Feature selection(FS)is a pivotal pre-processing step in developing data-driven models,influencing reliability,performance and optimization.Although existing FS techniques can yield high-performance metrics for certai...Feature selection(FS)is a pivotal pre-processing step in developing data-driven models,influencing reliability,performance and optimization.Although existing FS techniques can yield high-performance metrics for certain models,they do not invariably guarantee the extraction of the most critical or impactful features.Prior literature underscores the significance of equitable FS practices and has proposed diverse methodologies for the identification of appropriate features.However,the challenge of discerning the most relevant and influential features persists,particularly in the context of the exponential growth and heterogeneity of big data—a challenge that is increasingly salient in modern artificial intelligence(AI)applications.In response,this study introduces an innovative,automated statistical method termed Farea Similarity for Feature Selection(FSFS).The FSFS approach computes a similarity metric for each feature by benchmarking it against the record-wise mean,thereby finding feature dependencies and mitigating the influence of outliers that could potentially distort evaluation outcomes.Features are subsequently ranked according to their similarity scores,with the threshold established at the average similarity score.Notably,lower FSFS values indicate higher similarity and stronger data correlations,whereas higher values suggest lower similarity.The FSFS method is designed not only to yield reliable evaluation metrics but also to reduce data complexity without compromising model performance.Comparative analyses were performed against several established techniques,including Chi-squared(CS),Correlation Coefficient(CC),Genetic Algorithm(GA),Exhaustive Approach,Greedy Stepwise Approach,Gain Ratio,and Filtered Subset Eval,using a variety of datasets such as the Experimental Dataset,Breast Cancer Wisconsin(Original),KDD CUP 1999,NSL-KDD,UNSW-NB15,and Edge-IIoT.In the absence of the FSFS method,the highest classifier accuracies observed were 60.00%,95.13%,97.02%,98.17%,95.86%,and 94.62%for the respective datasets.When the FSFS technique was integrated with data normalization,encoding,balancing,and feature importance selection processes,accuracies improved to 100.00%,97.81%,98.63%,98.94%,94.27%,and 98.46%,respectively.The FSFS method,with a computational complexity of O(fn log n),demonstrates robust scalability and is well-suited for datasets of large size,ensuring efficient processing even when the number of features is substantial.By automatically eliminating outliers and redundant data,FSFS reduces computational overhead,resulting in faster training and improved model performance.Overall,the FSFS framework not only optimizes performance but also enhances the interpretability and explainability of data-driven models,thereby facilitating more trustworthy decision-making in AI applications.展开更多
To comprehensively utilize the valuable geological map,exploration profile,borehole,and geochemical logging data and the knowledge on the formation of the Jinshan Ag-Au deposit for forecasting the exploration targets ...To comprehensively utilize the valuable geological map,exploration profile,borehole,and geochemical logging data and the knowledge on the formation of the Jinshan Ag-Au deposit for forecasting the exploration targets of concealed ore bodies,three-dimensional Mineral Prospectivity Modeling(MPM)of the deposit has been conducted using the weights-of-evidence(WofE)method.Conditional independence between evidence layers was tested,and the outline results using the prediction-volume(P-V)and Student's t-statistic methods for delineating favorable mineralization areas from continuous posterior probability map were critically compared.Four exploration targets delineated ultimately by the Student's t-statistic method for the discovery of minable ore bodies in each of the target areas were discussed in detail.The main conclusions include:(1)three-dimensional modeling of a deposit using multi-source reconnaissance data is useful for MPM in interpreting their relationships with known ore bodies;(2)WofE modeling can be used as a straightforward tool for integrating deposit model and reconnaissance data in MPM;(3)the Student's t-statistic method is more applicable in binarizing the continuous prospectivity map for exploration targeting than the PV approach;and(4)two target areas within high potential to find undiscovered ore bodies were diagnosed to guide future near-mine exploration activities of the Jinshan deposit.展开更多
Satellite Component Layout Optimization(SCLO) is crucial in satellite system design.This paper proposes a novel Satellite Three-Dimensional Component Assignment and Layout Optimization(3D-SCALO) problem tailored to en...Satellite Component Layout Optimization(SCLO) is crucial in satellite system design.This paper proposes a novel Satellite Three-Dimensional Component Assignment and Layout Optimization(3D-SCALO) problem tailored to engineering requirements, aiming to optimize satellite heat dissipation while considering constraints on static stability, 3D geometric relationships between components, and special component positions. The 3D-SCALO problem is a challenging bilevel combinatorial optimization task, involving the optimization of discrete component assignment variables in the outer layer and continuous component position variables in the inner layer,with both influencing each other. To address this issue, first, a Mixed Integer Programming(MIP) model is proposed, which reformulates the original bilevel problem into a single-level optimization problem, enabling the exploration of a more comprehensive optimization space while avoiding iterative nested optimization. Then, to model the 3D geometric relationships between components within the MIP framework, a linearized 3D Phi-function method is proposed, which handles non-overlapping and safety distance constraints between cuboid components in an explicit and effective way. Subsequently, the Finite-Rectangle Method(FRM) is proposed to manage 3D geometric constraints for complex-shaped components by approximating them with a finite set of cuboids, extending the applicability of the geometric modeling approach. Finally, the feasibility and effectiveness of the proposed MIP model are demonstrated through two numerical examples"and a real-world engineering case, which confirms its suitability for complex-shaped components and real engineering applications.展开更多
Detecting cyber attacks in networks connected to the Internet of Things(IoT)is of utmost importance because of the growing vulnerabilities in the smart environment.Conventional models,such as Naive Bayes and support v...Detecting cyber attacks in networks connected to the Internet of Things(IoT)is of utmost importance because of the growing vulnerabilities in the smart environment.Conventional models,such as Naive Bayes and support vector machine(SVM),as well as ensemble methods,such as Gradient Boosting and eXtreme gradient boosting(XGBoost),are often plagued by high computational costs,which makes it challenging for them to perform real-time detection.In this regard,we suggested an attack detection approach that integrates Visual Geometry Group 16(VGG16),Artificial Rabbits Optimizer(ARO),and Random Forest Model to increase detection accuracy and operational efficiency in Internet of Things(IoT)networks.In the suggested model,the extraction of features from malware pictures was accomplished with the help of VGG16.The prediction process is carried out by the random forest model using the extracted features from the VGG16.Additionally,ARO is used to improve the hyper-parameters of the random forest model of the random forest.With an accuracy of 96.36%,the suggested model outperforms the standard models in terms of accuracy,F1-score,precision,and recall.The comparative research highlights our strategy’s success,which improves performance while maintaining a lower computational cost.This method is ideal for real-time applications,but it is effective.展开更多
Selecting proper descriptors(also known feature selection,FS)is key in the process of establishing mechanical properties prediction model of hot-rolled microalloyed steels by using machine learning(ML)algorithm.FS met...Selecting proper descriptors(also known feature selection,FS)is key in the process of establishing mechanical properties prediction model of hot-rolled microalloyed steels by using machine learning(ML)algorithm.FS methods based on data-driving can reduce the redundancy of data features and improve the prediction accuracy of mechanical properties.Based on the collected data of hot-rolled microalloyed steels,the association rules are used to mine the correlation information between the data.High-quality feature subsets are selected by the proposed FS method(FS method based on genetic algorithm embedding,GAMIC).Compared with the common FS method,it is shown on dataset that GAMIC selects feature subsets more appropriately.Six different ML algorithms are trained and tested for mechanical properties prediction.The result shows that the root-mean-square error of yield strength,tensile strength and elongation based on limit gradient enhancement(XGBoost)algorithm is 21.95 MPa,20.85 MPa and 1.96%,the correlation coefficient(R^(2))is 0.969,0.968 and 0.830,and the mean absolute error is 16.84 MPa,15.83 MPa and 1.48%,respectively,showing the best prediction performance.Finally,SHapley Additive exPlanation is used to further explore the influence of feature variables on mechanical properties.GAMIC feature selection method proposed is universal,which provides a basis for the development of high-precision mechanical property prediction model.展开更多
The authors regret that the original publication of this paper did not include Jawad Fayaz as a co-author.After further discussions and a thorough review of the research contributions,it was agreed that his significan...The authors regret that the original publication of this paper did not include Jawad Fayaz as a co-author.After further discussions and a thorough review of the research contributions,it was agreed that his significant contributions to the foundational aspects of the research warranted recognition,and he has now been added as a co-author.展开更多
Currently,there are a limited number of dynamic models available for braided composite plates with large overall motions,despite the incorporation of three-dimensional(3D)braided composites into rotating blade compone...Currently,there are a limited number of dynamic models available for braided composite plates with large overall motions,despite the incorporation of three-dimensional(3D)braided composites into rotating blade components.In this paper,a dynamic model of 3D 4-directional braided composite thin plates considering braiding directions is established.Based on Kirchhoff's plate assumptions,the displacement variables of the plate are expressed.By incorporating the braiding directions into the constitutive equation of the braided composites,the dynamic model of the plate considering braiding directions is obtained.The effects of the speeds,braiding directions,and braided angles on the responses of the plate with fixed-axis rotation and translational motion,respectively,are investigated.This paper presents a dynamic theory for calculating the deformation of 3D braided composite structures undergoing both translational and rotational motions.It also provides a simulation method for investigating the dynamic behavior of non-isotropic material plates in various applications.展开更多
In this paper,a feature selection method for determining input parameters in antenna modeling is proposed.In antenna modeling,the input feature of artificial neural network(ANN)is geometric parameters.The selection cr...In this paper,a feature selection method for determining input parameters in antenna modeling is proposed.In antenna modeling,the input feature of artificial neural network(ANN)is geometric parameters.The selection criteria contain correlation and sensitivity between the geometric parameter and the electromagnetic(EM)response.Maximal information coefficient(MIC),an exploratory data mining tool,is introduced to evaluate both linear and nonlinear correlations.The EM response range is utilized to evaluate the sensitivity.The wide response range corresponding to varying values of a parameter implies the parameter is highly sensitive and the narrow response range suggests the parameter is insensitive.Only the parameter which is highly correlative and sensitive is selected as the input of ANN,and the sampling space of the model is highly reduced.The modeling of a wideband and circularly polarized antenna is studied as an example to verify the effectiveness of the proposed method.The number of input parameters decreases from8 to 4.The testing errors of|S_(11)|and axis ratio are reduced by8.74%and 8.95%,respectively,compared with the ANN with no feature selection.展开更多
The development of digital twins for geotechnical structures necessitates the real-time updates of threedimensional(3D)virtual models(e.g.numerical finite element method(FEM)model)to accurately predict time-varying ge...The development of digital twins for geotechnical structures necessitates the real-time updates of threedimensional(3D)virtual models(e.g.numerical finite element method(FEM)model)to accurately predict time-varying geotechnical responses(e.g.consolidation settlement)in a 3D spatial domain.However,traditional 3D numerical model updating approaches are computationally prohibitive and therefore difficult to update the 3D responses in real time.To address these challenges,this study proposes a novel machine learning framework called sparse dictionary learning(T-3D-SDL)for real-time updating of time-varying 3D geotechnical responses.In T-3D-SDL,a concerned dataset(e.g.time-varying 3D settlement)is approximated as a linear superposition of dictionary atoms generated from 3D random FEM analyses.Field monitoring data are then used to identify non-trivial atoms and estimate their weights within a Bayesian framework for model updating and prediction.The proposed approach enables the real-time update of temporally varying settlements with a high 3D spatial resolution and quantified uncertainty as field monitoring data evolve.The proposed approach is illustrated using an embankment construction project.The results show that the proposed approach effectively improves settlement predictions along temporal and 3D spatial dimensions,with minimal latency(e.g.within minutes),as monitoring data appear.In addition,the proposed approach requires only a reasonably small number of 3D FEM model evaluations,avoids the use of widely adopted yet often criticized surrogate models,and effectively addresses the limitations(e.g.computational inefficiency)of existing 3D model updating approaches.展开更多
Cleats are the dominant micro-fracture network controlling the macro-mechanical behavior of coal.Improved understanding of the spatial characteristics of cleat networks is therefore important to the coal mining indust...Cleats are the dominant micro-fracture network controlling the macro-mechanical behavior of coal.Improved understanding of the spatial characteristics of cleat networks is therefore important to the coal mining industry.Discrete fracture networks(DFNs)are increasingly used in engineering analyses to spatially model fractures at various scales.The reliability of coal DFNs largely depends on the confidence in the input cleat statistics.Estimates of these parameters can be made from image-based three-dimensional(3D)characterization of coal cleats using X-ray micro-computed tomography(m CT).One key step in this process,after cleat extraction,is the separation of individual cleats,without which the cleats are a connected network and statistics for different cleat sets cannot be measured.In this paper,a feature extraction-based image processing method is introduced to identify and separate distinct cleat groups from 3D X-ray m CT images.Kernels(filters)representing explicit cleat features of coal are built and cleat separation is successfully achieved by convolutional operations on 3D coal images.The new method is applied to a coal specimen with 80 mm in diameter and 100 mm in length acquired from an Anglo American Steelmaking Coal mine in the Bowen Basin,Queensland,Australia.It is demonstrated that the new method produces reliable cleat separation capable of defining individual cleats and preserving 3D topology after separation.Bedding-parallel fractures are also identified and separated,which has his-torically been challenging to delineate and rarely reported.A variety of cleat/fracture statistics is measured which not only can quantitatively characterize the cleat/fracture system but also can be used for DFN modeling.Finally,variability and heterogeneity with respect to the core axis are investigated.Significant heterogeneity is observed and suggests that the representative elementary volume(REV)of the cleat groups for engineering purposes may be a complex problem requiring careful consideration.展开更多
Aerodynamic surrogate modeling mostly relies only on integrated loads data obtained from simulation or experiment,while neglecting and wasting the valuable distributed physical information on the surface.To make full ...Aerodynamic surrogate modeling mostly relies only on integrated loads data obtained from simulation or experiment,while neglecting and wasting the valuable distributed physical information on the surface.To make full use of both integrated and distributed loads,a modeling paradigm,called the heterogeneous data-driven aerodynamic modeling,is presented.The essential concept is to incorporate the physical information of distributed loads as additional constraints within the end-to-end aerodynamic modeling.Towards heterogenous data,a novel and easily applicable physical feature embedding modeling framework is designed.This framework extracts lowdimensional physical features from pressure distribution and then effectively enhances the modeling of the integrated loads via feature embedding.The proposed framework can be coupled with multiple feature extraction methods,and the well-performed generalization capabilities over different airfoils are verified through a transonic case.Compared with traditional direct modeling,the proposed framework can reduce testing errors by almost 50%.Given the same prediction accuracy,it can save more than half of the training samples.Furthermore,the visualization analysis has revealed a significant correlation between the discovered low-dimensional physical features and the heterogeneous aerodynamic loads,which shows the interpretability and credibility of the superior performance offered by the proposed deep learning framework.展开更多
Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of...Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.展开更多
Hypoxia is a typical feature of the tumor microenvironment,one of the most critical factors affecting cell behavior and tumor progression.However,the lack of tumor models able to precisely emulate natural brain tumor ...Hypoxia is a typical feature of the tumor microenvironment,one of the most critical factors affecting cell behavior and tumor progression.However,the lack of tumor models able to precisely emulate natural brain tumor tissue has impeded the study of the effects of hypoxia on the progression and growth of tumor cells.This study reports a three-dimensional(3D)brain tumor model obtained by encapsulating U87MG(U87)cells in a hydrogel containing type I collagen.It also documents the effect of various oxygen concentrations(1%,7%,and 21%)in the culture environment on U87 cell morphology,proliferation,viability,cell cycle,apoptosis rate,and migration.Finally,it compares two-dimensional(2D)and 3D cultures.For comparison purposes,cells cultured in flat culture dishes were used as the control(2D model).Cells cultured in the 3D model proliferated more slowly but had a higher apoptosis rate and proportion of cells in the resting phase(G0 phase)/gap I phase(G1 phase)than those cultured in the 2D model.Besides,the two models yielded significantly different cell morphologies.Finally,hypoxia(e.g.,1%O2)affected cell morphology,slowed cell growth,reduced cell viability,and increased the apoptosis rate in the 3D model.These results indicate that the constructed 3D model is effective for investigating the effects of biological and chemical factors on cell morphology and function,and can be more representative of the tumor microenvironment than 2D culture systems.The developed 3D glioblastoma tumor model is equally applicable to other studies in pharmacology and pathology.展开更多
Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the heart.Numerous researchers have made progress in correcting and predicting early heart d...Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the heart.Numerous researchers have made progress in correcting and predicting early heart disease,but more remains to be accomplished.The diagnostic accuracy of many current studies is inadequate due to the attempt to predict patients with heart disease using traditional approaches.By using data fusion from several regions of the country,we intend to increase the accuracy of heart disease prediction.A statistical approach that promotes insights triggered by feature interactions to reveal the intricate pattern in the data,which cannot be adequately captured by a single feature.We processed the data using techniques including feature scaling,outlier detection and replacement,null and missing value imputation,and more to improve the data quality.Furthermore,the proposed feature engineering method uses the correlation test for numerical features and the chi-square test for categorical features to interact with the feature.To reduce the dimensionality,we subsequently used PCA with 95%variation.To identify patients with heart disease,hyperparameter-based machine learning algorithms like RF,XGBoost,Gradient Boosting,LightGBM,CatBoost,SVM,and MLP are utilized,along with ensemble models.The model’s overall prediction performance ranges from 88%to 92%.In order to attain cutting-edge results,we then used a 1D CNN model,which significantly enhanced the prediction with an accuracy score of 96.36%,precision of 96.45%,recall of 96.36%,specificity score of 99.51%and F1 score of 96.34%.The RF model produces the best results among all the classifiers in the evaluation matrix without feature interaction,with accuracy of 90.21%,precision of 90.40%,recall of 90.86%,specificity of 90.91%,and F1 score of 90.63%.Our proposed 1D CNN model is 7%superior to the one without feature engineering when compared to the suggested approach.This illustrates how interaction-focused feature analysis can produce precise and useful insights for heart disease diagnosis.展开更多
In the field of automated fruit harvesting,precise and efficient fruit target recognition and localization play a pivotal role in enhancing the efficiency of harvesting robots.However,this domain faces two core challe...In the field of automated fruit harvesting,precise and efficient fruit target recognition and localization play a pivotal role in enhancing the efficiency of harvesting robots.However,this domain faces two core challenges:firstly,the dynamic nature of the automatic picking process requires fruit target detection algorithms to adapt to multi-view characteristics,ensuring effective recognition of the same fruit from different perspectives.Secondly,fruits in natural environments often suffer from interference factors such as overlapping,occlusion,and illumination fluctuations,which increase the difficulty of image capture and recognition.To address these challenges,this study conducted an in-depth analysis of the key features in fruit recognition and discovered that the stem,body,and base serve as constant and core information in fruit identification,exhibiting long-term dependent semantic relationships during the recognition process.These invariant features provide a stable foundation for dynamic fruit recognition,contributing to improved recognition accuracy and robustness.Specifically,the morphology and position of the stem,body,and base are relatively fixed,and the effective extraction of these features plays a crucial role in fruit recognition.This paper proposes a novel model,TransSSA,and designs two innovative modules to effectively extract fruit image features.The Self-Attention Core Feature Extraction(SAF)module integrates YOLOV8 and Swin Transformer as backbone networks and introduces the Shuffle Attention self-attention mechanism,significantly enhancing the ability to extract core features.This module focuses on constant features such as the stem,body,and base,ensuring accurate fruit recognition in different environments.On the other hand,the Squeeze and Excitation Aggregation(SAE)module combines the network’s ability to capture channel patterns with global knowledge,further optimizing the extraction of effective features.Additionally,to improve detection accuracy,this studymodifies the regression loss function to EIOU.To validate the effectiveness of the TransSSA model,this study conducted extensive visualization analysis to support the interpretability of the SAF and SAE modules.Experimental results demonstrate that TransSSA achieves a performance of 91.3%on a tomato dataset,fully proving its innovative capabilities.Through this research,we provide amore effective solution for using fruit harvesting robots in complex environments.展开更多
In the Visual Place Recognition(VPR)task,existing research has leveraged large-scale pre-trained models to improve the performance of place recognition.However,when there are significant environmental differences betw...In the Visual Place Recognition(VPR)task,existing research has leveraged large-scale pre-trained models to improve the performance of place recognition.However,when there are significant environmental differences between query images and reference images,a large number of ineffective local features will interfere with the extraction of key landmark features,leading to the retrieval of visually similar but geographically different images.To address this perceptual aliasing problem caused by environmental condition changes,we propose a novel Visual Place Recognition method with Cross-Environment Robust Feature Enhancement(CerfeVPR).This method uses the GAN network to generate similar images of the original images under different environmental conditions,thereby enhancing the learning of robust features of the original images.This enables the global descriptor to effectively ignore appearance changes caused by environmental factors such as seasons and lighting,showing better place recognition accuracy than other methods.Meanwhile,we introduce a large kernel convolution adapter to fine tune the pre-trained model,obtaining a better image feature representation for subsequent robust feature learning.Then,we process the information of different local regions in the general features through a 3-layer pyramid scene parsing network and fuse it with a tag that retains global information to construct a multi-dimensional image feature representation.Based on this,we use the fused features of similar images to drive the robust feature learning of the original images and complete the feature matching between query images and retrieved images.Experiments on multiple commonly used datasets show that our method exhibits excellent performance.On average,CerfeVPR achieves the highest results,with all Recall@N values exceeding 90%.In particular,on the highly challenging Nordland dataset,the R@1 metric is improved by 4.6%,significantly outperforming other methods,which fully verifies the superiority of CerfeVPR in visual place recognition under complex environments.展开更多
Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation technologies.Current methods for extracting features from mesh edges or ...Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation technologies.Current methods for extracting features from mesh edges or faces struggle with complex 3D models because edge-based approaches miss global contexts and face-based methods overlook variations in adjacent areas,which affects the overall precision.To address these issues,we propose the Feature Discrimination and Context Propagation Network(FDCPNet),which is a novel approach that synergistically integrates local and global features in mesh datasets.Methods FDCPNet is composed of two modules:(1)the Feature Discrimination Module,which employs an attention mechanism to enhance the identification of key local features,and(2)the Context Propagation Module,which enriches key local features by integrating global contextual information,thereby facilitating a more detailed and comprehensive representation of crucial areas within the mesh model.Results Experiments on popular datasets validated the effectiveness of FDCPNet,showing an improvement in the classification accuracy over the baseline MeshNet.Furthermore,even with reduced mesh face numbers and limited training data,FDCPNet achieved promising results,demonstrating its robustness in scenarios of variable complexity.展开更多
Kernel-based slow feature analysis(SFA)methods have been successfully applied in the industrial process fault detection field.However,kernel-based SFA methods have high computational complexity as dealing with nonline...Kernel-based slow feature analysis(SFA)methods have been successfully applied in the industrial process fault detection field.However,kernel-based SFA methods have high computational complexity as dealing with nonlinearity,leading to delays in detecting time-varying data features.Additionally,the uncertain kernel function and kernel parameters limit the ability of the extracted features to express process characteristics,resulting in poor fault detection performance.To alleviate the above problems,a novel randomized auto-regressive dynamic slow feature analysis(RRDSFA)method is proposed to simultaneously monitor the operating point deviations and process dynamic faults,enabling real-time monitoring of data features in industrial processes.Firstly,the proposed Random Fourier mappingbased method achieves more effective nonlinear transformation,contrasting with the current kernelbased RDSFA algorithm that may lead to significant computational complexity.Secondly,a randomized RDSFA model is developed to extract nonlinear dynamic slow features.Furthermore,a Bayesian inference-based overall fault monitoring model including all RRDSFA sub-models is developed to overcome the randomness of random Fourier mapping.Finally,the superiority and effectiveness of the proposed monitoring method are demonstrated through a numerical case and a simulation of continuous stirred tank reactor.展开更多
Deep Underground Science and Engineering(DUSE)is pleased to release this issue with feature articles reporting the advancement in several research topics related to deep underground.This issue contains one perspective...Deep Underground Science and Engineering(DUSE)is pleased to release this issue with feature articles reporting the advancement in several research topics related to deep underground.This issue contains one perspective article,two review articles,six research articles,and one case study article.These articles focus on underground energy storage,multiscale modeling for correlation between micro-scale damage and macro-scale structural degradation,mineralization and formation of gold mine,interface and fracture seepage,experimental study on tunnel-sand-pile interaction,and high water-content materials for deep underground space backfilling,analytical solutions for the crack evolution direction in brittle rocks,and a case study on the squeezing-induced failure in a water drainage tunnel and the rehabilitation measures.展开更多
Soil moisture is a key parameter in the exchange of energy and water between the land surface and the atmosphere.This parameter plays an important role in the dynamics of permafrost on the Qinghai-Xizang Plateau,China...Soil moisture is a key parameter in the exchange of energy and water between the land surface and the atmosphere.This parameter plays an important role in the dynamics of permafrost on the Qinghai-Xizang Plateau,China,as well as in the related ecological and hydrological processes.However,the region's complex terrain and extreme climatic conditions result in low-accuracy soil moisture estimations using traditional remote sensing techniques.Thus,this study considered parameters of the backscatter coefficient of Sentinel-1A ground range detected(GRD)data,the polarization decomposition parameters of Sentinel-1A single-look complex(SLC)data,the normalized difference vegetation index(NDVI)based on Sentinel-2B data,and the topographic factors based on digital elevation model(DEM)data.By combining these parameters with a machine learning model,we established a feature selection rule.A cumulative importance threshold was derived for feature variables,and those variables that failed to meet the threshold were eliminated based on variations in the coefficient of determination(R^(2))and the unbiased root mean square error(ubRMSE).The eight most influential variables were selected and combined with the CatBoost model for soil moisture inversion,and the SHapley Additive exPlanations(SHAP)method was used to analyze the importance of these variables.The results demonstrated that the optimized model significantly improved the accuracy of soil moisture inversion.Compared to the unfiltered model,the optimal feature combination led to a 0.09 increase in R^(2)and a 0.7%reduction in ubRMSE.Ultimately,the optimized model achieved a R²of 0.87 and an ubRMSE of 5.6%.Analysis revealed that soil particle size had significant impact on soil water retention capacity.The impact of vegetation on the estimated soil moisture on the Qinghai-Xizang Plateau was considerable,demonstrating a significant positive correlation.Moreover,the microtopographical features of hummocks interfered with soil moisture estimation,indicating that such terrain effects warrant increased attention in future studies within the permafrost regions.The developed method not only enhances the accuracy of soil moisture retrieval in the complex terrain of the Qinghai-Xizang Plateau,but also exhibits high computational efficiency(with a relative time reduction of 18.5%),striking an excellent balance between accuracy and efficiency.This approach provides a robust framework for efficient soil moisture monitoring in remote areas with limited ground data,offering critical insights for ecological conservation,water resource management,and climate change adaptation on the Qinghai-Xizang Plateau.展开更多
文摘Feature selection(FS)is a pivotal pre-processing step in developing data-driven models,influencing reliability,performance and optimization.Although existing FS techniques can yield high-performance metrics for certain models,they do not invariably guarantee the extraction of the most critical or impactful features.Prior literature underscores the significance of equitable FS practices and has proposed diverse methodologies for the identification of appropriate features.However,the challenge of discerning the most relevant and influential features persists,particularly in the context of the exponential growth and heterogeneity of big data—a challenge that is increasingly salient in modern artificial intelligence(AI)applications.In response,this study introduces an innovative,automated statistical method termed Farea Similarity for Feature Selection(FSFS).The FSFS approach computes a similarity metric for each feature by benchmarking it against the record-wise mean,thereby finding feature dependencies and mitigating the influence of outliers that could potentially distort evaluation outcomes.Features are subsequently ranked according to their similarity scores,with the threshold established at the average similarity score.Notably,lower FSFS values indicate higher similarity and stronger data correlations,whereas higher values suggest lower similarity.The FSFS method is designed not only to yield reliable evaluation metrics but also to reduce data complexity without compromising model performance.Comparative analyses were performed against several established techniques,including Chi-squared(CS),Correlation Coefficient(CC),Genetic Algorithm(GA),Exhaustive Approach,Greedy Stepwise Approach,Gain Ratio,and Filtered Subset Eval,using a variety of datasets such as the Experimental Dataset,Breast Cancer Wisconsin(Original),KDD CUP 1999,NSL-KDD,UNSW-NB15,and Edge-IIoT.In the absence of the FSFS method,the highest classifier accuracies observed were 60.00%,95.13%,97.02%,98.17%,95.86%,and 94.62%for the respective datasets.When the FSFS technique was integrated with data normalization,encoding,balancing,and feature importance selection processes,accuracies improved to 100.00%,97.81%,98.63%,98.94%,94.27%,and 98.46%,respectively.The FSFS method,with a computational complexity of O(fn log n),demonstrates robust scalability and is well-suited for datasets of large size,ensuring efficient processing even when the number of features is substantial.By automatically eliminating outliers and redundant data,FSFS reduces computational overhead,resulting in faster training and improved model performance.Overall,the FSFS framework not only optimizes performance but also enhances the interpretability and explainability of data-driven models,thereby facilitating more trustworthy decision-making in AI applications.
基金financially supported by the Ministry of Science and Technology of China(Nos.2022YFF0801201,2021YFC2900300)the National Natural Science Foundation of China(Nos.41872245,U1911202)the Guangdong Basic and Applied Basic Research Foundation(No.2020A1515010666)。
文摘To comprehensively utilize the valuable geological map,exploration profile,borehole,and geochemical logging data and the knowledge on the formation of the Jinshan Ag-Au deposit for forecasting the exploration targets of concealed ore bodies,three-dimensional Mineral Prospectivity Modeling(MPM)of the deposit has been conducted using the weights-of-evidence(WofE)method.Conditional independence between evidence layers was tested,and the outline results using the prediction-volume(P-V)and Student's t-statistic methods for delineating favorable mineralization areas from continuous posterior probability map were critically compared.Four exploration targets delineated ultimately by the Student's t-statistic method for the discovery of minable ore bodies in each of the target areas were discussed in detail.The main conclusions include:(1)three-dimensional modeling of a deposit using multi-source reconnaissance data is useful for MPM in interpreting their relationships with known ore bodies;(2)WofE modeling can be used as a straightforward tool for integrating deposit model and reconnaissance data in MPM;(3)the Student's t-statistic method is more applicable in binarizing the continuous prospectivity map for exploration targeting than the PV approach;and(4)two target areas within high potential to find undiscovered ore bodies were diagnosed to guide future near-mine exploration activities of the Jinshan deposit.
基金supported by the National Natural Science Foundation of China(No.92371206)the Postgraduate Scientific Research Innovation Project of Hunan Province,China(No.CX2023063).
文摘Satellite Component Layout Optimization(SCLO) is crucial in satellite system design.This paper proposes a novel Satellite Three-Dimensional Component Assignment and Layout Optimization(3D-SCALO) problem tailored to engineering requirements, aiming to optimize satellite heat dissipation while considering constraints on static stability, 3D geometric relationships between components, and special component positions. The 3D-SCALO problem is a challenging bilevel combinatorial optimization task, involving the optimization of discrete component assignment variables in the outer layer and continuous component position variables in the inner layer,with both influencing each other. To address this issue, first, a Mixed Integer Programming(MIP) model is proposed, which reformulates the original bilevel problem into a single-level optimization problem, enabling the exploration of a more comprehensive optimization space while avoiding iterative nested optimization. Then, to model the 3D geometric relationships between components within the MIP framework, a linearized 3D Phi-function method is proposed, which handles non-overlapping and safety distance constraints between cuboid components in an explicit and effective way. Subsequently, the Finite-Rectangle Method(FRM) is proposed to manage 3D geometric constraints for complex-shaped components by approximating them with a finite set of cuboids, extending the applicability of the geometric modeling approach. Finally, the feasibility and effectiveness of the proposed MIP model are demonstrated through two numerical examples"and a real-world engineering case, which confirms its suitability for complex-shaped components and real engineering applications.
基金funded by Institutional Fund Projects under grant no.(IFPDP-261-22)。
文摘Detecting cyber attacks in networks connected to the Internet of Things(IoT)is of utmost importance because of the growing vulnerabilities in the smart environment.Conventional models,such as Naive Bayes and support vector machine(SVM),as well as ensemble methods,such as Gradient Boosting and eXtreme gradient boosting(XGBoost),are often plagued by high computational costs,which makes it challenging for them to perform real-time detection.In this regard,we suggested an attack detection approach that integrates Visual Geometry Group 16(VGG16),Artificial Rabbits Optimizer(ARO),and Random Forest Model to increase detection accuracy and operational efficiency in Internet of Things(IoT)networks.In the suggested model,the extraction of features from malware pictures was accomplished with the help of VGG16.The prediction process is carried out by the random forest model using the extracted features from the VGG16.Additionally,ARO is used to improve the hyper-parameters of the random forest model of the random forest.With an accuracy of 96.36%,the suggested model outperforms the standard models in terms of accuracy,F1-score,precision,and recall.The comparative research highlights our strategy’s success,which improves performance while maintaining a lower computational cost.This method is ideal for real-time applications,but it is effective.
基金supported by the National Key Research and Development Program of China(Grant No.2021YFB3702404)the National Natural Science Foundation of China(Grant No.52104370)+4 种基金the Reviving-Liaoning Excellence Plan(XLYC2203186)Science and Technology Special Projects of Liaoning Province(Grant No.2022JH25/10200001)the Postdoctoral Research Fund for Northeastern(Grant No.20210203)Independent Projects of Basic Scientific Research(ZZ2021005)CITIC Niobium Steel Development Award Fund(2022-M1824).
文摘Selecting proper descriptors(also known feature selection,FS)is key in the process of establishing mechanical properties prediction model of hot-rolled microalloyed steels by using machine learning(ML)algorithm.FS methods based on data-driving can reduce the redundancy of data features and improve the prediction accuracy of mechanical properties.Based on the collected data of hot-rolled microalloyed steels,the association rules are used to mine the correlation information between the data.High-quality feature subsets are selected by the proposed FS method(FS method based on genetic algorithm embedding,GAMIC).Compared with the common FS method,it is shown on dataset that GAMIC selects feature subsets more appropriately.Six different ML algorithms are trained and tested for mechanical properties prediction.The result shows that the root-mean-square error of yield strength,tensile strength and elongation based on limit gradient enhancement(XGBoost)algorithm is 21.95 MPa,20.85 MPa and 1.96%,the correlation coefficient(R^(2))is 0.969,0.968 and 0.830,and the mean absolute error is 16.84 MPa,15.83 MPa and 1.48%,respectively,showing the best prediction performance.Finally,SHapley Additive exPlanation is used to further explore the influence of feature variables on mechanical properties.GAMIC feature selection method proposed is universal,which provides a basis for the development of high-precision mechanical property prediction model.
文摘The authors regret that the original publication of this paper did not include Jawad Fayaz as a co-author.After further discussions and a thorough review of the research contributions,it was agreed that his significant contributions to the foundational aspects of the research warranted recognition,and he has now been added as a co-author.
基金Project supported by the National Natural Science Foundation of China(Nos.12372071 and 12372070)the Aeronautical Science Fund of China(No.2022Z055052001)the Foundation of China Scholarship Council(No.202306830079)。
文摘Currently,there are a limited number of dynamic models available for braided composite plates with large overall motions,despite the incorporation of three-dimensional(3D)braided composites into rotating blade components.In this paper,a dynamic model of 3D 4-directional braided composite thin plates considering braiding directions is established.Based on Kirchhoff's plate assumptions,the displacement variables of the plate are expressed.By incorporating the braiding directions into the constitutive equation of the braided composites,the dynamic model of the plate considering braiding directions is obtained.The effects of the speeds,braiding directions,and braided angles on the responses of the plate with fixed-axis rotation and translational motion,respectively,are investigated.This paper presents a dynamic theory for calculating the deformation of 3D braided composite structures undergoing both translational and rotational motions.It also provides a simulation method for investigating the dynamic behavior of non-isotropic material plates in various applications.
基金National Natural Science Foundation of China(62161048)Sichuan Science and Technology Program(2022NSFSC0547,2022ZYD0109)。
文摘In this paper,a feature selection method for determining input parameters in antenna modeling is proposed.In antenna modeling,the input feature of artificial neural network(ANN)is geometric parameters.The selection criteria contain correlation and sensitivity between the geometric parameter and the electromagnetic(EM)response.Maximal information coefficient(MIC),an exploratory data mining tool,is introduced to evaluate both linear and nonlinear correlations.The EM response range is utilized to evaluate the sensitivity.The wide response range corresponding to varying values of a parameter implies the parameter is highly sensitive and the narrow response range suggests the parameter is insensitive.Only the parameter which is highly correlative and sensitive is selected as the input of ANN,and the sampling space of the model is highly reduced.The modeling of a wideband and circularly polarized antenna is studied as an example to verify the effectiveness of the proposed method.The number of input parameters decreases from8 to 4.The testing errors of|S_(11)|and axis ratio are reduced by8.74%and 8.95%,respectively,compared with the ANN with no feature selection.
基金supported by a grant from the Research Grant Council of Hong Kong Special Administrative Region(Project No.11207724).
文摘The development of digital twins for geotechnical structures necessitates the real-time updates of threedimensional(3D)virtual models(e.g.numerical finite element method(FEM)model)to accurately predict time-varying geotechnical responses(e.g.consolidation settlement)in a 3D spatial domain.However,traditional 3D numerical model updating approaches are computationally prohibitive and therefore difficult to update the 3D responses in real time.To address these challenges,this study proposes a novel machine learning framework called sparse dictionary learning(T-3D-SDL)for real-time updating of time-varying 3D geotechnical responses.In T-3D-SDL,a concerned dataset(e.g.time-varying 3D settlement)is approximated as a linear superposition of dictionary atoms generated from 3D random FEM analyses.Field monitoring data are then used to identify non-trivial atoms and estimate their weights within a Bayesian framework for model updating and prediction.The proposed approach enables the real-time update of temporally varying settlements with a high 3D spatial resolution and quantified uncertainty as field monitoring data evolve.The proposed approach is illustrated using an embankment construction project.The results show that the proposed approach effectively improves settlement predictions along temporal and 3D spatial dimensions,with minimal latency(e.g.within minutes),as monitoring data appear.In addition,the proposed approach requires only a reasonably small number of 3D FEM model evaluations,avoids the use of widely adopted yet often criticized surrogate models,and effectively addresses the limitations(e.g.computational inefficiency)of existing 3D model updating approaches.
文摘Cleats are the dominant micro-fracture network controlling the macro-mechanical behavior of coal.Improved understanding of the spatial characteristics of cleat networks is therefore important to the coal mining industry.Discrete fracture networks(DFNs)are increasingly used in engineering analyses to spatially model fractures at various scales.The reliability of coal DFNs largely depends on the confidence in the input cleat statistics.Estimates of these parameters can be made from image-based three-dimensional(3D)characterization of coal cleats using X-ray micro-computed tomography(m CT).One key step in this process,after cleat extraction,is the separation of individual cleats,without which the cleats are a connected network and statistics for different cleat sets cannot be measured.In this paper,a feature extraction-based image processing method is introduced to identify and separate distinct cleat groups from 3D X-ray m CT images.Kernels(filters)representing explicit cleat features of coal are built and cleat separation is successfully achieved by convolutional operations on 3D coal images.The new method is applied to a coal specimen with 80 mm in diameter and 100 mm in length acquired from an Anglo American Steelmaking Coal mine in the Bowen Basin,Queensland,Australia.It is demonstrated that the new method produces reliable cleat separation capable of defining individual cleats and preserving 3D topology after separation.Bedding-parallel fractures are also identified and separated,which has his-torically been challenging to delineate and rarely reported.A variety of cleat/fracture statistics is measured which not only can quantitatively characterize the cleat/fracture system but also can be used for DFN modeling.Finally,variability and heterogeneity with respect to the core axis are investigated.Significant heterogeneity is observed and suggests that the representative elementary volume(REV)of the cleat groups for engineering purposes may be a complex problem requiring careful consideration.
基金supported by the National Natural Science Foundation of China(Nos.92152301,12072282)。
文摘Aerodynamic surrogate modeling mostly relies only on integrated loads data obtained from simulation or experiment,while neglecting and wasting the valuable distributed physical information on the surface.To make full use of both integrated and distributed loads,a modeling paradigm,called the heterogeneous data-driven aerodynamic modeling,is presented.The essential concept is to incorporate the physical information of distributed loads as additional constraints within the end-to-end aerodynamic modeling.Towards heterogenous data,a novel and easily applicable physical feature embedding modeling framework is designed.This framework extracts lowdimensional physical features from pressure distribution and then effectively enhances the modeling of the integrated loads via feature embedding.The proposed framework can be coupled with multiple feature extraction methods,and the well-performed generalization capabilities over different airfoils are verified through a transonic case.Compared with traditional direct modeling,the proposed framework can reduce testing errors by almost 50%.Given the same prediction accuracy,it can save more than half of the training samples.Furthermore,the visualization analysis has revealed a significant correlation between the discovered low-dimensional physical features and the heterogeneous aerodynamic loads,which shows the interpretability and credibility of the superior performance offered by the proposed deep learning framework.
基金supported in part by the National Natural Science Foundation of China(82072019)the Shenzhen Basic Research Program(JCYJ20210324130209023)+5 种基金the Shenzhen-Hong Kong-Macao S&T Program(Category C)(SGDX20201103095002019)the Mainland-Hong Kong Joint Funding Scheme(MHKJFS)(MHP/005/20),the Project of Strategic Importance Fund(P0035421)the Projects of RISA(P0043001)from the Hong Kong Polytechnic University,the Natural Science Foundation of Jiangsu Province(BK20201441)the Provincial and Ministry Co-constructed Project of Henan Province Medical Science and Technology Research(SBGJ202103038,SBGJ202102056)the Henan Province Key R&D and Promotion Project(Science and Technology Research)(222102310015)the Natural Science Foundation of Henan Province(222300420575),and the Henan Province Science and Technology Research(222102310322).
文摘Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.
基金supported by the National Natural Science Foundation of China (No. 52275291)the Fundamental Research Funds for the Central Universitiesthe Program for Innovation Team of Shaanxi Province,China (No. 2023-CX-TD-17)
文摘Hypoxia is a typical feature of the tumor microenvironment,one of the most critical factors affecting cell behavior and tumor progression.However,the lack of tumor models able to precisely emulate natural brain tumor tissue has impeded the study of the effects of hypoxia on the progression and growth of tumor cells.This study reports a three-dimensional(3D)brain tumor model obtained by encapsulating U87MG(U87)cells in a hydrogel containing type I collagen.It also documents the effect of various oxygen concentrations(1%,7%,and 21%)in the culture environment on U87 cell morphology,proliferation,viability,cell cycle,apoptosis rate,and migration.Finally,it compares two-dimensional(2D)and 3D cultures.For comparison purposes,cells cultured in flat culture dishes were used as the control(2D model).Cells cultured in the 3D model proliferated more slowly but had a higher apoptosis rate and proportion of cells in the resting phase(G0 phase)/gap I phase(G1 phase)than those cultured in the 2D model.Besides,the two models yielded significantly different cell morphologies.Finally,hypoxia(e.g.,1%O2)affected cell morphology,slowed cell growth,reduced cell viability,and increased the apoptosis rate in the 3D model.These results indicate that the constructed 3D model is effective for investigating the effects of biological and chemical factors on cell morphology and function,and can be more representative of the tumor microenvironment than 2D culture systems.The developed 3D glioblastoma tumor model is equally applicable to other studies in pharmacology and pathology.
基金supported by the Competitive Research Fund of the University of Aizu,Japan(Grant No.P-13).
文摘Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the heart.Numerous researchers have made progress in correcting and predicting early heart disease,but more remains to be accomplished.The diagnostic accuracy of many current studies is inadequate due to the attempt to predict patients with heart disease using traditional approaches.By using data fusion from several regions of the country,we intend to increase the accuracy of heart disease prediction.A statistical approach that promotes insights triggered by feature interactions to reveal the intricate pattern in the data,which cannot be adequately captured by a single feature.We processed the data using techniques including feature scaling,outlier detection and replacement,null and missing value imputation,and more to improve the data quality.Furthermore,the proposed feature engineering method uses the correlation test for numerical features and the chi-square test for categorical features to interact with the feature.To reduce the dimensionality,we subsequently used PCA with 95%variation.To identify patients with heart disease,hyperparameter-based machine learning algorithms like RF,XGBoost,Gradient Boosting,LightGBM,CatBoost,SVM,and MLP are utilized,along with ensemble models.The model’s overall prediction performance ranges from 88%to 92%.In order to attain cutting-edge results,we then used a 1D CNN model,which significantly enhanced the prediction with an accuracy score of 96.36%,precision of 96.45%,recall of 96.36%,specificity score of 99.51%and F1 score of 96.34%.The RF model produces the best results among all the classifiers in the evaluation matrix without feature interaction,with accuracy of 90.21%,precision of 90.40%,recall of 90.86%,specificity of 90.91%,and F1 score of 90.63%.Our proposed 1D CNN model is 7%superior to the one without feature engineering when compared to the suggested approach.This illustrates how interaction-focused feature analysis can produce precise and useful insights for heart disease diagnosis.
基金supported in part by the Basic Research Project of Science and Technology Department of Jilin Province,China(Grant No.202002044JC).
文摘In the field of automated fruit harvesting,precise and efficient fruit target recognition and localization play a pivotal role in enhancing the efficiency of harvesting robots.However,this domain faces two core challenges:firstly,the dynamic nature of the automatic picking process requires fruit target detection algorithms to adapt to multi-view characteristics,ensuring effective recognition of the same fruit from different perspectives.Secondly,fruits in natural environments often suffer from interference factors such as overlapping,occlusion,and illumination fluctuations,which increase the difficulty of image capture and recognition.To address these challenges,this study conducted an in-depth analysis of the key features in fruit recognition and discovered that the stem,body,and base serve as constant and core information in fruit identification,exhibiting long-term dependent semantic relationships during the recognition process.These invariant features provide a stable foundation for dynamic fruit recognition,contributing to improved recognition accuracy and robustness.Specifically,the morphology and position of the stem,body,and base are relatively fixed,and the effective extraction of these features plays a crucial role in fruit recognition.This paper proposes a novel model,TransSSA,and designs two innovative modules to effectively extract fruit image features.The Self-Attention Core Feature Extraction(SAF)module integrates YOLOV8 and Swin Transformer as backbone networks and introduces the Shuffle Attention self-attention mechanism,significantly enhancing the ability to extract core features.This module focuses on constant features such as the stem,body,and base,ensuring accurate fruit recognition in different environments.On the other hand,the Squeeze and Excitation Aggregation(SAE)module combines the network’s ability to capture channel patterns with global knowledge,further optimizing the extraction of effective features.Additionally,to improve detection accuracy,this studymodifies the regression loss function to EIOU.To validate the effectiveness of the TransSSA model,this study conducted extensive visualization analysis to support the interpretability of the SAF and SAE modules.Experimental results demonstrate that TransSSA achieves a performance of 91.3%on a tomato dataset,fully proving its innovative capabilities.Through this research,we provide amore effective solution for using fruit harvesting robots in complex environments.
基金supported by Postgraduate Scientific Research Innovation Project of Hunan Province CX20230915National Natural Science Foundation of China under Grant 62472440.
文摘In the Visual Place Recognition(VPR)task,existing research has leveraged large-scale pre-trained models to improve the performance of place recognition.However,when there are significant environmental differences between query images and reference images,a large number of ineffective local features will interfere with the extraction of key landmark features,leading to the retrieval of visually similar but geographically different images.To address this perceptual aliasing problem caused by environmental condition changes,we propose a novel Visual Place Recognition method with Cross-Environment Robust Feature Enhancement(CerfeVPR).This method uses the GAN network to generate similar images of the original images under different environmental conditions,thereby enhancing the learning of robust features of the original images.This enables the global descriptor to effectively ignore appearance changes caused by environmental factors such as seasons and lighting,showing better place recognition accuracy than other methods.Meanwhile,we introduce a large kernel convolution adapter to fine tune the pre-trained model,obtaining a better image feature representation for subsequent robust feature learning.Then,we process the information of different local regions in the general features through a 3-layer pyramid scene parsing network and fuse it with a tag that retains global information to construct a multi-dimensional image feature representation.Based on this,we use the fused features of similar images to drive the robust feature learning of the original images and complete the feature matching between query images and retrieved images.Experiments on multiple commonly used datasets show that our method exhibits excellent performance.On average,CerfeVPR achieves the highest results,with all Recall@N values exceeding 90%.In particular,on the highly challenging Nordland dataset,the R@1 metric is improved by 4.6%,significantly outperforming other methods,which fully verifies the superiority of CerfeVPR in visual place recognition under complex environments.
基金Supported by the National Key R&D Program of China(2022YFC3803600).
文摘Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation technologies.Current methods for extracting features from mesh edges or faces struggle with complex 3D models because edge-based approaches miss global contexts and face-based methods overlook variations in adjacent areas,which affects the overall precision.To address these issues,we propose the Feature Discrimination and Context Propagation Network(FDCPNet),which is a novel approach that synergistically integrates local and global features in mesh datasets.Methods FDCPNet is composed of two modules:(1)the Feature Discrimination Module,which employs an attention mechanism to enhance the identification of key local features,and(2)the Context Propagation Module,which enriches key local features by integrating global contextual information,thereby facilitating a more detailed and comprehensive representation of crucial areas within the mesh model.Results Experiments on popular datasets validated the effectiveness of FDCPNet,showing an improvement in the classification accuracy over the baseline MeshNet.Furthermore,even with reduced mesh face numbers and limited training data,FDCPNet achieved promising results,demonstrating its robustness in scenarios of variable complexity.
基金supported by the Program of National Natural Science Foundation of China(U23A20329,62163036)Youth Academic and Technical Leaders Reserve Talent Training project(202105AC160094)Industrial Innovation Talent Special Project of Xingdian Talent Support Program(XDYC-CYCX-2022-0010).
文摘Kernel-based slow feature analysis(SFA)methods have been successfully applied in the industrial process fault detection field.However,kernel-based SFA methods have high computational complexity as dealing with nonlinearity,leading to delays in detecting time-varying data features.Additionally,the uncertain kernel function and kernel parameters limit the ability of the extracted features to express process characteristics,resulting in poor fault detection performance.To alleviate the above problems,a novel randomized auto-regressive dynamic slow feature analysis(RRDSFA)method is proposed to simultaneously monitor the operating point deviations and process dynamic faults,enabling real-time monitoring of data features in industrial processes.Firstly,the proposed Random Fourier mappingbased method achieves more effective nonlinear transformation,contrasting with the current kernelbased RDSFA algorithm that may lead to significant computational complexity.Secondly,a randomized RDSFA model is developed to extract nonlinear dynamic slow features.Furthermore,a Bayesian inference-based overall fault monitoring model including all RRDSFA sub-models is developed to overcome the randomness of random Fourier mapping.Finally,the superiority and effectiveness of the proposed monitoring method are demonstrated through a numerical case and a simulation of continuous stirred tank reactor.
文摘Deep Underground Science and Engineering(DUSE)is pleased to release this issue with feature articles reporting the advancement in several research topics related to deep underground.This issue contains one perspective article,two review articles,six research articles,and one case study article.These articles focus on underground energy storage,multiscale modeling for correlation between micro-scale damage and macro-scale structural degradation,mineralization and formation of gold mine,interface and fracture seepage,experimental study on tunnel-sand-pile interaction,and high water-content materials for deep underground space backfilling,analytical solutions for the crack evolution direction in brittle rocks,and a case study on the squeezing-induced failure in a water drainage tunnel and the rehabilitation measures.
基金supported by the Scientific Research Foundation for High-level Talents of Anhui University of Science and Technology(13230550)the Coal Industry Engineering Research Center of Mining Area Environmental and Disaster Cooperative Monitoring,Anhui University of Science and Technology(KSXTJC202305)+1 种基金the State Key Laboratory of Geodesy and Earth's Dynamics,Innovation Academy for Precision Measurement Science and Technology(SKLGED2023-5-1)the China Postdoctoral Science Foundation(2023M733604).
文摘Soil moisture is a key parameter in the exchange of energy and water between the land surface and the atmosphere.This parameter plays an important role in the dynamics of permafrost on the Qinghai-Xizang Plateau,China,as well as in the related ecological and hydrological processes.However,the region's complex terrain and extreme climatic conditions result in low-accuracy soil moisture estimations using traditional remote sensing techniques.Thus,this study considered parameters of the backscatter coefficient of Sentinel-1A ground range detected(GRD)data,the polarization decomposition parameters of Sentinel-1A single-look complex(SLC)data,the normalized difference vegetation index(NDVI)based on Sentinel-2B data,and the topographic factors based on digital elevation model(DEM)data.By combining these parameters with a machine learning model,we established a feature selection rule.A cumulative importance threshold was derived for feature variables,and those variables that failed to meet the threshold were eliminated based on variations in the coefficient of determination(R^(2))and the unbiased root mean square error(ubRMSE).The eight most influential variables were selected and combined with the CatBoost model for soil moisture inversion,and the SHapley Additive exPlanations(SHAP)method was used to analyze the importance of these variables.The results demonstrated that the optimized model significantly improved the accuracy of soil moisture inversion.Compared to the unfiltered model,the optimal feature combination led to a 0.09 increase in R^(2)and a 0.7%reduction in ubRMSE.Ultimately,the optimized model achieved a R²of 0.87 and an ubRMSE of 5.6%.Analysis revealed that soil particle size had significant impact on soil water retention capacity.The impact of vegetation on the estimated soil moisture on the Qinghai-Xizang Plateau was considerable,demonstrating a significant positive correlation.Moreover,the microtopographical features of hummocks interfered with soil moisture estimation,indicating that such terrain effects warrant increased attention in future studies within the permafrost regions.The developed method not only enhances the accuracy of soil moisture retrieval in the complex terrain of the Qinghai-Xizang Plateau,but also exhibits high computational efficiency(with a relative time reduction of 18.5%),striking an excellent balance between accuracy and efficiency.This approach provides a robust framework for efficient soil moisture monitoring in remote areas with limited ground data,offering critical insights for ecological conservation,water resource management,and climate change adaptation on the Qinghai-Xizang Plateau.
