Search

A therapeutic product is usually not suitable for all patients but for only a subpopulation. The safe and effective use of such a therapeutic product requires the co‐approval of a companion diagnostic device which can be used to identify suitable patients. While the first‐of‐a‐kind companion diagnostic device is often developed in conjunction with its intended therapeutic product and simultaneously validated through a randomized clinical trial, there remains room for the innovation of new and improved follow‐on companion diagnostic devices designed for the same therapeutic product. However, conducting a new randomized trial or a bridging study for the follow on companion devices may be unethical, expensive or unpractical. Hence, there arises a need for an external study to evaluate the concordance between the FDA‐approved comparator companion diagnostic device (CCD) and the subsequent follow‐on companion diagnostic devices (FCD), indirectly validating the latter. In this article, we introduce a novel external study design, referred to as the targeted treatment design, as an extension of the existing concordance design. Additionally, we present corresponding statistical analysis methods. Our approach combines the CCD randomized trial data and the FCD external study data, enabling the estimation of drug efficacy within the FCD+ and FCD‐ subpopulations—the parameters crucial for the validation of the FCD. Theoretical results and simulation studies validate the proposed methods and we further illustrate the proposed methods through an application in a real example of non‐small‐cell lung cancer. [ABSTRACT FROM AUTHOR]

Laser-induced breakdown spectroscopy (LIBS) has the potential to serve as a valuable tool in the field of metal failure estimation. In this work, 12Cr1MoV steel, a material with different grain size grades, was selected as the experimental sample. Spectral and acoustic data were recorded during the laser ablation process. Initially, it was revealed that the acoustic energy did not exhibit a significant downward trend with the continuous laser shots, but the acoustic energy fluctuations became more intense. In order to enhance the capacity to assess the grain size grade of heat-resistant steel, we advanced a novel proposition to integrate acoustic data with spectral data. Two data fusion strategies were proposed for the integration of spectral and acoustic data: first, dimensionality reduction followed by combination, and second, combination followed by dimensionality reduction. Subsequently, two classification models, linear discriminant analysis (LDA) and support vector machines (SVM), were constructed utilising three data types: spectral data, acoustic spectral data, and the aforementioned combined data set. The performance of the model trained on the combined data obtained based on the first strategy is superior to models trained on a single data type (spectral data or acoustic spectral data), achieving a classification accuracy of 92.29%. The second strategy yielded unsatisfactory results due to the significant difference in dimensions between spectral data and acoustic spectral data. To address this, a modification was proposed by carrying out spectral feature screening on spectra data using RFE before data fusion and studying the impact of the number of remaining variables after RFE processing on model performance. The results showed that the model achieved the highest classification accuracy of 98.85%. The measurement illustrates the effectiveness of integrating spectral and acoustic spectral data for enhanced metal assessment. [ABSTRACT FROM AUTHOR]

Geophysical 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]

Cold rolling chatter is one of the bottlenecks to improve the production quality and efficiency of high-strength thin strip, so it is very important to predict and identify the chatter states. The accumulation of industrial data from the rolling process and the development of machine learning technology have opened up a path to solve this problem. However, due to low density and uneven distribution of actual process data, knowledge learning and states identification of cold rolling chatter phenomena are confined. Therefore, based on the combination of actual production data and simulation data, a novel identification method is proposed and applied to identify the cold rolling chatter states. Firstly, the actual vibration signals are collected and the simulation data generated from chatter model are used to supplement data in chatter states. The sample space is constructed based on the semi-supervised transfer component analysis (SSTCA) to realize the fusion of actual production data and simulation data. Then, different cold rolling states are identified by particle swarm optimization-support vector machine (PSO-SVM) and back propagation neural network (BPNN), respectively. Finally, the identification results of PSO-SVM and BPNN are combined based on the Dempster-Shafer (D-S) theory. It can be drawn that SSTCA can effectively solve the problems of low density and uneven distribution of industrial data by fusion of multi-source data, and D-S theory can realize the connection of different machine learning methods. Furthermore, the presented method can more accurately identify different chatter states in the rolling process. [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]

Simultaneous Localization and Mapping (SLAM) is the foundation for high-precision localization, environmental awareness, and autonomous decision-making of autonomous vehicles. It has developed rapidly, but there are still challenges such as sensor errors, data fusion, and real-time computing. This paper proposes an optimization-based fusion algorithm that integrates IMU data, visual data and LiDAR data to construct a high-frequency visual-inertial odometry. The odometry is employed to obtain the relative pose transformation during the LiDAR data acquisition process, and eliminate the distortion of the point cloud by interpolation. By utilizing the local curvatures, some edge and plane features are extracted by LiDAR after removing the distortion, which are further combined with local map alignment to reconstruct the LiDAR constrains. In addition, the LiDAR odometer can be obtained through the initial values provided by high-frequency visual-inertial odometry. To address the cumulative error in odometers, adjacent keyframe and multi descriptor fusion loop constraints are combined to construct back-end optimization constraints, solving for high-accuracy localization results and constructing a 3D point cloud map of the surroundings. Compared with some classical algorithm, results show that the accuracy of this paper's algorithm is better than the laser SLAM method and the multi-sensor fusion SLAM method. Besides, the laser-assisted multi-feature visual-inertial odometry localization accuracy is also better than that of the single-feature visual-inertial odometry. In summary, the newly proposed SLAM method can largely improve the accuracy of odometry in real traffic scenarios. [ABSTRACT FROM AUTHOR]

Rapid advances in infrastructure health monitoring and sensing technologies allow the monitoring of infrastructure assets continuously and in real-time throughout their life span. However, smart and automated techniques for decision-making (e.g. maintaining or improving infrastructure performance) are in their infancy. The revolution in new sensing capabilities has led to rapidly increasing volumes of data, which makes traditional data analysis techniques inadequate. Adoption of Big Data (BD) analytics and Artificial Intelligence (AI) techniques are urgently needed to automatically integrate information from multiple sensors, extract knowledge and inform decision-making. The objective of this work was to provide a state-of-the-art review of data fusion and machine learning techniques applied to infrastructure health monitoring. In contrast to the previously published, related review articles, the focus of this review is on the techniques implemented by machine learning algorithms, their applications at each data processing stage in a machine learning framework, and their advantages and limitations. Finally, challenges and future trends for machine learning techniques and infrastructure health monitoring systems are discussed. As a review, this paper offers meaningful suggestions for employing data fusion and machine learning techniques in infrastructure health monitoring. [ABSTRACT FROM AUTHOR]

Laser melt injection (LMI) provides a new route for fabricating multi-material components with tailored physical performance and distributed functional properties. However, the widespread industrial adoption of metal matrix composite (MMC) fabricated by LMI is still hampered by repeatability and reliability compared to monolithic alloys. This study presents promising results that aim to bridge the knowledge gap by determining a novel method to correlate visual and infrared images with the quality of MMC. A CNN architecture-based hybrid fusion model integrating molten pool and spatter features is proposed based on process understanding for quality monitoring of MMCs fabricated by LMI. The laser energy density and powder feed rate are intentionally tuned to fabricate WC reinforced MMC with four different ceramic particle states. Five models are established based on the single-sensor data, data-level fusion, feature-level fusion, and multi-level hybrid fusion respectively and compared in quality identification performance by four quantitative metrics and two visualization models. The results show that the three multi-sensor fusion models can significantly improve the classification accuracy compared to the single sensor-based model. Compared with data-level fusion and feature-level fusion, the proposed multi-level hybrid fusion model can integrate the advantages of the two fusion models and exhibits the best classification performance by multiple feature extraction channels with complementary and redundant data. The InceptionV3-based hybrid fusion model achieves the highest overall accuracy of 97.44% among the four state-of-the-art CNN architectures. [ABSTRACT FROM AUTHOR]

Vision-inertial navigation offers a promising solution for aircraft to estimate ego-motion accurately in environments devoid of Global Navigation Satellite System (GNSS). However, existing approaches have limited adaptability for fixed-wing aircraft with high maneuverability and insufficient visual features, problems of low accuracy and subpar real-time arise. This paper introduces a novel vision-inertial heterogeneous data fusion methodology, aiming to enhance the navigation accuracy and computational efficiency of fixed-wing aircraft landing navigation. The visual front-end of the system extracts multi-scale infrared runway features and computes geo-reference runway image as observation. The infrared runway features are recognized efficiently and robustly by a lightweight end-to-end neural network from blurry infrared images, and the geo-reference runway is generated through projection of the runway's prior geographical information and prior pose. The fusion back-end of the navigation system is the Covariance Feedback Control based Cubature Kalman Filter (CFC-CKF) framework, which tightly integrates visual observations and inertial measurements for zero-drift pose estimation and curbs the effect of inaccurate kinematic noise statistics. Finally, real flight experiments demonstrate that the algorithm can estimate the pose at a frequency of 100 Hz and fulfill the navigation accuracy requirements for high-speed landing of fixed-wing aircraft. [ABSTRACT FROM AUTHOR]

In the wave of research on autonomous driving, 3D object detection from the Bird's Eye View (BEV) perspective has emerged as a pivotal area of focus. The essence of this challenge is the effective fusion of camera and LiDAR data into the BEV. Current approaches predominantly train and predict within the front view and Cartesian coordinate system, often overlooking the inherent structural and operational differences between cameras and LiDAR sensors. This paper introduces CL-FusionBEV, an innovative 3D object detection methodology tailored for sensor data fusion in the BEV perspective. Our approach initiates with a view transformation, facilitated by an implicit learning module that transitions the camera's perspective to the BEV space, thereby aligning the prediction module. Subsequently, to achieve modal fusion within the BEV framework, we employ voxelization to convert the LiDAR point cloud into BEV space, thereby generating LiDAR BEV spatial features. Moreover, to integrate the BEV spatial features from both camera and LiDAR, we have developed a multi-modal cross-attention mechanism and an implicit multi-modal fusion network, designed to enhance the synergy and application of dual-modal data. To counteract potential deficiencies in global reasoning and feature interaction arising from multi-modal cross-attention, we propose a BEV self-attention mechanism that facilitates comprehensive global feature operations. Our methodology has undergone rigorous evaluation on a substantial dataset within the autonomous driving domain, the nuScenes dataset. The outcomes demonstrate that our method achieves a mean Average Precision (mAP) of 73.3% and a nuScenes Detection Score (NDS) of 75.5%, particularly excelling in the detection of cars and pedestrians with high accuracies of 89% and 90.7%, respectively. Additionally, CL-FusionBEV exhibits superior performance in identifying occluded and distant objects, surpassing existing comparative methods. [ABSTRACT FROM AUTHOR]

Wayside monitoring is a promising cost-effective alternative to predict damage in the rolling stock. The main goal of this work is to present an unsupervised methodology to identify out-of-roundness (OOR) damage wheels, such as wheel flats and polygonal wheels. This automatic damage identification algorithm is based on the vertical acceleration evaluated on the rails using a virtual wayside monitoring system and involves the application of a two-step procedure. The first step aims to define a confidence boundary by using (healthy) measurements evaluated on the rail constituting a baseline. The second step of the procedure involves classifying damage of predefined scenarios with different levels of severities. The proposed procedure is based on a machine learning methodology and includes the following stages: (1) data collection, (2) damage-sensitive feature extraction from the acquired responses using a neural network model, i.e., the sparse autoencoder (SAE), (3) data fusion based on the Mahalanobis distance, and (4) unsupervised feature classification by implementing outlier and cluster analysis. This procedure considers baseline responses at different speeds and rail irregularities to train the SAE model. Then, the trained SAE is capable to reconstruct test responses (not trained) allowing to compute the accumulative difference between original and reconstructed signals. The results prove the efficiency of the proposed approach in identifying the two most common types of OOR in railway wheels. [ABSTRACT FROM AUTHOR]

This study proposes a machine tool vibration prediction method based on multi‐sensor fusion and a long short‐term memory (LSTM) network. Machine tool vibration significantly impacts machining quality, surface roughness, dimensional accuracy, and tool wear. By combining deep learning with industrial applications, this method achieves high‐precision vibration prediction through multi‐sensor data fusion. Data is input into the LSTM model to predict the next moment's vibration. Experimental results demonstrate strong prediction capability for periodic vibrations and machining‐specific vibration errors, effectively enhancing machining accuracy. [ABSTRACT FROM AUTHOR]

With the advancement and expansion of power system technology, ensuring the safe and stable operation of transmission lines has become increasingly crucial. Traditional manual inspection methods often suffer from low efficiency and high risks. In recent years, the rapid development of unmanned aerial vehicle (UAV) technology has provided a new solution for power system inspection. UAV inspection offers advantages such as high flexibility, wide coverage, and relatively low overall costs, effectively improving inspection efficiency, reducing inspection costs, and mitigating personnel safety risks. A comprehensive review of the current state of UAV inspections in power systems is provided in this study, introducing the main sensing technologies and applications of UAV inspection, including visible light cameras, infrared thermal imaging, depth cameras, compound eye cameras, radar, X-rays, and ultrasonic sensors. It also discusses the challenges faced by UAV inspections in power systems, such as the complexity of data processing, the lack of automation, and the absence of regulatory frameworks. Furthermore, it put forward future development trends, including multi-sensor fusion, edge computing, cloud computing centres, multi-UAV collaboration, and the cooperation of various unmanned clusters. This work aims to serve as a reference for the research and application of UAV inspections in power systems. [ABSTRACT FROM AUTHOR]

At present, there are diverse data sources and mature technologies for the 3D modeling of cities, and 3D modeling is also developing towards component-level and refined modeling. In this study, we combined the needs of refined management in the central area of Beijing and elaborated on the practice of using various point cloud collection devices to carry out multisource point cloud data collection and ultrafine 3D modeling in areas where flight operations are not possible. There are three main areas of innovation: (1) the development of full-element ground acquisition and multisource point cloud joint 3D modeling technology, which solves the technical problems of acquiring all types of ground scanning data, such as those obtained using static, station-, cart-, backpack-, and vehicle-mounted laser scanning instruments, and handheld scanners, as well as multisource point cloud data fusion and modeling; (2) the development of a vehicle-mounted ultrahigh-resolution image acquisition system, which improves the efficiency of the vehicle scanner by increasing the exposure frequency to enhance its travel speed and (3) the use of tools to automatically extract urban components based on point clouds, which improved the efficiency of 3D modeling and achieved the fine-grained modeling of massive components in the region. On the basis of the system platform, the management and implementation of urban component-level information can be achieved. [ABSTRACT FROM AUTHOR]

The growing adoption of electric vehicles offers a potential opportunity to reduce transportation sector carbon footprint. In our research, we studied vehicle purchase behavior with emphasis on alternative fuel vehicles using the vehicle purchase dataset ‘MaritzCX New Vehicle Customer Study.’ This study consisted of a two-level modeling approach. In the first level, purchasing of a new car was estimated based on consumers socio-economic characteristics. In the second level, the vehicle purchase decision was examined with a two-dimensional dependent variable – vehicle type and fuel type. We employed an innovative data fusion approach that probabilistically links records from MaritzCX with records from National Household Travel Survey with the objective of identifying new independent variables affecting the decision process while maximizing data fit. The final model included a host of independent variables from four different categories: vehicle-, economic-, demographic-, and spatial characteristics. Finally, the model results were employed to conduct an elasticity analysis. [ABSTRACT FROM AUTHOR]

Site investigation is crucial in geotechnical engineering. The cone penetration test (CPT) and the multichannel analysis of surface waves (MASWs) are widely used as geotechnical and geophysical methods, respectively. CPT offers high precision but requires a high cost and only provides soil information at limited locations. In contrast, MASW covers a broad range of soil information but has less accuracy compared to CPT. This study proposes a novel ensemble prediction method that fuses both CPT and MASW data to overcome the limitations of using either dataset alone. The method employs random forest (RF) and gradient boosting decision tree (GBDT) to achieve the transformation between the shear velocity and cone tip resistance (Vs–qc) and the prediction of qc at unknown locations. Unlike traditional empirical regression models, this method provides more accurate and reliable predictions by leveraging the complementary strengths of CPT and MASW. The proposed RF‐GBDT ensemble model is validated using data from the New Zealand Geotechnical Database. The results show that the established RF‐GBDT ensemble model outperforms simple empirical regression models and various popular machine learning models in the Vs–qc transformation and in predicting qc at unknown locations. Specifically, integrating MASW data increases the R2 at location CPT3 from 0.477 to 0.758, demonstrating that the proposed method can improve the predictions of soil parameters in areas with sparse data. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to improve the fault early warning effect of smart grid equipment through multi-sensor information fusion technology. Therefore, based on the analytical model of power grid fault diagnosis, this paper considers the influence of distributed generation in distribution network on fault diagnosis, as well as the misoperation or refusal of protection and switch, and the false alarm or leakage of alarm signal. At the same time, in order to display the results of fault diagnosis accurately and intuitively, an analytical model of fault diagnosis of distribution network based on multi-source information fusion is proposed. Finally, this paper verifies the effectiveness of this method through an example application. This article uses the PEDL dataset for experimental research, Through the comparison of fault data, it can be seen that compared with existing methods, the method proposed in this paper achieves the highest goodness of fit for warning, indicating the best fault warning effect.When there is enough training set, the prediction accuracy of the fault set can reach over 99%, Based on experimental analysis, it can be concluded that the proposed power grid equipment model has higher accuracy and reliability compared to traditional models. And the model in this article integrates the real-time monitoring function of power grid equipment and the equipment fault warning function, which improves the practicality of the power grid equipment monitoring system. [ABSTRACT FROM AUTHOR]

Displacement is an important parameter for evaluating structural performance. However, the accurate measurement of global dynamic displacement remains a challenging task. To solve this problem, this paper proposes a global dynamic displacement reconstruction method for lattice tower structures, fusing limited acceleration and strain data. First, the strain-displacement mapping method for cantilever beams with variable cross-sections is presented and then extended to lattice towers. Thereafter, a modified multi-rate data fusion algorithm incorporating Kalman filtering and the proposed strain-displacement mapping methods is developed to fuse the acceleration and strain data to reconstruct the global dynamic displacement of the tower. The numerical simulation, model test and full-scale test demonstrate that the reconstructed dynamic displacements using the proposed method agree well with the reference values in both the time and frequency domains, and the parametric analysis has also been carried out, exhibiting great robustness and high reconstruction accuracy. [ABSTRACT FROM AUTHOR]

We are aware that autonomous vehicle handles camera and LiDAR data pipelines and uses the sensor pictures to provide an autonomous object identification solution. While current research yields reasonable results, it falls short of offering practical solutions. For example, lane markings and traffic signs may become obscured by accumulation on roads, making it unsafe for a self-driving car to navigate. Moreover, the car’s sensors may be severely hindered by intense rain, snow, fog, or dust storms, which could endanger human safety. So, this research introduced Multi-Sensor Fusion and Segmentation for Deep Q-Network (DQN)-based Multi-Object Tracking in Autonomous Vehicles. Improved Adaptive Extended Kalman Filter (IAEKF) for noise reduction, Normalized Gamma Transformation-based CLAHE (NGT-CLAHE) for contrast enhancement, and Improved Adaptive Weighted Mean Filter (IAWMF) for adaptive thresholding have been used. A novel multi-segmentation using several segmentation methods and degrees dependent on the orientation of images has been used. DenseNet (D Net)-based multi-image fusion provides faster processing speeds and increased efficiency. The grid map-based pathways and lanes are chosen using the Energy Valley Optimizer (EVO) technique. This method easily achieves flexibility, robustness, and scalability by simplifying the complex activities. Furthermore, the YOLOv7 model is used for classification and detection. Metrics like velocity, accuracy rate, success rate, success ratio, and mean-squared error are used to assess the proposed method. [ABSTRACT FROM AUTHOR]

Copyright of Science & Technology of Food Industry is the property of Science & Technology of Food Industry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Multi-sensor information fusion (MSIF) technology based on deep convolutional neural networks (CNN) has been widely used in UAV obstacle avoidance. However, detection efficiency needs to be improved in practice because of its high computational complexity and limited airborne hardware resources. A lightweight CNN-based fast detection method based on the fusion of millimeter-wave (MMW) radar and camera is proposed in this paper. In the data preprocessing stage, the input images to the network were preprocessed based on the radar and image data. A rough detection algorithm calculates and segments the saliency image to obtain regions of interest (ROI). The computational complexity of the network training and prediction was reduced by setting the image pixels outside the ROI. In the detection stage based on deep learning, a lightweight network structure based on ResNet18 was designed to fuse the saliency images at different convolution depths. In the post-decoding stage, the calibration points are fused for local non-maximum suppression (NMS). In contrast to typical detection methods, the proposed method improves the detection speed by removing redundant pixels and local NMS, increasing the detection accuracy by fusing the feature information of the radar and camera in multiple stages. The experimental results indicate that compared with the latest lightweight network (YOLOv8n), the detection accuracy is increased by 10.51%, and the FPS increased by 44.43%. Compared with the latest YOLOv8s and YOLOv9m models, the FPS is increased by 3.0X-4.4X. The field programmable gate array (FPGA) implementation achieves a performance of 60.0 FPS. This is an improvement compared with typical methods, demonstrating that the proposed method is more effective than state-of-the-art models. [ABSTRACT FROM AUTHOR]

The agricultural WSN (wireless sensor network) has the characteristics of long operation cycle and wide coverage area. In order to cover as much area as possible, farms usually deploy multiple monitoring devices in different locations of the same area. Due to different types of equipment, monitoring data will vary greatly, and too many monitoring nodes also reduce the efficiency of the network. Although there have been some studies on data fusion algorithms, they have problems such as ignoring the dynamic changes of time series, weak anti-interference ability, and poor processing of data fluctuations. So in this study, a data fusion algorithm for optimal node tracking in agricultural wireless sensor networks is designed. By introducing the dynamic bending distance in the dynamic time warping algorithm to replace the absolute distance in the fuzzy association algorithm and combine the sensor's own reliability and association degree as the weighted fusion weight, which improved the fuzzy association algorithm. Finally, another three algorithm were tested for multi-temperature sensor data fusion. Compare with the kalman filter, arithmetic mean and fuzzy association algorithm, the average value of the improved data fusion algorithm is 29.5703, which is close to the average value of the other three algorithms, indicating that the data distribution is more even. Its extremely bad value is 8.9767, which is 10.04%, 1.14% and 9.85% smaller than the other three algorithms, indicating that it is more robust when dealing with outliers. Its variance is 2.6438, which is 2.82%, 0.65% and 0.27% smaller than the other three algorithms, indicating that it is more stable and has less data volatility. The results show that the algorithm proposed in this study has higher fusion accuracy and better robustness, which can obtain the fusion value that truly feedbacks the agricultural environment conditions. It reduces production costs by reducing redundant monitoring devices, the energy consumption and improves the data collection efficiency in wireless sensor networks. [ABSTRACT FROM AUTHOR]

Sea ice thickness (SIT) is a critical and sensitive parameter in the climate system, with its dynamic changes profoundly influencing global climate models, navigational routes, and the potential for Arctic resource development. Given the widespread application of current satellite remote sensing technology in monitoring SIT, significant uncertainties remain. This study first underscores the importance of in-situ observations as a direct measurement method for SIT. However, the limitations of in-situ data in terms of acquisition cost, spatiotemporal coverage continuity, and distribution uniformity significantly hinder the effective evaluation of multi-source SIT products. To address this, the study innovatively introduces the Triple Collocation (TC) method, which effectively mitigates the impact of errors from individual data sources on the overall evaluation results through a mutual validation mechanism among multiple satellite data sources. This allows for a scientific assessment of multi-source SIT products even in the context of scarce in-situ observations. The findings indicate that the TC method not only successfully resolves the challenges of multi-source data evaluation but also facilitates data integration among these products, significantly enhancing the overall accuracy and spatiotemporal consistency of SIT data. [ABSTRACT FROM AUTHOR]

ABSTRACT The study introduces three novel strategies for incorporating capabilities for dynamic modelling into multiblock regression methods by integrating sequentially orthogonalised partial least squares (SO‐PLS) with different dynamic modelling techniques. The study evaluates these strategies using synthetic datasets and an industrial example, comparing their performance in predictive ability, identification of process dynamics, and quantification of block contributions. Results suggest that these approaches can effectively model the dynamics with performance comparable to state‐of‐the‐art methods, providing, at the same time, insight into the dynamic order and block contributions. One of the strategies, sequentially orthogonalised dynamic augmented (SODA)–PLS, shows promise by ensuring that redundant information in the time dimension is not included, resulting in simpler and more easily interpretable dynamic models. These multiblock dynamic regression strategies have potential applications for improved process understanding in industrial settings, especially where multiple data sources and inherent time dynamics are present. [ABSTRACT FROM AUTHOR]

The current research effort is focused on improving the effective use of the multiple disparate sources of data available by proposing a novel maximum likelihood based probabilistic data fusion approach for modeling residential energy consumption. To demonstrate our data fusion algorithm, we consider energy usage by fuel type variables (for electricity and natural gas) in residential dwellings as our dependent variable of interest, drawn from residential energy consumption survey (RECS) data. The national household travel survey (NHTS) dataset was considered to incorporate additional variables that are not available in the RECS data. With a focus on improving the model for the residential energy use by fuel type, our proposed research provides a probabilistic mechanism for appropriately fusing records from the NHTS data with the RECS data. Specifically, instead of strictly matching records with only common attributes, we propose a flexible differential weighting method (probabilistic) based on attribute similarity (or dissimilarity) across the common attributes for the two datasets. The fused dataset is employed to develop an updated model of residential energy use with additional independent variables contributed from the NHTS dataset. The newly estimated energy use model is compared with models estimated RECS data exclusively to see if there is any improvement offered by the newly fused variables. In our analysis, the model fit measures provide strong evidence for model improvement via fusion as well as weighted contribution estimation, thus highlighting the applicability of our proposed fusion algorithm. The analysis is further augmented through a validation exercise that provides evidence that the proposed algorithm offers enhanced explanatory power and predictive capability for the modeling energy use. Our proposed data fusion approach can be widely applied in various sectors including the use of location-based smartphone data to analyze mobility and ridehailing patterns that are likely to influence energy consumption with increasing electric vehicle (EV) adoption. [ABSTRACT FROM AUTHOR]

Snow avalanches, one of the most severe natural hazards in mountainous regions, pose significant risks to human lives, infrastructure, and ecosystems. As climate change accelerates shifts in snowfall and temperature patterns, it is increasingly important to improve our ability to monitor and predict avalanches. This review explores the use of remote sensing technologies in understanding key geomorphological, geobotanical, and meteorological factors that contribute to avalanche formation. The primary objective is to assess how remote sensing can enhance avalanche risk assessment and monitoring systems. A systematic literature review was conducted, focusing on studies published between 2010 and 2025. The analysis involved screening relevant studies on remote sensing, avalanche dynamics, and data processing techniques. Key data sources included satellite platforms such as Sentinel-1, Sentinel-2, TerraSAR-X, and Landsat-8, combined with machine learning, data fusion, and change detection algorithms to process and interpret the data. The review found that remote sensing significantly improves avalanche monitoring by providing continuous, large-scale coverage of snowpack stability and terrain features. Optical and radar imagery enable the detection of crucial parameters like snow cover, slope, and vegetation that influence avalanche risks. However, challenges such as limitations in spatial and temporal resolution and real-time monitoring were identified. Emerging technologies, including microsatellites and hyperspectral imaging, offer potential solutions to these issues. The practical implications of these findings underscore the importance of integrating remote sensing data with ground-based observations for more robust avalanche forecasting. Enhanced real-time monitoring and data fusion techniques will improve disaster management, allowing for quicker response times and more effective policymaking to mitigate risks in avalanche-prone regions. [ABSTRACT FROM AUTHOR]

Agricultural sensors can greatly contribute to future technologies and systemic innovation in smart agriculture. However, the types and precision of sensors are limited to monitoring the agricultural environment with complex and diverse objects. The large and redundant monitoring data has also resulted in the low reliability of information perception. In this study, an improved radial basis function neural network (RBFNN) and Chernobyl disaster optimizer (ICDO) multi-sensor data fusion was proposed to improve the accuracy and reliability of single-sensor measurement. Firstly, an improved Chernobyl catastrophe optimization was performed on the neural network model. The good-point set theory was introduced to improve the initial population quality of the CDO, particularly for accuracy and speed. The adaptive Laplacian crossover operator was added to enhance the search performance. The better adaptive behavior was achieved in the high convergence speed. And then, the individual learning and differential evolution strategy were used to redefine the location update equation, in order to balance the local and global exploration. Secondly, the RBF neural network model was optimized by ICDO, in order to improve the stability of the model. Finally, the nonlinear mapping of the RBF neural network model was used to realize the multi-sensor data fusion with high accuracy. Three experiments were conducted to verify the improved model. The first one was to verify the ICDO. A large improvement was obtained in the solution accuracy and optimization stability, compared with particle swarm optimization (PSO), gray wolf optimization (GWO), firefly algorithm (FA), dung beetle optimizer (DBO), and subtraction average-based optimizer (SABO). The second one was to evaluate the quality of the atmospheric environment. Specifically, the atmospheric data was collected outside the South Subtropical Botanical Garden in Mazhang District, Zhanjiang City, Guangdong Province, China, from September 1, 2022, to September 30, 2023. The goodness of fit reached 0.999 for the prediction of atmospheric environmental quality, the mean square error was as low as 0.348, and the mean absolute percentage error was reduced to 0.729%. The third one was to classify the greenhouse environment. The data was collected in the greenhouses of the South Asian Tropical Botanical Garden. The accuracy rate of greenhouse environment classification was 99.21% with a precision rate of 99.91%. The data fusion was suitable for both indoor and outdoor environments, indicating better adaptability and high accuracy. This finding can also provide solid technical support to agricultural sensor data fusion in the field of precision agriculture. [ABSTRACT FROM AUTHOR]

Using multi-omics data for clustering (cancer subtyping) is crucial for precision medicine research. Despite numerous methods having been proposed, current approaches either do not perform satisfactorily or lack biological interpretability, limiting the practical application of these methods. Based on the biological hypothesis that patients with the same subtype may exhibit similar dysregulated pathways, we developed an Iterative Pathway Fusion approach for enhanced Multi-omics Clustering (IPFMC), a novel multi-omics clustering method involving two data fusion stages. In the first stage, omics data are partitioned at each layer using pathway information, with crucial pathways iteratively selected to represent samples. Ultimately, the representation information from multiple pathways is integrated. In the second stage, similarity network fusion was applied to integrate the representation information from multiple omics. Comparative experiments with nine cancer datasets from The Cancer Genome Atlas (TCGA), involving systematic comparisons with 10 representative methods, reveal that IPFMC outperforms these methods. Additionally, the biological pathways and genes identified by our approach hold biological significance, affirming not only its excellent clustering performance but also its biological interpretability. [ABSTRACT FROM AUTHOR]

Single-cell ribonucleic acid sequencing (scRNA-seq) technology can be used to perform high-resolution analysis of the transcriptomes of individual cells. Therefore, its application has gained popularity for accurately analyzing the ever-increasing content of heterogeneous single-cell datasets. Central to interpreting scRNA-seq data is the clustering of cells to decipher transcriptomic diversity and infer cell behavior patterns. However, its complexity necessitates the application of advanced methodologies capable of resolving the inherent heterogeneity and limited gene expression characteristics of single-cell data. Herein, we introduce a novel deep learning-based algorithm for single-cell clustering, designated scDFN, which can significantly enhance the clustering of scRNA-seq data through a fusion network strategy. The scDFN algorithm applies a dual mechanism involving an autoencoder to extract attribute information and an improved graph autoencoder to capture topological nuances, integrated via a cross-network information fusion mechanism complemented by a triple self-supervision strategy. This fusion is optimized through a holistic consideration of four distinct loss functions. A comparative analysis with five leading scRNA-seq clustering methodologies across multiple datasets revealed the superiority of scDFN, as determined by better the Normalized Mutual Information (NMI) and the Adjusted Rand Index (ARI) metrics. Additionally, scDFN demonstrated robust multi-cluster dataset performance and exceptional resilience to batch effects. Ablation studies highlighted the key roles of the autoencoder and the improved graph autoencoder components, along with the critical contribution of the four joint loss functions to the overall efficacy of the algorithm. Through these advancements, scDFN set a new benchmark in single-cell clustering and can be used as an effective tool for the nuanced analysis of single-cell transcriptomics. [ABSTRACT FROM AUTHOR]

Most existing studies have focused on identifying the origin of species with protected geographical indications while neglecting to determine the proximate geographical origin of different species. In this study, we investigated the feasibility of using near‐ and mid‐infrared spectroscopy to identify the origin of 156 Polygonatum kingianum samples from six regions in Yunnan, China. In this work, spectral images of different modes reveal more information about the P. kingianum. Comparing the performance of traditional machine learning models according to single spectrum and data fusion, the middle‐level data fusion‐principal component model has the best performance, and its sensitivity, specificity, and accuracy are all 1, and the model has the least number of variables. The residual convolutional neural network (ResNet) model constructed in the 1050–850 cm−1 band confirms that fewer variables are beneficial in improving the accuracy of the model. In conclusion, this study verifies the feasibility of the proposed strategy and establishes a practical model to determine the source of P. kingianum. [ABSTRACT FROM AUTHOR]

Underwater simultaneous localization and mapping (SLAM) is essential for effectively navigating and mapping underwater environments; however, traditional SLAM systems have limitations due to restricted vision and the constantly changing conditions of the underwater environment. This study thoroughly examined the underwater SLAM technology, particularly emphasizing the incorporation of deep learning methods to improve performance. We analyzed the advancements made in underwater SLAM algorithms. We explored the principles behind SLAM and deep learning techniques, examining how these methods tackle the specific difficulties encountered in underwater environments. The main contributions of this work are a thorough assessment of the research into the use of deep learning in underwater image processing and perception and a comparison study of standard and deep learning-based SLAM systems. This paper emphasizes specific deep learning techniques, including generative adversarial networks (GANs), convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and other advanced methods to enhance feature extraction, data fusion, scene understanding, etc. This study highlights the potential of deep learning in overcoming the constraints of traditional underwater SLAM methods, providing fresh opportunities for exploration and industrial use. [ABSTRACT FROM AUTHOR]

To address the challenges of suboptimal remote detection and significant computational burden in existing multi-sensor information fusion 3D object detection methods, a novel approach based on Bird's-Eye View (BEV) is proposed. This method utilizes an enhanced lightweight EdgeNeXt feature extraction network, incorporating residual branches to address network degradation caused by the excessive depth of STDA encoding blocks. Meantime, deformable convolution is used to expand the receptive field and reduce computational complexity. The feature fusion module constructs a two-stage fusion network to optimize the fusion and alignment of multi-sensor features. This network aligns image features to supplement environmental information with point cloud features, thereby obtaining the final BEV features. Additionally, a Transformer decoder that emphasizes global spatial cues is employed to process the BEV feature sequence, enabling precise detection of distant small objects. Experimental results demonstrate that this method surpasses the baseline network, with improvements of 4.5% in the NuScenes detection score and 5.5% in average precision for detection objects. Finally, the model is converted and accelerated using TensorRT tools for deployment on mobile devices, achieving an inference time of 138 ms per frame on the Jetson Orin NX embedded platform, thus enabling real-time 3D object detection. [ABSTRACT FROM AUTHOR]

As Location-Based Services (LBSs) rapidly develop, indoor localization technology is garnering significant attention as a critical component. Smartphones have become tools for indoor localization due to their highly integrated sensors, fast-evolving computational capabilities, and widespread user adoption. With the rapid advancement of smartphones, methods for smartphone-based indoor localization have increasingly attracted attention. Although there are reviews on indoor localization, there is still a lack of systematic reviews focused on smartphone-based indoor localization methods. In particular, existing reviews have not systematically analyzed smartphone-based indoor localization methods or considered the combination of smartphone sensor data with prior knowledge of the indoor environment to enhance localization performance. In this study, through systematic retrieval and analysis, the existing research was first categorized into three types to dissect the strengths and weaknesses based on the types of data sources integrated, i.e., single sensor data sources, multi-sensor data fusion, and the combination of spatial context with sensor data. Then, four key issues are discussed and the research gaps in this field are summarized. Finally, a comprehensive conclusion is provided. This paper offers a systematic reference for research and technological applications related to smartphone-based indoor localization methods. [ABSTRACT FROM AUTHOR]

In the era of the Internet of Things (IoT), the demand for accurate positioning services has become increasingly critical, as location-based services (LBSs) depend on users' location data to deliver contextual functionalities. While the Global Positioning System (GPS) is widely regarded as the standard for outdoor localization due to its reliability and comprehensive coverage, its effectiveness in indoor positioning systems (IPSs) is limited by the inherent complexity of indoor environments. This paper examines the various measurement techniques and technological solutions that address the unique challenges posed by indoor environments. We specifically focus on three key aspects: (i) a comparative analysis of the different wireless technologies proposed for IPSs based on various methodologies, (ii) the challenges of IPSs, and (iii) forward-looking strategies for future research. In particular, we provide an in-depth evaluation of current IPSs, assessing them through multidimensional matrices that capture diverse architectural and design considerations, as well as evaluation metrics established in the literature. We further examine the challenges that impede the widespread deployment of IPSs and highlight the potential risk that these systems may not be recognized with a single, universally accepted standard method, unlike GPS for outdoor localization, which serves as the golden standard for positioning. Moreover, we outline several promising approaches that could address the existing challenges of IPSs. These include the application of transfer learning, feature engineering, data fusion, multisensory technologies, hybrid techniques, and ensemble learning methods, all of which hold the potential to significantly enhance the accuracy and reliability of IPSs. By leveraging these advanced methodologies, we aim to improve the overall performance of IPSs, thus paving the way for more robust and dependable LBSs in indoor environments. [ABSTRACT FROM AUTHOR]

As cracks are a precursor landslide deformation feature, they can provide forecasting information that is useful for the early identification of landslides and determining motion instability characteristics. However, it is difficult to solve the size effect and noise-filtering problems associated with the currently available automatic crack detection methods under complex conditions using single remote sensing data sources. This article uses multidimensional target scene images obtained by UAV photogrammetry as the data source. Firstly, under the premise of fully considering the multidimensional image characteristics of different crack types, this article accomplishes the initial identification of landslide cracks by using six algorithm models with indicators including the roughness, slope, eigenvalue rate of the point cloud and pixel gradient, gray value, and RGB value of the images. Secondly, the initial extraction results are processed through a morphological repair task using three filtering algorithms (calculating the crack orientation, length, and frequency) to address background noise. Finally, this article proposes a multi-dimensional information fusion method, the Bayesian probability of minimum risk methods, to fuse the identification results derived from different models at the decision level. The results show that the six tested algorithm models can be used to effectively extract landslide cracks, providing Area Under the Curve (AUC) values between 0.6 and 0.85. After the repairing and filtering steps, the proposed method removes complex noise and minimizes the loss of real cracks, thus increasing the accuracy of each model by 7.5–55.3%. Multidimensional data fusion methods solve issues associated with the spatial scale effect during crack identification, and the F-score of the fusion model is 0.901. [ABSTRACT FROM AUTHOR]

Accurate quantitative precipitation estimation (QPE) is fundamental for a large number of hydrometeorological applications, especially when addressing extreme rainfall phenomena. This paper presents a comprehensive comparison of various rainfall estimation methods, specifically those relying on weather radar data, rain gauge data, and their fusion. The study evaluates the accuracy and reliability of each method in estimating rainfall for a severe event that occurred in Tuscany, Italy. The results obtained confirm that merging radar and rain gauge data outperforms both individual approaches by reducing errors and improving the overall reliability of precipitation estimates. This study highlights the importance of data fusion in enhancing the accuracy of QPE and also supports its application in operational contexts, providing further evidence for the greater reliability of merging methods. [ABSTRACT FROM AUTHOR]

Multisource data fusion technology integrates the strengths of various data sources, addressing the limitations of relying on a single source. Therefore, it has been widely applied in fields such as lithological classification and mineral exploration. However, traditional deep learning algorithms fail to distinguish the importance of different features effectively during fusion, leading to insufficient focus in the model. To address this issue, this paper introduces a ResHA network based on a hybrid attention mechanism to fuse features from ASTER remote sensing images, geochemical data, and DEM data. A case study was conducted in the Altay Orogenic Belt to demonstrate the lithological classification process. This study explored the impact of the submodule order on the hybrid attention mechanism and compared the results with those of MLP, KNN, RF, and SVM models. The experimental results show that (1) the ResHA network with hybrid attention mechanisms assigned reasonable weights to the feature sets, allowing the model to focus on key features closely related to the task. This resulted in a 7.99% improvement in classification accuracy compared with that of traditional models, significantly increasing the precision of lithological classification. (2) The combination of channel attention followed by spatial attention achieved the highest overall accuracy, 98.06%. [ABSTRACT FROM AUTHOR]

A wireless sensor network (WSN) can be used for various purposes, including area monitoring, health care, smart cities, and defence. Numerous complex issues arise in these applications, including energy efficiency, coverage, and intruder detection. Intruder detection is a significant obstacle in various wireless sensor network applications. It causes data fusion that jeopardizes the network's confidentiality, lifespan, and coverage. Various algorithm has been proposed for intruder detection where each node act as an agent, or some monitoring nodes are deployed for intruder detection. The proposed protocol detects intruders by transmitting a known bit from the Cluster Head (CH) to all nodes. The legal nodes must acknowledge their identification to the CH in order to be valid; otherwise, if the CH receives an incorrect acknowledgement from a node or receives no acknowledgement at all, it is an intruder. The proposed protocol assists in protecting sensor data from unauthorized access and detecting the intruder with its location through the identity of other legal nodes. The simulation results show that the proposed protocol delivers better results for identifying intruders for various parameters. [ABSTRACT FROM AUTHOR]

The authenticity and quality of traditional Chinese medicine (TCM) directly impact clinical efficacy and safety. Quality assessment of traditional Chinese medicine (QATCM) is a global concern due to increased demand and shortage of resources. Recently, modern analytical technologies have been extensively investigated and utilized to analyze the chemical composition of TCM. However, a single analytical technique has some limitations, and judging the quality of TCM only from the characteristics of the components is not enough to reflect the overall view of TCM. Thus, the development of multi-source information fusion technology and machine learning (ML) has further improved QATCM. Data information from different analytical instruments can better understand the connection between herbal samples from multiple aspects. This review focuses on the use of data fusion (DF) and ML in QATCM, including chromatography, spectroscopy, and other electronic sensors. The common data structures and DF strategies are introduced, followed by ML methods, including fast-growing deep learning. Finally, DF strategies combined with ML methods are discussed and illustrated for research on applications such as source identification, species identification, and content prediction in TCM. This review demonstrates the validity and accuracy of QATCM-based DF and ML strategies and provides a reference for developing and applying QATCM methods. [ABSTRACT FROM AUTHOR]

In recent years, diversified measurements reflect the system dynamics from a more comprehensive perspective in system modeling and analysis, such as scalars, waveform signals, images, and structured point clouds. To handle such multimodal structured high-dimensional (SHD) data, combining a large amount of data from multiple sites is necessary (i) to reduce the inherent population bias from a single site and (ii) to increase the model accuracy. However, impeded by data management policies and storage costs, data could not be easily shared or directly exchanged among different sites. Instead of simplifying or facilitating the data query process, we propose a federated multiple tensor-on-tensor regression (FedMTOT) framework to train the individual system model locally using (i) its own data and (ii) data features (not data itself) from other sites. Specifically, federated computation is executed based on alternating direction method of multipliers (ADMM) to satisfy data-sharing requirements, while the individual model at each site can still benefit from feature knowledge from other sites to improve its own model accuracy. Finally, two simulations and two case studies validate the superiority of the proposed FedMTOT framework. [ABSTRACT FROM AUTHOR]

Laser-induced breakdown spectroscopy (LIBS) is a promising technique to monitor carbon emissions in post-combustion flue gas. However, its measurement accuracy is susceptible to variations in gas temperature. In this work, a mid-level data fusion method integrating spectral and acoustic signals generated by laser-induced plasmas (LIPs) was proposed to improve the measurement accuracy. This method utilizes the high sensitivity of acoustic signals to variations in gas temperature, enabling a correction of temperature effects. The acoustic features were extracted from both the time-domain waveforms and frequency spectra, while the spectral features were selected using a SelectKBest method. These features were fused into a new array, on whose basis multivariate regression models including Partial Least Squares (PLS), Support Vector Machines (SVM), and Random Forest (RF) were trained. Data fusion significantly improved the predictive precision and trueness of SVM and RF models, with the RF model achieving the best performance: a coefficient of determination (R2) of 0.9941, a root-mean-square error (RMSE) of 0.4864, a mean absolute error (MAE) of 0.2587, and a mean absolute deviation (MAD) of 0.0980. Shapley additive explanation (SHAP) analysis revealed that in the RF model, the acoustic features that exhibited higher temperature sensitivity could be more frequently selected in the training process and thus had greater impacts on model outputs, which can better correct for the gas temperature effect. Furthermore, the potential of this method in industrial applications was demonstrated in an unsteady flow. [ABSTRACT FROM AUTHOR]

The identification of machining processes for low roughness samples is extremely challenging, and a reasonably quick identification of machining processes for low roughness parts is critical for ensuring that the samples are employed under the appropriate conditions and improving work efficiency. In this work, a new identification method of fusion of LIBS spectra and plasma acoustic emission signals (PAESs) with bimodal information is proposed, and the LIBS spectral data and PAES data of nine types of low roughness samples processed by three machining processes, namely horizontal milling, plain grinding, and vertical milling, are recorded and analyzed. The spectral intensities of the primary element Fe and trace element Mn are compared and analyzed. The spectrum intensities of the primary element Fe and trace element Mn, as well as the PAES maximum peak, are compared and examined. Using the PCA-SVM machine learning technique, the three recognition impacts of single LIBS data, single PAES data, and LIBS-PAES bimodal data fusion are examined and compared. At Ra = 0.4 μm and 0.8 μm, vertical milling produces significantly higher spectral intensities than plain grinding and horizontal milling, while horizontal milling produces significantly higher intensities than plain grinding. When the surface roughness of the samples is the same, variations in the machining process cause changes in the PAES. The recognition accuracy was 86.67% for the test set of single LIBS spectral data, 78.89% for the test set of single PAES data, and 97.11% for the training set, and 91.11% for the test set of LIBS-PAES bimodal data fusion, respectively. When compared to single-modal data recognition, bimodal data fusion greatly improves recognition ability, fully reflecting the benefits of bimodal data fusion. Based on the results of this study, it can be preliminarily concluded that the fusion of spectral and acoustic information in laser-induced breakdown spectroscopy detection is very promising for recognizing the surface state of parts in the machining field. [ABSTRACT FROM AUTHOR]

The evolution of traffic monitoring systems provides rich traffic data from multiple sensors. Fuzing the data has the potential to enhance the quality of travel time estimation. It also provides better spatial-temporal coverage in traffic observations. However, each sensor's unique data collection process results in fusion challenges with respect to the coverage and data quality differences between various sources. These factors determine the degree of confidence that should be considered when fuzing different types of data. To this end, this paper proposes an adaptive weight-based fusion technique (ABAFT) that considers data spatial coverage and quality or confidence as the factors constructing the weight. The proposed ABAFT was tested using different scenarios on synthetic GPS and Bluetooth MAC Scanners data from an urban arterial corridor. The results show that the ABAFT can increase the travel time estimation accuracy by over 10%, and reliability by over 8% compared to the single sensor estimators. It also outperforms the simple average and standard-error-based fusion by around 4%. ABAFT is easy to be implemented on multiple sources of information available to transport agencies for a single point of truth. [ABSTRACT FROM AUTHOR]

A high-quality land-use dataset is crucial for constructing a high-performance land-use classification model. Due to the complexity and spatial heterogeneity of land-use, the dataset construction process is inefficient and costly. This challenge affects the quality of datasets, consequently impacting the model's performance. The emerging field of Data-Centric Artificial Intelligence (DCAI) is expected to deliver techniques for dataset optimization, offering a promising solution to the problem. Therefore, this study proposes a data-centric framework named DCAI-CLUD for the construction of land-use datasets. Based on this framework, the accuracy and rate of data labeling are improved by 5.93 and 28.97%. The Gini index of the dataset and the proportion of samples with non-mixed land-use categories are enhanced by 3.27 and 8.52%. The overall accuracy (OA) and Kappa of the land-use classification model improved significantly by 27.87 and 58.08%. This study is the first to introduce DCAI into the field of geographic information and remote sensing and verify its effectiveness. The proposed framework can effectively improve the construction efficiency and quality of the dataset and synchronously optimize the model performance. Based on the proposed framework, we constructed a multi-source land-use dataset of major cities in China named CN-MSLU-100K. HIGHLIGHTS: A framework for optimizing the land-use dataset construction process is proposed. Filtering and pre-labeling improved the quality and efficiency of data labeling. The performance of land-use classification model is enhanced by dataset optimization. Preconceived results have a subjective impact on the data labelers. The first study to introduce DCAI for land-use classification is launched. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) is a highly promising research area meant to automatically identify and interpret human behaviour using data received from sensors in various contexts. The potential uses of HAR are many, among them health care, sports coaching or monitoring the elderly or disabled. Nonetheless, there are numerous hurdles to be circumvented for HAR's precision and usefulness to be improved. One of the challenges is that there is no uniformity in data collection and annotation making it difficult to compare findings among different studies. Furthermore, more comprehensive datasets are necessary so as to include a wider range of human activities in different contexts while complex activities, which consist of multiple sub‐activities, are still a challenge for recognition systems. Researchers have proposed new frontiers such as multi‐modal sensor data fusion and deep learning approaches for enhancing HAR accuracy while addressing these issues. Also, we are seeing more non‐traditional applications such as robotics and virtual reality/augmented world going forward with their use cases of HAR. This article offers an extensive review on the recent advances in HAR and highlights the major challenges facing this field as well as future opportunities for further researches. [ABSTRACT FROM AUTHOR]

Amid escalating global challenges such as population growth, pollution, and climate change, access to safe and clean water has emerged as a critical issue. It is estimated that there are 4 billion cases of water-related diseases worldwide that cause 3.4 million deaths every year. This underscores the urgent need for efficient water quality monitoring and assessment. Traditional assessment techniques include laboratory-based methods that are manual, costly, time-consuming, and risky. Although some studies leveraged Internet of Things (IoT)-based systems to examine water quality, they only relied on a limited number of water quality parameters (and thus do not offer a comprehensive and accurate water quality assessment), mainly due to the technical difficulties to integrate multiple sensors to a single device. In fact, due to the issues of multimodality, heterogeneity, and complexity of data, the interoperability among sensors with various measurements, sampling rates, and technical requirements makes it very challenging to seamlessly integrate multiple sensors into one device. This study overcame these technical challenges by leveraging multisensor data fusion capabilities to develop an intelligent cloud-based IoT multimodal edge sensing device to provide an automated, real-time, and comprehensive assessment process of water quality. First, a total of nine water quality parameters were identified and considered. Second, the sensing device was designed and developed using an ESP32 embedded system, which is a low-cost, low-power system on a chip (SoC) microcontroller integrated with Wi-Fi and dual-mode Bluetooth connectivity by fusing data from six different sensors that measure the nine identified water parameters on the edge. Third, the overall water quality was evaluated using the National Sanitation Foundation Water Quality Index (NSFWQI). Fourth, a cloud-based server was created to publish the data instantly, and a graphical user interface (GUI) was developed to provide easy-to-understand real-time visualization and information of the water quality. The real-world applicability and practicality of the developed IoT-enabled sensing device was tested and verified in a pilot project (i.e., a case study) of a building located in Newark, New Jersey, for a duration of 6 months. This paper adds to the body of knowledge by being the first research developing a single IoT-enabled device that is capable of reporting NSFWQI in real-time based on 9 water quality indicators encompassing both physical [temperature, total dissolved solids (TDS), turbidity, and pH] and chemical [potassium, phosphorus, nitrogen, dissolved oxygen (DO), and 5-day biochemical oxygen demand (BOD5)] parameters. Thus, this study serves as a multifaceted improvement across different dimensions, fostering healthier, more efficient, and technologically advanced environments. [ABSTRACT FROM AUTHOR]

Currently, the incidence of accidents involving falls from height at construction sites caused by workers climbing guardrails is still high. Traditional unsafe behavior management mainly relies on a safety patrol of construction-site supervisors, which consumes considerable laborpower and time. There is still a critical need for an automated safety management method to identify unsafe guardrail climbing behavior. This study proposes a worker behavior identification method based on visual data fusion of a worker's surrounding environment and posture data. Videos of seven participants' guardrail climbing behavior through multiangle and multidistance cameras were analyzed to verify this method. By analyzing the environment and posture of the participants, three methods based on environment, posture, and fusion data were used to detect the stage of guardrail climbing action of the workers and compare them with the ground truth labeled by safety experts. The precision and recall of worker guardrail climbing behavior based on the fusion method were 82% and 83% respectively, which is better performance than that obtained using a single method. The data fusion–based method avoids the misjudgment generated by a single detection method and can identify the guardrail climbing behavior more accurately. Practical Applications: Guardrail climbing is a typical unsafe behavior that exposes workers to a high risk of falling from height. However, there is a lack of research on the interaction between workers and guardrail systems in the construction industry. This study provides a nonintrusive method for automating detection and management of guardrail climbing behavior on construction site. Using existing surveillance cameras, this method can be deployed at low cost with slight interference with workers. Based on the detection, appropriate interventions are expected to effectively reduce workers' unsafe behaviors during construction and improve safety on site. The detection of guardrail climbing, which is one of the variety of unsafe behaviors associated with falls from height, can enrich the intelligent construction safety management system effectively. Moreover, this study also provides reference and quantitative indicators (e.g., a guardrail climbing unsafe behavior database) for risk assessment and early warning of workers who are exposed to risk of fall from height. [ABSTRACT FROM AUTHOR]

In order to realize high-precision diagnosis of bearings faults in a multi-sensor detection environment, a fault diagnosis method based on two-stage signal fusion and deep multi-scale multi-sensor networks is proposed. Firstly, the signals are decomposed and fused using weighted empirical wavelet transform to enhance weak features and reduce noise. Secondly, an improved random weighting algorithm is proposed to perform a second weighted fusion of the signals to reduce the total mean square error. The fused signals are input into the deep multi-scale residual network, the feature information of different convolutional layers is extracted through dilated convolution, and the features are fused using pyramid theory. Finally, the bearings states are classified according to the fusion features. Experiment results show the effectiveness and superiority of this method. • Application range of the traditional random weighted fusion algorithm is extended. • A new signal fusion method based on two-stage weighting is constructed. • An improved deep residual network is proposed to realize multi-scale features extraction and fusion enhancement. [ABSTRACT FROM AUTHOR]