledge service model of risk domain knowledge acquisition-organization-application. This model introduces the semantic reasoning and data fusion method to express, organize, and integrate the knowledge needs of different stages of risk events; provide enterprise managers with risk management knowledge service solutions; and provide new growth points for the innovation of interdisciplinary knowledge service theory. [ABSTRACT FROM AUTHOR]

Public cultural service is a product of a new era, and it is also an important product of the urbanization process. Public cultural services can not only improve the cohesion between the government and residents, but also it can improve the living standards and happiness index of residents. The public cultural service product is not only a symbol of the city, and it is more important to meet the needs and satisfaction of the residents. It needs to truly understand the preferences and needs of residents and then build public cultural service products according to their preferences. The social public cultural service model under the traditional model is dominated by the willingness of the government, which makes it difficult to truly understand the preferences and needs of residents. This paper uses data fusion and neural network methods to study the influencing factors in public cultural services. The results show that the data fusion method can capture the relationship between the factors of the public cultural service and the residents' preference, and the error of the four factors is less than 2.83% for the classification of the public cultural service. The largest prediction error is only 3.11%, and this part of the error comes from residents' satisfaction with the public cultural industry, which is an acceptable error. [ABSTRACT FROM AUTHOR]

With the continuous development of social economy, industry has become the main industry that contributes to the economy. In the process of industrial development, human operation is gradually replaced by machine operation, and the replacement of machines is followed. Over the years, machines have become more and more important in industry. However, although the machine liberates manpower, over time, it has experienced external pressures such as the environment and personnel and is internally affected by the technical level, experience, equipment familiarity, and physical and mental state of the maintenance personnel. Industrial machines tend to cause all sorts of problems when they run for too long. Therefore, it is ensured that the efficient operation and long-term operation of the machine are crucial issues. In view of the current situation and problems, this paper combines different equipment maintenance test data, adopts the method of high-performance computing overlap, establishes corresponding multisource data for data conversion and processing, and then uses the Bayesian method to analyze the multisource data. Parameter fusion and overfitting are performed, and finally the device is tested for prior data fusion using the overlap data model. The simulation results of this paper show that the high-performance overlap calculation method is effective and can effectively support the fusion analysis of maintainable multisource data. [ABSTRACT FROM AUTHOR]

Urban environments are regions of complex and diverse architecture. Their reconstruction and representation as three-dimensional city models have attracted the attention of many researchers and industry specialists, as they increasingly recognise the potential for new applications requiring detailed building models. Nevertheless, despite being investigated for a few decades, the comprehensive reconstruction of buildings remains a challenging task. While there is a considerable body of literature on this topic, including several systematic reviews summarising ways of acquiring and reconstructing coarse building structures, there is a paucity of in-depth research on the detection and reconstruction of façade openings (i.e., windows and doors). In this review, we provide an overview of emerging applications, data acquisition and processing techniques for building façade reconstruction, emphasising building opening detection. The use of traditional technologies from terrestrial and aerial platforms, along with emerging approaches, such as mobile phones and volunteered geography information, is discussed. The current status of approaches for opening detection is then examined in detail, separated into methods for three-dimensional and two-dimensional data. Based on the review, it is clear that a key limitation associated with façade reconstruction is process automation and the need for user intervention. Another limitation is the incompleteness of the data due to occlusion, which can be reduced by data fusion. In addition, the lack of available diverse benchmark datasets and further investigation into deep-learning methods for façade openings extraction present crucial opportunities for future research. [ABSTRACT FROM AUTHOR]

Many datasets in engineering applications are heterogeneous mixtures of noise-free data, noisy data with known noise variances, and noisy data with unknown noise variances. This article proposes a data fusion method called the multi-type data fusion (MTDF) model, which fully utilizes the information provided by each of these types of data. To capture the underlying trend implied in the multiple types of data, the method approximately interpolates the noise-free data, while regressing the noisy data. The prediction accuracy of the MTDF model is compared with those of various surrogate models (interpolation models, regression models, and multi-fidelity models) on both numerical and practical engineering problems. In the experiments, the proposed MTDF model demonstrates higher performance than the other benchmark models. The effects of noise level and sample size of the noise-free data on the model performance are investigated, along with the robustness of the MTDF model. The results demonstrate the satisfactory feasibility, practicality, and stability of the MTDF. [ABSTRACT FROM AUTHOR]

Data fusion describes the method of combining data from (at least) two initially independent data sources to allow for joint analysis of variables which are not jointly observed. The fundamental idea is to base inference on identifying assumptions, and on common variables which provide information that is jointly observed in all the data sources. A popular class of methods dealing with this particular missing-data problem in practice is based on covariate-based nearest neighbour matching, whereas more flexible semi- or even fully parametric approaches seem underrepresented in applied data fusion. In this article we compare two different approaches of nearest neighbour hot deck matching: One, Random Hot Deck, is a variant of the covariate-based matching methods which was proposed by Eurostat, and can be considered as a 'classical' statistical matching method, whereas the alternative approach is based on Predictive Mean Matching. We discuss results from a simulation study where we deviate from previous analyses of marginal distributions and consider joint distributions of fusion variables instead, and our findings suggest that Predictive Mean Matching tends to outperform Random Hot Deck. [ABSTRACT FROM AUTHOR]

Voltage sag is the most serious power quality problem in the three-phase symmetrical power system. The influence of multiple factors on the voltage sag level and low computational efficiency also pose challenges to the prediction of residual voltage amplitude of voltage sag. This paper proposes a voltage sag amplitude prediction method based on data fusion. First, the multi-dimensional factors that influence voltage sag residual voltage are analyzed. Second, these factors are used as input, and a model for predicting voltage sag residual voltage based on data fusion is constructed. Last, the model is trained and debugged to enable it to predict the voltage sag residual voltage. The accuracy and feasibility of the method are verified by using the actual power grid data from East China. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the information collected from wireless sensor network nodes has a great similarity and some errors exist in the data results, this study proposes a data fusion algorithm based on Kalman filter for wireless sensor network, which improves the efficacy and accuracy of uploaded data by filtering invalid data and shrunk data packets. The algorithm uses the Kalman filter algorithm with high real-time performance to integrate the data in the wireless sensor network according to the time series. On the basis of time data fusion, according to the characteristics of spatial distribution, the data fusion of multi-sensor at the gateway layer is further carried out according to the weight. In view of the characteristics of real-time changes of different position errors, the gateway layer uses spatial data as the basis to dynamically adjust the weight of each node using an adaptive weighting algorithm. Simulation experiments show that the algorithm is easy to implement, can effectively remove redundant information, and improve data accuracy and reliability. Compared with the improved batch estimation and adaptive weighting method, the root mean square error is reduced by about 7.9% and the accuracy is improved by 2.% after using this method. [ABSTRACT FROM AUTHOR]

In urban environmental management and public health evaluation efforts, there is an urgent need for fine-grained urban air quality monitoring. However, the high price and sparse distribution of air quality monitoring equipment make it difficult to develop effective and comprehensive fine-scale monitoring at the city scale. This has also led to air quality estimation methods based on incomplete monitoring data, which lack the ability to detect urban air quality differences within a neighborhood. To address this problem, this study proposes a refined urban air quality estimation method that fuses multisource spatio-temporal data. Based on the fact that urban air quality is easily affected by social activities, this method integrates meteorological data with urban social activity data to form a comprehensive environmental data set. It uses the spatio-temporal feature extraction model to extract the multi-source spatio-temporal features of the comprehensive environmental data set. Finally, the improved cascade forest algorithm is used to fit the relationship between the multisource spatio-temporal features and the air quality index (AQI) to construct an air quality estimation model, and the model is used to estimate the hourly PM2.5 index in Beijing on a 1 km × 1 km grid. The results show that the estimation model has excellent performance, and its goodness-of-fit (R2) and root mean square error (RMSE) reach 0.961 and 17.47, respectively. This method effectively achieves the assessment of urban air quality differences within a neighborhood and provides a new strategy for preventing information fragmentation and improving the effectiveness of information representation in the data fusion process. [ABSTRACT FROM AUTHOR]

Data modeling based on the fusion of data from multiple sources can improve modeling accuracy compared to a single data source. A new modular information fusion model based on genetic neural networks is designed for the urban landscape design process. A digital elevation model is created using an ordered sequence of numbers based on preprocessed sensor images. A 3D orthophoto is then obtained to generate a 3D landscape using an artificial parallax-assisted mechanism. The scale and resources of the regional landscape are described by the three-dimensional geometric dimension after data processing, and a modular landscape model with a clear subject is constructed. Finally, a genetic algorithm based on real number coding optimizes the initial weights of the neural network and selects suitable learning factors to train the neural network to complete the data fusion task and error analysis. The maintenance situation is analyzed by introducing a multifactor landscape maintenance evaluation method. The simulation results show that the fusion process of the above model is stable and the energy consumption of information fusion is low, which can promote the efficient construction of the landscape and has important application value for improving the landscape design and maintenance management. [ABSTRACT FROM AUTHOR]

As health issues continue to become more prevalent as the population grows, building a public health network is critical for enhancing the overall health quality of the community. This study offers an Internet of Things (IoT) based health care system that can be employed in the context of community medical care industrial areas. The main focus of this research is to develop a disease prediction strategy that could be applied to community health services using theoretical modelling. Using principal component analysis (PCA) and cluster analysis, an artificial bee colony (ABC) creates a nonlinear support vector machine (SVM) classifier pair. Feature-level fusion analysis was performed to detect probable abnormalities. The results of the experiments reveal that the SVM model offers significant benefits in disease prediction. In the SVM illness prediction model, the ABC algorithm has the best parameter optimization effect in terms of accuracy, time, and other factors. The suggested method outperformed the traditional SVM and BP neural network methods by 17.24 percent and 72.41 percent, respectively. It can lower the RMSE and improve assessment indicators like the precision recall rate and the F-measure, demonstrating the method's validity and accuracy. As a result, it is frequently used in community health management, geriatric community monitoring, and clinical medical therapy in an industrial environment. [ABSTRACT FROM AUTHOR]

This paper uses data analysis and action recognition algorithms to conduct in-depth research and analysis of professional sports competition judging and designs a professional sports competition-assisted judging system for use in actual judging. In this paper, a wearable motion capture system based on an inertial sensing unit is developed and designed for kayaking technical motion monitoring to achieve the acquisition, analysis, and quantitative evaluation of kayaker motion data. To limit the gyroscope and pose estimation error, a gradient descent method is used for multisensor data fusion to achieve athlete pose update, and a quaternion-driven human skeletal vector model is proposed to reconstruct the kayaker's paddling technical movements. By calculating the angular sequences of the left shoulder, right shoulder, left elbow, and right elbow joints of the athlete's upper limbs and comparing them with the optical motion capture system, the results show that the motion capture system developed in this paper is comparable to the optical motion capture system in terms of measurement accuracy. It ultimately affects the result of pose estimation. Therefore, high-resolution networks and low-resolution networks can continuously maintain high-resolution features of the image by allowing each representation layer to repeatedly accept the representation information of other networks. A step matrix model is constructed to encode the multiscale global temporal information of action sequences, and action classification is achieved by calculating the response of the step matrix of test samples to the step matrix of each category of actions. The algorithm achieves 78.96%, 91.84%, and 91.18% accuracy of action classification on the Northwestern-UCLA database, MSRC-12 database, and CAD-60 database, respectively. The designed visual motion tracking system was applied to record the motion data of the experimental subjects in the fine motion assessment task and construct the motion assessment database. The experimental results show that the average error between the prediction results of the proposed action assessment method and the manual scoring is 1.83, and the automated assessment of fine movements is effectively realized. [ABSTRACT FROM AUTHOR]

This paper describes a 16-year dataset of air pollution concentrations and air quality indicators over France. Using a kriging method that combines background air quality measurements and modeling with the CHIMERE chemistry transport model, hourly concentrations of NO 2 , O 3 , PM 10 and PM 2.5 are produced with a spatial resolution of about 4 km. Regulatory indicators (annual average, SOMO35 (sum of ozone means over 35 ppb), AOT40 (accumulated ozone exposure over a threshold of 40 ppb), etc.) are also calculated from these hourly data. The NO 2 and O 3 datasets cover the period 2000–2015, as well as the annual PM 10 data. Hourly PM 10 concentrations are not available from 2000 to 2007 due to known artifacts in PM 10 measurements. PM 2.5 data are only available from 2009 onwards due to the limited number of measuring stations available before this date. The overall dataset was evaluated over all years by a cross-validation process against background stations (rural, sub-urban and urban) to take into account the data fusion between measurement and models in the method. The results are very good for PM 10 , PM 2.5 and O 3. They show an overestimation of NO 2 concentrations in rural areas, while NO 2 background values in urban areas are well represented. Maps of the main indicators are presented over several years, and trends are calculated. Finally, exposure and trends are calculated for the three main health-related indicators: annual averages of PM 2.5 , NO 2 and SOMO35. The DOI link for the dataset is 10.5281/zenodo.5043645 (Real et al., 2021). We hope that the publication of this open dataset will facilitate further studies on the impacts of air pollution. [ABSTRACT FROM AUTHOR]

Landsat has provided the longest fine resolution data archive of Earth's environment since 1972; however, one of the challenges in using Landsat data for various applications is its frequent large data gaps and heavy cloud contaminations. One pressing research topic is to generate the regular time series by integrating coarse-resolution satellite data through data fusion techniques. This study presents a novel spatiotemporal fusion (STF) method based on a depthwise separable convolutional neural network (DSC), namely, STFDSC, to generate Landsat-surface reflectance time series at 8-day intervals by fusing Landsat 30 m with high-quality Moderate Resolution Imaging Spectroradiometer (MODIS) 500 m surface reflectance data. The STFDSC method consists of three main stages: feature extraction, feature fusion and prediction. Features were first extracted from Landsat and MODIS surface reflectance changes, and the extracted multilevel features were then stacked and fused. Both low-level and middle-level features that were generally ignored in convolutional neural network (CNN)-based fusion models were included in STFDSC to avoid key information loss and thus ensure high prediction accuracy. The prediction stage generated a Landsat residual image and is combined with original Landsat data to obtain predictions of Landsat imagery at the target date. The performance of STFDSC was evaluated in the Greater Khingan Mountains (GKM) in Northeast China and the Ziwuling (ZWL) forest region in Northwest China. A comparison of STFDSC with four published fusion methods, including two classic fusion methods (FSDAF, ESTARFM) and two machine learning methods (EDCSTFN and STFNET), was also carried out. The results showed that STFDSC made stable and more accurate predictions of Landsat surface reflectance than other methods in both the GKM and ZWL regions. The root-mean-square-errors (RMSEs) of TM bands 2, 3, 4, and 7 were 0.0046, 0.0038, 0.0143, and 0.0055 in GKM, respectively, and 0.0246, 0.0176, 0.0280, and 0.0141 in ZWL, respectively; it can be potentially used for generating the global surface reflectance and other high-level land products. [ABSTRACT FROM AUTHOR]

Aiming at the problem of multi-sensor data fusion, an adaptive weighted data fusion algorithm based on batch estimation is proposed in this paper. The algorithm uses time series and space series to calculate the variance of the collected data in batches, and uses the data consistency detection to eliminate noise points, and then obtain the adaptive factor. Then, the data is fused by adaptive weighting method to obtain the predicted value. In this paper, simulation experiments are carried out to simulate the data of the Internet of Things. The results show that the adaptive weighted multi-sensor data fusion technology of batch estimation can improve the accuracy of sensor measurement and the reliability of the system when processing data. The weighted average method reduces the root mean square error by 10% and improves the accuracy by 2.3% compared with the traditional adaptive method. [ABSTRACT FROM AUTHOR]

How to effectively realize the perception and fusion of data in the enterprise management society is the core problem that must be solved by enterprise management. On the basis of defining the resource system of enterprise management society, a semantic-oriented metadata model is proposed, combined with the classification of user needs, to build a data fusion framework for enterprise management society based on multisource data. The study designs a multilayer convolutional neural network model to process the data and proposes a recommendation path for the implementation of user data services for the enterprise management society based on the data operation center of the enterprise management society. Finally, it proposes suggestions for the development of the data fusion of the enterprise management society by improving the data fusion standard of the enterprise management society from multiple sources, actively formulating the data opening policy, and exploring the personal data collection and storage protection scheme. Experiments show that the scheme designed in this study is 5% more accurate than the state-of-the-art scheme. [ABSTRACT FROM AUTHOR]

With the development of information collection technology, the data that people need to deal with are also increasing, which brings problems such as isomerization of data types, poor data quality, and fast data generation speed. At present, as an important method of data fusion technology, data fusion method based on deep learning has become an effective way of data fusion under the background of big data, which has important research significance. There is a problem with heterogeneous data types between time series data and text data, and it is difficult to fuse them effectively by traditional data fusion methods. In order to make full use of the information contained in text data and improve the accuracy of time series prediction, this paper proposes a data fusion model based on FC-SAE. In this model, GloVe and CNN are used to extract the features of text data, FC neural network is used to extract the potential features of time series data, and then, the SEA model is used to fuse the data, which fully discovers the relationship between data and greatly improves the prediction accuracy. [ABSTRACT FROM AUTHOR]

Well-estimated air pollutant concentration fields are critically important to compensate for observations that are only sparsely available, especially over non-urban areas. Previous data fusion methods generally used statistical models to relate observations of target variables to proxy data and supporting variables at known stations. In this study, we developed a new data fusion paradigm by designing a deep-learning model framework and workflow to learn multivariable spatial correlations from chemical transport model (CTM) simulations, before using it to estimate PM 2.5 reanalysis fields from station observations. The model was composed of two modules as an explainable PointConv operation to pre-process isolated observations and a regression grid-to-grid network to build correlations among multiple variables. The model was trained with only CTM simulations and supporting geographical covariates. The trained model was evaluated in two aspects of (1) reproducing raw PM 2.5 CTM simulations and (2) generating reanalysis and fused PM 2.5 fields. First, the model was able to reproduce the CTM simulations well on a full domain from sampled CTM data items at sparse locations with an average R2=0.94 and RMSE = 4.85 µgm-3. Second, the fused PM 2.5 fields estimated from observations achieved a good performance with R2=0.77 (RMSE = 14.29 µgm-3) and R2=0.84 (RMSE = 12.96 µgm-3) respectively evaluated at the stringent city level and station level. The generated reanalysis PM 2.5 fields have complete spatial coverage within the modeling domain. One significant benefit of the fusion framework is that the model training does not rely on observations, which can be used to predict PM 2.5 fields in newly set up observation networks such as those using portable sensors. Meanwhile, in the prediction procedure, only station observations are used along with supporting covariates. The fusion model has high computing efficiency (< 1 s d -1) due to acceleration using a graphical processing unit (GPU). As an alternative to generate chemical reanalysis fields, the method can be readily implemented in near-real time and be universally applied for other simulated variables with measurements available. [ABSTRACT FROM AUTHOR]

Providing accurate and reliable railway regional environmental data is a key consideration in operation control and dynamic dispatching of high-speed train. However, there are problems of low reliability and high uncertainty in the single data processing of high-speed train operating area environment. Therefore, this paper proposes a novel multisource sensor data fusion method based on a three-level information fusion framework. Firstly, the feature of the same kind of sensor data is extracted by the Kalman Filter (KF) algorithm as the input of back propagation neural network (BPNN). Then input the sample site into the BPNN for training and recognition, the feature fusion of heterogeneous sensor data is carried out, the decision output of BPNN is obtained, the output results are normalized, and its output is used as the basic probability assignment of Dempster–Shafer (D-S) evidence theory and synthesis rules. Finally, the decision fusion of multisource data is realized by D-S evidence theory. The simulation results show that compared with the traditional single fusion algorithm, the algorithm improves the accuracy of the prediction of high-speed train operation environment and reduces the MAPE from 13.82% to 7.455%, and the RMSE from 0.77 to 0.69, and meanwhile, increases the R2 from 0.87 to 0.97. [ABSTRACT FROM AUTHOR]

This paper adopts the method of multisource big data fusion to conduct an in-depth study and analysis of precision poverty alleviation and uses big data statistical analysis model to explore and analyze it. Combining the characteristics of big data itself and the development of precision poverty alleviation, it focuses on the exploration of big data and introduces the background, development status, and achieved results of poverty alleviation with typical cases, followed by the analysis of the problems in the process of big data precision poverty alleviation and the study of the improvement path of big data technology precision poverty alleviation. Through the comparative analysis of the simulation accuracy of three models, the results show that the random forest model has the lowest error rate, after which the importance degree of indicators is derived using the model. In addition, the empirical analysis of the preprocessed sample data for multidimensional identification of poor households yields the contribution rate of each dimensional indicator that leads to multidimensional poverty of farm households, establishing scientific judging criteria to accurately judge whether farm households are poor on the one hand and selecting accurate identification methods to achieve accurate identification of poor households on the other hand. The tenfold crossover method is used to verify the errors in the test sample set. When the number of classification trees is greater than 100, it will gradually increase. Therefore, it is most appropriate to select the number of trees as 100. The multidimensional accurate identification model of farm household poverty constructed in this paper has an accuracy rate of 90.26% for the identification of poor households. By analyzing the accuracy rate of model identification and the contribution rate of multidimensional indicators leading to the poverty of farm households at the same time, the poverty degree of farm households under each dimensional indicator is derived, to accurately identify the poor households and their poverty status. The results show that the multidimensional accurate identification model of farm household poverty has the accurate identification ability and application value in the identification problem of poor households, and through the implementation of the model algorithm, a good application environment of accurate identification of poverty is created, which provides technical support to help poverty alleviation work and improve the accuracy of identification of poor households. [ABSTRACT FROM AUTHOR]

Data have multiplied at an exponential rate in the age of the Internet. Large amounts of data can be combined at this science hotspot. Making sense of big data has become increasingly difficult due to its volume, velocity, precision, and variety (sometimes referred to as heterogeneity). Many data sources are employed to create data heterogeneity. Big data fusion has both advantages and disadvantages when it comes to integrating data from a variety of sources. The focus of this work is on large data fusion using deep learning approaches to combine datasets from a variety of different sources. It is also possible to combine data from many sources. People are increasingly turning to the Internet and web-based services to meet their daily demands. Storage media can hold data in a variety of formats. Managing the vast volume of data is quite tough for an organization (referred to as "big data"). These data are rationally combined and incorporated into the system. Data fusion will be the subject of this paper. The process of collecting data and making judgments based on that data has become much more challenging as a result of technological advancements. The heterogeneity of data is made possible by the great volume, precision, and, most critically, variety of big data. A wide range of data sources can both help and hinder big-data converging. This study was created to introduce several methods and techniques for semantically merging huge datasets. [ABSTRACT FROM AUTHOR]

First‐year ice (FYI) and multi‐year ice (MYI) are the two most common ice types in the Arctic. In this article, the classification of FYI and MYI over the Arctic region in the winter of 2019/2020 and 2020/2021 is investigated by combining the data of the scatterometer on Chinese‐French Oceanography Satellite (CFOSCAT) and the Advanced Microwave Scanning Radiometer‐2 (AMSR‐2) based on the Tree Augmented Naive Bayes (TAN) classifier. The CFOSCAT/AMSR ice type classification results are validated by using Ocean and Sea Ice Satellite Application Facility (OSI SAF) sea ice type products, Canadian Ice Service ice charts, and synthetic‐aperture radar data. The results showed that the overall MYI extent change trend retrieved from CFOSCAT/AMSR was consistent with the OSI SAF product with a correlation coefficient of 0.89 for winter of 2019/2020 and 0.88 for 2020/2021. In addition, CFOSCAT/AMSR identified a slightly larger MYI extent than OSI SAF and the average deviation between them is 10.1% for 2019/2020 while 8.3% for 2020/2021. Besides, CFOSCAT/AMSR can identify more MYI pixels when the MYI concentration is relatively low in the Western Arctic region. We also used CFOSCAT data only to retrieve ice type and found that the active and passive microwave data fusion could capture more MYI pixels located near the boundary of MYI and FYI main body, and the introduction of AMSR‐2 data in ice type classification could reduce the error caused by the abnormal values of CFOSCAT parameters. Key Points: Sea ice type in the Arctic was classified by combining the CFOSCAT and AMSR‐2 data for the winter of 2019/2020 and 2020/2021The CFOSCAT/AMSR‐2 classification detects a daily average MYI extent of 2.26 × 106 km2 in 2019/2020 and 2.04 × 106 km2 in 2020/2021The average difference of MYI extent between CFOSCAT/AMSR and OSI SAF is 0.25 × 106 km2 in 2019/2020 and 0.14 × 106 km2 in 2020/2021 [ABSTRACT FROM AUTHOR]

Because traffic flow data has complex spatial dependence and temporal correlation, it is a challenging problem for researchers in the field of Intelligent Transportation to accurately predict traffic flow by analyzing spatio-temporal traffic data. Based on the idea of spatio-temporal data fusion, fully considering the correlation of traffic flow data in the time dimension and the dependence of spatial structure, this paper proposes a new spatio-temporal traffic flow prediction model based on Graph Neural Network (GNN), which is called Bidirectional-Graph Recurrent Convolutional Network (Bi-GRCN). First, aiming at the spatial dependence between traffic flow data and traffic roads, Graph Convolution Network (GCN) which can directly analyze complex non-Euclidean space data is selected for spatial dependence modeling, to extract the spatial dependence characteristics. Second, considering the temporal dependence of traffic flow data on historical data and future data in its time-series period, Bidirectional-Gate Recurrent Unit (Bi-GRU) is used to process historical data and future data at the same time, to learn the temporal correlation characteristics of data in the bidirectional time dimension from the input data. Finally, the full connection layer is used to fuse the extracted spatial features and the learned temporal features to optimize the prediction results so that the Bi-GRCN model can better extract the spatial dependence and temporal correlation of traffic flow data. The experimental results show that the model can not only effectively predict the short-term traffic flow but also get a good prediction effect in the medium- and long-term traffic flow prediction. [ABSTRACT FROM AUTHOR]

In the fields of traffic management, traffic health, and vehicle safety, vehicle speed prediction is an important research topic. The greater the difference between vehicle speed and average vehicle speed, or the more discrete the vehicle speed distribution, the higher the accident rate. This paper proposes a vehicle speed prediction method based on adaptive KF (Kalman filtering) in the ARMA (Autoregressive Moving Average) environment to address the problem of high-speed moving vehicle speed prediction. The ARMA theory is used to model the prediction of speed time series. The contribution rate of each coefficient representing the original time series is different after fitting the original time series with the ARMA model, so each coefficient must be given a certain weight. Multisource traffic data fusion and interval speed prediction are carried out on the basis of few-shot data preprocessing and traffic state division, according to different traffic states. The speed prediction accuracy is very high, according to the algorithm verification results. [ABSTRACT FROM AUTHOR]

Sensing is an essential part in autonomous driving and intelligent transportation systems. It enables the vehicle to better understand itself and its surrounding environment. Vehicular networks support information sharing among different vehicles and hence enable the multi‐vehicle multi‐sensor cooperative sensing, which can greatly improve the sensing performance. However, there are a couple of issues to be addressed. First, the multi‐sensor data fusion needs to deal with heterogeneous data formats. Second, the cooperative sensing process needs to deal with low data quality and perception blind spots for some vehicles. In order to solve the above problems, in this paper the occupancy grid map is adopted to facilitate the fusion of multi‐vehicle and multi‐sensor data. The dynamic target detection frame and pixel information of the camera data are mapped to the static environment of the LiDAR point cloud, and the space‐based occupancy probability distribution kernel density estimation characterization fusion data is designed , and the occupancy grid map based on the probability level and the spatial level is generated. Real‐world experiments show that the proposed fusion framework is better compatible with the data information of different sensors and expands the sensing range by involving the collaborations among multiple vehicles in vehicular networks. [ABSTRACT FROM AUTHOR]

Summary: In recent years, the demand for reliable and accurate nondestructive evaluation (NDE) of structural systems has been growing and several nondestructive testing (NDT) techniques are being combined to address the issues of uncertainty in the testing results. However, the synergistic combination of multiple NDT techniques and the interpretation of the testing results require the ability to process and analyze data from several sources, a process that is referred to as "data fusion." The latter has received considerable attention since the beginning of the 21st century, thanks to the advances in sensor technologies and data acquisition systems. Also, the new era of "Big Data" where heterogeneous data are measured by different sensors and processed for a unified purpose is another factor contributing to this rapid development and the establishment of new NDT opportunities. This article reviews the recent studies involving NDE data fusion for the inspection of structures and examines the state‐of‐the‐art mathematical expressions used in different fusion algorithms. Challenges in the handling of the NDE data and the application of fusion algorithms are also identified and discussed. A generic framework of applying NDE data fusion is described, and a roadmap for potential research prospects in NDE data fusion is provided. [ABSTRACT FROM AUTHOR]

Dictionary learning has gradually attracted attention due to its powerful feature representation ability. However, the time-shift property of collected signals hinders the recognition of various bearing states. In addition, existing dictionary learning methods are mostly designed based on a single domain, while common data fusion methods used in data-driven cannot be directly extended to dictionary learning. In this paper, a novel adaptive generalized domain data fusion-driven kernel sparse representation classification method (AGDFDK-SRC) is proposed. First, to avoid the effect of the time-shift property on dictionary learning, a class-specific kernel sub-dictionary learning method is proposed, by which the non-linear signal data is mapped into high-dimensional feature space via a kernel trick. Second, the class-specific kernel sub-dictionaries are learned by kernel K-singular value decomposition in a data-driven manner. Then, an adaptive generalized domain data fusion strategy is developed for dictionary learning, which implements data fusion of multiple domain signals to enhance the feature mining ability and representation ability of the learned dictionary. Finally, a kernel sparse classification method is designed to achieve intelligent bearing fault diagnosis. Two bearing datasets are exploited to verify the recognition performance of AGDFDK-SRC, indicating that the AGDFDK-SRC obtains superior average classification accuracies of 98.23% and 99.50%, respectively. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is highly sensitive for lesion detection. Sequences obtained with different settings can capture specific characteristics of lesions. Such multi-parametric MRI information has been shown to aid radiologist performance in lesion classification, as well as improving the performance of artificial intelligence models in various tasks. However, obtaining multi-parametric MRI makes the examination costly from both financial and time perspectives, and there may also be safety concerns for special populations, thus making acquisition of the full spectrum of MRI sequences less durable. In this study, a sophisticated I ntegrated MRI M ulti- P arametric increment fusi O n generato R wi T h A tte NT ion Network (IMPORTANT-Net) is developed to generate absent sequences/parameters. First, the parameter reconstruction module is used to encode and restore the existing MRI parameters to obtain the corresponding latent representation information at any scale level. Then the multi-parametric fusion with attention module enables the interaction of the encoded information from different parameters through a set of algorithmic strategies, and applies different weights to the information through the attention mechanism after information fusion to obtain refined representation information. Finally, a increment fusion scheme embedded in a V -shape generation module is used to combine the hierarchical representations to generate specified absent MRI parameter. Results showed that our IMPORTANT-Net is capable of synthesizing absent MRI, outperforms comparable state-of-the-art networks and more importantly benefit downstream tasks. The codes are available at https://github.com/Netherlands-Cancer-Institute/MRI_IMPORTANT_NET • Multi-parameter fusion module realizes the interaction between different parameters. • The attention module optimizes the contribution of the fused parameters. • Hierarchical increment leads to both global and local analysis and fusion. • Synthesized images can improve the performance of AI models in downstream tasks. [ABSTRACT FROM AUTHOR]

Completing continuous circular capsulorhexis (CCC) requires the operator to perform fine operations, which is difficult to do accurately when continuous fine actions are out of balance in the classification of CCC procedures. Multimodal deep learning can improve the classifier's performance, but the recognition accuracy of inferior classes is difficult to improve. To solve these problems, a bidirect-gate recurrent unit (Bi-GRU)-attention-based multimodal, multi-timescale data fusion network (BiMNet) is proposed, which contains a data extraction module called a skip-concatenate gate recurrent unit (SC-GRU), a bimodal data fusion attention computation, and a decoder module. The combination of these modules can fully extract the features of different temporal scales in multimodal action data and fuse them effectively. The model is validated using the ophthalmologist CCC multimodal maneuver dataset, which was collected by the data collection platform constructed in this research, achieving an accuracy of 0.9124 ± 0.0125 in continuous action sequence segmentation and improving the F1-score of minority class recognition to over 80%, making it more effective than baseline algorithms. • A Bi-GRU-attention-based multimodal data fusion network (BiMNet) is proposed. • The skip-concatenate GRU module and a bimodal data fusion module are proposed. • BiMNet can improve the classification effect of dealing with imbalanced data. • Established a multimodal maneuver dataset of continuous circular capsulorhexis. [ABSTRACT FROM AUTHOR]

• Data diversity and heterogeneity may hinder the development of healthcare systems. • Data fabric is a context-independent option to improve the data lifecycle management. • Digital Twins solves the contextualization problems shown by data fabrics options. • The evaluation via a healthcare system shows the proposal is reliable and efficient. Recent technological improvements have made it possible for pervasive computing intelligent environments, augmented by sensors and actuators, to offer services that support society's aims for a wide variety of applications. This requires the fusion of data gathered from multiple sensors to convert them into information to obtain valuable knowledge. Poor implementation of data fusion hinders the appropriate actions from being taken and offering the appropriate support to users and environment needs, particularly relevant in the healthcare domain. Data fusion poses challenges that are mainly related to the quality of the data or data sources, the definition of a data fusion process and evaluating the data fusion carried out. There is also a lack of holistic engineering frameworks to address these challenges. These frameworks should be able to support automated methods of extracting knowledge from information, selecting algorithms and techniques, assessing information and evaluating information fusion systems in an automatic and standardized manner. This work proposes a holistic framework to improve data fusion in pervasive systems, addressing the issues identified by means of two processes: the first of which guides the design of the system architecture and focuses on data management. It is based on a previous proposal that integrated aspects of Data Fabric and Digital Twins to solve data management and data contextualization and representation issues, respectively. The extension of the previous proposal presented here was mainly defined by integrating aspects and techniques from different well-known multi-sensor data fusion models. The previous proposal identified high-level data processing activities and was intended to facilitate their traceability to components in the system architecture. However, the previously defined stages are not completely adequate in a data fusion process and the data processing tasks to be performed in each stage are not described in detail, especially in the data fusion stages. The second process of the framework deals with evaluating data fusion systems and is based on international standards to ensure the quality of the data fusion tasks performed by such systems. This process also offers guidelines for designing the architecture of an evaluation subsystem to automatically perform data fusion evaluation in runtime as part of the system. To illustrate the proposal, a system for preventing the spread of COVID-19 in nursing homes is described that was developed using the proposed guidelines It is also illustrated by a description of how the data fusion tasks it supports are evaluated by the proposed evaluation process. The overall evaluation of the data fusion performed by this system was considered satisfactory, which indicates that the proposal facilitates the design and development of data fusion systems and helps to achieve the necessary quality requirements. [ABSTRACT FROM AUTHOR]

• Modeling of variation in GR rainfall error by rain type and intensity. • Modeling of DPR rainfall error and variable error parameters. • Hierarchical Bayesian fusion was used to integrate DPR and GR rainfall data. • HB fusion considered varying parameters in rainfall error modeling. • HB fusion outperformed CB fusion and improved the original DPR rainfall product. The optimal fusion of multisource rainfall data can improve the accuracy and resolution of a posteriori estimates, which is beneficial for hydrological and meteorological applications. In this study, the errors of ground-based dual-polarization radar (GR) and dual-frequency precipitation radar (DPR) on global precipitation measurement (GPM) satellite rainfall estimation were modeled, and a hierarchical Bayesian (HB) framework was developed for GR and DPR rainfall data fusion. According to the matched optimal estimated GR rainfall and rain gauge data, the GR rainfall error was analyzed, and the error variance varying with rain type and intensity was described and modeled. The rain types were classified based on disdrometer and dual-polarization radar data. By comparing the DPR rainfall product with GR rainfall, the DPR rainfall error was divided into systematic and random errors. The systematic error was linearly fitted, and the probability distributions for the random error and the variable error parameters were analyzed and modeled. Because the parameters for GR and DPR rainfall errors varied with rain type and intensity, we developed a HB fusion approach considering the varying parameters in rainfall error modeling. The performance of the fusion algorithm was evaluated using matched GR and DPR cases, which showed that the HB fusion can effectively improve the consistency between the original DPR rainfall product and rain gauge data, reducing the relative bias by an average of 30% and improving the correlation by an average of 20%. Compared with the conventional Bayesian (CB) fusion algorithm, which is based on overall error modeling, the HB fusion results can improve the root mean square error by an average of 24% and relative bias by 14%. [ABSTRACT FROM AUTHOR]

U.S. background ozone is defined as ground-level ozone in the absence of any domestic anthropogenic emissions. It plays an important role in the U.S. regulatory framework, as it corresponds to the theoretical minimum ozone that can be achieved at a location. Although some studies estimated background ozone from observations, it cannot be measured directly, and therefore air quality models have been used to estimate its levels across different parts of the country. These estimates are uncertain given the inherent uncertainty in air quality modeling. Recently data fusion techniques have been used to improve those estimates using ground-level ozone observations and satellite data. Here, we used two adjustment methods to improve on air quality model-derived estimates of background ozone: a Multi-Variate Linear Regression (MVLR) model and a machine learning (ML) algorithm, called Random Forest (RF), with a focus on thirteen urban areas in the U.S. These adjustments regress observed ozone on the simulated background and anthropogenic ozone (by a regional air quality model) and their combinations with spatial and temporal variables. The RF-ML algorithm showed the biggest improvement in model performance, compared to MVLR and the base air quality model predictions. Applying the MVLR adjustment, the background ozone estimates increased in most locations. Furthermore, applying the RF ML model adjustment increased background ozone estimates even more, highlighting the enhanced contribution of background ozone in recent years that constitutes a larger portion of total ozone and exceeds NAAQS in some regions. Our results are consistent with other observational and modeling studies in that the highest background ozone levels were estimated in the western U.S. and over higher elevations. • We first estimated background ozone in the U.S. using air quality models. • We used data fusion methods and machine learning to adjust the background ozone. • Adjustment methods improved the air quality model performance for total ozone. • Applying adjustment methods increased background ozone estimates in most locations. • The highest background ozone levels were estimated in the western U.S. [ABSTRACT FROM AUTHOR]