Search

Currently, the rapid development of the industrial Internet has led to the creation of a massive number of intelligent agents that are widely and distributively applied in various edge scenarios. The work conditions in these edge scenarios are complex, uncertain, and random. Traditional manual updates or human judgments are used for task decision-making in large-scale distributive intelligent agent edge work scenarios, which lack dynamic perception and autonomous recognition capabilities for edge work conditions. This inevitably leads to low decision-making accuracy, poor reliability, and ultimately, task failure. To address this issue, this study proposes an adaptive task identification strategy based on cloud-edge collaboration. This method utilizes a cloud-edge collaborative industrial intelligent application architecture to achieve cloud-based training and encapsulation of the task model, with online calling at the edge-end. Then, edge-end intelligent agents identify edge work conditions through multi-source data fusion, enabling accurate task decision-making. Finally, the edge-end requests the cloud for task model matching. The effectiveness of the proposed method is validated in an industrial safety situation virtual detection system. [ABSTRACT FROM AUTHOR]

In the column chromatography elution process of traditional Chinese medicine (TCM), the real-time monitoring of active components plays an important role in product quality control. In this study, the column chromatography elution process in preparing of Ginkgo biloba leaf extract was performed in bench scale, where near-infrared (NIR) spectroscopy and Raman spectroscopy were collected to determine the concentration changes of several critical quality attributes. Based on single spectral data and fused spectral data, partial least squares and support vector machine models were established, respectively. The results indicated that for most analytes, models based on Raman spectra were superior to NIR spectral models, and fusion models established by the mid-level data fusion approach were superior to the single spectral models. The coefficients of determination (R t 2) of the optimal Raman and mid-level data fusion models were all higher than 0.96. The concentration profiles predicted by the mid-level data fusion quantitative models were in better agreement with the real trends defined by measured values. This is the first-ever study reporting the real-time monitoring of TCM column chromatography process by Raman spectroscopy combined with NIR spectroscopy, having vital reference values for process monitoring and understanding of the column chromatography for other TCM. [Display omitted] • The elution process of Ginkgo biloba leaves was monitored by near-infrared and Raman. • Partial least squares and support vector machine were used for quantitative analysis. • The mid-level data fusion models showed the better prediction ability. • Data fusion was a promising method for the analysis of column chromatography process. [ABSTRACT FROM AUTHOR]

The era of modern smartphones, running on Android version 7.0 and higher, facilitates nowadays acquisition of raw dual-frequency multi-constellation GNSS observations. This paves the way for GNSS community data to be potentially exploited for precise positioning, GNSS reflectometry or geoscience applications at large. The continuously expanding global GNSS infrastructure along with the enormous volume of prospective GNSS community data bring, however, major challenges related to data acquisition, its storage, and subsequent processing for deriving various parameters of interest. In addition, such large datasets cannot be managed manually anymore, leading thus to the need for fully automated and sophisticated data processing pipelines. Application of Machine Learning Technology for GNSS IoT data fusion (CAMALIOT) was an ESA NAVISP Element 1 project (NAVISP-EL1-038.2) with activities aiming to address the aforementioned points related to GNSS community data and their exploitation for scientific applications with the use of Machine Learning (ML). This contribution provides an overview of the CAMALIOT project with information on the designed and implemented cloud-native software for GNSS processing and ML at scale, developed Android application for retrieving GNSS observations from the modern generation of smartphones through dedicated crowdsourcing campaigns, related data ingestion and processing, and GNSS analysis concerning both conventional and smartphone GNSS observations. With the use of the developed GNSS engine employing an Extended Kalman Filter, example processing results related to the Zenith Total Delay (ZTD) and Slant Total Electron Content (STEC) are provided based on the analysis of observations collected with geodetic-grade GNSS receivers and from local measurement sessions involving Xiaomi Mi 8 that collected GNSS observations using the developed Android application. For smartphone observations, ZTD is derived in a differential manner based on a single-frequency double-difference approach employing GPS and Galileo observations, whereas satellite-specific STEC time series are obtained through carrier-to-code leveling based on the geometry-free linear combination of observations from both GPS and Galileo constellations. Although the ZTD and STEC time series from smartphones were derived on a demonstration basis, a rather good level of consistency of such estimates with respect to the reference time series was found. For the considered periods, the RMS of differences between the derived smartphone-based time series of differential zenith wet delay and reference values were below 3.1 mm. In terms of satellite-specific STEC time series expressed with respect to the reference STEC time series, RMS of the offset-reduced differences below 1.2 TECU was found. Smartphone-based observations require special attention including additional processing steps and a dedicated parameterization in order to be able to acquire reliable atmospheric estimates. Although with lower measurement quality compared to traditional sources of GNSS data, an augmentation of ground-based networks of fixed high-end GNSS receivers with GNSS-capable smartphones would however, form an interesting source of complementary information for various studies relying on GNSS observations. [ABSTRACT FROM AUTHOR]

The variation in improvement among individuals with addiction after abstinence is a critical issue. Here, we aimed to identify robust multimodal markers associated with high response to 8-month abstinence in the individuals with heroin use disorder (HUD) and explore whether the identified markers could be generalized to the individuals with methamphetamine use disorder (MUD). According to the median of craving changes, 53 individuals with HUD with 8-month abstinence were divided into two groups: higher craving reduction and lower craving reduction. At baseline, clinical variables, cortical thickness and subcortical volume, fractional anisotropy (FA) of fibers and resting-state functional connectivity (RSFC) were extracted. Different strategies (single metric, multimodal neuroimaging fusion and multimodal neuroimaging-clinical data fusion) were used to identify reliable features for discriminating the individuals with HUD with higher craving reduction from those with lower reduction. The generalization ability of the identified features was validated in the 21 individuals with MUD. Multimodal neuroimaging-clinical fusion features with best performance was achieved an 87.1 ± 3.89% average accuracy in individuals with HUD, with a moderate accuracy of 66.7% when generalizing to individuals with MUD. The multimodal neuroimaging features, primarily converging in frontal regions (e.g., the left superior frontal (LSF) thickness, FA of the LSF-occipital tract, and RSFC of left middle frontal-right superior temporal lobe), collectively contributed to prediction alongside dosage and attention impulsiveness. In this study, we identified the validated multimodal frontal neuroimaging markers associated with higher response to long-term abstinence and revealed insights for the neural mechanisms of addiction abstinence, contributing to clinical strategies and treatment for addiction. [ABSTRACT FROM AUTHOR]

Accurate quantification of snow cover facilitates the prediction of snowmelt runoff, the assessment of freshwater availability, and the analysis of Earth's energy balance. Existing fractional snow cover (FSC) data, however, often suffer from limitations such as spatial and temporal gaps, compromised accuracy, and coarse spatial resolution. These limitations significantly hinder the ability to monitor snow cover dynamics effectively. To address these formidable challenges, this study introduces a novel data fusion framework specifically designed to generate high-resolution (1 km) daily FSC estimation across vast regions like North America, regardless of weather conditions. It achieved this by effectively integrating the complementary spatiotemporal characteristics of both coarse- and fine-resolution FSC data through a multi-stage processing pipeline. This pipeline incorporates innovative strategies for bias correction, gap filling, and consideration of dynamic characteristics of snow cover, ultimately leading to high accuracy and high spatiotemporal completeness in the fused FSC data. The accuracy of the fused FSC data was thoroughly evaluated over the study period (September 2015 to May 2016), demonstrating excellent consistency with independent datasets, including Landsat-derived FSC (total 24 scenes; RMSE=6.8–18.9 %) and ground-based snow observations (14,350 stations). Notably, the fused data outperforms the widely used Interactive Multi-sensor Snow and Ice Mapping System (IMS) daily snow cover extent data in overall accuracy (0.92 vs. 0.91), F1_score (0.86 vs. 0.83), and Kappa coefficient (0.80 vs. 0.77). Furthermore, the fused FSC data exhibits superior performance in accurately capturing the intricate daily snow cover dynamics compared to IMS data, as confirmed by superior agreement with ground-based observations in four snow-cover phenology metrics. In conclusion, the proposed data fusion framework offers a significant advancement in snow cover monitoring by generating high-accuracy, spatiotemporally complete daily FSC maps that effectively capture the spatial and temporal variability of snow cover. These FSC datasets hold substantial value for climate projections, hydrological studies, and water management at both global and regional scales. [ABSTRACT FROM AUTHOR]

Street view imagery (SVI) is instrumental for sensing urban environments, benefitting numerous domains such as urban morphology, health, greenery, and accessibility. Billions of images worldwide have been made available by commercial services such as Google Street View and crowdsourcing services such as Mapillary and KartaView where anyone from anywhere can upload imagery while moving. However, while the data tend to be plentiful, have high coverage and quality, and are used to derive rich insights, they remain simple and limited in metadata as characteristics such as weather, quality, and lighting conditions remain unknown, making it difficult to evaluate the suitability of the images for specific analyses. We introduce Global Streetscapes — a dataset of 10 million crowdsourced and free-to-use SVIs sampled from 688 cities across 210 countries and territories, enriched with more than 300 camera, geographical, temporal, contextual, semantic, and perceptual attributes. The cities included are well balanced and diverse, and are home to about 10% of the world's population. Deep learning models are trained on a subset of manually labelled images for eight visual-contextual attributes pertaining to the usability of SVI — panoramic status, lighting condition, view direction, weather, platform, quality, presence of glare and reflections, achieving accuracy ranging from 68.3% to 99.9%, and used to automatically label the entire dataset. Thanks to its scale and pre-computed standard semantic information, the data can be readily used to benefit existing use cases and to unlock new applications, including multi-city comparative studies and longitudinal analyses, as affirmed by a couple of use cases in the paper. Moreover, the automated processes and open-source code facilitate the expansion and updates of the dataset and encourage users to create their own datasets. With the rich manual annotations, some of which are provided for the first time, and diverse conditions present in the images, the dataset also facilitates assessing the heterogeneous properties of crowdsourced SVIs and provides a benchmark for evaluating future computer vision models. We make the Global Streetscapes dataset and the code to reproduce and use it publicly available in https://github.com/ualsg/global-streetscapes. [Display omitted] • Largest labelled dataset, with 346 attributes that characterise street photos. • Baseline models and ground truth labels for benchmarking computer vision models. • Reproducible framework to sample and enrich SVIs from cities all around the world. • In-depth discussion of how the dataset could drive novel research questions. • Taking forward the work of Mapillary and KartaView, and their contributors. [ABSTRACT FROM AUTHOR]

Prediction of Remaining Useful Life (RUL) for Rolling Element Bearings (REB) has attracted widespread attention from academia and industry. However, there are still several bottlenecks, including the effective utilization of multi-sensor data, the interpretability of prediction models, and the prediction across the entire life cycle, which limit prediction accuracy. In view of that, we propose a knowledge-based explainable life-cycle RUL prediction framework. First, considering the feature fusion of fast-changing signals, the Pearson correlation coefficient matrix and feature transformation objective function are incorporated to an Improved Graph Convolutional Autoencoder. Furthermore, to integrate the multi-source signals, a Cascaded Multi-head Self-attention Autoencoder with Characteristic Guidance is proposed to construct health indicators. Then, the whole life cycle of REB is divided into different stages based on the Continuous Gradient Recognition with Outlier Detection. With the development of Measurement-based Correction Life Formula and Bidirectional Recursive Gated Dual Attention Unit, accurate life-cycle RUL prediction is achieved. Data from self-designed test rig and PHM 2012 Prognostic challenge datasets are analyzed with the proposed framework and five existing prediction models. Compared with the strongest prediction model among the five, the proposed framework demonstrates significant improvements. For the data from self-designed test rig, there is a 1.66 % enhancement in Corrected Cumulative Relative Accuracy (CCRA) and a 49.00 % improvement in Coefficient of Determination (R2). For the PHM 2012 datasets, there is a 4.04 % increase in CCRA and a 120.72 % boost in R2. [Display omitted] • Advocate explainable knowledge-data integration for RUL prediction throughout the life cycle, leveraging multi-sensor data. • Introduce a novel unsupervised learning framework that integrates IGCA and CMSACG to construct HI. • A two-stage prediction framework, fusing MCLF and BR-GDAU, is proposed for predicting the life cycle RUL. • The effectiveness of the proposed framework is validated using both Self-Designed Experiment-Derived and PHM 2012 Prognostic Challenge Bearing Datasets. [ABSTRACT FROM AUTHOR]

Modern species delimitation is challenged by past morphological descriptions, a mix of applied species concepts, missing tools for complex evolutionary processes and large multi-approach datasets, and nonstandardized data integration. The vision is to have less subjective and standardized species delimitation approaches based on modern integrative taxon-omics under a unified species concept, integrating the discovery of genetic entities with the fusion of automatically extracted information from multi-approach data to find natural taxonomic units. Artificial Intelligence (AI) approaches have been launched to tackle delimitation issues using classification/clustering methods based on supervised/unsupervised learning, although data fusion and problematic and unknown species represent active fields of research. AI can help accelerate the revision and unraveling of eukaryotic biodiversity on a scale not seen before. Although species are central units for biological research, recent findings in genomics are raising awareness that what we call species can be ill-founded entities due to solely morphology-based, regional species descriptions. This particularly applies to groups characterized by intricate evolutionary processes such as hybridization, polyploidy, or asexuality. Here, challenges of current integrative taxonomy (genetics/genomics + morphology + ecology, etc.) become apparent: different favored species concepts, lack of universal characters/markers, missing appropriate analytical tools for intricate evolutionary processes, and highly subjective ranking and fusion of datasets. Now, integrative taxonomy combined with artificial intelligence under a unified species concept can enable automated feature learning and data integration, and thus reduce subjectivity in species delimitation. This approach will likely accelerate revising and unraveling eukaryotic biodiversity. Although species are central units for biological research, recent findings in genomics are raising awareness that what we call species can be ill-founded entities due to solely morphology-based, regional species descriptions. This particularly applies to groups characterized by intricate evolutionary processes such as hybridization, polyploidy, or asexuality. Here, challenges of current integrative taxonomy (genetics/genomics +morphology +ecology, etc.) become apparent: different favored species concepts, lack of universal characters/markers, missing appropriate analytical tools for intricate evolutionary processes, and highly subjective ranking and fusion of datasets. Now, integrative taxon-omics combined with artificial intelligence under a unified species concept can enable automated feature learning and data integration, and thus reduce subjectivity in species delimitation. This approach will likely accelerate revising and unraveling eukaryotic biodiversity. [ABSTRACT FROM AUTHOR]

Freehand three-dimensional (3D) ultrasound (US) is of great significance for clinical diagnosis and treatment, it is often achieved with the aid of external devices (optical and/or electromagnetic, etc.) that monitor the location and orientation of the US probe. However, this external monitoring is often impacted by imaging environment such as optical occlusions and/or electromagnetic (EM) interference. To address the above issues, we integrated a binocular camera and an inertial measurement unit (IMU) on a US probe. Subsequently, we built a tight coupling model utilizing the unscented Kalman algorithm based on Lie groups (UKF-LG), combining vision and inertial information to infer the probe's movement, through which the position and orientation of the US image frame are calculated. Finally, the volume data was reconstructed with the voxel-based hole-filling method. The experiments including calibration experiments, tracking performance evaluation, phantom scans, and real scenarios scans have been conducted. The results show that the proposed system achieved the accumulated frame position error of 3.78 mm and the orientation error of 0.36° and reconstructed 3D US images with high quality in both phantom and real scenarios. The proposed method has been demonstrated to enhance the robustness and effectiveness of freehand 3D US. Follow-up research will focus on improving the accuracy and stability of multi-sensor fusion to mak e the system more practical in clinical environments. [ABSTRACT FROM AUTHOR]

[Display omitted] • Fusion of varied data sources are used to develop more informed flood extent maps. • SVM outscored the MLE, RF, Iso cluster, and Otsu's algorithms in all strategies. • PCA-based technique outperforms the other three approaches. • First and Second approaches performed better in VV than VH polarisation. Accurate and timely mapping of flood extent is crucial for effective disaster response and management. However, existing methods often face challenges in integrating diverse data sources and leveraging advanced techniques for precise inundation mapping. This research aimed to address this gap by proposing and evaluating four different methods for improving flood extent mapping in Sindh, Pakistan, by integrating various data sources, including precipitation, Synthetic Aperture Radar (SAR), buildings, population, and optical data. The first strategy involves categorizing post-flood SAR data immediately using non-parametric (Support Vector Machine (SVM) and Random Forest (RF)), parametric (Maximum Likelihood Estimation (MLE)), and cluster (ISO) algorithms for Vertical transmit and Vertical received (VV) and Vertical transmit and Horizontal received (VH) polarisations. The second method relies on Otsu's method for automatic thresholding on post-flood event VH and VV data. The third approach utilizes both pre- and post-flood event data by creating a stack of Pre-event VH, Pre-event VV, Post-event VH, and Post-event VV data, which is then classified using the SVM, RF, MLE, and ISO algorithms. Lastly, the fourth method employs the stack of Principal Component Analysis (PCA) bands, consisting of PCA components 1, 2, and 3, to categorize data for flooding using the SVM, RF, MLE, and ISO algorithms. The rationale behind evaluating these diverse methods was to identify the most effective approach for accurately mapping flood extent by exploiting the strengths of different algorithms and data processing techniques. The accuracy and precision of these approaches were rigorously evaluated using Landsat-9 Normalized Difference Water Index (NDWI) as a reference dataset, along with error matrix and compound value (C v) metrics. The findings show that a PCA-based technique with SVM is marginally superior (based on the overall accuracy and Kappa coefficient with a value of 92.20 % and kappa coefficient 0.821) than the other approaches tested in the study. By reducing the dimensionality of the dataset while preserving relevant information, PCA offers a computationally efficient approach to flood extent mapping. Among all the approaches, the collective performance of the algorithms was computed using the C v metric. The SVM algorithm with a C v of 1.25 demonstrated the best performance, followed by the RF algorithm with C v of 1.5, and the MLE algorithm with C v of 2.5. The worst performing algorithm among all is found to be ISO with C v of 4. It comes into view that first and second approach underperformed in VH polarisation compared to the VV polarisation and provide a more accurate representation of flooded area in VV polarisation. The flood extent with highest accuracy, together with the world's gridded population, latest Microsoft's Global ML Building Footprints, and OpenStreetMap building data are used in conjunction to estimate the number of people and buildings at risk within the study area. [ABSTRACT FROM AUTHOR]

This paper explores the parallel collaboration of multimodal physiological signals, combining eye tracker output signals, motor imagery, and error-related potentials to control a computer mouse. Specifically, a parallel working mechanism is implemented in the decision layer, where the eye tracker manages cursor movements, and motor imagery manages click functions. Meanwhile, the eye tracker output signals are integrated with electroencephalography data to detect the idle state for asynchronous control. Additionally, error-related potentials evoked by visual feedback, are detected to reduce the cost of error corrections. To efficiently collect data and provide continuous evaluations, we performed offline training and online testing in the designed paradigm. To further validate the practicability, we conducted online experiments on the real-world computer, focusing on a scenario of opening and closing files. The experiments involved seventeen subjects. The results showed that the stability of the eye tracker was optimized from 67.6% to 95.2% by the designed filter, providing the support for parallel control. The accuracy of motor imagery conducted simultaneously with fixations reached 93.41 ± 2.91%, proving the feasibility of parallel control. Furthermore, the real-world experiments took 45.86 ± 14.94 s to complete three movements and clicks, and showed a significant improvement compared to the baseline experiment without automatic error correction, validating the practicability of the system and the efficacy of error-related potentials detection. Moreover, this system freed users from the stimulus paradigm, enabling a more natural interaction. To sum up, the parallel collaboration of multimodal physiological signals is novel and feasible, the designed mouse is practical and promising. [ABSTRACT FROM AUTHOR]

A multi-sensor information fusion algorithm based on fault-tolerant Kalman filter is proposed in phase-sensitive optical time-domain reflectometer (Φ-OTDR) system, for achieving fading-free distributed vibration sensing. Firstly, a fault-tolerant dual-core complementary array model is designed. The Rayleigh scattering signal denoising, and vibration existence judgment of localization points are carried out to obtain the differentiated frequency demodulation results of the sensing points of the dual-core fiber array. Then a fault-tolerant control strategy is used to determine the sensor weight coefficients and vibration judgment coefficients during data fusion processing, and array data fusion is carried out based on time series data using Kalman filter to realize error value identification and filling. The advantage of this method is the combination of redundant data in a complementary way to improve the system stability. The frequency response ranges from 10 Hz to 2400 Hz and the localization accuracy is 98.33%. The influence of key parameters on the frequency demodulation performance of fault-tolerant Kalman filter is discussed, and a standard deviation of 14.6 Hz and an average error of 7.6 Hz are obtained. The demodulation frequency data matrix obtained by the classical demodulation method has a demodulation error probability of 89.18%, which proves the widespread existence of demodulation errors in vibration signals. The fusion error of demodulation frequency is reduced to 0.25 Hz, the frequency demodulation accuracy reaches 100%, and the demodulation error caused by interference attenuation can be completely eliminated. This system based on fault-tolerant Kalman filter has the characteristics of simple multiplexing structure, interference fading resistance and stable demodulation performance. • A sensor information fusion algorithm based on fault-tolerant Kalman filter is proposed to achieve fading-free sensing. [ABSTRACT FROM AUTHOR]

This study focuses on the improvement of the tracking performance of space observation radar systems. Coherent radar systems usually provide an observation vector including four observables (range, range rate, azimuth, elevation) measured at a given epoch. Moreover, for some coherent radars, such as the TIRA system, it is possible to determine an additional parameter, the range rate, which is extracted from the collected complex amplitude. The tracking performance can be improved by increasing the observation parameter accuracy. The influence of each parameter on the overall tracking performance can be assessed by conducting a sensitivity analysis. The investigation shows that the best way to increase the accuracy of the state vector is by improving the angle estimates. The TIRA system is equipped with a tracking radar and an imaging radar. A powerful solution to improve the tracking performance is the realization of a multi-sensor data fusion between the two radars of the system. [ABSTRACT FROM AUTHOR]

Spatial similarity provides an important basis for geographic information processing and is widely applied in multi-source data fusion and update, data retrieval and query, and cartographic generalization. To address the shape description and similarity measurement of polygon entities, this study presents a new hierarchical shape description approach and examines its application in similarity measurement of polygon entities. Using the rotation and segmentation methods, we first constructed a hierarchical shape description model for target polygon entities, followed by measurement of global and hierarchical shape description of polygon entities, respectively, using the farthest-point-distance and geometric feature description methods. Finally, we constructed a comprehensive similarity measurement model through a weighted integration of position, size, direction, and shape. The hierarchical shape description approach proposed in this paper can be applied to the shape similarity measurement of polygon elements, similarity measurement after spatial object simplification, and multi-scale polygon entity matching. The experimental results showed that the hierarchical shape description approach and similarity measurement model are able to effectively measure spatial similarity between different polygon entities, and have obtained good application results. [ABSTRACT FROM AUTHOR]

In the current context of big data, data quality management has become a hot topic in data science research. This article focused on the intelligent monitoring needs of complex data structures and explored data quality evaluation indicators and monitoring methods for complex environments. Key technologies such as data fusion, cleaning, and quality evaluation were focused on research, and a data quality monitoring system for multi-dimensional data environments was constructed to verify its application effectiveness in multi-source data environments, as well as specific measures to improve data quality. On this basis, a data quality evaluation model based on data mining was utilized, and a real-time monitoring system was established for application research. When the number of consistency issues was 30, the response time was 300ms, and the success rate of processing was 95%. The lowest processing success rate was 88%, and the highest was 100%. The overall processing success rate of the system was very good. The research results of this article provided theoretical and methodological support for enterprises to effectively carry out data quality management, which has important theoretical significance and application value. [ABSTRACT FROM AUTHOR]

Against the backdrop of climate change becoming a global hot topic, global carbon emissions continue to grow. As the world's largest developing country, China is facing increasingly severe pressure to reduce emissions in its development. At the same time, in the current context of low-carbon transformation, the country has also begun to vigorously promote the carbon emission trading market. In the development process of China's carbon emissions trading market, there are still problems such as uneven data quality, insufficient data accuracy and standardization, which affect the normal operation of the carbon emissions trading market. Therefore, while the carbon emissions trading market is rapidly developing, it is necessary to establish a comprehensive carbon emissions data management system. This article analyzes the problems and future development directions of China's carbon emission data management system, and designs an overall design scheme for a carbon emission data management system based on multi-source data fusion. Through comparative experiments of UOS (ultimate Oscillator) indicators, it was found that the data transmission capacity of the carbon emission data management system designed in this paper with multi-source data can gradually improve the UOS value through continuous use. At the end of the experiment, it obtained a UOS value of up to 91.23%, far exceeding the efficiency of traditional data transmission. [ABSTRACT FROM AUTHOR]

Coherence scanning interferometry (CSI), based on the principle of interference, can achieve sub-nanometer precision for height measurements. On the other hand, focus variation microscopy (FVM), combining the small depth of field of the objective, is a widely used surface topography measurement method suited to surface topography that is mostly optically rough. In this paper, we propose a method to simultaneously obtain the interferometric fringe data and focus variation FVM image stack, from a single vertical scanning process, using a CSI instrument without any hardware modifications. Using a 3D Fourier transform, the FVM signal, looks takes the form of a "bowtie" and the CSI signal resembles two "umbrellas" that are separated in 3D K-space. The signal is recovered using a 3D inverse Fourier transform and the surface topography can be determined by fusing the CSI and FVM signals. Since both signals come from the same instrument and scanning process, there is no need for coordinate registration and data interpolation during the data fusion process. Our method combines the features of CSI and FVM measurement, thereby improving the robustness and data coverage of the measurement. An all-in-focus surface topography map can also be generated using this method. This focusing feature has the potential to significantly improve the defect detection and quality control ability of CSI instruments. • Extracting focus variation data from coherence scanning interferometry without any hardware modifications. • No need for coordinate registration and data interpolation during the data fusion process. • Combining the features of CSI and FVM measurement, thereby improving the robustness and data coverage of the measurement. • All-in-focus surface topography map can be generated using this method for defect detection and quality control. [ABSTRACT FROM AUTHOR]

Depression and anxiety are common in patients undergoing spinal surgery and might negatively impact outcomes. This study investigates the possible effect of these diagnoses on patient reported outcomes following lumbar fusion. Retrospective review of a registry containing prospectively collected data of lumbar fusion procedures at a single institution was performed from May 23, 2012 to June 15, 2022. Patients with a minimum of two year follow-up were included. Demographic information, diagnoses, medications, patient-reported outcomes measures (PROMs), and complications data at preoperative, three months, six months, 1 year, and two years postoperative were collected. Statistical analysis was performed using Student's t -tests, χ2, binomial correlation, odds ratios, logistic regression, and mean clinically important difference. A total of 156 patients were included (60 males, 96 females) with mean age 62.6 ± 11.1 years at surgery. Thirty-nine (25%) had depression and/or anxiety (DA). Baseline Oswestry Disability Index (ODI) and EuroQol Group 5D questionnaire (EQ5D) scores were significantly worse in the DA cohort compared to controls (ODI 51.1 ± 18.3 vs. 42.9 ± 15.8; P = 0.010, EQ5D 0.46 ± 0.21 vs. 0.57 ± 0.21; P = 0.005). Both cohorts experienced similar relative improvement at two years (delta ODI −18.2 ± 27.9 vs. −17.8 ± 22.1; P = 0.924, EQ5D 6.8 ± 33.8 vs. 8.1 ± 32.9; P = 0.830). Absolute outcome scores were worse in the DA cohort at all intervals. DA were not independently predictive of changes in PROMs (delta ODI mean difference 4.49, r2 = 0.36, P = 0.924). The present study showed similar improvement in PROMs following lumbar fusion for patients with anxiety and depression compared to healthy controls. These data suggest these patients are no less likely to benefit from appropriately planned lumbar fusion. [ABSTRACT FROM AUTHOR]

Accurate wheel slip estimation facilitates Wheeled Mobile Robots (WMRs) with improved localization and traversability monitoring which are crucial to their autonomy in challenging planetary environments. Although distributed track-level fusion offers better computational efficiency, often sensor-level fusion is adopted in slip estimators of planetary rovers. Extending upon our earlier work, we develop a novel explicit track-to-track fusion algorithm for multi-sensor networks of unscented Kalman filters that has immediate application to slip ratio estimation in WMRs. The algorithm demonstrates better consistency compared to the existing fusion techniques since it implements a sub-optimal fusion rule to sequentially combine local tracks. It also saves computational power due to the recursive propagation of cross-covariance matrices based on the statistical linearization technique, instead of performing online optimizations. We prove that this recursion only requires the information of the first and last tracks in a sequence if all local tracks are unbiased. We rigorously study various key properties of the developed fusion algorithm and show its superior level of confidence when compared to the two prominent fusion methods of sequential and batch covariance intersection. The slip ratio estimation in a six-wheel WMR is considered as a case study, where the steerable wheel sets act as a network of sensors. The proposed slip estimator works based on the rigid body kinematics and readings of purely proprioceptive sensors, i.e., an inertial measurement unit and encoders. The slip estimator's performance is evaluated in a high-fidelity software-in-the-loop simulation environment connecting MATLAB and CM Lab's Vortex Studio software. In a comparison study that considers four rival strategies, we show the superiority of the proposed fusion method offering a balance between consistency, accuracy, and speed in real-time slip estimations. • Developing a sequential track-to-track fusion algorithm considering correlations. • Recursively propagating the correlations based on statistical linearization. • Using only proprioceptive sensors for slip estimation of planetary wheeled rovers. • Providing a balance between accuracy, consistency and efficiency in slip estimation. [ABSTRACT FROM AUTHOR]

Accurately identifying the stage of the excavator working cycle is the prerequisite to achieve the staged energy-saving control. However, current identification methods often overlook the influence of hydraulic system latency on identification results and depend on a single model, resulting in poor generalization performance of the identification approaches. Moreover, expert calibration system remains a necessary factor for improving identification accuracy. Aiming at these issues, a hybrid multi-scale feature extractor and a decision-level data fusion classifier approach (HMSFE-DFC) is proposed to identify the working cycle stages of excavator. The input signal employs mixed signals from the main pump pressure and the control current of the proportional solenoid valve to reduce the response delay caused by the single main pump pressure signal. A hybrid multi-scale feature extractor is constructed using a convolutional neural network temporal self-attention feature extraction mechanism and one-dimensional ResNet-50 architecture to extract multiscale features. To prevent overfitting, a decision-level data fusion classifier is used to fuse the decisions information of numerous classifiers. The accuracy of stage identification for 10 consecutive working cycles reaches 95.21%, which verifies its effectiveness. • A hybrid multiscale feature extractor and decision level data fusion classifier approach is presented. • The main pump pressure and control current of the proportional solenoid valve are mixed to reduce the response delay. • The proposed approach can achieve an identification accuracy of 95.21% for 10 consecutive working cycles of an excavator. [ABSTRACT FROM AUTHOR]

Accurate and robust localization is a critical requirement for autonomous driving and intelligent robots, particularly in complex dynamic environments and various motion scenarios. However, existing LiDAR odometry methods often struggle to promptly respond to changes in the surroundings and motion conditions with fixed parameters through execution, hindering their ability to adaptively adjust system model parameters. Additionally, current localization techniques frequently overlook the confidence level associated with their pose results, leading the autonomous systems to unconditionally accept estimated outputs, even when they may be erroneous. In this paper, we propose a robust data-model dual-driven fusion with uncertainty estimation for the LiDAR–IMU localization system, which integrates the advantages of data-driven and model-driven approaches. We introduce data-driven feature encoder modules for LiDAR and IMU raw data, enabling the system to detect changes in the environment and motion status. Subsequently, these data-driven findings are incorporated into a filtering based model, allowing for the adaptive refinement of system model parameters. Furthermore, we refine the representation of uncertainty based on the Extended-Kalman-Filter model covariance, integrating uncertainty from sensor data and model parameters, which helps to evaluate the confidence of fusion system results. We conducted extensive experiments on two publicly available datasets and one dataset we collected with three sequences, verifying the accuracy of our method. In addition, we have demonstrated the robustness of our method in different motion states and scenarios through comparative experiments, as well as the effectiveness of our refined uncertainty estimation, compared with existing great methods, such as Fast-LIO2 and LIO-SAM, the localization accuracy has been improved by 8.3%. [ABSTRACT FROM AUTHOR]

Regional ionospheric Total Electron Content (TEC) models are most significant to investigate the variability of ionosphere during all-weather conditions. Since the ground-based TEC measurements are not available in oceanic and polar regions, space-based observations are incorporated to increase the positional accuracy and reliability of Global Ionospheric TEC Maps (GIMs). Therefore, data fusion techniques are necessary to enhance the prediction capability of regional ionospheric models by considering multi-source data. In view of this, an attempt is made to investigate Equatorial Ionization Anomaly (EIA) structures in low-latitudinal Indian region using multi-instrument data. Data observations from background model CODEGIM, available International GNSS Service (IGS) stations in India, GNSS receivers at KLEF and Tripura stations, FORMOSAT/COSMIC radio occultation and SWARM during geomagnetic storm period August 26–28, 2021 are used for the study. Spherical Harmonics Function (SHF) of order 4 is employed along with Weighted Least Squares analysis (WLS), where separate weight constraint is computed for each data source. TEC maps of spatial resolution 5° x 5° and temporal resolution of 1 h are generated to illustrate the dynamic behavior of ionosphere. The standard deviation for 3 days is obtained as 0.42, 0.61 and 1.43 TECU respectively. TEC depletions and enhancements are observed on August 27 and 28, with mean values of 12.74 and 15.27 TECU respectively, demonstrating negative and positive storm effects. [ABSTRACT FROM AUTHOR]

This paper presents a digital twin-assisted online monitoring and control system for machining operations. Process information including Cutter-Workpiece Engagement (CWE) maps are extracted from the virtual model of the process and fused with the CNC internal data as well as the measured external sensor data. Several applications are illustrated to demonstrate the system. Adaptive control of cutting load based on directly measured forces or reconstructed forces from an accelerometer-integrated tool holder is demonstrated. The spindle current data integrated with CWE information from the virtual model is utilized for the estimation of tool wear progression and tool breakage detection. Digital twin-assisted chatter detection and avoidance are presented by avoiding false alarms at the cutter's entry into and exit from work material which triggers transient vibrations. It is shown that by utilization of the digital twin data and information fusion, robust process monitoring and control can be achieved while anomalies and false alarms are avoided. [ABSTRACT FROM AUTHOR]

In recent years, GPS data on truck movements have become much more available, leading researchers and practitioners to leverage these sources to generate a wealth of data and information related to truck OD flows. In this study large amount of truck GPS data used to investigate characteristics of freight transportation in particularly OD land uses and freight vehicle classes. Aiming to realize the freight flows characteristics of the Chicago Metropolitan Agency Planning (CMAP) region. The data are used primarily to gain insight into the nature of urban goods movement and the distribution of retail goods. The main objective in this respect is analyzing urban freight flows and retail goods movement. The data-driven analysis generates a number of interesting findings regarding the nature and volume of trips by light-duty, medium-duty, and heavy-duty truck that serve various types of retail and industrial functions are generated. The design of this study especially its land use data fusion aspect is expected to benefit both practitioners and researchers as they plan future data collection, model calibration and urban freight studies. [ABSTRACT FROM AUTHOR]

Data-driven Digital Twin approaches have gained popularity in research literature, particularly in relation to Industry 4.0 achievements. Data-driven Digital Twins process widely available real-time data in an automated manner to extract models from various systems of interest. However, these model extraction approaches commonly lack systematic integration of expert knowledge from human experts, such as engineers. Combining valuable expert knowledge with data-driven model extraction approaches is a highly complex task that can significantly contribute to more accurate models within shorter time periods. In this paper, we provide a comprehensive overview of the research done on fusion of data and expert knowledge for Digital Twins to identify and describe the current gap. Resulting from our findings, we propose an initial framework for integrating expert knowledge and data for Digital Twin model extraction. Subsequently, we provide an overview of the main challenges and opportunities in fusing data and expert knowledge in the context of Digital Twins. [ABSTRACT FROM AUTHOR]

Smart and connected health (SCH) accelerates the development and integration of information science and engineering approaches to support the digital transformation of health and medicine in populated societies. Sensor data based human activity recognition (HAR) as an effective means of SCH is promising for healthcare monitoring and ambient assisted living. This paper focuses on multi-position sensor data fusion enabled HAR, and proposes a multi-channel deep learning framework. The main contributions include: (1) A multi-channel hybrid deep learning model (1DCNN-Att-BiLSTM) that merges a one-dimensional convolutional neural network, a bidirectional long short-term memory model, and an attention mechanism is proposed to significantly improve the recognition performance of HAR models by extracting and selecting local and global behavioral features in the spatial and temporal domains; (2) Publicly accessible datasets Shoaib AR, Shoaib SA, and HAPT are collected and processed to build multi-position sensor data pool for model's evaluation; (3) Thoroughly evaluating the classification performance of seven sensor data fusion patterns from different body positions within the parallel network structure of the multi-channel framework; (4) Comparing the recognition performance metrics of traditional machine learning models, deep learning models, and hybrid models with our proposed model. Extensive experiments demonstrate that our approach achieves competitive performance. [ABSTRACT FROM AUTHOR]

• A multimodal computational approach was used for the 3D survey of a panel painting. • Data from close-range photogrammetry and laser microprofilometry were fused. • The warping arrow before and after restoration was quantified on the 3D point cloud. • Multi-temporal monitoring of the painting is computed via Cloud-to-Cloud distance. • Micrometric roughness of paint layers is measured by laser microprofilometry. This paper reports the results obtained from the workflow designed for the 3D survey of a Renaissance panel painting using close-range photogrammetry and conoscopic laser microprofilometry, before and after its restoration. The artwork under examination is the central panel of a Renaissance polyptych realized by a late Gothic painter active in central Italy in the late 15th century. This painting has had a rather troubled conservation history following numerous adverse events that have severely damaged it structurally. In preparation for restoration work, the fusion of point cloud data derived from active and passive sensors served to create a single multi-resolution model on which to conduct advanced metrological analyses for multi-temporal monitoring of the changes undergone by the panel painting during and after structural restoration. [ABSTRACT FROM AUTHOR]

Biometrics is a field that has been given importance in recent years and has been extensively studied. Biometrics can use physical and behavioural differences that are unique to individuals to recognize and identify them. Today, biometric information is used in many areas such as computer vision systems, entrance systems, security and recognition. In this study, a new biometrics database containing silhouette, thermal face and skeletal data based on the distance between the joints was created to be used in behavioural and physical biometrics studies. The fact that many cameras were used in previous studies increases both the processing intensity and the material cost. This study aimed to both increase the recognition performance and reduce material costs by adding thermal face data in addition to soft and behavioural biometrics with the optimum camera. The presented data set was created in accordance with both motion recognition and person identification. Various data loss scenarios and multi-biometrics approaches based on data fusion have been tried on the created data sets and the results have been given comparatively. In addition, the correlation coefficient of the motion frames method to obtain energy images from silhouette data was tested on this dataset and yielded high-accuracy results for both motion and person recognition. [ABSTRACT FROM AUTHOR]

Digital transformation in manufacturing necessitates the integration of advanced fields such as robotics, the Internet of Things (IoT), and data science. The latter two, in particular, introduce a unique set of challenges related to data acquisition and processing, especially for emerging manufacturing sectors that lack substantial data volumes for analytical software. This paper specifically addresses the challenges associated with limited data within the context of precision poultry farming. We begin by identifying the specific challenges encountered during the development of a smart poultry management software system. Subsequently, we propose potential solutions for each identified challenge. The outcome of this study is a comprehensive algorithm for data processing that encapsulates these proposed solutions, offering a practical approach to overcoming data limitations in precision poultry farming. [ABSTRACT FROM AUTHOR]

Process abnormalities can result in serious accidents that may lead to unexpected loss of life and property. Early fault detection and diagnosis are essential to prevent these accidents. In the efficient operation of industrial systems, alarm systems play a crucial role. Developing new sensors and alarm adjustment networks has increased the possibility of generating multiple alarms. The alarm flood is the most important type of this problem. In this study, a new algorithm is proposed to diagnose the root cause of the fault through the classification of alarm floods. The main novelty of this algorithm is to use transfer entropy as a criterion to detect the similarity between the alarm flood sequences. The other innovations include calculating transfer entropy between the process variable and the alarm data, multi-sensor information fusion for large-scale plants and simultaneous alarms, and proposing an online version of the algorithm for the early prediction of the type of fault occurring. Finally, the Tennessee Eastman Process system, as a simulator, and the Saveh rotary cement kiln, as a real industrial system, are applied to evaluate the proposed method. • Diagnosing the root cause of the faults through the classification of the alarm floods. • Using transfer entropy to detect the similarity between the alarm flood sequences. • Calculation of the transfer entropy between the process variable and the alarm data. • Multi-sensor information fusion for large-scale plant and simultaneous alarms. • An online method for early predict of the root cause of the alarm floods occurring. [ABSTRACT FROM AUTHOR]

• Methodology for a complete geometrical analysis of the vaults of Notre-Dame de Paris after the fire. • 2D image-based method for comparison before and after the fire. • 3D point cloud-based method for comparison before and after the fire. • New method for accurate alignment of very large point clouds. The work presented in this article was carried out following the fire (April 15, 2019) that ravaged Notre-Dame de Paris. The goal was to establish in a short and limited time-span the structural diagnosis of the remaining vaults of the cathedral. The analysis relied on 2D and 3D data acquired before and after the fire, and available at that time. Two complementary methods have been developed to estimate potential displacements from multi-temporal surveys. The first method is mainly based on the processing of image collections obtained with photogrammetric routines right after the fire. The second method, based on the processing of raw 3D data acquired with Terrestrial Laser Scanning, was developed afterward to refine and complete the analysis. Both methods have benefited from essential functionalities offered by two open-source solutions proven to enable "real-based" modeling in Cultural Heritage contexts, namely Micmac and CloudCompare. This paper presents the complementary use of these two software packages whilst detailing some procedural computing approaches to document and support structural diagnosis in an emergency situation. The limits and capabilities of each method are exposed and analyzed, toward the objective to develop 2.5D and 3D based geometrical analysis, respectively from photogrammetric and lasergrammetric sources. The results are presented and discussed regarding their potential usage for a quantitative and accurate diagnosis of vaults. [ABSTRACT FROM AUTHOR]

There has been a recent emphasis on integrating physical models and deep neural networks (DNNs) for SAR target recognition, to improve performance and achieve a higher level of physical interpretability. The attributed scattering center (ASC) parameters garnered the most interest, being considered as additional input data or features for fusion in most methods. However, the performance greatly depends on the ASC optimization result, and the fusion strategy is not adaptable to different types of physical information. Meanwhile, the current evaluation scheme is inadequate to assess the model's robustness and generalizability. Thus, we propose a physics inspired hybrid attention (PIHA) mechanism and the once-for-all (OFA) evaluation protocol to address the above issues. PIHA leverages the high-level semantics of physical information to activate and guide the feature group aware of local semantics of target, so as to re-weight the feature importance based on knowledge prior. It is flexible and generally applicable to various physical models, and can be integrated into arbitrary DNNs without modifying the original architecture. The experiments involve a rigorous assessment using the proposed OFA, which entails training and validating a model on either sufficient or limited data and evaluating on multiple test sets with different data distributions. Our method outperforms other state-of-the-art approaches in 12 test scenarios with same ASC parameters. Moreover, we analyze the working mechanism of PIHA and evaluate various PIHA enabled DNNs. The experiments also show PIHA is effective for different physical information. The source code together with the adopted physical information is available at https://github.com/XAI4SAR/PIHA. [ABSTRACT FROM AUTHOR]

The combination of InSAR and GNSS data can provide more accurate measurements of coseismic 3D surface deformations, which are crucial in determining earthquake source parameters. Currently, the methods for inverting coseismic 3D surface deformations by integrating GNSS and InSAR data using the strain model (SM) (e.g., Simultaneous and integrated strain tensor estimation from geodetic measurements to obtain 3D displacement maps (SISTEM), SM-VCE) simply select GNSS points based on a certain number or distance, without considering the weight influence of the spatial distribution of G NSS points on the InSAR and GNSS data fusion results. To address this issue, this paper proposes a new method that uses Voronoi diagrams analyze the contribution of GNSS points to the deformation at target points. In this paper, GNSS points with high contribution can be used to construct observation value equations and optimize the internal weight of GNSS data. The proposed approach characterizes the contribution of GNSS data to target points by analyzing the changes in the Delaunay triangulation area formed before and after the target points are added to the GNSS data. Simulation experiments reveal that the proposed method outperforms conventional methods in accuracy and completeness. The proposed method is then applied to map the coseismic 3D surface deformations of the 2020 Mw6.5 Monte Cristo Range earthquake and find that the maximum deformation in the east–west, north–south, and vertical directions is about 13 cm, 11 cm, and 24 cm, respectively. [ABSTRACT FROM AUTHOR]

Layer thickness of thin and multi-layer coatings is a major design parameter to functionalise surfaces in a broad range of industrial applications. Conventional measurement methods are often complex, expensive, and limited in thickness range and applicability, particularly for thin coatings on fragile substrates and/or with complex compositions. An innovative methodology is introduced based on nanoindentation, leveraging data fusion and nanoindentation augmentation with in-situ current measurement, to evaluate functional and physical layer thickness by material properties and statistical modelling techniques. Two cases concerning coatings for semiconductor and tribomechanical applications are described, exhibiting faster, cheaper, and metrologically competitive results over current techniques. [ABSTRACT FROM AUTHOR]

Spatiotemporal fusion (STF) is crucial for reconciling the conflict between temporal and spatial resolutions of remote sensing observations. However, fusing images in heterogeneous areas remains challenging under continuous missing values. Moreover, most current STF methods only consider temporal errors and disregard the spatial scale error in time variation. Therefore, we proposed a Quick Spatiotemporal Fusion with Coarse- and Fine-Resolution Scale Transformation Errors and Pixel-Based Synthesis Base Image Pair (STEPSBI). First, the optimal pixel-based image synthesis strategy was designed using all available fine- and coarse-resolution images. Then, the scale transformation error (STE) of coarse-resolution downscaling to fine-resolution in temporal variation was quantified. And a residual term was introduced to reduce the prediction error from the temporal variation. Finally, the spatial scale and temporal errors were corrected using the results of super-pixel segmentation as spatial weights. This model has two strengths: (1) Pixel-based image synthesis alleviates the absence of base images under continuous missing values; and (2) STE correction restores spatial details of heterogeneous areas in rapid land cover change. In scenarios of continuous missing images, abrupt land cover changes, and high-resolution heterogeneity, we evaluated STEPSBI, the Gap Filling and Savitzky–Golay filtering method (GF-SG), the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), the Flexible Spatiotemporal DAta Fusion (FSDAF), the cross-attention-based adaptive weighting fusion network (CAFE), and the Multi-scene Spatiotemporal Fusion Network (MUSTFN). The results indicate that STEPSBI yields better overall performance than other models in cropland, woodland, grassland, and other land cover types. Furthermore, ablation experiments demonstrated that each component improved the model's performance. In addition, STEPSBI had higher fusion efficiency because it was developed on the Google Earth Engine cloud computing platform. Therefore, STEPSBI was feasible for advancing fine monitoring of spatiotemporal image fusion under continuous missing values and heterogeneous surfaces. The program of STEPBSI is freely available at: https://code.earthengine.google.com/684844aa42f64fa6b4eebe3bc0dd6483. [ABSTRACT FROM AUTHOR]

The wood industry demands advanced methods for material classification and workpiece characteristic modelling to enhance process monitoring and adaptive process control. This paper presents a sensor fusion approach that integrates data from acoustic emissions, airborne sound, and power consumption during the milling of solid wood and wood-based composites. The aims are to achieve accurate material classification and to model workpiece characteristics such as surface roughness or density. A design matrix was generated by extracting relevant features from the multimodal signals to serve as an input for the classification and regression algorithms. The tested classification approaches to differentiate between workpiece type demonstrated high precision with an average validation accuracy of 92.16 %. Regression models for predicting the surface roughness showed R 2 values between 0.79 and 0.97. The density could be predicted with R2 values between 0.84 and 0.98. As a conclusion, workpiece types could be classified and important workpiece properties during machining, such as surface roughness and density, could be well described by using information from multiple sensors during machining. [ABSTRACT FROM AUTHOR]

Based on the rapid development of Internet new generation information technology, campus culture has become an important force to promote educational innovation. However, the uneven quality of campus culture teaching is also increasingly exposed. Therefore, we propose a set of campus culture intelligent quality assessment feedback system driven by data and knowledge. Based on real multi-modal campus culture data, the evaluation system covers different online teaching forms, and can comprehensively consider and measure the core elements of quality evaluation from the perspective of teachers and students, so as to achieve accurate evaluation and feedback of campus culture. This paper proposes to combine emotion computing with big data analysis, construct a theoretical framework of multi-modal emotion analysis from the perspective of multi-spatial fusion, and explore the students' learning emotion recognition and intelligent assessment based on multi-modal data fusion. By studying the key issues, logical path and implementation path of multimodal learning emotion analysis in campus culture, this paper reveals the mechanism of student emotion development from the perspective of campus culture, expands the intervention practice of student group emotion, and provides technical support and action guidance for after-school teaching and research on campus culture. [ABSTRACT FROM AUTHOR]

To improve the accuracy of bearing fault diagnosis in a multisensor monitoring environment, it is necessary to obtain more accurate and effective fault classification features for bearings. Accordingly, a bearing fault classification feature extraction method based on multisensor fusion technology and an enhanced binary one-dimensional ternary pattern (EB-1D-TP) algorithm were proposed in this study. First, an optimal equalization weighting algorithm was established to realize high-precision fusion of bearing signals by introducing an optimal equalization factor and determining the theoretical optimal equalization factor value. Second, an enhanced binary encoding method similar to balanced ternary encoding was developed, which increases the difference between the different fault features of the bearing. Finally, the new sequence obtained after encoding was used as the input to a support vector machine to classify and diagnose the faults of the rolling bearing. The experimental results show that the algorithm can significantly improve the accuracy and speed of rolling-bearing fault classification. Combining fusion-encoding features with other intelligent classification methods, the classification results were improved. • An optimized equalization random weighting algorithm is proposed. • A "Zero Removal" enhancement processing technique is proposed. • A new encoding method more suitable for one-dimensional signal is constructed. [ABSTRACT FROM AUTHOR]

This paper proposes a robust finite element Kalman filter for the state estimation of flexible space tether systems, which are critical for space exploration and satellite missions. Due to the limited access to placing sensors along the flexible tether to measure them directly, the measurement of the state of these systems is challenging. To address this, a fully expandable, scalable, and robust approach is developed that fuses position/velocity sensors at tether ends, distributed fiber optic strain measurement along the tether, and a position/velocity estimation by a finite element-based Kalman filter to estimate the state of the tether system. The proposed estimator is mathematically proven to be observable, stable, and robust. The effectiveness of the estimator is demonstrated through numerical simulations of a space tether system in orbit, and the method can be extended to any flexible body system. The results of the simulations show that the proposed approach can accurately estimate the state of the tether system, even in the presence of disturbances and noise. • Expandable, scalable FE-Kalman state estimator for flexible space tether systems. • Data fusion with tether end position/velocity, distributed fiber optic strain measure, and estimated internal position/velocity. • Mathematically proven observability, stability, and robustness to noise of the estimator. [ABSTRACT FROM AUTHOR]

The Internet of Medical Things (IoMT) bolstered the smart health care industry in present times by enabling quicker patient monitoring and disease diagnosis. However, there have been problems that need to be resolved using Artificial Intelligence (AI) methods. The major goal of this endeavor is to develop an IoMT-based data fusion system for multi-sensor smart healthcare network. To do this, a new optimization and deep learning approaches are being used in this work. In this research work, a unique smart healthcare framework, Tasmanian and Lichtenberg Optimized Attention Deep Convolution (TasLA) is developed for IoMT systems. This system uses an intelligent data fusion algorithms for collecting of medical data and the diagnosis of disorders. Here, data pretreatment and normalization processes are carried out in order to provide a dataset with balanced attribute information. The qualities or characteristics that will aid in classification are then selected using the most modern Tasmanian Devil Optimization (TDO) approach. The Attention Deep Convolution Classification (ADCC) algorithm is also used to classify the medical condition, thereby improving classification precision and reducing false predictions. To optimally compute the loss function during prediction, the Lichtenberg Optimization (LO) technique is employed to enhance classification performance. The effectiveness and results of the proposed TasLA model are validated and contrasted using various benchmark datasets such as Hungarian, Cleveland, Echocardiogram, and Z-Alizadeh. [ABSTRACT FROM AUTHOR]

The evidence for instrumented fusion in the setting of degenerative, traumatic, or congenital deformity is well established. Data on fusion indications in intradural spinal tumors (IDST) are scarce and reduced to retrospective studies. The objective of this work is to systematically review the published literature since 2015 and analyze the change of practice patterns for stabilization and fusion after intradural tumor resection in adults. A systematic literature review was performed via PubMed with the terms: "intradural spinal tumors", "intramedullary spinal tumors", and "intraspinal tumors". The analysis was limited to adult patients with IDST and studies with more than 10 patients. Data on the proportion of patients who underwent instrumentation and had postoperative deformity was pooled in a meta-analysis. A total of 1073 articles were identified and 47 papers were selected. All the studies were retrospective series and a total of 2473 patients were included. The follow-up ranged from 1 to 96 months, the pooled spinal fixation rate was 6% (95% CI 4.5%–7.6%), the pooled laminoplasty rate was 14.4% (95% CI 5.9%–23%), the pooled rate of postoperative deformity or malalignment in patients with a follow up of at least 6 months was 2.1% (95% CI 1.2%–3%) and just 7 patients were reoperated due to progressive deformity. Based on existing evidence, the rate of fusion during resection of intradural spinal tumors is low. Prophylactic fixation is often unnecessary and only indicated in unique cases that require extensive bony resection. [ABSTRACT FROM AUTHOR]

In wearable sensing, accurate estimation of physiological parameters is paramount, although these signals can be corrupted by noise. The fusion of data from multiple sensor sources has the potential to enhance accuracy, even in the presence of disruptive noise. This paper aims to introduce and compare various existing state-of-the-art and novel data fusion techniques to improve the reliability of heart rate estimation. The comparisons were implemented using the MIT-BIH Arrhythmia database with additive noise signals taken from MIT Noise Stress Test Database. When it comes to the challenging low signal-to-noise ratio (SNR) regions, the Kalman fusion and the α -trim mean filtering approach exhibits the best performance. The Kalman fusion approach dominates when both channels are corrupted, while the α -trim mean filtering elimination algorithm takes the lead when at least one channel is clean. To make the most of these strengths, we have developed an innovative algorithm that can switch between the two fusion methods based on a signal quality indicator (SQI) that serves as a surrogate SNR. This algorithm outperforms the baseline 2-channel RR-interval averaging approach by ≃ 54 % and ≃ 21 % at SNRs of 20 dB and − 20 dB respectively. Moreover, it outperforms other cutting-edge heart rate estimation methods. • Investigation of fusion methods for heart rate estimation from ECG signals. • Signal quality aware fusion algorithm selection. • Fusion methods analyzed at varying input signal-to-noise ratios. • Signal quality index proposed as a surrogate for input signal-to-noise ratio. • Fusion selection method proposed for varying input signal-to-noise ratios. [ABSTRACT FROM AUTHOR]

• Identify gaps in state-of-the-art research to support healthcare AI trustworthiness. • Explore the explainable AI and fusion in healthcare. • Explore legitimacy, morality, and robustness standards for AI policymakers. • Assessment quality, bias risk, and data fusion for medical AI trustworthiness. • Examine eight research gaps to guide future study and assist researchers. In the last few years, the trend in health care of embracing artificial intelligence (AI) has dramatically changed the medical landscape. Medical centres have adopted AI applications to increase the accuracy of disease diagnosis and mitigate health risks. AI applications have changed rules and policies related to healthcare practice and work ethics. However, building trustworthy and explainable AI (XAI) in healthcare systems is still in its early stages. Specifically, the European Union has stated that AI must be human-centred and trustworthy, whereas in the healthcare sector, low methodological quality and high bias risk have become major concerns. This study endeavours to offer a systematic review of the trustworthiness and explainability of AI applications in healthcare, incorporating the assessment of quality, bias risk, and data fusion to supplement previous studies and provide more accurate and definitive findings. Likewise, 64 recent contributions on the trustworthiness of AI in healthcare from multiple databases (i.e., ScienceDirect, Scopus, Web of Science, and IEEE Xplore) were identified using a rigorous literature search method and selection criteria. The considered papers were categorised into a coherent and systematic classification including seven categories: explainable robotics, prediction, decision support, blockchain, transparency, digital health, and review. In this paper, we have presented a systematic and comprehensive analysis of earlier studies and opened the door to potential future studies by discussing in depth the challenges, motivations, and recommendations. In this study a systematic science mapping analysis in order to reorganise and summarise the results of earlier studies to address the issues of trustworthiness and objectivity was also performed. Moreover, this work has provided decisive evidence for the trustworthiness of AI in health care by presenting eight current state-of-the-art critical analyses regarding those more relevant research gaps. In addition, to the best of our knowledge, this study is the first to investigate the feasibility of utilising trustworthy and XAI applications in healthcare, by incorporating data fusion techniques and connecting various important pieces of information from available healthcare datasets and AI algorithms. The analysis of the revised contributions revealed crucial implications for academics and practitioners, and then potential methodological aspects to enhance the trustworthiness of AI applications in the medical sector were reviewed. Successively, the theoretical concept and current use of 17 XAI methods in health care were addressed. Finally, several objectives and guidelines were provided to policymakers to establish electronic health-care systems focused on achieving relevant features such as legitimacy, morality, and robustness. Several types of information fusion in healthcare were focused on in this study, including data, feature, image, decision, multimodal, hybrid, and temporal. [ABSTRACT FROM AUTHOR]

Multi-view semi-supervised classification is inherently a challenging task in multi-view learning due to the lack of label information. Existing methods generally suffer from insufficient data fusion, expensive computation cost in the solution procedure and fail in tackling unseen samples directly, intensively limiting their applicability and efficiency in real scenarios. To address these issues, we propose an adaptive collaborative fusion method, seeking for an appropriate representation and fusion for multi-view data. The main advantage of the proposed method is that it simultaneously fuses both multiple feature projections and similarity graphs to learn a joint projection subspace as well as a unified similarity graph that fully preserve the correlation and distinction among views. Meanwhile, our method can coalesce different views in an adaptive-weighting manner, making the learned subspace more discriminative and facilitating label propagation on the fused graph. Furthermore, an acceleration strategy has been designed to reduce the computational complexity, thereby making the proposed method scalable to relatively large-scale data. Finally, an alternating optimization has been adopted to solve the formulated objective function. Extensive experiments on synthetic and real-world datasets are conducted to demonstrate the effectiveness and superiority of our proposed method. • Propose a collaborative fusion method for multi-view semi-supervised learning. • Adaptively fuse different views to learn a joint projection and a unified graph. • The proposed method can efficiently deal with large-scale multi-view data. • Experiments on various datasets validate the method effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

Concerned with deploying zero-emission energy sources, reducing energy wasted through transmission lines, and managing power supply and demand, monitoring and controlling microgrids have found utter importance. Accordingly, this paper aims to investigate the efficacy of state estimation fusion for a synchronous generator as well as an induction motor in order to ameliorate system monitoring. A third-order nonlinear state-space model, that operates based on actual input data taken from the Smart Microgrid Laboratory, is assumed for each of the electrical machines. The model parameters are set according to the parameters of the electrical machines. A fusion structure based on the internet of things communication network, which is modified to increase uncertainty, is presented for fusing the state estimates. The data fusion topology is distributed and relies on two data fusion models. The first model is a set of state estimators, referred to as data input-feature output model. The second one fuses the estimators' outputs based on supervised machine learning methods, referred to as feature input-feature output model. The simulation results in MATLAB and Python show the efficiency of linear regression methods compared with other leveraged methods for data fusion. By comparing the results obtained from both simple and complex estimation filters, it can be deduced that combining simple filters, extended Kalman filter in this case, with simple data fusion methods, linear regression in this case, can produce much more accurate results in a short period of time. Besides, this study shows that the averaging operators are unsuitable for estimation fusion by referring to their convexity condition. • Regression methods can outperform other methods for the purpose of data fusion. • Simple filters combined with simple fusion methods boost state estimation accuracy. • The averaging operators are unsuitable for estimation fusion due to performing convex fusion. [ABSTRACT FROM AUTHOR]

The automatic positioning of underground mobile applications plays a crucial role in enabling intelligent coal mining. However, due to the diverse kinematics and dynamics of these applications, various positioning methods have been proposed to match different targets. Nonetheless, the accuracy and applicability of these methods still fall short of meeting the requirements for field applications. Based on the vibration characteristics of underground mobile devices, a multi-sensor fusion positioning system is developed to enhance the accuracy of positioning in long and narrow global positioning system denied (GPS-denied) underground coal mine roadways. The system combines inertial navigation (INS), odometer, and ultra wide band (UWB) technologies through extended Kalman filter (EKF) and unscented Kalman filter (UKF). This approach enables accurate positioning by recognizing target carrier vibrations and facilitating fast conversion between multi-sensor fusion modes. The proposed system is tested on both a small unmanned mine vehicle (UMV) and a large roadheader, demonstrating that UKF enhances stability for roadheaders with strong nonlinear vibrations while EKF is more suitable for flexible UMVs. Detailed results confirm that the proposed system achieves an accuracy level of 0.15 m, meeting most coal mine application requirements. • An accurate and widely applicable positioning solution is presented. • The applicable positioning method is converted based on vibration recognition. • UKF performs better in large mining applications while EKF suits mobile robots. [ABSTRACT FROM AUTHOR]

Playing games between humans and robots have become a widespread human–robot confrontation (HRC) application. Although many approaches were proposed to enhance the tracking accuracy by combining different information, the problems of the intelligence degree of the robot and the anti-interference ability of the motion capture system still need to be solved. In this paper, we present an adaptive reinforcement learning (RL) based multimodal data fusion (AdaRL-MDF) framework teaching the robot hand to play Rock–Paper–Scissors (RPS) game with humans. It includes an adaptive learning mechanism to update the ensemble classifier, an RL model providing intellectual wisdom to the robot, and a multimodal data fusion structure offering resistance to interference. The corresponding experiments prove the mentioned functions of the AdaRL-MDF model. The comparison accuracy and computational time show the high performance of the ensemble model by combining k-nearest neighbor (k-NN) and deep convolutional neural network (DCNN). In addition, the depth vision-based k-NN classifier obtains a 100% identification accuracy so that the predicted gestures can be regarded as the real value. The demonstration illustrates the real possibility of HRC application. The theory involved in this model provides the possibility of developing HRC intelligence. • Providing a new multimodal data fusion-based ensemble classifier by combining depth data and sEMG signals. • Building a RL model to teach the robot to play the Rock–Paper–Scissors game with humans. • Designing a hierarchical trigger mechanism to control the updated procedure. [ABSTRACT FROM AUTHOR]

Recently, remote sensing community has seen a surge in the use of multimodal data for different tasks such as land cover classification, change detection and many more. However, handling multimodal data requires synergistically using the information from different sources. Currently, deep learning (DL) techniques are being religiously used in multimodal data fusion owing to their superior feature extraction capabilities. But, DL techniques have their share of challenges. Firstly, DL models are mostly constructed in the forward fashion limiting their feature extraction capability. Secondly, multimodal learning is generally addressed in a supervised setting, which leads to high labelled data requirement. Thirdly, the models generally handle each modality separately, thus preventing any cross-modal interaction. Hence, we propose a novel self-supervision oriented method of multimodal remote sensing data fusion. For effective cross-modal learning, our model solves a self-supervised auxiliary task to reconstruct input features of one modality from the extracted features of another modality, thus enabling more representative pre-fusion features. To counter the forward architecture, our model is composed of convolutions both in backward and forward directions, thus creating self-looping connections, leading to a self-correcting framework. To facilitate cross-modal communication, we have incorporated coupling across modality-specific extractors using shared parameters. We evaluate our approach on three remote sensing datasets, namely Houston 2013 and Houston 2018, which are HSI-LiDAR datasets and TU Berlin, which is an HSI-SAR dataset, where we achieve the respective accuracy of 93.08%, 84.59% and 73.21%, thus beating the state of the art by a minimum of 3.02%, 2.23% and 2.84%. • Self-looping blocks with shared weights across time for feature refinement. • Multiscale kernels are used for self-looping blocks for spatial diversity. • Cross-modal communication with shared weights across modalities. • Weight sharing across modalities and time enable efficient parameter controlling. • Robust cross-modal learning with self-supervised cross-modal reconstruction. [ABSTRACT FROM AUTHOR]

• Using multiple sensors to enable SUR to obtain high-precision estimated data. • Building MSIF model with multisource factors to enhance SUR's practicality in tasks. • Considering multi-sensor information to offset position, velocity and tracking error. • Combining with BPNN to improve the MSIF's effectiveness, accuracy, and feasibility. Currently, most of the existing fusion methods ignore the rich multi-source information of different types of sensor nodes in the underwater unknown environment, which makes it challenging for Autonomous Underwater Vehicles (AUVs) to accurately perceive the external environment and make actionable decisions. Considering the key issues such as attitude estimation, positioning and obstacle avoidance involved in performing AUV tasks, this paper proposed a Multi-Source Information Fusion (MSIF) model for Spherical Underwater Robots (SURs) we developed based on various low-cost sensors. Multi-source information from an Inertial Measurement Unit (IMU), Pressure Sensor Array (PSA), Obstacle Avoidance Sensor Array (OASA), Depth Sensor (DS), Looking-Down Camera (LDC) and Acoustic Communication System (ACS) were fused to enable SUR to obtain high-precision estimated data for attitude estimation, positioning and obstacle avoidance, etc. More precisely, according to the correlation between the sensors, the optimized model was constructed to compensate for angle errors, velocity errors, orientation errors, etc. Subsequently, a machine learning method using Back Propagation Neural Network (BPNN) was proposed to improve the accuracy and effectiveness of the MSIF model through feature selection, data training, and feature estimation, etc. Finally, a series of experiments were performed under different scenarios, such as motion and obstacle avoidance experiments. The theoretical derivation and comprehensive evaluations demonstrated the effectiveness and feasibility of the proposed model, which provided a new reference value for solving issues such as attitude estimation, positioning and obstacle avoidance of AUVs. [ABSTRACT FROM AUTHOR]

Navigation/positioning systems have become critical to many applications, such as autonomous driving, Internet of Things (IoT), Unmanned Aerial Vehicle (UAV), and smart cities. However, it is difficult to provide a robust, accurate, and seamless solution with single navigation/positioning technology. For example, the Global Navigation Satellite System (GNSS) cannot perform satisfactorily indoors; consequently, multi-sensor integrated systems provide the solution, as they compensate for the limitations of single technology by using the complementary characteristics of different sensors. This article describes a thorough investigation into multi-sensor data fusion, which over the last ten years has been used for integrated positioning/navigation systems. In this article, different navigation/positioning systems are classified and elaborated upon from three aspects: (1) sources, (2) algorithms and architectures, and (3) scenarios, which we further divide into two categories: (i) analytics-based fusion and (ii) learning-based fusion. For analytics-based fusion, we discuss the Kalman filter and its variants, graph optimization methods, and integrated schemes. For learning-based fusion, several supervised, unsupervised, reinforcement learning, and deep learning techniques are illustrated in multi-sensor integrated positioning/navigation systems. Design consideration of these integrated systems is discussed in detail from several aspects and their application scenarios are categorized. Finally, future directions for their research and implementation are discussed. • Classifying integrated navigation systems with sources, algorithms, and scenarios. • Classifying multi-sensor fusion based on absolute and relative positioning sources. • Analytics-based and learning-based algorithms are discussed and classified. • Design considerations include state selection, observability, time synchronization. • Classifying application scenarios into 6 categories, including automated driving. [ABSTRACT FROM AUTHOR]