Semi-Supervised Clustering Algorithm Based on Deep Feature Mapping

Clustering analysis is one of the main concerns in data mining.A common approach to the clustering process is to bring together points that are close to each other and separate points that are away from each other.Therefore,measuring the distance between sample points is crucial to the effectiveness of clustering.Filtering features by label information and mea-suring the distance between samples by these features is a common supervised learning method to reconstruct distance metric.However,in many application scenarios,it is very expensive to obtain a large number of labeled samples.In this paper,to solve the clustering problem in the few supervised sample and high data dimensionality scenarios,a novel semi-supervised clustering algorithm is proposed by designing an improved prototype network that attempts to reconstruct the distance metric in the sample space with a small amount of pairwise supervised information,such as Must-Link and Cannot-Link,and then cluster the data in the new metric space.The core idea is to make the similar ones closer and the dissimilar ones further away through embedding mapping.Extensive experiments on both real-world and synthetic datasets show the effectiveness of this algorithm.Average clustering metrics on various datasets improved by 8%compared to the comparison algorithm.

Application of Self-Organizing Feature Map Neural Network Based on K-means Clustering in Network Intrusion Detection

Due to the widespread use of the Internet,customer information is vulnerable to computer systems attack,which brings urgent need for the intrusion detection technology.Recently,network intrusion detection has been one of the most important technologies in network security detection.The accuracy of network intrusion detection has reached higher accuracy so far.However,these methods have very low efficiency in network intrusion detection,even the most popular SOM neural network method.In this paper,an efficient and fast network intrusion detection method was proposed.Firstly,the fundamental of the two different methods are introduced respectively.Then,the selforganizing feature map neural network based on K-means clustering(KSOM)algorithms was presented to improve the efficiency of network intrusion detection.Finally,the NSLKDD is used as network intrusion data set to demonstrate that the KSOM method can significantly reduce the number of clustering iteration than SOM method without substantially affecting the clustering results and the accuracy is much higher than Kmeans method.The Experimental results show that our method can relatively improve the accuracy of network intrusion and significantly reduce the number of clustering iteration.

CLUSTERING PROPERTIES OF FUZZY KOHONEN'S SELF-ORGANIZING FEATURE MAPS

A new clustering algorithm called fuzzy self-organizing feature maps is introduced. It can process not only the exact digital inputs, but also the inexact or fuzzy non-digital inputs, such as natural language inputs. Simulation results show that the new algorithm is superior to original Kohonen’s algorithm in clustering performance and learning rate.

The Testing Intelligence System Based on Factor Models and Self-Organizing Feature Maps

Presented is a new testing system based on using the factor models and self-organizing feature maps as well as the method of filtering undesirable environment influence. Testing process is described by the factor model with simplex structure, which represents the influences of genetics and environmental factors on the observed parameters - the answers to the questions of the test subjects in one case and for the time, which is spent on responding to each test question to another. The Monte Carlo method is applied to get sufficient samples for training self-organizing feature maps, which are used to estimate model goodness-of-fit measures and, consequently, ability level. A prototype of the system is implemented using the Raven＇s Progressive Matrices （Advanced Progressive Matrices） - an intelligence test of abstract reasoning. Elimination of environment influence results is performed by comparing the observed and predicted answers to the test tasks using the Kalman filter, which is adapted to solve the problem. The testing procedure is optimized by reducing the number of tasks using the distribution of measures to belong to different ability levels after performing each test task provided the required level of conclusion reliability is obtained.

Trajectory Tracking of COVID-19 Epidemic Risk Using Self-organizing Feature Map

The ongoing COVID-19 has become a worldwide pandemic with increasing confirmed cases and deaths across the globe.By July 2022,the number of cumulative confirmed cases reported to the World Health Organization(WHO)has risen to 550 million,with more than 6 million deaths in total.The analysis of its epidemic risk remains the focus of attention all over the world for a long time.The Self-organizing feature map(SOM),a vector quantization method,offers a data mapping approach to tracking the response of time series data on a well-trained map.This study aims at a trajectory tracking of COVID-19 epidemic risk in 237 countries measured by the number of new confirmed cases and deaths per day for over one year.A hybrid clustering method uses SOM and K-means to generate a risk map and then displays the trajectory of daily risk on the map.The experimental results demonstrate the promising functionality of SOM for trajectory tracking and give experts insights into the dynamic changes of COVID-19 risk.

磁共振T_(2)^(*)mapping序列联合纹理特征参数对绝经后骨质疏松症的诊断价值

目的:探讨磁共振T_(2)^(*)mapping序列联合纹理特征参数在诊断女性绝经后骨质疏松症(postmenopausal osteoporosis,PMOP)中的应用价值。方法:回顾性分析2019年3月至2021年4月某院收治的50例PMOP患者(作为骨质疏松组)的临床资料,另选择50例绝经后骨量正常(骨密度>120 mg/cm^(3))的体检者为骨量正常组和50例绝经后骨量减少(80 mg/cm^(3)<骨密度<120 mg/cm^(3))者为骨量减少组。3组均行磁共振腰椎常规序列及T_(2)^(*)mapping扫描,提取图像纹理特征。对比3组腰椎T_(2)^(*)值及纹理特征参数(能量、对比、相关、逆差距及熵),采用Spearman相关性分析腰椎T_(2)^(*)值、纹理特征参数与女性发生POMP的相关性,通过多因素Logistics回归分析确定女性发生PMOP的独立预测因子,采用ROC曲线分析T_(2)^(*)mapping序列联合纹理特征参数对PMOP的诊断效能,构建发生POMP的列线图预测模型并对模型进行验证。结果:3组腰椎T_(2)^(*)值、能量、对比、相关、逆差距及熵比较,差异有统计学意义(P<0.05)。Spearman相关分析结果显示,腰椎T_(2)^(*)值、对比及熵与发生POMP呈显著正相关关系,能量、相关及逆差距与发生POMP呈显著负相关关系(P<0.05)。T_(2)^(*)值、能量、对比、相关、逆差距及熵均为POMP发生的独立预测因子(P<0.05)。T_(2)^(*)mapping序列联合纹理特征参数诊断的AUC、敏感度及特异度均优于单项参数诊断。列线图预测模型预测女性发生POMP的概率为75.00%,经验证模型具有较高的区分度、校准能力和净获益率。结论:磁共振T_(2)^(*)mapping序列联合纹理特征参数对女性发生POMP的诊断效能良好,T_(2)^(*)值、能量、对比、相关、逆差距及熵可作为临床筛选POMP高危人群的敏感指标。

Improving model performance in mapping cropland soil organic matter using time-series remote sensing data

Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effective management policies.As a spatial information prediction technique,digital soil mapping(DSM)has been widely used to spatially map soil information at different scales.However,the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance.To overcome this limitation,this study systematically assessed a framework of“information extractionfeature selection-model averaging”for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou,China in 2021.The results showed that using the framework of dynamic information extraction,feature selection and model averaging could efficiently improve the accuracy of the final predictions(R^(2):0.48 to 0.53)without having obviously negative impacts on uncertainty.Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM,which improved the R^(2)of random forest from 0.44 to 0.48 and the R^(2)of extreme gradient boosting from 0.37to 0.43.Forward recursive feature selection(FRFS)is recommended when there are relatively few environmental covariates(<200),whereas Boruta is recommended when there are many environmental covariates(>500).The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty.When the structures of initial prediction models are similar,increasing in the number of averaging models did not have significantly positive effects on the final predictions.Given the advantages of these selected strategies over information extraction,feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales,so this approach can provide more reliable references for soil conservation policy-making.

A Normalizing Flow-Based Bidirectional Mapping Residual Network for Unsupervised Defect Detection

Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside it.Consequently,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature spaces.Additionally,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly detection.The two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection performance.Comparative experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior performance.On the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 categories.Especially,it achieves 100%optimal detection performance in five categories.On the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.

Analysis of morphological characteristics of gravels based on digital image processing technology and self-organizing map

A comprehensive understanding of spatial distribution and clustering patterns of gravels is of great significance for ecological restoration and monitoring.However,traditional methods for studying gravels are low-efficiency and have many errors.This study researched the spatial distribution and cluster characteristics of gravels based on digital image processing technology combined with a self-organizing map(SOM)and multivariate statistical methods in the grassland of northern Tibetan Plateau.Moreover,the correlation of morphological parameters of gravels between different cluster groups and the environmental factors affecting gravel distribution were analyzed.The results showed that the morphological characteristics of gravels in northern region(cluster C)and southern region(cluster B)of the Tibetan Plateau were similar,with a low gravel coverage,small gravel diameter,and elongated shape.These regions were mainly distributed in high mountainous areas with large topographic relief.The central region(cluster A)has high coverage of gravels with a larger diameter,mainly distributed in high-altitude plains with smaller undulation.Principal component analysis(PCA)results showed that the gravel distribution of cluster A may be mainly affected by vegetation,while those in clusters B and C could be mainly affected by topography,climate,and soil.The study confirmed that the combination of digital image processing technology and SOM could effectively analyzed the spatial distribution characteristics of gravels,providing a new mode for gravel research.

English-Chinese Neural Machine Translation Based on Self-organizing Mapping Neural Network and Deep Feature Matching

The traditional Chinese-English translation model tends to translate some source words repeatedly,while mistakenly ignoring some words.Therefore,we propose a novel English-Chinese neural machine translation based on self-organizing mapping neural network and deep feature matching.In this model,word vector,two-way LSTM,2D neural network and other deep learning models are used to extract the semantic matching features of question-answer pairs.Self-organizing mapping(SOM)is used to classify and identify the sentence feature.The attention mechanism-based neural machine translation model is taken as the baseline system.The experimental results show that this framework significantly improves the adequacy of English-Chinese machine translation and achieves better results than the traditional attention mechanism-based English-Chinese machine translation model.

Mapping winter wheat using phenological feature of peak before winter on the North China Plain based on time-series MODIS data

By employing the unique phenological feature of winter wheat extracted from peak before winter （PBW） and the advantages of moderate resolution imaging spectroradiometer （MODIS） data with high temporal resolution and intermediate spatial resolution, a remote sensing-based model for mapping winter wheat on the North China Plain was built through integration with Landsat images and land-use data. First, a phenological window, PBW was drawn from time-series MODIS data. Next, feature extraction was performed for the PBW to reduce feature dimension and enhance its information. Finally, a regression model was built to model the relationship of the phenological feature and the sample data. The amount of information of the PBW was evaluated and compared with that of the main peak （MP）. The relative precision of the mapping reached up to 92% in comparison to the Landsat sample data, and ranged between 87 and 96% in comparison to the statistical data. These results were sufficient to satisfy the accuracy requirements for winter wheat mapping at a large scale. Moreover, the proposed method has the ability to obtain the distribution information for winter wheat in an earlier period than previous studies. This study could throw light on the monitoring of winter wheat in China by using unique phenological feature of winter wheat.

Feature Extraction of Kernel Regress Reconstruction for Fault Diagnosis Based on Self-organizing Manifold Learning

The feature space extracted from vibration signals with various faults is often nonlinear and of high dimension.Currently,nonlinear dimensionality reduction methods are available for extracting low-dimensional embeddings,such as manifold learning.However,these methods are all based on manual intervention,which have some shortages in stability,and suppressing the disturbance noise.To extract features automatically,a manifold learning method with self-organization mapping is introduced for the first time.Under the non-uniform sample distribution reconstructed by the phase space,the expectation maximization(EM) iteration algorithm is used to divide the local neighborhoods adaptively without manual intervention.After that,the local tangent space alignment(LTSA) algorithm is adopted to compress the high-dimensional phase space into a more truthful low-dimensional representation.Finally,the signal is reconstructed by the kernel regression.Several typical states include the Lorenz system,engine fault with piston pin defect,and bearing fault with outer-race defect are analyzed.Compared with the LTSA and continuous wavelet transform,the results show that the background noise can be fully restrained and the entire periodic repetition of impact components is well separated and identified.A new way to automatically and precisely extract the impulsive components from mechanical signals is proposed.

A Topology Mapping Method for Feature Extraction of Irregular Curve Shape

ＡＴｏｐｏｌｏｇｙＭａｐｐｉｎｇＭｅｔｈｏｄｆｏｒＦｅａｔｕｒｅＥｘｔｒａｃｔｉｏｎｏｆＩｒｒｅｇｕｌａｒＣｕｒｖｅＳｈａｐｅＧＵＯＺｉｈａｉ；ＷＡＮＧＷｅｉ；ＪＩＡＧｕａｎｇ郭子海，王薇，贾光（Ｄｅｐｔ．ｏｆＣｏｍｐｕｔｅｒＳｃｉｅｎｃｅａｎｄＥｎ...

Cytogenetic Mapping of Disease Resistance Genes and Analysis of Their Distribution Features on Chromosomes in Maize

Cytogenetic maps of four clusters of disease resistance genes were generated by ISH of the two RFLP markers tightly linked to and flanking each of maize resistance genes and the cloned resistance genes from other plant species onto maize chromosomes, combining with data published before. These genes include Helminthosporium turcium Pass resistance genes Ht1, Htn1 and Ht2, Helminthosporium maydis Nisik resistance genes Rhm1 and Rhm2, maize dwarf mosaic virus resistance gene Mdm1, wheat streak mosaic virus resistance gene Wsm1, Helminthosporium carbonum ULLstrup resistance gene Hml and the cloned Xanthomonas oryzae pv. Oryzae resistance gene Xa21 of rice, Cladosporium fulvum resistance genes Cf-9 and Cf-2.1 of tomato,and Pseudomonas syringae resistance gene RPS2 of Arabidopsis. Most of the tested disease resistance genes located on the four chromosomes, i.e., chromosomes1, 3, 6 and 8, and they closely distributed at the interstitial regions of these chromosomal long arms with percentage distances ranging 31.44(±3.72)-72.40(±3.25) except for genes Rhm1, Rhm2, Mdm1 and Wsm1 which mapped on the satellites of the short arms of chromosome6. It showed that the tested RFLP markers and genes were duplicated or triplicated in maize genome. Homology and conservation of disease resistance genes among species, and relationship between distribution features and functions of the genes were discussed. The results provide important scientific basis for deeply understanding structure and function of disease resistance genes and breeding in maize.

Evaluation of effective spectral features for glacial lake mapping by using Landsat-8 OLI imagery

Glacial lake mapping provides the most feasible way for investigating the water resources and monitoring the flood outburst hazards in High Mountain Region.However,various types of glacial lakes with different properties bring a constraint to the rapid and accurate glacial lake mapping over a large scale.Existing spectral features to map glacial lakes are diverse but some are generally limited to the specific glaciated regions or lake types,some have unclear applicability,which hamper their application for the large areas.To this end,this study provides a solution for evaluating the most effective spectral features in glacial lake mapping using Landsat-8 imagery.The 23 frequently-used lake mapping spectral features,including single band reflectance features,Water Index features and image transformation features were selected,then the insignificant features were filtered out based on scoring calculated from two classical feature selection methods-random forest and decision tree algorithm.The result shows that the three most prominent spectral features(SF)with high scores are NDWI1,EWI,and NDWI3(renamed as SF8,SF19 and SF12 respectively).Accuracy assessment of glacial lake mapping results in five different test sites demonstrate that the selected features performed well and robustly in classifying different types of glacial lakes without any influence from the mountain shadows.SF8 and SF19 are superior for the detection of large amount of small glacial lakes,while some lake areas extracted by SF12 are incomplete.Moreover,SF8 achieved better accuracy than the other two features in terms of both Kappa Coefficient(0.8812)and Prediction(0.9025),which further indicates that SF8 has great potential for large scale glacial lake mapping in high mountainous area.

A survey: which features are required for dynamic visual simultaneous localization and mapping?

In recent years,simultaneous localization and mapping in dynamic environments(dynamic SLAM)has attracted significant attention from both academia and industry.Some pioneering work on this technique has expanded the potential of robotic applications.Compared to standard SLAM under the static world assumption,dynamic SLAM divides features into static and dynamic categories and leverages each type of feature properly.Therefore,dynamic SLAM can provide more robust localization for intelligent robots that operate in complex dynamic environments.Additionally,to meet the demands of some high-level tasks,dynamic SLAM can be integrated with multiple object tracking.This article presents a survey on dynamic SLAM from the perspective of feature choices.A discussion of the advantages and disadvantages of different visual features is provided in this article.

An Object-based Approach for Two-level Gully Feature Mapping Using High-resolution DEM and Imagery： A Case Study on Hilly Loess Plateau Region, China

Gully feature mapping is an indispensable prerequisite for the motioning and control of gully erosion which is a widespread natural hazard. The increasing availability of high-resolution Digital Elevation Model(DEM) and remote sensing imagery, combined with developed object-based methods enables automatic gully feature mapping. But still few studies have specifically focused on gully feature mapping on different scales. In this study, an object-based approach to two-level gully feature mapping, including gully-affected areas and bank gullies, was developed and tested on 1-m DEM and Worldview-3 imagery of a catchment in the Chinese Loess Plateau. The methodology includes a sequence of data preparation, image segmentation, metric calculation, and random forest based classification. The results of the two-level mapping were based on a random forest model after investigating the effects of feature selection and class-imbalance problem. Results show that the segmentation strategy adopted in this paper which considers the topographic information and optimal parameter combination can improve the segmentation results. The distribution of the gully-affected area is closely related to topographic information, however, the spectral features are more dominant for bank gully mapping. The highest overall accuracy of the gully-affected area mapping was 93.06% with four topographic features. The highest overall accuracy of bank gully mapping is 78.5% when all features are adopted. The proposed approach is a creditable option for hierarchical mapping of gully feature information, which is suitable for the application in hily Loess Plateau region.

Assessing Landsat-8 and Sentinel-2 spectral-temporal features for mapping tree species of northern plantation forests in Heilongjiang Province,China

Background:Accurate mapping of tree species is highly desired in the management and research of plantation forests,whose ecosystem services are currently under threats.Time-series multispectral satellite images,e.g.,from Landsat-8(L8)and Sentinel-2(S2),have been proven useful in mapping general forest types,yet we do not know quantitatively how their spectral features(e.g.,red-edge)and temporal frequency of data acquisitions(e.g.,16-day vs.5-day)contribute to plantation forest mapping to the species level.Moreover,it is unclear to what extent the fusion of L8 and S2 will result in improvements in tree species mapping of northern plantation forests in China.Methods:We designed three sets of classification experiments(i.e.,single-date,multi-date,and spectral-temporal)to evaluate the performances of L8 and S2 data for mapping keystone timber tree species in northern China.We first used seven pairs of L8 and S2 images to evaluate the performances of L8 and S2 key spectral features for separating these tree species across key growing stages.Then we extracted the spectral-temporal features from all available images of different temporal frequency of data acquisition(i.e.,L8 time series,S2 time series,and fusion of L8 and S2)to assess the contribution of image temporal frequency on the accuracy of tree species mapping in the study area.Results:1)S2 outperformed L8 images in all classification experiments,with or without the red edge bands(0.4%–3.4%and 0.2%–4.4%higher for overall accuracy and macro-F1,respectively);2)NDTI(the ratio of SWIR1 minus SWIR2 to SWIR1 plus SWIR2)and Tasseled Cap coefficients were most important features in all the classifications,and for time-series experiments,the spectral-temporal features of red band-related vegetation indices were most useful;3)increasing the temporal frequency of data acquisition can improve overall accuracy of tree species mapping for up to 3.2%(from 90.1%using single-date imagery to 93.3%using S2 time-series),yet similar overall accuracies were achieved using S2 time-series(93.3%)and the fusion of S2 and L8(93.2%).Conclusions:This study quantifies the contributions of L8 and S2 spectral and temporal features in mapping keystone tree species of northern plantation forests in China and suggests that for mapping tree species in China's northern plantation forests,the effects of increasing the temporal frequency of data acquisition could saturate quickly after using only two images from key phenological stages.

Configurable ontology mapping based on multi-feature

A configurable ontology mapping approach based on different kinds of concept feature information is introduced in this paper. In this approach, ontology concept feature information is classified as five kinds, which respectively corresponds to five kinds of concept similarity computation methods. Many existing ontology mapping approaches have adopted the multi-feature reasoning, whereas not all feature information can be com- puted in the real ontology mapping and only fractional feature information needs to be selected in the mapping computation. Consequently a eonfigurable ontology mapping model is introduced, which is composed of CMT model, SMT model and related transformation model. Through the configurable model, users can conveniently select the most suitable features and configure the suitable weights. Simultaneously, a related 3-step ontology mapping approach is also introduced. Associated with the traditional name and instance learner-based ontology mapping approach, this approach is evaluated by an ontology mapping application example.

Blank Panel Design of Integral Wing Skin Panels Based on Feature Mapping Methods

A blank panel design algorithm based on feature mapping methods for integral wing skin panels with supercritical airfoil surface is presented.The model of a wing panel is decomposed into features,and features of the panel are decomposed into information of location,direction,dimension and Boolean types.Features are mapped into the plane through optimal surface development algorithm.The plane panel is modeled by rebuilding the mapped features.Blanks of shot-peen forming panels are designed to identify the effectiveness of the methods.