Due to the interrelationship between the base placement of the manipulator and its operation object,it is significant to analyze the accessibility and workspace of manipulators for the optimization of their base locat...Due to the interrelationship between the base placement of the manipulator and its operation object,it is significant to analyze the accessibility and workspace of manipulators for the optimization of their base location.A new method is presented to optimize the base placement of manipulators through motion planning optimization and location optimization in the feasible area for manipulators.Firstly,research problems and contents are outlined.And then the feasible area for the manipulator base installation is discussed.Next,index depended on the joint movements and used to evaluate the kinematic performance of manipulators is defined.Although the mentioned indices in last section are regarded as the cost function of the latter,rapidly-exploring random tree(RRT) and rapidly-exploring random tree*(RRT*) algorithms are analyzed.And then,the proposed optimization method of manipulator base placement is studied by means of simulation research based on kinematic performance criteria.Finally,the conclusions could be proved effective from the simulation results.展开更多
Sampling-based planning algorithms play an important role in high degree-of-freedom motion planning(MP)problems,in which rapidly-exploring random tree(RRT)and the faster bidirectional RRT(named RRT-Connect)algorithms ...Sampling-based planning algorithms play an important role in high degree-of-freedom motion planning(MP)problems,in which rapidly-exploring random tree(RRT)and the faster bidirectional RRT(named RRT-Connect)algorithms have achieved good results in many planning tasks.However,sampling-based methods have the inherent defect of having difficultly in solving planning problems with narrow passages.Therefore,several algorithms have been proposed to overcome these drawbacks.As one of the improved algorithms,Rapidlyexploring random vines(RRV)can achieve better results,but it may perform worse in cluttered environments and has a certain environmental selectivity.In this paper,we present a new improved planning method based on RRT-Connect and RRV,named adaptive RRT-Connect(ARRT-Connect),which deals well with the narrow passage environments while retaining the ability of RRT algorithms to plan paths in other environments.The proposed planner is shown to be adaptable to a variety of environments and can accomplish path planning in a short time.展开更多
The Darjeeling Himalayan region,characterized by its complex topography and vulnerability to multiple environmental hazards,faces significant challenges including landslides,earthquakes,flash floods,and soil loss that...The Darjeeling Himalayan region,characterized by its complex topography and vulnerability to multiple environmental hazards,faces significant challenges including landslides,earthquakes,flash floods,and soil loss that critically threaten ecosystem stability.Among these challenges,soil erosion emerges as a silent disaster-a gradual yet relentless process whose impacts accumulate over time,progressively degrading landscape integrity and disrupting ecological sustainability.Unlike catastrophic events with immediate visibility,soil erosion’s most devastating consequences often manifest decades later through diminished agricultural productivity,habitat fragmentation,and irreversible biodiversity loss.This study developed a scalable predictive framework employing Random Forest(RF)and Gradient Boosting Tree(GBT)machine learning models to assess and map soil erosion susceptibility across the region.A comprehensive geo-database was developed incorporating 11 erosion triggering factors:slope,elevation,rainfall,drainage density,topographic wetness index,normalized difference vegetation index,curvature,soil texture,land use,geology,and aspect.A total of 2,483 historical soil erosion locations were identified and randomly divided into two sets:70%for model building and 30%for validation purposes.The models revealed distinct spatial patterns of erosion risks,with GBT classifying 60.50%of the area as very low susceptibility,while RF identified 28.92%in this category.Notable differences emerged in high-risk zone identification,with GBT highlighting 7.42%and RF indicating 2.21%as very high erosion susceptibility areas.Both models demonstrated robust predictive capabilities,with GBT achieving 80.77%accuracy and 0.975 AUC,slightly outperforming RF’s 79.67%accuracy and 0.972 AUC.Analysis of predictor variables identified elevation,slope,rainfall and NDVI as the primary factors influencing erosion susceptibility,highlighting the complex interrelationship between geo-environmental factors and erosion processes.This research offers a strategic framework for targeted conservation and sustainable land management in the fragile Himalayan region,providing valuable insights to help policymakers implement effective soil erosion mitigation strategies and support long-term environmental sustainability.展开更多
This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting de...This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.展开更多
Mapping and monitoring the distribution of croplands and crop types support policymakers and international organizations by reducing the risks to food security,notably from climate change and,for that purpose,remote s...Mapping and monitoring the distribution of croplands and crop types support policymakers and international organizations by reducing the risks to food security,notably from climate change and,for that purpose,remote sensing is routinely used.However,identifying specific crop types,cropland,and cropping patterns using space-based observations is challenging because different crop types and cropping patterns have similarity spectral signatures.This study applied a methodology to identify cropland and specific crop types,including tobacco,wheat,barley,and gram,as well as the following cropping patterns:wheat-tobacco,wheat-gram,wheat-barley,and wheat-maize,which are common in Gujranwala District,Pakistan,the study region.The methodology consists of combining optical remote sensing images from Sentinel-2 and Landsat-8 with Machine Learning(ML)methods,namely a Decision Tree Classifier(DTC)and a Random Forest(RF)algorithm.The best time-periods for differentiating cropland from other land cover types were identified,and then Sentinel-2 and Landsat 8 NDVI-based time-series were linked to phenological parameters to determine the different crop types and cropping patterns over the study region using their temporal indices and ML algorithms.The methodology was subsequently evaluated using Landsat images,crop statistical data for 2020 and 2021,and field data on cropping patterns.The results highlight the high level of accuracy of the methodological approach presented using Sentinel-2 and Landsat-8 images,together with ML techniques,for mapping not only the distribution of cropland,but also crop types and cropping patterns when validated at the county level.These results reveal that this methodology has benefits for monitoring and evaluating food security in Pakistan,adding to the evidence base of other studies on the use of remote sensing to identify crop types and cropping patterns in other countries.展开更多
The quality of hot-rolled steel strip is directly affected by the strip crown.Traditional machine learning models have shown limitations in accurately predicting the strip crown,particularly when dealing with imbalanc...The quality of hot-rolled steel strip is directly affected by the strip crown.Traditional machine learning models have shown limitations in accurately predicting the strip crown,particularly when dealing with imbalanced data.This limitation results in poor production quality and efficiency,leading to increased production costs.Thus,a novel strip crown prediction model that uses the Boruta and extremely randomized trees(Boruta-ERT)algorithms to address this issue was proposed.To improve the accuracy of our model,we utilized the synthetic minority over-sampling technique to balance the imbalance data sets.The Boruta-ERT prediction model was then used to select features and predict the strip crown.With the 2160 mm hot rolling production lines of a steel plant serving as the research object,the experimental results showed that 97.01% of prediction data have an absolute error of less than 8 lm.This level of accuracy met the control requirements for strip crown and demonstrated significant benefits for the improvement in production quality of steel strip.展开更多
The first problem considered in this article reads： is it possible to find upper estimates for the spanning tree congestion in bipartite graphs, which are better than those for general graphs？ It is proved that ther...The first problem considered in this article reads： is it possible to find upper estimates for the spanning tree congestion in bipartite graphs, which are better than those for general graphs？ It is proved that there exists a bipartite version of the known graph with spanning tree congestion of order n3/2, where n is the number of vertices. The second problem is to estimate spanning tree congestion of random graphs. It is proved that the standard model of random graphs cannot be used to find graphs whose spanning tree congestion has order greater than n3/2.展开更多
Machine learning has emerged as a pivotal tool in deciphering and managing this excess of information in an era of abundant data.This paper presents a comprehensive analysis of machine learning algorithms,focusing on ...Machine learning has emerged as a pivotal tool in deciphering and managing this excess of information in an era of abundant data.This paper presents a comprehensive analysis of machine learning algorithms,focusing on the structure and efficacy of random forests in mitigating overfitting—a prevalent issue in decision tree models.It also introduces a novel approach to enhancing decision tree performance through an optimized pruning method called Adaptive Cross-Validated Alpha CCP(ACV-CCP).This method refines traditional cost complexity pruning by streamlining the selection of the alpha parameter,leveraging cross-validation within the pruning process to achieve a reliable,computationally efficient alpha selection that generalizes well to unseen data.By enhancing computational efficiency and balancing model complexity,ACV-CCP allows decision trees to maintain predictive accuracy while minimizing overfitting,effectively narrowing the performance gap between decision trees and random forests.Our findings illustrate how ACV-CCP contributes to the robustness and applicability of decision trees,providing a valuable perspective on achieving computationally efficient and generalized machine learning models.展开更多
A large number of logistics operations are needed to transport fabric rolls and dye barrels to different positions in printing and dyeing plants, and increasing labor cost is making it difficult for plants to recruit ...A large number of logistics operations are needed to transport fabric rolls and dye barrels to different positions in printing and dyeing plants, and increasing labor cost is making it difficult for plants to recruit workers to complete manual operations. Artificial intelligence and robotics, which are rapidly evolving, offer potential solutions to this problem. In this paper, a navigation method dedicated to solving the issues of the inability to pass smoothly at corners in practice and local obstacle avoidance is presented. In the system, a Gaussian fitting smoothing rapid exploration random tree star-smart(GFS RRT^(*)-Smart) algorithm is proposed for global path planning and enhances the performance when the robot makes a sharp turn around corners. In local obstacle avoidance, a deep reinforcement learning determiner mixed actor critic(MAC) algorithm is used for obstacle avoidance decisions. The navigation system is implemented in a scaled-down simulation factory.展开更多
Recently a great deal of effort has been made to explicitly determine the mean first-passage time （MFPT） between two nodes averaged over all pairs of nodes on a fractal network. In this paper, we first propose a fam...Recently a great deal of effort has been made to explicitly determine the mean first-passage time （MFPT） between two nodes averaged over all pairs of nodes on a fractal network. In this paper, we first propose a family of generalized delayed recursive trees characterized by two parameters, where the existing nodes have a time delay to produce new nodes. We then study the MFPT of random walks on this kind of recursive tree and investigate the effect of the time delay on the MFPT. By relating random walks to electrical networks, we obtain an exact formula for the MFPT and verify it by numerical calculations. Based on the obtained results, we further show that the MFPT of delayed recursive trees is much shorter, implying that the efficiency of random walks is much higher compared with the non-delayed counterpart. Our study provides a deeper understanding of random walks on delayed fractal networks.展开更多
Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced th...Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced the generation of weak decision trees while ensured its diversity.The base learner used a weighted voting mechanism to replace the traditional average method,which improved the prediction accuracy.Finally,the analysis method of the correlation between steel grades was proposed to solve the problem of unstable prediction accuracy of multiple steel grades.The experimental results show that the improved prediction model of mechanical properties has high accuracy:the prediction accuracy of yield strength and tensile strength within the error of±20 MPa reaches 93.20%and 97.62%,respectively,and that of the elongation rate under the error of±5%has reached 96.60%.展开更多
We prove that a random labeled (unlabeled) tree is balanced. We also prove that random labeled and unlabeled trees are strongly k-balanced for any k ≥ 3. Definition: Color the vertices ...We prove that a random labeled (unlabeled) tree is balanced. We also prove that random labeled and unlabeled trees are strongly k-balanced for any k ≥ 3. Definition: Color the vertices of graph G with two colors. Color an edge with the color of its endpoints if they are colored with the same color. Edges with different colored endpoints are left uncolored. G is said to be balanced if neither the number of vertices nor and the number of edges of the two different colors differs by more than one.展开更多
k-ary trees are one of the most basic data structures in Computer Science. A new method is presented to determine how many there are with n nodes. This method gives additional insight into their structure and provides...k-ary trees are one of the most basic data structures in Computer Science. A new method is presented to determine how many there are with n nodes. This method gives additional insight into their structure and provides a new algo-rithm to efficiently generate such a tree randomly.展开更多
Random pixel selection is one of the image steganography methods that has achieved significant success in enhancing the robustness of hidden data.This property makes it difficult for steganalysts’powerful data extrac...Random pixel selection is one of the image steganography methods that has achieved significant success in enhancing the robustness of hidden data.This property makes it difficult for steganalysts’powerful data extraction tools to detect the hidden data and ensures high-quality stego image generation.However,using a seed key to generate non-repeated sequential numbers takes a long time because it requires specific mathematical equations.In addition,these numbers may cluster in certain ranges.The hidden data in these clustered pixels will reduce the image quality,which steganalysis tools can detect.Therefore,this paper proposes a data structure that safeguards the steganographic model data and maintains the quality of the stego image.This paper employs the AdelsonVelsky and Landis(AVL)tree data structure algorithm to implement the randomization pixel selection technique for data concealment.The AVL tree algorithm provides several advantages for image steganography.Firstly,it ensures balanced tree structures,which leads to efficient data retrieval and insertion operations.Secondly,the self-balancing nature of AVL trees minimizes clustering by maintaining an even distribution of pixels,thereby preserving the stego image quality.The data structure employs the pixel indicator technique for Red,Green,and Blue(RGB)channel extraction.The green channel serves as the foundation for building a balanced binary tree.First,the sender identifies the colored cover image and secret data.The sender will use the two least significant bits(2-LSB)of RGB channels to conceal the data’s size and associated information.The next step is to create a balanced binary tree based on the green channel.Utilizing the channel pixel indicator on the LSB of the green channel,we can conceal bits in the 2-LSB of the red or blue channel.The first four levels of the data structure tree will mask the data size,while subsequent levels will conceal the remaining digits of secret data.After embedding the bits in the binary tree level by level,the model restores the AVL tree to create the stego image.Ultimately,the receiver receives this stego image through the public channel,enabling secret data recovery without stego or crypto keys.This method ensures that the stego image appears unsuspicious to potential attackers.Without an extraction algorithm,a third party cannot extract the original secret information from an intercepted stego image.Experimental results showed high levels of imperceptibility and security.展开更多
Controls, especially effficiency controls on dynamical processes, have become major challenges in many complex systems. We study an important dynamical process, random walk, due to its wide range of applications for m...Controls, especially effficiency controls on dynamical processes, have become major challenges in many complex systems. We study an important dynamical process, random walk, due to its wide range of applications for modeling the transporting or searching process. For lack of control methods for random walks in various structures, a control technique is presented for a class of weighted treelike scale-free networks with a deep trap at a hub node. The weighted networks are obtained from original models by introducing a weight parameter. We compute analytically the mean first passage time （MFPT） as an indicator for quantitatively measurinM the et^ciency of the random walk process. The results show that the MFPT increases exponentially with the network size, and the exponent varies with the weight parameter. The MFPT, therefore, can be controlled by the weight parameter to behave superlinearly, linearly, or sublinearly with the system size. This work provides further useful insights into controllinM eftlciency in scale-free complex networks.展开更多
The Arctic region is experiencing accelerated sea ice melt and increased iceberg detachment from glaciers due to climate change.These drifting icebergs present a risk and engineering challenge for subsea installations...The Arctic region is experiencing accelerated sea ice melt and increased iceberg detachment from glaciers due to climate change.These drifting icebergs present a risk and engineering challenge for subsea installations traversing shallow waters,where ice-berg keels may reach the seabed,potentially damaging subsea structures.Consequently,costly and time-intensive iceberg manage-ment operations,such as towing and rerouting,are undertaken to safeguard subsea and offshore infrastructure.This study,therefore,explores the application of extra tree regression(ETR)as a robust solution for estimating iceberg draft,particularly in the preliminary phases of decision-making for iceberg management projects.Nine ETR models were developed using parameters influencing iceberg draft.Subsequent analyses identified the most effective models and significant input variables.Uncertainty analysis revealed that the superior ETR model tended to overestimate iceberg drafts;however,it achieved the highest precision,correlation,and simplicity in estimation.Comparison with decision tree regression,random forest regression,and empirical methods confirmed the superior perfor-mance of ETR in predicting iceberg drafts.展开更多
Scientists have introduced new methods for capturing energy from ocean waves.Specifically,scientists have focused on a type of wave energy converter(WEC)that is nonbuoyant(i.e.,a body that cannot float).Typically,the ...Scientists have introduced new methods for capturing energy from ocean waves.Specifically,scientists have focused on a type of wave energy converter(WEC)that is nonbuoyant(i.e.,a body that cannot float).Typically,the WEC is most effective when it is in resonance,which occurs when the natural frequency of the WEC aligns with that of the ocean waves.Therefore,accurately predicting the movement of the WEC is crucial for adjusting its system to resonate with the incoming waves for optimal performance.In this study,artificial intelligence techniques,such as random forest,extra trees(ET),and support vector machines,are created to forecast the vertical movement of a nonbuoyant WEC.The developed models require two variables as input,namely,the water wave height and its time period.A total of approximately 4500 data points,which include nonlinear water wave height and duration ob-tained from a laboratory experiment,are used as the input for these models,with the resulting vertical movement as the output.When comparing the three models based on their processing speed and accuracy,the ET model stands out as the most efficient.Ultimately,the ET model is tested using data from a real ocean setting.展开更多
针对复杂果园环境行间导航树干检测问题,提出一种基于多线激光雷达(Light detection and ranging,Li DAR)的主干形果树树干层级检测方法,使用16线VLP-16型LiDAR采集车辆周围的果园点云数据,通过目标分割和树干检测2个步骤层次化检测树干...针对复杂果园环境行间导航树干检测问题,提出一种基于多线激光雷达(Light detection and ranging,Li DAR)的主干形果树树干层级检测方法,使用16线VLP-16型LiDAR采集车辆周围的果园点云数据,通过目标分割和树干检测2个步骤层次化检测树干,去除非树干目标,提高树干检测精度。首先,设置环形感兴趣区域(Region of interest,ROI),采用地面拟合算法移除地面点云,消除果园目标点云之间的连通性;其次,设置矩形ROI,采用基于密度的带噪声空间聚类(Density-based spatial clustering of applications with noise,DBSCAN)算法对非地面点云进行x Oy平面聚类,根据Li DAR测量分辨率和果园目标参数设置DBSCAN算法超参数,将非地面点云分割为若干目标簇;然后,从全局和局部2个尺度提取目标簇的几何和强度特征,用这些特征描述树干与其他果园目标间的差异;最后,采用训练好的树干检测器融合特征,将目标簇划分为树干与非树干2个类别,输出树干簇。树干检测步骤采用随机森林(Random forest,RF)算法进行离线特征选择与融合,使用树干和非树干训练样本,基于基尼指数(Gini index,GI)改变量评价特征重要性,从初始特征中选择22个鉴别力较强的特征,再融合这些特征生成树干检测器。实验场景为标准化种植核桃园,共采集1317帧点云数据,从中分割12213个目标簇,其中,树冠、杂草、支撑杆、围栏、土坡、农具、行人等非树干目标占比58.04%。按照帧比例1∶4将目标簇随机划分为训练集和测试集,测试集树干检测精确率为99.16%、召回率为99.21%、F1分数为99.19%,树干层级检测平均帧耗时85.25 ms。本文方法能对复杂果园场景快速、精准地检测出树干,满足果园行间导航对树干检测的准确性和实时性要求。展开更多
基金Supported by the National Science and Technology Support Program of China(No.2013BAK03B01)
文摘Due to the interrelationship between the base placement of the manipulator and its operation object,it is significant to analyze the accessibility and workspace of manipulators for the optimization of their base location.A new method is presented to optimize the base placement of manipulators through motion planning optimization and location optimization in the feasible area for manipulators.Firstly,research problems and contents are outlined.And then the feasible area for the manipulator base installation is discussed.Next,index depended on the joint movements and used to evaluate the kinematic performance of manipulators is defined.Although the mentioned indices in last section are regarded as the cost function of the latter,rapidly-exploring random tree(RRT) and rapidly-exploring random tree*(RRT*) algorithms are analyzed.And then,the proposed optimization method of manipulator base placement is studied by means of simulation research based on kinematic performance criteria.Finally,the conclusions could be proved effective from the simulation results.
基金supported in part by the National Science Foundation of China(61976175,91648208)the Key Project of Natural Science Basic Research Plan in Shaanxi Province of China(2019JZ-05)。
文摘Sampling-based planning algorithms play an important role in high degree-of-freedom motion planning(MP)problems,in which rapidly-exploring random tree(RRT)and the faster bidirectional RRT(named RRT-Connect)algorithms have achieved good results in many planning tasks.However,sampling-based methods have the inherent defect of having difficultly in solving planning problems with narrow passages.Therefore,several algorithms have been proposed to overcome these drawbacks.As one of the improved algorithms,Rapidlyexploring random vines(RRV)can achieve better results,but it may perform worse in cluttered environments and has a certain environmental selectivity.In this paper,we present a new improved planning method based on RRT-Connect and RRV,named adaptive RRT-Connect(ARRT-Connect),which deals well with the narrow passage environments while retaining the ability of RRT algorithms to plan paths in other environments.The proposed planner is shown to be adaptable to a variety of environments and can accomplish path planning in a short time.
文摘The Darjeeling Himalayan region,characterized by its complex topography and vulnerability to multiple environmental hazards,faces significant challenges including landslides,earthquakes,flash floods,and soil loss that critically threaten ecosystem stability.Among these challenges,soil erosion emerges as a silent disaster-a gradual yet relentless process whose impacts accumulate over time,progressively degrading landscape integrity and disrupting ecological sustainability.Unlike catastrophic events with immediate visibility,soil erosion’s most devastating consequences often manifest decades later through diminished agricultural productivity,habitat fragmentation,and irreversible biodiversity loss.This study developed a scalable predictive framework employing Random Forest(RF)and Gradient Boosting Tree(GBT)machine learning models to assess and map soil erosion susceptibility across the region.A comprehensive geo-database was developed incorporating 11 erosion triggering factors:slope,elevation,rainfall,drainage density,topographic wetness index,normalized difference vegetation index,curvature,soil texture,land use,geology,and aspect.A total of 2,483 historical soil erosion locations were identified and randomly divided into two sets:70%for model building and 30%for validation purposes.The models revealed distinct spatial patterns of erosion risks,with GBT classifying 60.50%of the area as very low susceptibility,while RF identified 28.92%in this category.Notable differences emerged in high-risk zone identification,with GBT highlighting 7.42%and RF indicating 2.21%as very high erosion susceptibility areas.Both models demonstrated robust predictive capabilities,with GBT achieving 80.77%accuracy and 0.975 AUC,slightly outperforming RF’s 79.67%accuracy and 0.972 AUC.Analysis of predictor variables identified elevation,slope,rainfall and NDVI as the primary factors influencing erosion susceptibility,highlighting the complex interrelationship between geo-environmental factors and erosion processes.This research offers a strategic framework for targeted conservation and sustainable land management in the fragile Himalayan region,providing valuable insights to help policymakers implement effective soil erosion mitigation strategies and support long-term environmental sustainability.
基金This work was supported in part by the National Natural Science Foundation of China(61601418,41602362,61871259)in part by the Opening Foundation of Hunan Engineering and Research Center of Natural Resource Investigation and Monitoring(2020-5)+1 种基金in part by the Qilian Mountain National Park Research Center(Qinghai)(grant number:GKQ2019-01)in part by the Geomatics Technology and Application Key Laboratory of Qinghai Province,Grant No.QHDX-2019-01.
文摘This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.
文摘Mapping and monitoring the distribution of croplands and crop types support policymakers and international organizations by reducing the risks to food security,notably from climate change and,for that purpose,remote sensing is routinely used.However,identifying specific crop types,cropland,and cropping patterns using space-based observations is challenging because different crop types and cropping patterns have similarity spectral signatures.This study applied a methodology to identify cropland and specific crop types,including tobacco,wheat,barley,and gram,as well as the following cropping patterns:wheat-tobacco,wheat-gram,wheat-barley,and wheat-maize,which are common in Gujranwala District,Pakistan,the study region.The methodology consists of combining optical remote sensing images from Sentinel-2 and Landsat-8 with Machine Learning(ML)methods,namely a Decision Tree Classifier(DTC)and a Random Forest(RF)algorithm.The best time-periods for differentiating cropland from other land cover types were identified,and then Sentinel-2 and Landsat 8 NDVI-based time-series were linked to phenological parameters to determine the different crop types and cropping patterns over the study region using their temporal indices and ML algorithms.The methodology was subsequently evaluated using Landsat images,crop statistical data for 2020 and 2021,and field data on cropping patterns.The results highlight the high level of accuracy of the methodological approach presented using Sentinel-2 and Landsat-8 images,together with ML techniques,for mapping not only the distribution of cropland,but also crop types and cropping patterns when validated at the county level.These results reveal that this methodology has benefits for monitoring and evaluating food security in Pakistan,adding to the evidence base of other studies on the use of remote sensing to identify crop types and cropping patterns in other countries.
基金supported by the National Natural Science Foundation of China(Grant Nos.52074085,U21A20117 and U21A20475)the Fundamental Research Funds for the Central Universities(Grant No.N2004010)the Liaoning Revitalization Talents Program(XLYC1907065).
文摘The quality of hot-rolled steel strip is directly affected by the strip crown.Traditional machine learning models have shown limitations in accurately predicting the strip crown,particularly when dealing with imbalanced data.This limitation results in poor production quality and efficiency,leading to increased production costs.Thus,a novel strip crown prediction model that uses the Boruta and extremely randomized trees(Boruta-ERT)algorithms to address this issue was proposed.To improve the accuracy of our model,we utilized the synthetic minority over-sampling technique to balance the imbalance data sets.The Boruta-ERT prediction model was then used to select features and predict the strip crown.With the 2160 mm hot rolling production lines of a steel plant serving as the research object,the experimental results showed that 97.01% of prediction data have an absolute error of less than 8 lm.This level of accuracy met the control requirements for strip crown and demonstrated significant benefits for the improvement in production quality of steel strip.
文摘The first problem considered in this article reads： is it possible to find upper estimates for the spanning tree congestion in bipartite graphs, which are better than those for general graphs？ It is proved that there exists a bipartite version of the known graph with spanning tree congestion of order n3/2, where n is the number of vertices. The second problem is to estimate spanning tree congestion of random graphs. It is proved that the standard model of random graphs cannot be used to find graphs whose spanning tree congestion has order greater than n3/2.
文摘Machine learning has emerged as a pivotal tool in deciphering and managing this excess of information in an era of abundant data.This paper presents a comprehensive analysis of machine learning algorithms,focusing on the structure and efficacy of random forests in mitigating overfitting—a prevalent issue in decision tree models.It also introduces a novel approach to enhancing decision tree performance through an optimized pruning method called Adaptive Cross-Validated Alpha CCP(ACV-CCP).This method refines traditional cost complexity pruning by streamlining the selection of the alpha parameter,leveraging cross-validation within the pruning process to achieve a reliable,computationally efficient alpha selection that generalizes well to unseen data.By enhancing computational efficiency and balancing model complexity,ACV-CCP allows decision trees to maintain predictive accuracy while minimizing overfitting,effectively narrowing the performance gap between decision trees and random forests.Our findings illustrate how ACV-CCP contributes to the robustness and applicability of decision trees,providing a valuable perspective on achieving computationally efficient and generalized machine learning models.
基金National Natural Science Foundation of China (No.61903078)。
文摘A large number of logistics operations are needed to transport fabric rolls and dye barrels to different positions in printing and dyeing plants, and increasing labor cost is making it difficult for plants to recruit workers to complete manual operations. Artificial intelligence and robotics, which are rapidly evolving, offer potential solutions to this problem. In this paper, a navigation method dedicated to solving the issues of the inability to pass smoothly at corners in practice and local obstacle avoidance is presented. In the system, a Gaussian fitting smoothing rapid exploration random tree star-smart(GFS RRT^(*)-Smart) algorithm is proposed for global path planning and enhances the performance when the robot makes a sharp turn around corners. In local obstacle avoidance, a deep reinforcement learning determiner mixed actor critic(MAC) algorithm is used for obstacle avoidance decisions. The navigation system is implemented in a scaled-down simulation factory.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.61203155 and 11232005)the Natural Science Foundation of Zhejiang Province,China (Grant No.LQ12F03003)the Hong Kong Research Grants Council under the GRF Grant CityU (Grant No.1109/12)
文摘Recently a great deal of effort has been made to explicitly determine the mean first-passage time （MFPT） between two nodes averaged over all pairs of nodes on a fractal network. In this paper, we first propose a family of generalized delayed recursive trees characterized by two parameters, where the existing nodes have a time delay to produce new nodes. We then study the MFPT of random walks on this kind of recursive tree and investigate the effect of the time delay on the MFPT. By relating random walks to electrical networks, we obtain an exact formula for the MFPT and verify it by numerical calculations. Based on the obtained results, we further show that the MFPT of delayed recursive trees is much shorter, implying that the efficiency of random walks is much higher compared with the non-delayed counterpart. Our study provides a deeper understanding of random walks on delayed fractal networks.
文摘Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced the generation of weak decision trees while ensured its diversity.The base learner used a weighted voting mechanism to replace the traditional average method,which improved the prediction accuracy.Finally,the analysis method of the correlation between steel grades was proposed to solve the problem of unstable prediction accuracy of multiple steel grades.The experimental results show that the improved prediction model of mechanical properties has high accuracy:the prediction accuracy of yield strength and tensile strength within the error of±20 MPa reaches 93.20%and 97.62%,respectively,and that of the elongation rate under the error of±5%has reached 96.60%.
文摘We prove that a random labeled (unlabeled) tree is balanced. We also prove that random labeled and unlabeled trees are strongly k-balanced for any k ≥ 3. Definition: Color the vertices of graph G with two colors. Color an edge with the color of its endpoints if they are colored with the same color. Edges with different colored endpoints are left uncolored. G is said to be balanced if neither the number of vertices nor and the number of edges of the two different colors differs by more than one.
文摘k-ary trees are one of the most basic data structures in Computer Science. A new method is presented to determine how many there are with n nodes. This method gives additional insight into their structure and provides a new algo-rithm to efficiently generate such a tree randomly.
文摘Random pixel selection is one of the image steganography methods that has achieved significant success in enhancing the robustness of hidden data.This property makes it difficult for steganalysts’powerful data extraction tools to detect the hidden data and ensures high-quality stego image generation.However,using a seed key to generate non-repeated sequential numbers takes a long time because it requires specific mathematical equations.In addition,these numbers may cluster in certain ranges.The hidden data in these clustered pixels will reduce the image quality,which steganalysis tools can detect.Therefore,this paper proposes a data structure that safeguards the steganographic model data and maintains the quality of the stego image.This paper employs the AdelsonVelsky and Landis(AVL)tree data structure algorithm to implement the randomization pixel selection technique for data concealment.The AVL tree algorithm provides several advantages for image steganography.Firstly,it ensures balanced tree structures,which leads to efficient data retrieval and insertion operations.Secondly,the self-balancing nature of AVL trees minimizes clustering by maintaining an even distribution of pixels,thereby preserving the stego image quality.The data structure employs the pixel indicator technique for Red,Green,and Blue(RGB)channel extraction.The green channel serves as the foundation for building a balanced binary tree.First,the sender identifies the colored cover image and secret data.The sender will use the two least significant bits(2-LSB)of RGB channels to conceal the data’s size and associated information.The next step is to create a balanced binary tree based on the green channel.Utilizing the channel pixel indicator on the LSB of the green channel,we can conceal bits in the 2-LSB of the red or blue channel.The first four levels of the data structure tree will mask the data size,while subsequent levels will conceal the remaining digits of secret data.After embedding the bits in the binary tree level by level,the model restores the AVL tree to create the stego image.Ultimately,the receiver receives this stego image through the public channel,enabling secret data recovery without stego or crypto keys.This method ensures that the stego image appears unsuspicious to potential attackers.Without an extraction algorithm,a third party cannot extract the original secret information from an intercepted stego image.Experimental results showed high levels of imperceptibility and security.
基金Supported by the National Natural Science Foundation of China under Grant Nos 61173118,61373036 and 61272254
文摘Controls, especially effficiency controls on dynamical processes, have become major challenges in many complex systems. We study an important dynamical process, random walk, due to its wide range of applications for modeling the transporting or searching process. For lack of control methods for random walks in various structures, a control technique is presented for a class of weighted treelike scale-free networks with a deep trap at a hub node. The weighted networks are obtained from original models by introducing a weight parameter. We compute analytically the mean first passage time （MFPT） as an indicator for quantitatively measurinM the et^ciency of the random walk process. The results show that the MFPT increases exponentially with the network size, and the exponent varies with the weight parameter. The MFPT, therefore, can be controlled by the weight parameter to behave superlinearly, linearly, or sublinearly with the system size. This work provides further useful insights into controllinM eftlciency in scale-free complex networks.
文摘The Arctic region is experiencing accelerated sea ice melt and increased iceberg detachment from glaciers due to climate change.These drifting icebergs present a risk and engineering challenge for subsea installations traversing shallow waters,where ice-berg keels may reach the seabed,potentially damaging subsea structures.Consequently,costly and time-intensive iceberg manage-ment operations,such as towing and rerouting,are undertaken to safeguard subsea and offshore infrastructure.This study,therefore,explores the application of extra tree regression(ETR)as a robust solution for estimating iceberg draft,particularly in the preliminary phases of decision-making for iceberg management projects.Nine ETR models were developed using parameters influencing iceberg draft.Subsequent analyses identified the most effective models and significant input variables.Uncertainty analysis revealed that the superior ETR model tended to overestimate iceberg drafts;however,it achieved the highest precision,correlation,and simplicity in estimation.Comparison with decision tree regression,random forest regression,and empirical methods confirmed the superior perfor-mance of ETR in predicting iceberg drafts.
文摘Scientists have introduced new methods for capturing energy from ocean waves.Specifically,scientists have focused on a type of wave energy converter(WEC)that is nonbuoyant(i.e.,a body that cannot float).Typically,the WEC is most effective when it is in resonance,which occurs when the natural frequency of the WEC aligns with that of the ocean waves.Therefore,accurately predicting the movement of the WEC is crucial for adjusting its system to resonate with the incoming waves for optimal performance.In this study,artificial intelligence techniques,such as random forest,extra trees(ET),and support vector machines,are created to forecast the vertical movement of a nonbuoyant WEC.The developed models require two variables as input,namely,the water wave height and its time period.A total of approximately 4500 data points,which include nonlinear water wave height and duration ob-tained from a laboratory experiment,are used as the input for these models,with the resulting vertical movement as the output.When comparing the three models based on their processing speed and accuracy,the ET model stands out as the most efficient.Ultimately,the ET model is tested using data from a real ocean setting.
文摘针对复杂果园环境行间导航树干检测问题,提出一种基于多线激光雷达(Light detection and ranging,Li DAR)的主干形果树树干层级检测方法,使用16线VLP-16型LiDAR采集车辆周围的果园点云数据,通过目标分割和树干检测2个步骤层次化检测树干,去除非树干目标,提高树干检测精度。首先,设置环形感兴趣区域(Region of interest,ROI),采用地面拟合算法移除地面点云,消除果园目标点云之间的连通性;其次,设置矩形ROI,采用基于密度的带噪声空间聚类(Density-based spatial clustering of applications with noise,DBSCAN)算法对非地面点云进行x Oy平面聚类,根据Li DAR测量分辨率和果园目标参数设置DBSCAN算法超参数,将非地面点云分割为若干目标簇;然后,从全局和局部2个尺度提取目标簇的几何和强度特征,用这些特征描述树干与其他果园目标间的差异;最后,采用训练好的树干检测器融合特征,将目标簇划分为树干与非树干2个类别,输出树干簇。树干检测步骤采用随机森林(Random forest,RF)算法进行离线特征选择与融合,使用树干和非树干训练样本,基于基尼指数(Gini index,GI)改变量评价特征重要性,从初始特征中选择22个鉴别力较强的特征,再融合这些特征生成树干检测器。实验场景为标准化种植核桃园,共采集1317帧点云数据,从中分割12213个目标簇,其中,树冠、杂草、支撑杆、围栏、土坡、农具、行人等非树干目标占比58.04%。按照帧比例1∶4将目标簇随机划分为训练集和测试集,测试集树干检测精确率为99.16%、召回率为99.21%、F1分数为99.19%,树干层级检测平均帧耗时85.25 ms。本文方法能对复杂果园场景快速、精准地检测出树干,满足果园行间导航对树干检测的准确性和实时性要求。
