Optimal Neighborhood Size Research Articles

Community detection using Jaya optimization algorithm based on deep learning methods and KNN graph-based clustering

Purpose In this paper, community identification has been considered as the most critical task of social network analysis. The purpose of this paper is to organize the nodes of a given network graph into distinct clusters or known communities. These clusters will therefore form the different communities available within the social network graph. Design/methodology/approach To date, numerous methods have been developed to detect communities in social networks through graph clustering techniques. The k-means algorithm stands out as one of the most well-known graph clustering algorithms, celebrated for its straightforward implementation and rapid processing. However, it has a serious drawback because it is insensitive to initial conditions and always settles on local optima rather than finding the global optimum. More recently, clustering algorithms that use a reciprocal KNN (k-nearest neighbors) graph have been used for data clustering. It skillfully overcomes many major shortcomings of k-means algorithms, especially about the selection of the initial centers of clusters. However, it does face its own challenge: sensitivity to the choice of the neighborhood size parameter k, which is crucial for selecting the nearest neighbors during the clustering process. In this design, the Jaya optimization method is used to select the K parameter in the KNN method. Findings The experiment on real-world network data results show that the proposed approach significantly improves the accuracy of methods in community detection in social networks. On the other hand, it seems to offer some potential for discovering a more refined hierarchy in social networks and thus becomes a useful tool in the analysis of social networks. Originality/value This paper introduces an enhancement to the KNN graph-based clustering method by proposing a local average vector method for selecting the optimal neighborhood size parameter k. Furthermore, it presents an improved Jaya algorithm with KNN graph-based clustering for more effective community detection in social network graphs.

Granular structure evaluation and selection based on justifiable granularity principle

Granular structures are fundamental components of human granulation intelligence and different views or scales of granulation result in different granular structures. Therefore, the evaluation and selection of optimal granular structures can lay the foundation for problem-solving. Information granules are basic components of granular structures. The principle of justifiable granularity presents a coherent method for designing information granules. Therefore, this study performs granular structure evaluation and selection based on the justifiable granularity principle. First, it proposes a new evaluation criterion for granular structures that considers the coverage and specificity of all information granules in a granular structure. Thereafter, coverage and specificity are evaluated based on a core sample of the information granule. Subsequently, a detailed formulation is provided to compute the significance of the granular structure according to the proposed evaluation criterion. Finally, a general framework for granular structure selection is presented, and a detailed algorithm for selecting the optimal granular structure with the aid of the justifiable granularity principle is provided. The proposed method is employed to determine the optimal attribute and select the optimal neighborhood size for neighborhood classifiers. Experiments and analyses have demonstrated the necessity, reasonableness, and effectiveness of the proposed method.

A dynamic annealing learning for PLSOM neural networks: Applications in medicine and applied sciences

In recent years, the field of unsupervised learning in neural networks has witnessed significant advancements. This innovative learning technique holds great promise for applications in diverse domains, with particular significance in the realms of medicine and applied sciences such as medical image analysis, drug discovery, predictive analytics, and pattern recognition. The neighborhood function plays a crucial role in the Improved Parameter-Less Self-Organizing Map (PLSOM2) algorithm by governing the rate of change in the vicinity of the winning neuron. During learning iterations, the neighborhood size is dynamically adjusted to encompass the activated neighboring neurons relative to the winning neuron. The training process begins with a larger neighborhood radius, promoting rough ordering, and gradually refines the process by reducing the radius for fine-tuning. This dynamic neighborhood size significantly influences the final training outcome of the PLSOM2 algorithm. However, one of the major bottlenecks of the PLSOM2 algorithm has been the slow ordering time and the challenge of determining an optimal neighborhood size. These issues often lead to topological defects during training, such as kinks or warps in the output maps. Merely increasing processing time has proven insufficient to overcome these challenges. In this paper, we propose a novel dynamic neighborhood function designed to accelerate the convergence process of the PLSOM2 algorithm, achieving the best shape and adaptation of the neighborhood width. The study demonstrates that by improving the neighborhood function of the PLSOM2 algorithm, map distortion can be effectively suppressed. Importantly, this enhancement enables the algorithm to handle network size, neighborhood size, and the large dimensional output space adeptly. It adaptively decreases the neighborhood size over time, ensuring convergence while appropriately managing network growth and avoiding twisting and misconfiguration. To assess the effectiveness of the proposed method, we conducted an extensive set of experiments across eight real-world benchmark datasets. Notably, the outcomes of these experiments are presented showcases the results of paired t-tests, highlighting the consistency and robustness of the proposed algorithm's performance. Despite non-significant p-values in many cases, the algorithm consistently excels across various datasets, underlining its practical significance. On the other hand, presents the results of One-way Analysis of Variance (ANOVA) tests. These results further reinforce the consistency of the performance of algorithm, as indicated by p-values exceeding the common significance threshold of 0.05. The combined findings from both tables provide strong statistical evidence of the proposed algorithm's robustness and effectiveness across diverse datasets. The proposed research introduces a dynamic neighborhood function that not only improves the PLSOM2 algorithm's convergence but also enhances its adaptability and topological preservation. These enhancements, supported by the statistical tests results, underscore the algorithm's practical significance and its suitability for real-world applications, where statistical significance may not always capture the full extent of its capabilities.

Optimum k-Nearest Neighbors for Heading Synchronization on a Swarm of UAVs under a Time-Evolving Communication Network.

Heading synchronization is fundamental in flocking behaviors. If a swarm of unmanned aerial vehicles (UAVs) can exhibit this behavior, the group can establish a common navigation route. Inspired by flocks in nature, the k-nearest neighbors algorithm modifies the behavior of a group member based on the k closest teammates. This algorithm produces a time-evolving communication network, due to the continuous displacement of the drones. Nevertheless, this is a computationally expensive algorithm, especially for large groups. This paper contains a statistical analysis to determine an optimal neighborhood size for a swarm of up to 100 UAVs, that seeks heading synchronization using a simple P-like control algorithm, in order to reduce the calculations on every UAV, this is especially important if it is intended to be implemented in drones with limited capabilities, as in swarm robotics. Based on the literature of bird flocks, that establishes that the neighborhood of every bird is fixed around seven teammates, two approaches are treated in this work: (i) the analysis of the optimum percentage of neighbors from a 100-UAV swarm, that is necessary to achieve heading synchronization, and (ii) the analysis to determine if the problem is solved in swarms of different sizes, up to 100 UAVs, while maintaining seven nearest neighbors among the members of the group. Simulation results and a statistical analysis, support the idea that the simple control algorithm behaves like a flock of starlings.

A Feature Extraction Algorithm Based on Optimal Neighborhood Size

The feature extraction of a point cloud fragment model is the basis of fragment splicing, which provides the technical support for research on the segmentation, splicing, and restoration of fragment surfaces. High-quality feature extraction, however, is a complicated process due to the diversity of the surface information of a fragment model. For this subject, a high-efficient point cloud feature extraction method was proposed to address a new method for extracting feature lines. First, the projection distance feature of the point cloud model was calculated to identify the potential feature points. Furthermore, the local information of the possible feature points was used to construct the adaptive neighborhoods for identifying the feature points based on neighborhoods of the model. The clustering fusion of the feature points was proposed according to the discrimination threshold values of the feature points. Finally, the Laplace operator was utilized to refine and connect the feature points to form smooth feature lines. The experimental results showed that the proposed method was automatic, highly efficient, and with good adaptability that could effectively extract the detailed features and construct the complete feature lines. Moreover, results showed that the provided framework could extract the features of simple structure models and be feasible to a certain extent for fragment models with abundant features.

BUILDING DETECTION FROM AERIAL LIDAR POINT CLOUD USING DEEP LEARNING

Abstract. With the development and widespread application of aerial LiDAR, point cloud data can easily be acquired and used in many fields. The accurate detection of buildings from an aerial LiDAR point cloud has attracted much attention owing to its wide range of applications, such as updating building maps and constructing 3D city models. However, such applications remain challenging in the fields of photogrammetry, remote sensing, and computer vision. In this paper, we discuss the features that contribute to building detection accuracy from an aerial LiDAR point cloud using a deep-learning-based method (KPConv). We evaluated the influence of neighborhood size, intensity, RGB, and normal vectors on building detection. The study area was approximately 6 km2, consisting of 133 million points and 8,099 buildings. The density of the point cloud data was eight points/m2. We compared search radii of 4, 10, 25, and 50 m for finding neighboring points. The results suggest that an optimal neighborhood size improves the accuracy of building detection. For searching neighboring points, a radius of 25 m is optimal when the building area is less than 1000 m2, whereas a radius of 50 m is optimal when the building area is larger than 1000 m2.We also compared different features as inputs to KPConv for training and testing, such as i) 3D coordinates only, ii) 3D coordinates and intensity, iii) 3D coordinates and RGB, iv) 3D coordinates and normal vectors, and v) 3D coordinates, intensity, RGB, and normal vectors. The results suggest that neither intensity nor normal vectors contribute to the accuracy of building detection, while the features of RGB have a limited effect on the results.

Assessing the impact of 3D point neighborhood size selection on unsupervised spall classification with 3D bridge point clouds

The performance of point cloud-based defect classification algorithms depends on the quality of the computed geometric features, which in turn is strongly affected by the selection of the neighborhood size of local 3D points. Many existing algorithms select a single scene-specific value as the neighborhood size parameter and apply it uniformly to all 3D points while computing features. By doing so, some defect features end up being smoothened out at locations where the selected neighborhood size is larger than the optimal choice for those points. Conversely, geometric features might not always capture the local 3D structure if they are calculated based on less than optimal number of neighbors. This paper investigates and assesses the relationship between neighborhood size selection and the performance of point cloud-based unsupervised spall classification algorithms in a quantitative manner. Among the presented neighborhood selection approaches, an entropy-based approach that incorporates a tailored optimal neighborhood size for every point in a point cloud, resulted in a significant improvement over the performance of current state-of-the-art approaches. The performed quantitative study also demonstrated the robustness of this approach to variables, such as subsampling percentage, maximum neighborhood size and different noise levels. The implemented research testbed is comprised of statistically significant number of spall defect datasets generated from five different bridges. The outcome of this research is expected to improve the reliability of point cloud-based condition assessment for concrete bridges.

Feature Selection using Simulated Annealing with Optimal Neighborhood Approach

The one of the metaheuristic approaches that can be used was simulated annealing (SA) algorithm which inspired by annealing metallurgical process. This algorithm shows advantages in finding global optimum of given function which will be used in feature selection. In this study, we will trying to combine the neighborhood size and limited approach by using data simulation comparing between two function which is Akaike Index Criterion (AIC) function and Bayesian Index Criterion (BIC) function. The result of this experiment shows that the selected variables using optimal neighborhood size and limit the selected variable provide the result of goodness model around 98% of accuracy and specificity and 94% of sensitivity compared with simulated annealing algorithms without any modification using both AIC function and BIC function, and in the simulation also shows that BIC function give better result than AIC function.

Improved Supervised Learning-Based Approach for Leaf and Wood Classification From LiDAR Point Clouds of Forests

Accurately classifying 3-D point clouds into woody and leafy components has been an interest for applications in forestry and ecology including the better understanding of radiation transfer between canopy and atmosphere. The past decade has seen an increase in the methods attempting to classify leaves and wood in point clouds based on radiometric or geometric features. However, classification purely based on radiometric features is sensor-specific, and the method by which the local neighborhood of a point is defined affects the accuracy of classification based on geometric features. Here, we present a leaf-wood classification method combining geometrical features defined by radially bounded nearest neighbors at multiple spatial scales in a machine learning model. We compared the performance of three different machine learning models generated by the random forest (RF), XGBoost, and lightGBM algorithms. Using multiple spatial scales eliminates the need for an optimal neighborhood size selection and defining the local neighborhood by radially bounded nearest neighbors makes the method broadly applicable for point clouds of varying quality. We assessed the model performance at the individual tree- and plot-level on field data from tropical and deciduous forests, as well as on simulated point clouds. The method has an overall average accuracy of 94.2% on our data sets. For other data sets, the presented method outperformed the methods in literature in most cases without the need for additional postprocessing steps that are needed in most of the existing methods. We provide the entire framework as an open-source python package.

Ligand Binding Thermodynamic Cycles: Hysteresis, the Locally Weighted Histogram Analysis Method, and the Overlapping States Matrix.

Free energy perturbation (FEP) simulations have been widely applied to obtain predictions of the relative binding free energy for a series of congeneric ligands binding to the same receptor, which is an essential component for the lead optimization process in computer-aided drug discovery. In the case of several congeneric ligands forming a perturbation map involving a closed thermodynamic cycle, the summation of the estimated free energy change along each edge in the cycle using Bennett acceptance ratio (BAR) usually will deviate from zero due to systematic and random errors, which is the hysteresis of cycle closure. In this work, the advanced reweighting techniques binless weighted histogram analysis method (UWHAM) and locally weighted histogram analysis method (LWHAM) are applied to provide statistical estimators of the free energy change along each edge in order to eliminate the hysteresis effect. As an example, we analyze a closed thermodynamic cycle involving four congeneric ligands which bind to HIV-1 integrase, a promising target which has emerged for antiviral therapy. We demonstrate that, compared with FEP and BAR, more accurate and hysteresis-free estimates of free energy differences can be achieved by using UWHAM to find a single estimate of the density of states based on all of the data in the cycle. Furthermore, by comparison of LWHAM results obtained from the inclusion of different numbers of neighboring states with UWHAM estimation involving all the states, we show how to determine the optimal neighborhood size in the LWHAM analysis to balance the trade-offs between computational cost and accuracy of the free energy prediction. Even with the smallest neighborhood, LWHAM can improve the BAR free energy estimates using the same input data as BAR. We introduce an overlapping states matrix that is constructed by using the global jump formula of LWHAM and plot its heat map. The heat map provides a quantitative measure of the overlap between pairs of alchemical/thermodynamic states. We explain how to identify and improve the FEP calculations along the edges that most likely cause large systematic errors by using the heat map of the overlapping states matrix and by comparing the BAR and UWHAM estimates of the free energy change.

Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification

Kernel methods have been successfully applied to the areas of pattern recognition and data mining. In this paper, we mainly discuss the issue of propagating labels in kernel space. A Kernel-Induced Label Propagation (Kernel-LP) framework by mapping is proposed for high-dimensional data classification using the most informative patterns of data in kernel space. The essence of Kernel-LP is to perform joint label propagation and adaptive weight learning in a transformed kernel space. That is, our Kernel-LP changes the task of label propagation from the commonly-used Euclidean space in most existing work to kernel space. The motivation of our Kernel-LP to propagate labels and learn the adaptive weights jointly by the assumption of an inner product space of inputs, i.e., the original linearly inseparable inputs may be mapped to be separable in kernel space. Kernel-LP is based on existing positive and negative LP model, i.e., the effects of negative label information are integrated to improve the label prediction power. Also, Kernel-LP performs adaptive weight construction over the same kernel space, so it can avoid the tricky process of choosing the optimal neighborhood size suffered in traditional criteria. Two novel and efficient out-of-sample approaches for our Kernel-LP to involve new test data are also presented, i.e., (1) direct kernel mapping and (2) kernel mapping-induced label reconstruction, both of which purely depend on the kernel matrix between training set and testing set. Owing to the kernel trick, our algorithms will be applicable to handle the high-dimensional real data. Extensive results on real datasets demonstrate the effectiveness of our approach.

Automated Construction of Multiple Regional Libraries for Neighborhoodwise Local Multiple Endmember Unmixing

Endmember variability has been recognized as a major source of error in spectral unmixing. Although numerous unmixing algorithms have been developed, there is a gap between the studies emphasizing automated processing and those focusing on estimation accuracy. Endmember variability is rarely considered in most automated processing approaches, while existing unmixing algorithms that accommodate endmember variability partially rely on human involvement. To fill this gap, an automated unmixing chain prototype is proposed in this research, which integrates endmember extraction, refinement, and multiple endmember spectral mixture analysis (MESMA). In particular, this prototype is designed to automate three processing steps with intelligent approaches, including optimal size determination to generate neighborhoods as a spatial constraint, endmember refinement to select representative endmembers in spectral libraries, and automated construction of multiple regional libraries. Based on this prototype, three specific local and global MESMA variants with different neighborhood types were implemented, and their performances to estimate urban impervious surface abundance were compared. Analyses indicate three major conclusions. First, by examining spatial dependence of endmember spectra, an optimal neighborhood size can be obtained, with which a localized neighborhood can be derived by aggregating spatially close image segments. Second, by applying spatial and iterative K-means spectral clustering to endmembers from the identified neighborhoods, parsimonious and representative endmembers can be refined from a large endmember pool. Accordingly, a local spectral library can be automatically constructed in each neighborhood. Third, neighborhoodwise object-based MESMA (NEW OB-MESMA) significantly outperforms the other two MESMA variants with improved estimation accuracy and increased computational efficiency.

Joint Label Consistent Dictionary Learning and Adaptive Label Prediction for Semisupervised Machine Fault Classification

In this paper, we propose a semisupervised label consistent dictionary learning (SSDL) framework for machine fault classification. SSDL is a semisupervised extension of recent fully supervised label consistent dictionary learning approach, since the number of labeled machine data is usually limited in practice. To enable the supervised dictionary learning model to use both labeled and commonly readily available unlabeled data for enhancing performance, we propose to incorporate the merits of label prediction and present a joint label consistent dictionary learning and adaptive label prediction technique. In this setting, we first employ the existing label prediction model to estimate the labels of unlabeled training signals in a transductive fashion for enriching supervised prior. Then, we use predicted labeled data for label consistent dictionary learning. After that, we apply the discriminant sparse codes as the adaptive reconstruction weights for label prediction to update the estimated labels of unlabeled training data and the discriminative sparse codes matrix for label consistent dictionary learning so that classification performance can be enhanced. Thus, an informative dictionary, a sparse-code matrix, and an optimal multiclass classifier can be alternately obtained from one objective function. Besides, the tricky process of choosing optimal kernel width and neighborhood size can also be effectively voided in our scheme due to the adaptive weights. Extensive simulations on several machine fault datasets show that our SSDL method can deliver enhanced performance over other state-of-the-arts for machine fault classification.

Viewing urban decay from the sky: A multi-scale analysis of residential vacancy in a shrinking U.S. city

Demographic shifts result in not only urban sprawl but also urban decay. Although urban vacant land is a sign of economic decline, it is beneficial to the improvement of urban ecology since it provides a variety of critical ecosystem services. It is unclear how socioeconomic/ecological drivers collectively affect the emergence and dynamics of vacant land within the urban context of population decrease and economic decline in different shrinking cities. To address this issue, this research performed comprehensive analyses to examine and quantify the impacts of social processes, economic conditions, urban ecological and spatial proximity factors on residential vacant land at both the block group level and the parcel level through incorporating high spatial resolution multispectral aerial photographs and GIS datasets. Results indicate three major conclusions. First, the mean lot NDVI is found to be a consistently effective measurement of residential landscape management behaviors at both levels, which is significantly and positively related to residential vacancy. Second, proximity factors indirectly and partially characterize a number of socioeconomic variables. Third, a ratio index called neighborhood vacancy prevalence was proposed to capture the neighborhood blight effect, and a potentially optimal neighborhood size was obtained among different neighborhood radii. By considering different categories of variables, residential vacancy can be explained and modeled adequately at both the aggregate and fine levels. Urban planners, geographers and social scientists could benefit from the explanatory and predictive model at the fine scale to yield the most updated parcel data with acceptable estimation accuracy for various practical applications.

Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features

Abstract. 3D scene analysis by automatically assigning 3D points a semantic label has become an issue of major interest in recent years. Whereas the tasks of feature extraction and classification have been in the focus of research, the idea of using only relevant and more distinctive features extracted from optimal 3D neighborhoods has only rarely been addressed in 3D lidar data processing. In this paper, we focus on the interleaved issue of extracting relevant, but not redundant features and increasing their distinctiveness by considering the respective optimal 3D neighborhood of each individual 3D point. We present a new, fully automatic and versatile framework consisting of four successive steps: (i) optimal neighborhood size selection, (ii) feature extraction, (iii) feature selection, and (iv) classification. In a detailed evaluation which involves 5 different neighborhood definitions, 21 features, 6 approaches for feature subset selection and 2 different classifiers, we demonstrate that optimal neighborhoods for individual 3D points significantly improve the results of scene interpretation and that the selection of adequate feature subsets may even further increase the quality of the derived results.

Signal Denoising Based on the Adaptive Shrinkage Function and Neighborhood characteristics

In order to provide more accurate and better denoising results, a novel denoising method based on an adaptive shrinkage function and neighborhood characteristics is proposed in this paper for one-dimensional signal. According to the number of large coefficients in neighborhoods of small coefficients, the small coefficients are shrunk term by term so as to preserve more useful information in detail coefficients. Several denoising experiments are performed in this paper. The optimal neighborhood size is selected to perform the more effective signal denoising. The visual perception of denoising signals shows that the proposed method can preserve information of original signal very well. Numerical results indicate that the proposed method is very effective and superior to hard thresholding, NeighShrink scheme and neighboring coefficients preservation scheme for almost all noise levels.

Isospectral Manifold Learning Algorithm

PDF HTML阅读 XML下载 导出引用 引用提醒 等谱流形学习算法 DOI: 10.3724/SP.J.1001.2013.04465 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 国家自然科学基金(60970067,61033013,60775045);东吴学者计划(14317360);苏州大学国家预研基金(SDY2011A25) Isospectral Manifold Learning Algorithm Author: Affiliation: Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:基于谱方法的流形学习算法的目标是发现嵌入在高维数据空间中的低维表示.近年来,该算法已得到广泛的应用.等谱流形学习是谱方法中的主要内容之一.等谱流形学习源于这样的结论:只要两个流形的谱相同,其内部结构就是相同的.而谱计算难以解决的问题是近邻参数的选择以及如何构造合理邻接权.为此,提出了等谱流形学习算法(isospectral manifold learning algorithm,简称IMLA).它通过直接修正稀疏重构权矩阵,将类内的判别监督信息和类间的判别监督信息同时融入邻接图,达到既能保持数据间稀疏重建关系,又能利用监督信息的目的,与PCA等算法相比具有明显的优势.该算法在3 个常用人脸数据集(Yale,ORL,Extended Yale B)上得到了验证,这进一步说明了IMLA 算法的有效性. Abstract:Manifold learning based on spectral method has been widely used recently for discovering a low-dimensional representation in the high-dimensional vector space. Isospectral manifold learning is one of the main contents of spectrum method. Isospectral manifold learning stems from the conclusions that if only the spectrums of manifold are the same, so are their internal structures. However, the difficult task about the calculation of the spectrum is how to select the optimal neighborhood size and construct reasonable neighboring weights. In this paper, a supervised technique called isospectral manifold learning algorithm (IMLA) is proposed. By modifying directly sparse reconstruction weight, IMLA takes into account the within-neighboring information and between-neighboring information. Thus, it not only preserves the sparse reconstructive relationship, but also sufficiently utilizes discriminant information. Compared with PCA and other algorithms, IMLA has obvious advantages. Experimental results on face databases (Yale, ORL and Extended Yale B) show the effectiveness of the IMLA method. 参考文献 相似文献 引证文献

A shape-based segmentation method for mobile laser scanning point clouds

Segmentation of mobile laser point clouds of urban scenes into objects is an important step for post-processing (e.g., interpretation) of point clouds. Point clouds of urban scenes contain numerous objects with significant size variability, complex and incomplete structures, and holes or variable point densities, raising great challenges for the segmentation of mobile laser point clouds. This paper addresses these challenges by proposing a shape-based segmentation method. The proposed method first calculates the optimal neighborhood size of each point to derive the geometric features associated with it, and then classifies the point clouds according to geometric features using support vector machines (SVMs). Second, a set of rules are defined to segment the classified point clouds, and a similarity criterion for segments is proposed to overcome over-segmentation. Finally, the segmentation output is merged based on topological connectivity into a meaningful geometrical abstraction. The proposed method has been tested on point clouds of two urban scenes obtained by different mobile laser scanners. The results show that the proposed method segments large-scale mobile laser point clouds with good accuracy and computationally effective time cost, and that it segments pole-like objects particularly well.

DIMENSIONALITY BASED SCALE SELECTION IN 3D LIDAR POINT CLOUDS

Abstract. This papers presents a multi-scale method that computes robust geometric features on lidar point clouds in order to retrieve the optimal neighborhood size for each point. Three dimensionality features are calculated on spherical neighborhoods at various radius sizes. Based on combinations of the eigenvalues of the local structure tensor, they describe the shape of the neighborhood, indicating whether the local geometry is more linear (1D), planar (2D) or volumetric (3D). Two radius-selection criteria have been tested and compared for finding automatically the optimal neighborhood radius for each point. Besides, such procedure allows a dimensionality labelling, giving significant hints for classification and segmentation purposes. The method is successfully applied to 3D point clouds from airborne, terrestrial, and mobile mapping systems since no a priori knowledge on the distribution of the 3D points is required. Extracted dimensionality features and labellings are then favorably compared to those computed from constant size neighborhoods.

Deriving the optimal scale for relating topographic attributes and cover crop plant biomass

The use of cover crops generates a number of agro-ecological benefits for sustainable row-crop agriculture. However, their performance across agricultural fields is often highly spatially variable and there is insufficient information on factors affecting this variability and on tools to manage it. Topography is one of the main factors affecting spatial patterns of plant growth in the American Midwest. Digital elevation models are readily available for deriving topographic attributes; also sensor digital data can be used to indirectly assess cover crop biomass. However, processing procedures for identifying the proper scale of topographic and biomass representations are not well defined. The objectives of this study are to examine how relationships between cover crop biomass, assessed using the normalized difference vegetation index (NDVI), and topography depend on the neighborhood size used for deriving topographic attributes and creating NDVI maps; and identify the optimal neighborhood size for correlation and regression analyses. Slope, relative elevation and the potential solar radiation index were the variables that contributed the most to explaining variability in NDVI for raw data. However, other topographic attributes became significant predictors of NDVI at larger neighborhood sizes. We demonstrated that neighborhood size greatly affects some topographic attributes, i.e. curvature, flow accumulation, flow length and the wetness index; and changing the neighborhood size in both topography and NDVI considerably changes the strength of the prediction performance in multiple regression models. We studied six neighborhood sizes from 1 to 40m and the original raw data. On average, across all studied fields the best performance of multiple regression, as determined by the adjusted-R2, was obtained at neighborhood sizes 20 and 40m. Parameters of semivariogram models for terrain slope, such as the spatial autocorrelation range and the nugget/sill ratio, were found to be good indicators of prediction performance and optimum neighborhood size for filtering the raw data. The results demonstrate that topographic effects on growth and biomass production of cover crops are most pronounced at certain spatial scales, and topographic model predictions will be most accurate when used at the optimal scales.