Search

In light of the rapid advancement in communication technology facilitated by the Internet of Things (IoT), the demand for effective data analysis and utilization has surged. This is particularly crucial as it involves the collection of data from various objects and devices in diverse ways. A robust methodology designed to improve data fusion while simultaneously upholding data confidentiality and optimizing data weight. This research work introduces a privacy-preserving lightweight cryptographic model (PP-LWC) tailored for IoT environments. It employs a novel data fusion process, integrating weight optimization and iterative data fusion, to enhance data integrity and confidentiality. The model utilizes differential privacy techniques, adding controlled noise to queries, ensuring data privacy without compromising on computational efficiency. By incorporating unique encryption and signature verification mechanisms within IoT clusters, it effectively safeguards against both internal and external threats, maintaining robust security in resource-constrained settings. This approach strikes a balance between preserving privacy and ensuring lightweight cryptographic operations, crucial for the vast and diverse landscape of IoT devices. PPLWC is evaluated considering the various parameters such as computation overhead for single signature generation, and computation overhead for single signature verification. Cost comparison for signature verification mechanism, Communication cost for sending a broadcast message. Comparison of communication cost for sending and broadcast messages. Comparative analysis with the existing model proves the model's efficiency by outperforming the existing technique. [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]

Road accidents are an inevitable aspect of daily life, and predicting crashes is crucial for minimizing disruptions and advancing intelligent transportation technologies. This study aims to design an ensemble fusion decision system using various base classifiers and a meta-classifier to improve crash prediction efficiency within the driver-vehicle-environment system. We adopted a data-driven strategy to analyze four categories of features—driver demographics, vehicle telemetry, driver inputs, and environmental conditions—collected from a driving simulator. Optimized modeling strategies using AdaBoost, XGBoost, GBM, LightGBM, and CatBoost were implemented. Moreover, statistical logit models were also used to assess the likelihood of crashes and the correlations among key variables. Furthermore, three resampling strategies, SMOTE-TL, SMOTE-ENN, and ADASYN, were employed to address class imbalance. The best performance was achieved with GBM, XGBoost, and AdaBoost as base classifiers, SMOTE-TL for balancing, and CatBoost as the meta-classifier, with 89.78% precision, 95.69% recall, and 92.64% F1-score. [ABSTRACT FROM AUTHOR]

The fusion of 3D textured mesh scene data can effectively and seamlessly integrate multiple spatially related 3D geographical scene models into larger and more comprehensive datasets. Existing methods usually have different degrees of texture distortion and unreduced texture problems in the splicing area, and these methods do not consider the current situation of Level of Detail(LoD) data organisation in the 3D textured mesh model. We propose a 3D textured mesh scene data fusion method considering multiple scales and resolutions. First, seamless extraction of splicing areas was achieved based on spatial relationship constraints and orthogonal inverse projection principles. Second, the sparse scene structure concept was employed to generate sparse summary scene images. Finally, a dual simplification operator for both mesh and texture was proposed to construct multi-resolution 3D textured mesh models, simultaneously reconstructing triangular facets and textures within the splicing regions. We used multiple 3D textured mesh data constructed from aerial obliques to conduct data fusion experimental verification. The results indicate that our method exhibits minimal texture distortion during grid reconstruction in splicing areas and model simplification, effectively reducing the amount of simplified texture data. Additionally, our method adeptly addresses multilevel detailed 3D textured mesh models, demonstrating good feasibility and advancement. [ABSTRACT FROM AUTHOR]

Multimodal tactile sensors, as key information input channel in human‐machine interactions, have faced the significant challenges including high power‐consumption, multimodal data fusion, and wireless transmission. In this work, a battery‐free multimodal wireless tactile sensor (TC‐MWTS) based on tribo‐capacitive coupled effect for normal and shear force fusion sensing is proposed, which is enabled by a 3D structure combining a triboelectric sensor and a capacitive sensor coupled with an inductive coil. A triboelectric sensor equipped with contact‐discharge structures exhibits 25‐fold wireless signal enhancement compared to conventional triboelectric sensors. Based on the characteristics of dual time‐frequency domain information existing in the wireless signals, both normal and shear forces can simultaneously be converted into voltage amplitude V and eigenfrequency f, respectively, without crosstalk and complex decoupling signals. The TC‐MWTS exhibits a maximum sensitivity of 2.47 V kPa−1 for normal force from 2 to 30 kPa and a sensitivity of 0.28 MHz N−1 for shear force between 0.3 and 1.0 N. Finally, the excellent sensing capability of TC‐MWTS to sense complex multidimensional forces in human‐machine interaction is demonstrated. This work innovatively proposes a new mechanism and methodology for effectively fusing and processing multimodal tactile information, which may drive the tremendous development of low‐power multimodal tactile sensing system. [ABSTRACT FROM AUTHOR]

The increasing frequency and sophistication of cyber-attacks pose significant threats to organizational entities and critical national infrastructure, leading to substantial financial and operational consequences. Detecting such attacks early and accurately remains a complex endeavour, compounded by challenges in intrusion detection system (IDS) design, the exploitation of zero-day attacks, and issues of reliability and resiliency in physical systems. This research addresses these challenges through a two-fold approach: firstly, implementing input data fusion from diverse and heterogeneous sources, and secondly, fusing classifiers from multiple deep learning (DL)-based algorithms. The success of machine learning (ML) and DL models for IDS relies on meticulous data collection and classifier selection. The paper underscores the limitations of relying on single datasets and ML/DL algorithms, emphasizing potential biases and training restrictions. Rigorous experiments were conducted to identify optimal DL architectures, ensuring the creation of models that exhibit robust generalization on new traffic instances, leading to trusted and unbiased results. The study demonstrates the efficacy of the proposed models through comprehensive evaluations and metrics. Results indicate that the fusion of data and classifiers significantly improves model generalization. The paper also outlines key challenges and future trends in data fusion, emphasizing its role in enhancing IDS performance for securing critical infrastructure. [ABSTRACT FROM AUTHOR]

The field of teacher education is subject to intense scrutiny and policy reform and within this context, the voices of those working within the field are often marginalised. Drawing on our larger study of teacher educators, we addressed the key research question: "How do those who work in the field of teacher education articulate and represent the nature of their work?." Using a fusion of arts-based and data science research methods and the theory of practice architectures, we examined the ways that teacher educators' work is mediated within cultural-discursive, material-economic, and social-political domains. We argue that while ambiguous dimensions exist in teacher educators' practices, they remain hopeful about their work and find spaces to create alternative sayings, doings and relatings as they prepare teachers for the profession. We contend that using both text-based and visual images facilitates the generation of enhanced meanings to highlight the complexity of teacher educators' work to those within and outside the profession. [ABSTRACT FROM AUTHOR]

Under the background of globalization, cultural and creative tourism has gradually become a new trend of tourism, providing tourists with rich and diverse travel experience. This paper discusses the development status, characteristics and integration strategies of cultural and creative tourism under the new normal. Through the analysis of the existing literature, it is found that cultural creative tourism not only brings economic benefits to the region, but also promotes the protection and inheritance of local culture. At the same time, technological advances and data convergence provide new opportunities for the promotion and management of cultural and creative tourism. But it also brings challenges, such as how to ensure sustainable development and how to meet the growing demand of tourists. Finally, based on the method of multiple linear regression analysis, the paper analyzes the factors that affect the development of cultural creative tourism. [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]

The stable hydrogen isotope in precipitation is an effective environmental tracer for climatic and hydrologic studies. However, accurate and high-precision precipitation hydrogen isoscapes are currently unavailable in China. In this study, a data fusion method based on Convolutional Neural Networks (CNN) is used to fuse the hydrogen isotopic composition (δ2Hp) of observations and isotope-equipped general circulation model (iGCM) simulations. A precipitation hydrogen isoscape with a temporal resolution of monthly and a spatial resolution of 50–60 km is established for East China for the 1969–2017 period. Prior to building the isoscape, the performance of three data fusion methods (DFMs) and two bias correction methods (BCMs) is compared. The results indicate that the CNN fusion method performs the best with a correlation coefficient larger than 0.90 and root mean square error smaller than 10.5‰when using observation as a benchmark. The fusion methods based on back propagation and long short-term memory neural network perform similarly, while slightly outperforming the bias correction methods. Thus, the CNN method is used to generate the hydrogen isoscape, and the temporal and spatial distribution characteristics of the hydrogen isotope in precipitation are analyzed based on this dataset. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ2Hp is consistent with the temperature effect in northern China, and consistent with the precipitation amount effect in southern China. The trend of the δ2Hp time series is consistent with that of observed precipitation and temperature. Overall, the generated isoscape effectively reproduces the observations, and has the characteristics of time continuity and relative spatial regularity, which can provide valuable data support for tracking atmospheric and hydrological processes. [ABSTRACT FROM AUTHOR]

The use of Lamb waves within a guided wave (GW)–based scheme holds promise toward monitoring and nondestructive evaluation (NDE) of plate structures. Their short wavelength enables interaction with small defects and they can travel long distances, thus offering extensive spatial coverage. In boosting the performance of these schemes for more advanced damage identification tasks, such as precise damage localization and quantification, the fusion of measurement data with models is advantageous. Such a hybrid scheme, which relies on the inclusion of engineering models, is hampered by the short wavelengths of GW-based schemes. Short wavelengths require a fine discretization of numerical models in space and in time, which results in high computational costs. In alleviating this issue, we propose a reduced-order model (ROM) relying on exploitation of the frequency response function (FRF) principle, which is parameterized with respect to the positioning of local defects. Through appropriate coordinate transformations, the surrogate, constructed based on the matching pursuit (MP) algorithm, can exploit the mechanical properties of the wave so that only a small amount of training simulations are needed. The efficacy of the proposed surrogate is demonstrated in a synthetic inverse setting, using a particle swarm optimization (PSO) strategy. [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]

Due to the limitations inherent in satellite sensor capabilities, it remains a challenge to balance the temporal and spatial resolutions of current remote sensing observations. Spatiotemporal fusion has emerged as a viable approach to address this issue. Many spatiotemporal fusion models have been proposed to fuse surface reflectance initially; however, their adaption for land surface temperature (LST), particularly with the 'fusion-then-retrieval (FTR)' or 'retrieval-then-fusion (RTF)' strategy, has not yet been comprehensively explored. This paper describes a comparative study of the two strategies within the context of LST fusion using three classic fusion methods including the spatial and temporal adaptive reflectance fusion model (STARFM), the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) and the flexible spatiotemporal data fusion model (FSDAF). The findings illuminate nuanced applicability across different models: (1) the FTR strategy is more suitable for STARFM; (2) the strategic applicability for ESTARFM and FSDAF is strongly related to the reference images; (3) the STARFM and FSDAF models are easily affected by the time interval between the predicted date and the reference date. This work is expected to provide practical guidance for synthesizing high spatiotemporal LST data with fusion models. [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]

Dempster-Shafer (D-S) evidence theory has extensive applications in the field of data fusion. It uses the mass function to replace the probability distribution in Bayesian Probability theory, which has the advantages of weak constraints and representing uncertainty. However, many existing uncertainty measures can not be well applied to the mass function, leading to many defects in some scenarios. For example, many methods can not fully reflect the relationship between focal elements. Therefore, how to improve the uncertainty measurement, and make full use of the advantages of the mass function, so as to further accurately express the system state, is still a hot topic worth studying. To solve this problem, we propose a Belief Interval Euclidean Distance (BIED) entropy of the mass function. This method combines nonspecificity and discord measurement of the mass function and is suitable for various situations. In this paper, we introduce a large number of numerical examples to demonstrate the practicality of the BIED entropy. Compared with existing advanced methods, the BIED entropy can better identify the quantity relationship and similarity relationship between focal elements, and exhibit a linear trend with the changing cardinality of focal elements. Finally, we implement a BIED entropy-based multi-sensor data fusion on various kinds of datasets. The experimental results indicate that BIED entropy has relatively high robustness, with the target recognition accuracy close to 79.33% and the F1-Score close to 77.29%. [ABSTRACT FROM AUTHOR]

To investigate drivers' gaze behavior and the characteristics of their gaze positions while driving, a natural driving behavior test method was employed alongside a non-contact eye-tracking device to conduct an in-vehicle experiment for collecting gaze data. Initially, we utilized the traditional approach to delineate the area of interest, analyzing variations in pupil diameter, gaze positions, and the duration spent in each area throughout the driving task, thereby compiling statistics on drivers' gaze patterns. Subsequently, harnessing the You Only Look Once version 5 architecture, we can precisely identify the position of vehicles and obstacles from the captured images. Enhancements to the network model—including streamlining and integrating an attention mechanism—have significantly refined target detection accuracy. In the final analysis, by correlating drivers' gaze data with the positional information of upcoming obstacles, we can accurately assess where drivers are looking. This fusion of data allows for a more nuanced observation of gaze dispersion and position within a one-second timeframe, providing valuable insights into drivers' attention distribution and driving behaviors. [ABSTRACT FROM AUTHOR]

For many years, spectral remote sensing has been essential for research on the Earth's surface. The data from a single satellite sensor is sometimes insufficient to fulfil the expanding needs of remote sensing applications. Spatial-temporal fusion techniques have become an effective way for merging spectral data from many sources and times, enabling improved data analysis and interpretation. The goal of this review paper is to offer a thorough examination of the historical growth of spatio-temporal fusion techniques for spectral remote sensing. The classification of all currently used fusion approaches, such as Unmixing, Weight-based, Bayesian-based, machine learning-based, and hybrid methods, is covered in detail. Additionally, it evaluates pixel-level, decision-level, and feature-level-based data fusion techniques and compares and contrasts their advantages and disadvantages. The report also discusses spatiotemporal fusion's difficulties and recommends future advances. For those working in remote sensing research and practice, it offers an invaluable resource. In conclusion, this review paper provides a comprehensive overview of spatio-temporal fusion systems for spectral remote sensing, including an analysis of their comparative benefits and drawbacks and a description of their historical development. It aims to stimulate further research and development of spatio-temporal fusion methods for spectral remote sensing. In summary, this review paper presents a comprehensive overview of spatio-temporal fusion methods for spectral remote sensing, including their historical development, categorization of existing techniques and applications, and a comparative analysis of their strengths and limitations. It also discusses the current challenges and future research directions, providing a valuable resource for the remote sensing community. [ABSTRACT FROM AUTHOR]

Several landslide susceptibility (LS) maps at various scales of analysis have been performed with specific zoning purposes and techniques. Supervised machine learning algorithms (ML) have become one of the most diffused techniques for landslide prediction, whose reliability is firmly based on the quality of input data. Site-specific landslide inventories are often more accurate and complete than national or worldwide databases. For these reasons, detailed landslide inventory and predisposing variables must be collected to derive reliable LS products. However, high-quality data are often rare, and risk managers must consider lower-resolution available products with no more than informative purposes. In this work, we compared different ML models to select the most accurate for large-scale LS assessment within the Municipality of Rome. The ExtraTreesClassifier outperformed the others reaching an average F1-score of 0.896. Thereafter, we addressed the reliability of open-source LS maps at different scales of analysis (global to regional) by means of statistical and spatial analysis. The obtained results shed light on the difference in hazard zoning depending on the scale and mapping unit. An approach for low-resolution LS data fusion was attempted, assessing the importance of the adopted criteria, which increased the ability to detect occurred landslides while maintaining precision. [ABSTRACT FROM AUTHOR]

Policymakers often require information on programs' long‐term impacts that is not available when decisions are made. For example, while rigorous evidence from the Oregon Health Insurance Experiment (OHIE) shows that having health insurance influences short‐term health and financial measures, the impact on long‐term outcomes, such as mortality, will not be known for many years following the program's implementation. We demonstrate how data fusion methods may be used address the problem of missing final outcomes and predict long‐run impacts of interventions before the requisite data are available. We implement this method by concatenating data on an intervention (such as the OHIE) with auxiliary long‐term data and then imputing missing long‐term outcomes using short‐term surrogate outcomes while approximating uncertainty with replication methods. We use simulations to examine the performance of the methodology and apply the method in a case study. Specifically, we fuse data on the OHIE with data from the National Longitudinal Mortality Study and estimate that being eligible to apply for subsidized health insurance will lead to a statistically significant improvement in long‐term mortality. [ABSTRACT FROM AUTHOR]

Satellite imagery provides a global perspective for studying river hydrology and water quality, but clouds remain a fundamental limitation of optical sensors. Explicit studies of this problem were limited to specific locations or regions. In this study, we characterize the global severity of this limitation by analyzing 22 years of daily satellite cloud cover data and modeled river discharge for a global sample 21,642 river reaches of diverse sizes and climates. Our results show that the bias in observed river discharge is highly organized in space, particularly affecting Tropical and Arctic rivers. Given the fundamental nature of this cloud limitation, optical satellites will always provide a biased representation of river conditions. We discuss several strategies to mitigate bias, including modeling, data fusion, and temporal averaging, yet these methods introduce their own challenges and uncertainties. Plain Language Summary: This study examines how optical satellite imagery, which is vital for understanding rivers worldwide, is hindered by clouds specifically when observing rivers. We analyzed 22 years of daily data covering 21,642 sections of rivers of various sizes and climates. Our findings reveal that cloud cover significantly biases the distribution of river discharges we observe, especially for Tropical and Arctic rivers. This means that satellite images do not represent river conditions accurately. Our research provides the first comprehensive analysis of its extent and impact. Ultimately, while satellite technology continues to improve, clouds remain a challenge in obtaining precise river data, highlighting the need for innovative solutions. Key Points: We evaluated the impact of cloud cover on satellite optical remote sensing across a global sample of river reachesDirect optical satellite observations can present a highly biased, and geographically variable, view of river conditionsSeasonal relationships of clouds and discharge predict the ability of optical satellites to observe the distribution of river discharge [ABSTRACT FROM AUTHOR]

AbstractPanax notoginseng (Burk.) F.H. Chen (P. notoginseng), a precious medicinal herb, provides both considerable values. There is confusion in the market regarding the geographical origins of P. notoginseng. It is of paramount importance to authenticate geographical origins of P. notoginseng, which will facilitate the rational utilization of resources and sustainable development. Principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) were employed to investigate the influence of the tissue and data fusion strategy for the authentication of P. notoginseng origins. The PLS-DA model employing the main root spectra demonstrated great potential for authenticating P. notoginseng origin. The PLS-DA training and test sets based on feature-level fusion (VIP) spectral data were 100% accurate, indicating excellent potential in authenticating P. notoginseng. The data fusion strategy improved the authentication. The article presents a reliable and efficacious novel methodology for authenticating P. notoginseng origins and a scientific foundation for its quality control. [ABSTRACT FROM AUTHOR]

Summary: Many optimal sensor placement (OSP) techniques have been developed basing on known external loads. However, it is often difficult to obtain excitation measurements. Therefore, the development of OSP under unknown inputs (OSP‐UI) is desirable. In this paper, based on modal Kalman filter (MKF), an OSP‐UI approach (MKF‐OSP‐UI) is proposed for optimally determining the number and locations of multitype sensors with the aim of minimizing the reconstructed responses errors. An MKF‐based approach previously developed by the authors is first employed for estimating multiscale structural responses and unknown loads. Then, an error covariance matrix is defined as a measure of the differences between the reconstructed responses and the corresponding actual ones. By using the covariance matrix of measurement noise for normalization, the ill‐conditioning problem caused by data fusion of multiscale responses is avoided. The sensors that have few contributions to the reconstructed responses are removed from the candidate set during iteration procedure. The sensor placement is finally determined when the estimation errors are below the preset level. Numerical results show that the sensor configuration determined by the proposed approach has a better performance on the joint estimation of multiscale responses and unknown inputs, as compared with that determined by experience. [ABSTRACT FROM AUTHOR]

AbstractGeophysical data are often integrated into geological data for 3D modeling of underground spaces. However, the existing single-view approach means it is difficult to adequately fuse the valid information between the two types of data, and the complexity of lithological decoding and classification is high. To address this issue, a multi-view ensemble machine learning (ML) framework is proposed. Initially, the original dataset of lithology prediction is constructed by aligning geological and geophysical data with different spatial scales. Next, the dataset is divided into three datasets of structural strength, density, and moisture content according to the lithology properties of the geophysical data. The proposed framework is then used to capture the lithologic characteristics under different views to achieve the prediction of lithologic labels. In this process, a self-attentive mechanism is used to adaptively fuse the valid information under each view. To validate the proposed framework, it is applied to a project in Jiaxing, Zhejiang Province, China. Compared with existing ML methods, the proposed multi-view ensemble ML framework improves modeling accuracy and constructs models with low uncertainty. The framework can be extended to other multi-source data fusion tasks across geoscience domains. [ABSTRACT FROM AUTHOR]

To meet the growing demand for integrated monitoring of complex power grid equipment, it is necessary to improve the situational awareness model of power transformers. The model is expected to assist monitoring personnel in timely identifying transformers with deteriorating trends among massive and discrete monitoring information, and to make responses in advance. However, the current transformer state awareness technology generally has the problem of single data source and poor timeliness, and still requires monitoring personnel to make artificial analysis and prediction in combination with telemetry information, which cannot fully meet the requirements of power grid equipment monitoring. This paper is based on multi-source data fusion technology, through associating and mining transformer alarm information, equipment maintenance records and power transmission and transformation online monitoring data, to extract the dimension features of transformer operation situation assessment. By constructing a multi-layer perceptron model, a transformer state transition model based on the principle of Markov chain is established, which can predict possible defects 2 h in advance and achieve good results, and determine the transformer state early warning index, providing sufficient time for monitoring personnel to deploy transformer operation and maintenance work in advance. Finally, the effectiveness of the method proposed in this paper is proved by the case of transformer crisis state in a city substation, and the method proposed in this paper has important significance for transformer state early warning. [ABSTRACT FROM AUTHOR]

In order to reduce the influence of environmental noise and different operating conditions on the accuracy of motor fault diagnosis, this paper proposes a capsule network method combining multi-channel signals and the efficient channel attention (ECA) mechanism, sampling the data from multiple sensors and visualizing the one-dimensional time-frequency domain as a two-dimensional symmetric dot pattern (SDP) image, then fusing the multi-channel image data and extracting the image using a capsule network combining the ECA attention mechanism features to match eight different fault types for fault classification. In order to guarantee the universality of the suggested model, data from Case Western Reserve University (CWRU) is used for validation. The suggested multi-channel signal fusion ECA attention capsule network (MSF-ECA-CapsNet) model fault identification accuracy may reach 99.21%, according to the experimental findings, which is higher than the traditional method. Meanwhile, the method of multi-sensor data fusion and the use of the ECA attention mechanism make the diagnosis accuracy much higher. [ABSTRACT FROM AUTHOR]

Corn, as one of the three major grain crops in China, plays a crucial role in ensuring national food security through its yield and quality. With the advancement of agricultural intelligence, agricultural robot technology has gained significant attention. High-precision navigation is the basis for realizing various operations of agricultural robots in corn fields and is closely related to the quality of operations. Corn leaf and stalk recognition and ranging are the prerequisites for achieving high-precision navigation and have attracted much attention. This paper proposes a corn leaf and stalk recognition and ranging algorithm based on multi-sensor fusion. First, YOLOv8 is used to identify corn leaves and stalks. Considering the large differences in leaf morphology and the large changes in field illumination that lead to discontinuous identification, an equidistant expansion polygon algorithm is proposed to post-process the leaves, thereby increasing the average recognition completeness of the leaves to 86.4%. Secondly, after eliminating redundant point clouds, the IMU data are used to calculate the confidence of the LiDAR and depth camera ranging point clouds, and point cloud fusion is performed based on this to achieve high-precision ranging of corn leaves. The average ranging error is 2.9 cm, which is lower than the measurement error of a single sensor. Finally, the stalk point cloud is processed and clustered using the FILL-DBSCAN algorithm to identify and measure the distance of the same corn stalk. The algorithm combines recognition accuracy and ranging accuracy to meet the needs of robot navigation or phenotypic measurement in corn fields, ensuring the stable and efficient operation of the robot in the corn field. [ABSTRACT FROM AUTHOR]

With the increasing number of ongoing space missions for Earth Observation (EO), there is a need to enhance data products by combining observations from various remote sensing instruments. We introduce a new Transformer-based approach for data fusion, achieving up to a 10- to-30-fold increase in the spatial resolution of our hyperspectral data. We trained the network on a synthetic set of Sentinel-2 (S2) and Sentinel-3 (S3) images, simulated from the hyperspectral mission EnMAP (30 m resolution), leading to a fused product of 21 bands at a 30 m ground resolution. The performances were calculated by fusing original S2 (12 bands, 10, 20, and 60 m resolutions) and S3 (21 bands, 300 m resolution) images. To go beyond EnMap's ground resolution, the network was also trained using a generic set of non-EO images from the CAVE dataset. However, we found that training the network on contextually relevant data is crucial. The EO-trained network significantly outperformed the non-EO-trained one. Finally, we observed that the original network, trained at 30 m ground resolution, performed well when fed images at 10 m ground resolution, likely due to the flexibility of Transformer-based networks. [ABSTRACT FROM AUTHOR]

Ocean satellite data are often impeded by intrinsic limitations in resolution and accuracy. However, conventional data reconstruction approaches encounter substantial challenges when facing the nonlinear oceanic system and high-resolution fusion of variables. This research presents a Discrete Satellite Gridding Neural Network (DSGNN), a new machine learning method that processes satellite data within a discrete grid framework. By transforming the positional information of grid elements into a standardized vector format, the DSGNN significantly elevates the accuracy and resolution of data fusion through a neural network model. This method's innovative aspect lies in its discretization and fusion technique, which not only enhances the spatial resolution of oceanic data but also, through the integration of multi-element datasets, better reflects the true physical state of the ocean. A comprehensive analysis of the reconstructed datasets indicates the DSGNN's consistency and reliability across different seasons and oceanic regions, especially in its adept handling of complex nonlinear interactions and small-scale oceanic features. The DSGNN method has demonstrated exceptional competence in reconstructing global ocean datasets, maintaining small error variance, and achieving high congruence with in situ observations, which is almost equivalent to 1/12° hybrid coordinate ocean model (HYCOM) data. This study offers a novel and potent strategy for the high-resolution reconstruction and fusion of ocean satellite datasets. [ABSTRACT FROM AUTHOR]

In recent years, deep learning techniques for pansharpening multiresolution images have gained increasing interest. Due to the lack of ground truth data, most deep learning solutions rely on synthetic reduced-resolution data for supervised training. This approach has limitations due to the statistical mismatch between real full-resolution and synthetic reduced-resolution data, which affects the models' generalization capacity. Consequently, there has been a shift towards unsupervised learning frameworks for pansharpening deep learning-based techniques. Unsupervised schemes require defining sophisticated loss functions with at least two components: one for spectral quality, ensuring consistency between the pansharpened image and the input multispectral component, and another for spatial quality, ensuring consistency between the output and the panchromatic input. Despite promising results, there has been limited investigation into the interaction and balance of these loss terms to ensure stability and accuracy. This work explores how unsupervised spatial and spectral consistency losses can be reliably combined preserving the outocome quality. By examining these interactions, we propose a general rule for balancing the two loss components to enhance the stability and performance of unsupervised pansharpening models. Experiments on three state-of-the-art algorithms using WorldView-3 images demonstrate that methods trained with the proposed framework achieve good performance in terms of visual quality and numerical indexes. [ABSTRACT FROM AUTHOR]

For high-precision navigation, obtaining and maintaining high-precision point-of-interest (POI) data on the road network is crucial. In urban areas with complex terrains, the accuracy of traditional road network POI acquisition methods often falls short. To address this issue, we introduce DualNet-PoiD, a hybrid neural network designed for the efficient recognition of road network POIs in intricate urban environments. This method leverages multimodal sensory data, incorporating both vehicle trajectories and remote sensing imagery. Through an enhanced dual-attention dilated link network (DAD-LinkNet) based on ResNet18, the system extracts static geometric features of roads from remote sensing images. Concurrently, an improved gated recirculation unit (GRU) captures dynamic traffic characteristics implied by vehicle trajectories. The integration of a fully connected layer (FC) enables the high-precision identification of various POIs, including traffic light intersections, gas stations, parking lots, and tunnels. To validate the efficacy of DualNet-PoiD, we collected 500 remote sensing images and 50,000 taxi trajectory data samples covering road POIs in the central urban area of the mountainous city of Chongqing. Through comprehensive area comparison experiments, DualNet-PoiD demonstrated a high recognition accuracy of 91.30%, performing robustly even under conditions of complex occlusion. This confirms the network's capability to significantly improve POI detection in challenging urban settings. [ABSTRACT FROM AUTHOR]

Due to the limitation of a single sensor such as only camera or only LiDAR, the Visual SLAM detects few effective features in the case of poor lighting or no texture. The LiDAR SLAM will also degrade in an unstructured environment and open spaces, which reduces the accuracy of pose estimation and the quality of mapping. In order to solve this problem, on account of the high efficiency of Visual odometry and the high accuracy of LiDAR odometry, this paper investigates the multi-sensor fusion of bidirectional visual–inertial odometry with 3D LiDAR for pose estimation. This method can couple the IMU with the bidirectional vision respectively, and the LiDAR odometry is obtained assisted by the bidirectional visual inertial. The factor graph optimization is constructed, which effectively improves the accuracy of pose estimation. The algorithm in this paper is compared with LIO-LOAM, LeGO-LOAM, VINS-Mono, and so on using challenging datasets such as KITTI and M2DGR. The results show that this method effectively improves the accuracy of pose estimation and has high application value for mobile robots. [ABSTRACT FROM AUTHOR]

Cracks are a common defect in civil infrastructures, and their occurrence is often closely related to structural loading conditions, material properties, design and construction, and other factors. Therefore, detecting and analyzing cracks in civil infrastructures can effectively determine the extent of damage, which is crucial for safe operation. In this paper, Web of Science (WOS) and Google Scholar were used as literature search tools and "crack", "civil infrastructure", and "computer vision" were selected as search terms. With the keyword "computer vision", 325 relevant documents were found in the study period from 2020 to 2024. A total of 325 documents were searched again and matched with the keywords, and 120 documents were selected for analysis and research. Based on the main research methods of the 120 documents, we classify them into three crack detection methods: fusion of traditional methods and deep learning, multimodal data fusion, and semantic image understanding. We examine the application characteristics of each method in crack detection and discuss its advantages, challenges, and future development trends. [ABSTRACT FROM AUTHOR]

Person re-identification (ReID) refers to the task of retrieving target persons from image libraries captured by various distinct cameras. Over the years, person ReID has yielded favorable recognition outcomes under typical visible light conditions, yet there remains considerable scope for enhancement in challenging conditions. The challenges and research gaps include the following: multi-modal data fusion, semi-supervised and unsupervised learning, domain adaptation, ReID in 3D space, fast ReID, decentralized learning, and end-to-end systems. The main problems to be solved, which are the occlusion problem, viewpoint problem, illumination problem, background problem, resolution problem, openness problem, etc., remain challenges. For the first time, this paper uses person ReID in special scenarios as a basis for classification to categorize and analyze the related research in recent years. Starting from the perspectives of person ReID methods and research directions, we explore the current research status in special scenarios. In addition, this work conducts a detailed experimental comparison of person ReID methods employing deep learning, encompassing both system development and comparative methodologies. In addition, we offer a prospective analysis of forthcoming research approaches in person ReID and address unresolved concerns within the field. [ABSTRACT FROM AUTHOR]

This study aims to improve the accuracy of the detection of adulterated minced beef with chicken, duck, and pork. A series of tests were carried out to quantitatively detect the adulterants in beef using hyperspectral reflectance (R) and transmittance (T) spectral data fusion. Firstly, three types of adulterants (chicken, duck, and pork) were added to the beef with a mass percentage of 2% to 50% concentration interval of 2%, respectively. Then the reflectance spectral data was collected to combine with SVM (support vector machine, SVM), random forest (RF), and long short-term memory (LSTM). A classification model was established to classify the samples into chicken, duck, and pork adulterated and pure beef samples (4 groups). Then, a partial least squares model (PLSR) was built from the single reflectance and transmittance spectral data to quantify the concentrations of adulterants. The performance of the model was optimized by competitive adaptive reweighted sampling (CARS), irrelevant variable elimination (UVE), and primary and intermediate data fusion. The predictions were also conducted on adulterants such as chicken, duck, and pork, according to the intermediate-level data fusion. The results showed the greatest effectiveness values of improvement were 3.9%, 9.3%, and 4.5% over those in the optimal model with single spectral data, respectively. The models with the best prediction results for chicken and duck samples withadulterants were the de trending (DT) pre-processed UVE-PLSR, with corresponding coefficients of determination (r-squaredprediction, ) and root mean square error (RMSEP) of 0.984 5 and 1.8651、 0.986 0 and 1.7711, respectively, and the bestprediction model for adulterated pork samples was RAW-CARS-PLSR, with corresponding and RMSEP of 0.975 1 and 2.366 5. Hyperspectral imaging combined with data fusion can effectively detect the adulterants in beef with high accuracy and speed. The intermediate-level data fusion can maximize the performance of the improved model. [ABSTRACT FROM AUTHOR]

In the context of global climate change and rising anthropogenic loads, outbreaks of both endemic and invasive pests, pathogens, and diseases pose an increasing threat to the health, resilience, and productivity of natural forests and forest plantations worldwide. The effective management of such threats depends on the opportunity for early-stage action helping to limit the damage expand, which is difficult to implement for large territories. Recognition technologies based on the analysis of Earth observation data are the basis for effective tools for monitoring the spread of degradation processes, supporting pest population control, forest management, and conservation strategies in general. In this study, we present a machine learning-based approach for recognizing damaged forests using open source remote sensing images of Sentinel-2 supported with Google Earth data on the example of bark beetle, Polygraphus proximus Blandford, polygraph. For the algorithm development, we first investigated and annotated images in channels corresponding to natural color perception--red, green, and blue--available at Google Earth. Deep neural networks were applied in two problem formulations: semantic segmentation and detection. As a result of conducted experiments, we developed a model that is effective for a quantitative assessment of the changes in target objects with high accuracy, achieving 84.56% of F1-score, determining the number of damaged trees and estimating the areas occupied by withered stands. The obtained damage masks were further integrated with medium-resolution Sentinel-2 images and achieved 81.26% of accuracy, which opened the opportunity for operational monitoring systems to recognize damaged forests in the region, making the solution both rapid and cost-effective. Additionally, a unique annotated dataset has been collected to recognize forest areas damaged by the polygraph in the region of study. [ABSTRACT FROM AUTHOR]

Background: In recent years, computational aesthetics and neuroaesthetics have provided novel insights into understanding beauty. Building upon the findings of traditional aesthetics, this study aims to combine these two research methods to explore an interdisciplinary approach to studying aesthetics. Method: Abstract artworks were used as experimental materials. Based on traditional aesthetics and in combination, features of composition, tone, and texture were selected. Computational aesthetic methods were then employed to correspond these features to physical quantities: blank space, gray histogram, Gray Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Gabor filters. An electroencephalogram (EEG) experiment was carried out, in which participants conducted aesthetic evaluations of the experimental materials in different contexts (genuine, fake), and their EEG data were recorded to analyze the impact of various feature classes in the aesthetic evaluation process. Finally, a Support Vector Machines (SVMs) was utilized to model the feature data, Event-Related Potentials (ERPs), context data, and subjective aesthetic evaluation data. Result: Behavioral data revealed higher aesthetic ratings in the genuine context. ERP data indicated that genuine contexts elicited more negative deflections in the prefrontal lobes between 200 and 1000 ms. Class II compositions demonstrated more positive deflections in the parietal lobes at 50–120 ms, while Class I tones evoked more positive amplitudes in the occipital lobes at 200–300 ms. Gabor features showed significant variations in the parieto-occipital area at an early stage. Class II LBP elicited a prefrontal negative wave with a larger amplitude. The results of the SVM models indicated that the model incorporating aesthetic subject and context data (ACC = 0.76866) outperforms the model using only parameters of the aesthetic object (ACC = 0.68657). Conclusion: A positive context tends to provide participants with a more positive aesthetic experience, but abstract artworks may not respond to this positivity. During aesthetic evaluation, the ERP data activated by different features show a trend from global to local. The SVM model based on multimodal data fusion effectively predicts aesthetics, further demonstrating the feasibility of the combined research approach of computational aesthetics and neuroaesthetics. [ABSTRACT FROM AUTHOR]

Machine learning (ML) models for predicting gas permeability through polymers have traditionally relied on experimental data. While these models exhibit robustness within familiar chemical domains, reliability wanes when applied to new spaces. To address this challenge, we present a multi-tiered multi-task learning framework empowered with advanced machine-crafted polymer fingerprinting algorithms and data fusion techniques. This framework combines scarce "high-fidelity" experimental data with abundant diverse "low-fidelity" simulation or synthetic data, resulting in predictive models that display a high level of generalizability across novel chemical spaces. Additionally, this multi-task scheme capitalizes on known physics and interrelated properties, such as gas diffusivity and solubility, both of which are closely tied to permeability. By amalgamating high throughput generated simulation data with available experimental data for gas permeability, diffusivity, and solubility for various gases, we construct multi-task deep learning models. These models can simultaneously predict all three properties for all gases under consideration, with markedly enhanced predictive accuracy, particularly compared to traditional models reliant solely on experimental data for a singular property. This strategy underscores the potential of coupling high-throughput classical simulations with data fusion methodologies to yield state-of-the-art property predictors, especially when experimental data for targeted properties is scarce. [ABSTRACT FROM AUTHOR]

This work introduces a novel fault-tolerance technique for data fusion in Unmanned Aerial Vehicles (UAVs), designed to address sensor faults through a deep learning-based framework. Unlike traditional methods that rely on hardware redundancy, our approach leverages Long Short-Term Memory (LSTM) networks for state estimation and a moving average (MA) algorithm for fault detection. The novelty of our technique lies in its dual strategy: utilizing LSTMs to analyze residuals and detect errors, while the MA algorithm identifies faulty sensors by monitoring variations in sensor data. This method allows for effective error correction and system recovery by replacing faulty measurements with reliable ones, eliminating the need for a fault-free prediction model. The approach has been validated through offline testing on real sensor data from a hexarotor UAV with simulated faults, demonstrating its efficacy in maintaining robust UAV operations without resorting to redundant hardware solutions. [ABSTRACT FROM AUTHOR]

Cataracts are common eye disorders characterized by the clouding of the lens, preventing light from passing through and impairing vision. Various factors, including changes in the lens's hydration or alterations in its proteins, may contribute to their development. Regular eye examinations conducted by an ophthalmologist or optometrist are imperative for detecting cataracts and other ocular conditions early on. Manual checks by caregivers pose several problems, including subjectivity, human error, and a lack of expertise. Biomedical fusion involves combining or linking various characteristics specific to certain diseases from different medical imaging resources. The primary objectives of this approach in disease classification are to reduce the error rate and increase the number of retrieved features. The aim of this study is to evaluate the outcomes associated with fusing visual features related to left and right eye cataract characteristics. Additionally, we investigate the impact of limited variability in deep learning models, specifically in the classification of cataract fundus versus normal fundus images. To address this issue, this study introduces CataractNetDetect, an innovative multi-label deep learning classification system that fuses feature representations from pairs of fundus images (e.g., left and right eyes) for the automatic diagnosis of various ocular disorders. Our focus is on achieving improved performance by stacking discriminative deep feature representations to combine two fundus images into a unified feature representation. Several deep learning architectures are utilized as feature descriptors, including ResNet-50, DenseNet-121, and Inception-V3, enhancing the resilience and quality of representations. Fine-tuning of these DL architectures is conducted using the ImageNet dataset, followed by an integrated stacking approach combining ResNet-50, DenseNet-121, and Inception-V3 models. The model is trained on the publicly available ODIR-5k dataset, which includes 5000 left/right eye images depicting eight different ocular conditions, ranging from healthy states to uncommon ailments such as cataracts, glaucoma, age-related macular degeneration (AMD), diabetes, hypertension, and myopia abnormalities. Moreover, extensive preprocessing of the images is performed, including data augmentation, noise reduction, contrast enhancement, scaling, and circular border cropping. The CataractNetDetect system demonstrates F1-scores, AUC, and maximum validation scores of 98.0%, 97.9%, and 100%, respectively. This ensemble-based model distinguishes itself by surpassing the performance of conventional established methodologies, including ResNet-50, DenseNet-121, and Inception-V3, thereby underscoring its efficacy in diagnostic applications. [ABSTRACT FROM AUTHOR]

The utilization of digital statistical processes in images and videos can effectively tackle numerous challenges encountered in optical sensors. This research endeavors to overcome the limitations inherent in traditional focus models, particularly their inadequate accuracy. It aims to bolster the precision of real-time perception and dynamic control by employing enhanced data fusion methodologies. The ultimate objective is to facilitate information services that enable seamless interaction and profound integration between computational and physical processes within an open environment. To achieve this, an enhanced sum-modulus difference (SMD) evaluation function has been proposed. This innovation is founded on the concept of threshold value evaluation, aimed at rectifying the accuracy shortcomings of traditional focusing models. Through the computation of each gray value after threshold segmentation, the method identifies the most suitable threshold for image segmentation. This identified threshold is then applied to the focus search strategy employing the radial basis function (RBF) algorithm. Furthermore, an intelligent focusing system has been developed on the Zynq development platform, encompassing both hardware design and software program development. The test results affirm that the focusing model based on the improved SMD evaluation function rapidly identifies the peak point of the gray variance curve, ascertains the optimal focal plane position, and notably enhances the sensitivity of the focusing model. [ABSTRACT FROM AUTHOR]

In recent years, there has been growing interest in digital twin technology in both industry and academia. This versatile technology has found applications across various industries. Wind energy systems are particularly suitable for digital twin platforms due to the integration of multiple subsystems. This study aims to explore the current state of predictive digital twin platforms for wind energy systems by surveying literature from the past five years, identifying challenges and limitations, and addressing future research opportunities. This review is structured around four main research questions. It examines commonly employed methodologies, including physics-based modeling, data-driven approaches, and hybrid modeling. Additionally, it explores the integration of data from various sources such as IoT sensors, historical databases, and external application programming interfaces. The review also delves into key features and technologies behind real-time systems, including communication networks, edge computing, and cloud computing. Finally, it addresses current challenges in predictive digital twin platforms. Addressing these research questions enables the development of hybrid modeling strategies with data fusion algorithms, which allow for interpretable predictive digital twin platforms in real time. Filter methods with dimensionality reduction algorithms minimize the computational resource demand in real-time operating algorithms. Moreover, advancements in high-bandwidth communication networks facilitate efficient data transmission between physical assets and digital twins with reduced latency. [ABSTRACT FROM AUTHOR]

With the rapid advancement of intelligent transportation systems, cooperative vehicle infrastructure systems emerge as a vital frontier for development. Real-time mutual fusion of perception data is a crucial technology for ensuring the security of ITS systems. However, the computation-intensive nature of perception data fusion poses a significant challenge in terms of computing resource allocation and scheduling. In this paper, we propose a vehicle-road cooperative network that facilitates computation offloading during the real-time perception data fusion process. We present an architecture that enables users to generate tasks and offload computations, and we formulate an integer nonlinear programming problem within this framework. Considering the dynamic, random, and time-varying characteristics of cooperative vehicle infrastructure systems, we introduced the Deep Deterministic Policy Gradient (DDPG) algorithm for perception fusion computing offloading (DDPG-PFCO). Through extensive experiments conducted on a real map, experimental results show that the proposed algorithm outperforms other comparison algorithms, exhibiting significant improvements in performance. [ABSTRACT FROM AUTHOR]

Robotic platforms including Unmanned Aerial Vehicles (UAVs) require an accurate and reliable source of position information, especially in indoor environments where GNSS cannot be used. This is typically accomplished by using multiple independent position sensors. This paper presents a UAV position estimation mechanism based on a particle filter, that combines information from visual odometry cameras and visual detection of fiducial markers. The article proposes very compact, lightweight and robust method for indoor localization, that can run with high frequency on the UAV's onboard computer. The filter is implemented such that it can seamlessly handle sensor failures and disconnections. Moreover, the filter can be extended to include inputs from additional sensors. The implemented approach is validated on data from real-life UAV test flights, where average position error under 0.4 m was achieved. [ABSTRACT FROM AUTHOR]

Assessing sleep posture, a critical component in sleep tests, is crucial for understanding an individual's sleep quality and identifying potential sleep disorders. However, monitoring sleep posture has traditionally posed significant challenges due to factors such as low light conditions and obstructions like blankets. The use of radar technolsogy could be a potential solution. The objective of this study is to identify the optimal quantity and placement of radar sensors to achieve accurate sleep posture estimation. We invited 70 participants to assume nine different sleep postures under blankets of varying thicknesses. This was conducted in a setting equipped with a baseline of eight radars—three positioned at the headboard and five along the side. We proposed a novel technique for generating radar maps, Spatial Radio Echo Map (SREM), designed specifically for data fusion across multiple radars. Sleep posture estimation was conducted using a Multiview Convolutional Neural Network (MVCNN), which serves as the overarching framework for the comparative evaluation of various deep feature extractors, including ResNet-50, EfficientNet-50, DenseNet-121, PHResNet-50, Attention-50, and Swin Transformer. Among these, DenseNet-121 achieved the highest accuracy, scoring 0.534 and 0.804 for nine-class coarse- and four-class fine-grained classification, respectively. This led to further analysis on the optimal ensemble of radars. For the radars positioned at the head, a single left-located radar proved both essential and sufficient, achieving an accuracy of 0.809. When only one central head radar was used, omitting the central side radar and retaining only the three upper-body radars resulted in accuracies of 0.779 and 0.753, respectively. This study established the foundation for determining the optimal sensor configuration in this application, while also exploring the trade-offs between accuracy and the use of fewer sensors. [ABSTRACT FROM AUTHOR]

The labor shortage and rising costs in the greenhouse industry have driven the development of automation, with the core of autonomous operations being positioning and navigation technology. However, precise positioning in complex greenhouse environments and narrow aisles poses challenges to localization technologies. This study proposes a multi-sensor fusion positioning and navigation robot based on ultra-wideband (UWB), an inertial measurement unit (IMU), odometry (ODOM), and a laser rangefinder (RF). The system introduces a confidence optimization algorithm based on weakening non-line-of-sight (NLOS) for UWB positioning, obtaining calibrated UWB positioning results, which are then used as a baseline to correct the positioning errors generated by the IMU and ODOM. The extended Kalman filter (EKF) algorithm is employed to fuse multi-sensor data. To validate the feasibility of the system, experiments were conducted in a Chinese solar greenhouse. The results show that the proposed NLOS confidence optimization algorithm significantly improves UWB positioning accuracy by 60.05%. At a speed of 0.1 m/s, the root mean square error (RMSE) for lateral deviation is 0.038 m and for course deviation is 4.030°. This study provides a new approach for greenhouse positioning and navigation technology, achieving precise positioning and navigation in complex commercial greenhouse environments and narrow aisles, thereby laying a foundation for the intelligent development of greenhouses. [ABSTRACT FROM AUTHOR]

The rapid development of active safety systems in the automotive industry and research in autonomous driving requires reliable, high-precision sensors that provide rich information about the surrounding environment and the behaviour of other road users. In practice, there is always some non-zero mounting misalignment, i.e., angular inaccuracy in a sensor's mounting on a vehicle. It is essential to accurately estimate and compensate for this misalignment further programmatically (in software). In the case of radars, imprecise mounting may result in incorrect/inaccurate target information, problems with the tracking algorithm, or a decrease in the power reflected from the target. Sensor misalignment should be mitigated in two ways: through the correction of an inaccurate alignment angle via the estimated value of the misalignment angle or alerting other components of the system of potential sensor degradation if the misalignment is beyond the operational range. This work analyses misalignment's influences on radar sensors and other system components. In the mathematically proven example of a vertically misaligned radar, pedestrian detectability dropped to one-third of the maximum range. In addition, mathematically derived heading estimation errors demonstrate the impact on data association in data fusion. The simulation results presented show that the angle of misalignment exponentially increases the risk of false track splitting. Additionally, the paper presents a comprehensive review of radar alignment techniques, mostly found in the patent literature, and implements a baseline algorithm, along with suggested key performance indicators (KPIs) to facilitate comparisons for other researchers. [ABSTRACT FROM AUTHOR]

With the development of precision sensing instruments and data storage devices, the fusion of multi-sensor data in gearbox fault diagnosis has attracted much attention. However, existing methods have difficulty in capturing the local temporal dependencies of multi-sensor monitoring information, and the inescapable noise severely decreases the accuracy of multi-sensor information fusion diagnosis. To address these issues, this paper proposes a fault diagnosis method based on dynamic graph convolutional neural networks and hard threshold denoising. Firstly, considering that the relationships between monitoring data from different sensors change over time, a dynamic graph structure is adopted to model the temporal dependencies of multi-sensor data, and, further, a graph convolutional neural network is constructed to achieve the interaction and feature extraction of temporal information from multi-sensor data. Secondly, to avoid the influence of noise in practical engineering, a hard threshold denoising strategy is designed, and a learnable hard threshold denoising layer is embedded into the graph neural network. Experimental fault datasets from two typical gearbox fault test benches under environmental noise are used to verify the effectiveness of the proposed method in gearbox fault diagnosis. The experimental results show that the proposed DDGCN method achieves an average diagnostic accuracy of up to 99.7% under different levels of environmental noise, demonstrating good noise resistance. [ABSTRACT FROM AUTHOR]

With the increase in the number of Global Navigation Satellite System (GNSS) satellites and their operating frequencies, richer observation data are provided for the tightly coupled Global Navigation Satellite System/Inertial Navigation System (GNSS/INS). In this paper, we propose an efficient and robust combined navigation scheme to address the key issues of system accuracy, robustness, and computational efficiency. The tightly combined system fuses multi-source data such as the pseudo-range, the pseudo-range rate, and dual-antenna observations from the GNSS and the horizontal attitude angle from the vertical gyro (VG) in order to realize robust navigation in a sparse satellite observation environment. In addition, to cope with the high computational load faced by the system when the satellite observation conditions are good, we propose a weighted quasi-optimal satellite selection algorithm that reduces the computational burden of the navigation system by screening the observable satellites while ensuring the accuracy of the observation data. Finally, we comprehensively evaluate the proposed system through simulation experiments. The results show that, compared with the loosely coupled navigation system, our system has a significant improvement in state estimation accuracy and still provides reliable attitude estimation in regions with poor satellite observation conditions. In addition, in comparison experiments with the optimal satellite selection algorithm, our proposed satellite selection algorithm demonstrates greater advantages in terms of computational efficiency and engineering practicability. [ABSTRACT FROM AUTHOR]