Natural Neighborhood Research Articles

On the Characterizations of Approach Groups

In this paper, we present several characterizations on approach groups, and ultra-approach groups. In doing so, we first give necessary and sufficient conditions for an approach structure to be compatible with group structure. We show that every ultra-approach group is ultra uniformizable. Secondly, starting with an approach space, and its natural neighborhood system on a group, we characterize the resulting neighborhood approach group. Finally, we show that the category of ultra-approach-Cauchy group is a topological category, and more importantly, we show that the category of ultra-approach -Cauchy groups and the category of strongly normal limit groups are isomorphic.

An Inclusional-Dialogic Approach to Qualitative Inquiry

My research looks into collaborative learning and co-creativity in educational contexts. This paper presents my research trajectory towards inclusional-dialogic perception, discernment, and expression. I understand this phenomenon as thinking from presence: a natural inquiry process that is immersive, dialogic, and inherently embodied; a creative dialogue between self and habitat. I combine Natural Inclusionality and dialogism as my philosophical foundations. Importantly, I extend the notion of thinking from presence to the research inquiry itself, broadening the scope of scientific explorations of experience. Thus, the inquiry becomes a dance in between extraspection (outward perception) and introspection (inward sensing), brought together in an empathic second perspective. The natural inclusional approach entails a move away from the logic and language of definition into the logic and language of flow. This article discusses how fluid logic has shaped my research approach and my writing, with three emergent features. First, the inquiry and its documentation constitute an open-ended and serendipitous dialogue with the phenomena in focus. Second, research analysis and writing moves away from the predominance of the textual, recognizing that the translation of the experience into language is not an unavoidable necessity. It also underlines the significance of the visual and poetic expression of philosophy, methods, and findings, fusing science and art into partnership. Third, the disseminative writing is immersive. It openly brings forth an interplay between subjective and objective. My own lived, personal experience of the researched phenomena is a central layer of experiential meaning making, affording contemplative insight. Centering my research approach around the notion of thinking from presence is not a purely epistemological issue. It speaks to the nature of reality and captures the overarching desire to contribute to a deeper human understanding of the self in the context of its natural neighborhood.

A neighborhood-based robust clustering algorithm using Apollonius function kernel

Density Peak Clustering (DPC) is a useful algorithm for grouping data points based on their closeness and density. It is widely used in various areas of computer science. It can detect the peak density in each period of the clustering steps and assign the rest of the data to the next steps. Peak density clustering analysis is able to discover clusters of arbitrary shapes, but usually, when the data set is large, it is computationally expensive and difficult to apply to high-dimensional data. When the distance between clusters is significantly different, it is unable to distinguish adjacent clusters with different densities. To deal with such issues, a new clustering algorithm based on neighborhoods and the Apollonius kernel is proposed. The proposed algorithm can be implemented with four steps. 1) Estimation of natural neighbor, 2) Identification of core points, 3) Merging the cores of a cluster and separating the cores of different clusters, 4) Using the Apollonius kernel between the core points and the farthest points to assign the remaining points to the clusters and find the noise points. The local density estimation process based on the natural neighborhood of high-density points and their integration, as well as border point classification, allows the proposed method to reveal the local cluster structure. As a result, the adjoining clusters with distinctive densities are recognized, and the computation is substantially reduced. The proposed method is validated on some synthetic data sets and the UCI data set experimentally and has a high 10% accuracy.

WRND: A weighted oversampling framework with relative neighborhood density for imbalanced noisy classification

Imbalanced data and label noise are ubiquitous challenges in data mining and machine learning that severely impair classification performance. The synthetic minority oversampling technique (SMOTE) and its variants have been proposed, but they are easily constrained by hyperparameter optimization such as k-nearest neighbors, their performance deteriorates owing to noise, they rarely consider data distribution information, and they cause high complexity. Furthermore, SMOTE-based methods perform random linear interpolation between each minority class sample and its randomly selected k-nearest neighbors, regardless of sample differences and distribution information. To address the above problems, an adaptive, robust, and general weighted oversampling framework based on relative neighborhood density (WRND) is proposed. It can combine with most SMOTE-based sampling algorithms easily and improve performance. First, it adaptively distinguishes and filters noisy and outlier samples by introducing the natural neighbor, which inherently avoids the extra noise and overlapping samples introduced by the synthesis of noisy samples. The relative neighborhood density of each sample can then be obtained, which reflects the intra-class and inter-class distribution information within the natural neighborhood. To alleviate the blindness of SMOTE-based methods, the number and locations of synthetic samples are informedly assigned based on distribution information and reasonable generalization of natural neighborhoods of original samples. Extensive experiments on 23 benchmark datasets and six classic classifiers with eight pairs of representative sampling algorithms and two state-of-the-art frameworks, significantly demonstrate the effectiveness of the WRND framework. Code and framework are available at https://github.com/dream-lm/WRND_framework.

GNaN: A natural neighbor search algorithm based on universal gravitation

The natural neighbor (NaN) method and its search algorithm (NaN-Searching) are widely used in many fields, including pattern recognition and image processing. NaN-Searching fundamentally overcomes the problem of the conventional nearest neighbor algorithm in selecting parameters for datasets with arbitrary shapes and achieves good results. However, this algorithm uses the conventional distance metric as the neighbor judgment criterion, which cannot accurately reflect the overall structure of the dataset in the process of neighbor search. Inspired by Newton’s law of universal gravitation, we propose a NaN search algorithm based on universal gravitation (GNaN-Searching). Our algorithm calculates gravitation using the structural features of data points in the dataset, it utilizes the gravitation between data as the neighbor judgment criterion, and inherits the no-parameter and dynamic neighborhood characteristics of the NaN search algorithm. Experimental results show that the natural neighborhood graph obtained by our method has a high performance in the representation of manifold data. We also applied the new method to clustering and outlier detection and achieved satisfactory results.

Extended natural neighborhood for SMOTE and its variants in imbalanced classification

Imbalanced data classification is a challenging issue encountered in many practical applications. Synthetic minority oversampling technique (SMOTE) and its variants are popular resampling methods. However, in most of these methods, the neighborhood determined by k-nearest neighbor (kNN) cannot reflect the local distribution precisely, leading to the generation of noisy examples. To solve this problem, we propose a neighborhood concept without parameter k called extended natural neighbor (ENaN), which is derived from natural neighbor (NaN). ENaN unites kNN and reverse kNN to determine neighbors adaptively according to the sample distribution. Compared to NaN, ENaN explores broad neighborhoods, which facilitates to improve the quality of generated examples. ENaN-based SMOTE (ENaNSMOTE) can improve the sample distribution obtained by SMOTE and NaNSMOTE. Extensive experiments using 30 synthetic and 20 real-world datasets prove the effectiveness of ENaN in SMOTE and its variants.

Density-Distance Outlier Detection Algorithm Based on Natural Neighborhood

Outlier detection is of great significance in the domain of data mining. Its task is to find those target points that are not identical to most of the object generation mechanisms. The existing algorithms are mainly divided into density-based algorithms and distance-based algorithms. However, both approaches have some drawbacks. The former struggles to handle low-density modes, while the latter cannot detect local outliers. Moreover, the outlier detection algorithm is very sensitive to parameter settings. This paper proposes a new two-parameter outlier detection (TPOD) algorithm. The method proposed in this paper does not need to manually define the number of neighbors, and the introduction of relative distance can also solve the problem of low density and further accurately detect outliers. This is a combinatorial optimization problem. Firstly, the number of natural neighbors is iteratively calculated, and then the local density of the target object is calculated by adaptive kernel density estimation. Secondly, the relative distance of the target points is computed through natural neighbors. Finally, these two parameters are combined to obtain the outlier factor. This eliminates the influence of parameters that require users to determine the number of outliers themselves, namely, the top-n effect. Two synthetic datasets and 17 real datasets were used to test the effectiveness of this method; a comparison with another five algorithms is also provided. The AUC value and F1 score on multiple datasets are higher than other algorithms, indicating that outliers can be found accurately, which proves that the algorithm is effective.

The relative roles of different land-use types in bike-sharing demand: A machine learning-based multiple interpolation fusion method

Land use plays a crucial role in promoting the bike-sharing demand. Traditionally, studies on bike-sharing demand (BSD) are mainly focused on its prediction through regression methods, but the influence of MAUP (modifiable areal unit problem) in modeling is ignored. This paper aims to model spatial BSD distribution and prove the driving forces of different land use types to BSD through a machine-learning-based multiple interpolation fusion method. The hotspot detection model is employed to establish sample points covering different land use types in urban areas. In order to capture the differences in adaptations among different urban regions and for different data sizes, six machine learning methods are applied and evaluated to improve BSD estimation by fusing five spatial interpolation algorithms, including Inverse Distance Weight, Spline, Kriging, Natural Neighborhood and Trend. The methodological verification of Beijing City shows that the fusion models improve the estimation performance compared with individual interpolation algorithms, and that GRNN (generalized regression neural network) method is superior to all the others. According to fitting results of all POIs based on the GRNN fusion model, we identify which types of facilities correspond to customers that will have a stronger preference for bike-sharing and demonstrate which facility names are more prominent in each land use type. The conclusions presented here enrich our understanding relationships between land-use and BSD, which provide a valuable foundation for the bike-sharing development. Compared with implementing regression in an analysis zone or a square grid, troubles caused by the MAUP are effectively solved through this method.

NaNG-ST: A natural neighborhood graph-based self-training method for semi-supervised classification

The self-training method has been favored by scholars in semi-supervised classification. One of the greatest challenges in self-training methods is finding high-confidence unlabeled samples at each iteration. While multiple variations of self-training methods are developed, the strategy of finding high-confidence unlabeled samples heavlies on parameters and only utilizes labeled data alone, which makes the self-training method limited by the distribution of labeled data. To solve the above issues, a novel natural neighborhood graph-based self-training method (NaNG-ST) is proposed. In NaNG-ST, a parameter-free natural neighborhood graph (NaNG) is first constructed. The NaNG roughly reveals the real data distribution by exploiting unlabeled and labeled data. Based on NaNG, homogeneous and heterogeneous edges are defined to divide unlabeled samples into three cases. After that, homogeneous and heterogeneous edges can use the revealed distribution rather than labeled data alone to help NaNG-ST fast and effectively find confident unlabeled samples without any parameters. Besides, they also help NaNG-ST not to be limited by the distribution of initial labeled data. When a few initial labeled data can not roughly represent the distribution of the entire data, the NaNG helps NaNG-ST restore the real data distribution better. Intensive experiments on real-world data sets prove that NaNG-ST outperforms 7 popular semi-supervised self-taught approaches in terms of classification accuracy, mean F-measure and required running time.

Neighborhood discovery via augmented network community structure

The geospatial characteristics of transportation networks structurally constrain their features, and as a result, analysis methods designed for social networks typically fail to capture useful characteristics or make informative comparisons. In the case of road networks, natural constraints on the edge distribution weaken the ability of standard community detection algorithms to find clusters of nodes that align with natural neighborhood extents. We show that by adding edge weights based on the similarity of localized subgraph features, we can apply modularity-based community detection algorithms to uncover improved neighborhood shapes and extents. The use of local network characteristics allows the feature analysis to be completed in linear time, thus making the approach expandable to very large networks. We demonstrate this technique with an application to central Tokyo.

Gökova Körfezi Kıyı Hattında (Muğla, Türkiye) Çok Değişkenli İstatistiksel Analizler Kullanılarak Yüzey Suyu Kalite Parametrelerinin Değerlendirilmesi

In this study, some physico-chemical parameters of seven selected sampling sites (SSs) along the northern coastal line of Gökova Bay were investigated monthly. Then collected data were evaluated through the multivariate statistical analyses. Monthly distribution of water quality parameters was created using box plot across the SSs. When the parameters were examined with Spearman's rho correlation, the highest positive correlations were found to be between DO (Dissolved oxygen)‒SO (Saturated oxygen), EC (Electrical conductivity)‒Salt (Salinity), DO‒BOD5 (Biological oxygen demand), SO‒BOD5, TP (Total phosphorus)‒PO4 (Ortho-phosphate), while the highest negative correlations were found to be between WT (Water temperature)‒DO, EC‒NO3 (Nitrate nitrogen), Salt‒NO3, WT‒SO. When Kruskal Wallis Test was applied to water quality parameters, WT, DO, SO, SUS (Suspended solids), TP, NO2, PO4, NH4, NO3, BOD5 differed significantly in terms of sampling months (p

Reconstructing High-Precision Coral Reef Geomorphology from Active Remote Sensing Datasets: A Robust Spatial Variability Modified Ordinary Kriging Method

Active remote sensing technology represented by multi-beam and lidar provides an important approach for the effective acquisition of underwater coral reef geomorphological information. A spatially continuous surface model of coral reef geomorphology reconstructed from active remote sensing datasets can provide important geomorphological parameters for the research of coral reef geomorphological and ecological changes. However, the surface modeling methods commonly used in previous studies, such as ordinary kriging (OK) and natural neighborhood (NN), often represent a “smoothing effect”, which causes the strong spatial variability of coral reefs to be imprecisely reflected by the reconstructed surfaces, thus affecting the accurate calculation of subsequent geomorphological parameters. In this study, a spatial variability modified OK (OK-SVM) method is proposed to reduce the impact of the “smoothing effect” on the high-precision reconstruction of the complex geomorphology of coral reefs. The OK-SVM adopts a collaborative strategy of global parameter transformation, local residual correction, and extremum correction to modify the spatial variability of the reconstructed model, while maintaining high local accuracy. The experimental results show that the OK-SVM has strong robustness to spatial variability modification. This method was applied to the geomorphological reconstruction of the northern area of a coral atoll in the Nansha Islands, South China Sea, and the performance was compared with that of OK and NN. The results show that OK-SVM has higher numerical accuracy and attribute accuracy in detailed morphological fidelity, and is more adaptable in the geomorphological reconstruction of coral reefs with strong spatial variability. This method is relatively reliable for achieving high-precision reconstruction of complex geomorphology of coral reefs from active remote sensing datasets, and has potential to be extended to other geomorphological reconstruction applications.

Revisiting Epistemic Logic with Names

This paper revisits the multi-agent epistemic logic presented in [10], where agents and sets of agents are replaced by abstract, intensional "names". We make three contributions. First, we study its model theory, providing adequate notions of bisimulation and frame morphisms, and use them to study the logic's expressive power and definability. Second, we show that the logic has a natural neighborhood semantics, which in turn allows to show that the axiomatization in [10] does not rely on possibly controversial introspective properties of knowledge. Finally, we extend the logic with common and distributed knowledge operators, and provide a sound and complete axiomatization for each of these extensions. These results together put the original epistemic logic with names in a more modern context and opens the door for a logical analysis of epistemic phenomena where group membership is uncertain or variable.

Wolf is Coming—Dynamic Classification Prediction Model of Vespa Mandarinia

Given the threat of Vespa mandarinia invasion to ecological balance, according to the data and information provided, the dynamic reproduction model of Vespa mandarinia is established by using natural domain interpolation, and the variation law of total bumblebee with time, latitude, and longitude is obtained. At the same time, we established the classification prediction model by using a neural network and established the mapping relationship between time and space to evaluation grade.We meshed the area provided by the title, assigned values to the location of Vespa mandarinia (VM), and established a VM diffusion model with natural neighborhood interpolation. Its propagation process is simulated by cellular automata. It is determined that VM spreads in a circular shape centered at (122.93174°W, 48.93457°N) and (122.57376°W, 49.07848°N) in the Washington area, with the farthest distance being 1184.4 km and 985 km respectively.We set up a classification prediction model for better classification. According to the image upload time and location, SVM and neural network are used for classification prediction, and the classification accuracy is 74.26% and 97.60%, respectively, and the neural network has higher classification accuracy. So we choose the neural network.

How the variations of terrain factors affect the optimal interpolation methods for multiple types of climatic elements?

The spatial interpolation of meteorological data have important applications in ecological environment monitoring, such as soil erosion, ecological vulnerability evaluation. However, there are significant differences in the interpolation accuracy of climatic elements under different topographic and geomorphic conditions. Based on data of 810 meteorological stations across the country, five typical interpolation methods, namely ordinary Kriging method, inverse distance weight method, spline function method, natural neighborhood method and trend surface method, were utilized in this paper to analyze and compare the interpolation accuracy of five climate factors, namely temperature, precipitation, accumulated temperature(>10°),wind speed and sunshine hours, under different topographic and geomorphological conditions. The results showed that: (1) Ordinary kriging method of temperature had better applicability in plain, hill and medium-large undulating mountain areas for temperature while the inverse distance weight method and spline function method had higher interpolation accuracy in the platform area and the small undulating mountain area, respectively. (2) The optimal interpolation of the precipitation in plain, platform and medium-large undulating mountain areas was ordinary kriging method while the inverse distance weight method and spline function method had better applicability in small undulating mountain area. (3) For accumulated temperature (>10 °C), the spline function method had higher interpolation accuracy in plain and platform areas, while ordinary kriging method had better applicability in hilly, small and medium-large undulating mountain area al (4) The optimal spatial interpolation of wind speed in plain and hilly areas was the inverse distance weight method. The natural neighborhood method and the spline function method had the best applicability in plateau, medium-large undulating mountainous areas and small undulating mountain areas, respectively. (5) For sunshine hours, the optimal spatial interpolations in plain and hilly areas were natural neighborhood method and spline function method, respectively, while the ordinary kriging method and the inverse distance weighting method had better applicability in platform, large undulating mountainous areas and small undulating mountainous areas, respectively .

2.5D self-potential forward modeling by natural-infinite element coupling method

The self-potential method is an effective method for time-lapse monitoring of underground fluxes, in particular of contaminants. High efficiency and precise forward modeling are necessary for data interpretation and inversion. The natural element method is a new meshless numerical modeling method based on Voronoi diagram, Delaunay triangulation, and natural neighborhood interpolation, where the model nodes are arranged flexibly without grid constraints. However, adding boundary conditions is cumbersome for multi-source models. The infinite element method is an effective numerical method for truncated boundary problems without loading boundary conditions. A new numerical modeling approach is proposed by the coupling of natural elements and infinite elements and applied to redox self-potential models which are multi-source models. The numerical result shows the global stiffness matrix of the new coupled method is sparse, symmetric and independent of the position of field sources, which is helpful to improve forward modeling efficiency. The new method has high precision and is suitable for multi-source models.

Microhabitat characteristics affecting the occurrence and diversity of queen hornets (genus Vespa) in an urban green area

Urban parks and green areas are increasing globally. However, when hornets (genus Vespa) in particular among wild organisms adapt to and settle in urban green spaces, they are likely to come into conflict with humans. In this study in Cheonan city, South Korea, between April and June 2017, we used hornet traps to capture queen hornets that were awakening from hibernation, and identified the characteristics of these queen hornets. We selected three green types of urban areas, namely a natural-type neighborhood park, a children’s park, and a remnant forest. We analyzed the simple regression between captured queen hornets and time over an eight-week period, as well as the relationship between captured queen hornets and microhabitat variables (including Normalized Difference Vegetation Index, canopy openness, elevation, land cover rate, and herbaceous plant cover rate), and green type. Over time, there was a significant increase in the number of Vespa ducalis and Vepsa analis that were late in awakening from hibernation. The number of captured queen hornets was significantly different in urban parks compared with in the remnant forest. However, V. ducalis was as frequently captured in the natural neighborhood park as were other queen hornet species. Some queen hornet species were significantly positively correlated with elevation (Vespa crabro, Vespa mandarinia, V. ducalis), herbaceous plant cover rate (all species of queen hornets), broad-leaved forest (all species of queen hornets), and artificially barren ground (all species of queen hornets) of microhabitat. Different species were affected differently by the microhabitat variables tested. Consequently, we recommend that when urban green spaces are created, design criteria for complex urban parks should aim at ensuring suitability for use by local residents, and for hornet conservation.

AN AEROSOL LIDAR DATA VISUALIZATION METHOD BASED ON ARCGIS

Abstract. The geographical information, temporal and spatial distribution of pollution sources cannot be accurately described by the traditional aerosol lidar inversion data. In order to accurately locate the pollution sources and monitor the spatial and temporal distribution of pollutants, an aerosol lidar data visualization method based on ArcGIS is proposed in this paper. A natural neighborhood method is used to perform group interpolation on ArcGIS software, and the range range-extinction coefficient relationship diagram is plotted using the aerosol optical data obtained from Klett inversion algorithm. The geographic information is added to the lidar inversion data in this diagram. The aerosol spatial and temporal distribution range and the direction of aerosol diffusion are accurately displayed directly. The change of aerosol concentration is plotted in different colors, the visually displaying the concentration of pollutants in the detection area is realized. The aerosol detection data in the sunny and haze days in Yinchuan are visualized in this paper. The result shows that this method can quickly determine the geographical location of pollution sources and visualize the spatial and temporal distribution of aerosols. This method can be used to display aerosol data with geographic information for meteorological and environmental protection departments. This method can provide data support for meteorological and environmental protection departments to quickly determine the location and concentration of pollution sources.

Natural neighborhood-based classification algorithm without parameter k

Various kinds of k-Nearest Neighbor (KNN) based classification methods are the bases of many well-established and high-performance pattern recognition techniques. However, such methods are vulnerable to parameter choice. Essentially, the challenge is to detect the neighborhood of various datasets while ignoring the data characteristics. This article introduces a new supervised classification algorithm, Natural Neighborhood Based Classification Algorithm (NNBCA). Findings indicate that this new algorithm provides a good classification result without artificially selecting the neighborhood parameter. Unlike the original KNN-based method, which needs a prior k, NNBCA predicts different k for different samples. Therefore, NNBCA is able to learn more from flexible neighbor information both in the training and testing stages. Thus, NNBCA provides a better classification result than other methods.

Natural neighborhood graph-based instance reduction algorithm without parameters

Instance-based learning often uses all instances in a training set to construct inference structures. The large number of instances and attributes may lead to high storage requirements and low search efficiency. Instance reduction is developed to address these issues by removing irrelevant instances and noises from the training set. However, existing reduction techniques still have the shortcomings of parameter dependency and relatively low accuracy and reduction rates. In this study, we present a natural neighborhood graph-based instance reduction algorithm, namely, NNGIR. A natural neighborhood graph (NaNG) is automatically constructed by the natural neighbor search algorithm. This graph can provide a compact description of the nearest neighbor relation over pairs of instances. NNGIR applies NaNG to divide the original training set into noisy, border and internal instances. Next, the algorithm obtains a reduced set by eliminating noisy and redundant points. NNGIR has three main advantages: (1) it is a non-parameter instance reduction algorithm due to the use of natural neighborhood graphs; (2) it strongly increases the reduction rate while maintaining or even improving the predication accuracy; (3) its fluctuation of reduction rates for different types of data sets is notably small. The efficiency of NNGIR is supported by the positive results from the experiments conducted on both synthetic and real data sets.