SOFM Neural Network Research Articles

The Application of the SOFM Neural Network and Internet of Things in Rural Revitalization

The Application of the SOFM Neural Network and Internet of Things in Rural Revitalization

Ecosystem service pattern of Fuzhou City based on ecosystem service bundles.

Based on InVEST model, recreational opportunity spectrum, factor analysis, cold and hot spot analysis, SOFM neural network, relief degree of land surface (RDLS) methods, we evalua-ted six kinds of ecosystem service in Fuzhou City and analyzed the trade-offs and synergies among them, with the aim to clarify the dominant services and the spatial pattern of service bundles in different topographical regions. The results showed substantial spatial heterogeneity in different ecosystem services of Fuzhou City. Water yield, carbon sequestration, habitat quality, and recreational opportunities were totally high, whereas the supply of agricultural products and soil and water conservation were low and substantial differences. The interaction between water yield and cultural servi-ces were synergies, but trade-offs occurred among regulating service, supporting service and agricultural products service. There were spatial aggregations for both trade-offs and synergies. Ecosystem service bundles could be divided into suburban recreation bundle, water conservation bundle, agricultural products bundle, urban life bundle, and forest ecological conservation bundle. The composition of service bundles clusters was different under different RDLS, with obvious spatial heterogeneity.

Analysis of Topics of Interdisciplinary Research in the Field of Library Science and Information Science from the Perspective of Altmetrics

On the basis of identifying the interdisciplinary research topics in the field of Library and Information Science, this paper constructed Altmetrics indicator systems and makes SOFM neural network clustering analysis on the comprehensive influence of the research topics, in order to provide reference for the interdisciplinary crossover and integration of Library and Information discipline in China under the background of “New Liberal Arts”. The study found that the 20 interdisciplinary research topics could be divided into four types according to their influence composition characteristics: comprehensive hotspots, online social hotspots, academic hotspots, potential hotspots. Interdisciplinary hot topics were important for the intersection and integration of library and information field and other disciplines, and high impact research topics deserved close attention from Chinese scholars.

Land use zoning using a coupled gridding-self-organizing feature maps method: A case study in China

Huangshui River Valley (HRV) is a typical valley area located in the northeast of the Qinghai-Tibetan plateau. Its long and narrow space, large vertical gradient and diverse land use types bring great challenges to the land use zoning in this region. The paper aims to propose a gridding-self-organizing feature maps (SOFM) coupled method based on grid cell, which will be more reliable and refined, if compared to the method of commonly used administrative regions as the basic analytic units. Firstly the focused study area is divided into 500 m × 500 m grid cells. Six indexes, including grassland, cultivated land, forest land, construction land, population density and per capita income are both spatialized and quantified in every grid. Meanwhile, that SOFM neural network model is at the usage of classifying the land use into six zoning areas can be certain. And urban area, urban-rural transition area, agriculture-forestry transition area, typical agricultural area, agriculture-pastoral transition area, and typical pastoral area are sure to belong to them. Its results can vividly indicate the actual situation where land use pattern is in constant changes in Huangshui River Valley (HRV). The research will provide a specific method for the substantial utilization of land resources.

Spatio-Temporal Patterns of Urban-Rural Development and Transformation in East of the “Hu Huanyong Line”, China

Urban-rural development and transformation is profoundly changing the socioeconomic system as well as the natural environment. The study uses the AHP (Analytic Hierarchy Process) method to construct a top-down index of human activity based around five dimensions (population, land, industry, society, and environment) to evaluate the spatial characteristics in the region east of the Hu Huanyong line, China, in 1994 and 2010. Then, we investigate the spatial-temporal pattern using the methods of hotspot analysis, local Moran’s I index and Pearson correlation coefficient. The calculation showed that: (1) northeast China was experiencing an economic recession during study period, and the implementation of revitalization plan have not controlled the recession trend yet; (2) Pearson correlation analysis showed that the improvement of population quality promote the development of industry and society systems significantly during study period; and (3) negative correlation between Population Development Index (PDI) change and Population Transformation Index (PTI) change (along with the Society Transformation Index (STI) change and Industry Transformation Index (ITI) change) reflected that east of the Hu Huanyong line, China was in a “demographic dividend” period. Then, with the help of SOFM neural network algorithm, we divided the study area into six types of region, and found that municipalities, provincial capitals, Yangtze River Delta region and cities on the North China Plain owned the greatest development, while cities in southwest and northeast China showed relatively poor development during study period.

Pattern Classification Based on Self-Organizing Feature Mapping Neural Network

Traditional pattern classification methods are not always efficient because sample data sets are sometimes incomplete and there are exceptions and counter examples. In this paper, SOFM neural network is applied in pattern classification of two-dimensional vectors after analysis of its structure and algorithm. The method to establish SOFM network via MATLAB7.0 is introduced before the network is applied to classify two-dimensional vectors. The adjustment process of weight vectors together with classification performance of SOFM model are also tested in the condition of different number of training steps. The simulation results show that the classification approach based on SOFM model is effective because of its fast speed, high accuracy and strong generalization ability.

A Star Map Recognition Method Based on Multi-Layers SOFM Network

Putting forward a kind of star identification algorithm based on SOFM neural network. Firstly, using dynamic threshold selection algorithm what is based on supporting vector machine select guide stars to composite the navigation star database, then a recognition system what contain multiple parallel SOFM subnets for star map recognition is designed. Simulated recognition results show that the SOFM network can extract complex feature recognition navigation star from the chart. Compared with the traditional triangle algorithm, this algorithm has better recognition accuracy, robustness and real-time.

Study on Layout Planning of Transfer Hub Integration of Urban Passenger Transit

In the background of the integration, how to scientifically and reasonably distribute transfer hubs becomes the problem needed to be solved urgently on traffic experts. First of all, this paper gives initial selections of transfer hub layout planning; then, on the basis of analyzing the influence factors of the layout planning, the evaluation index system is built; and based on rough set attribute reduction knowledge, the cluster analysis of initial selections is done by using the SOFM neural network, drawing the suboptimal alternatives; afterwards, through the establishment of the TOPSIS model based on entropy weight, the suboptimal alternatives are further optimalized, ultimately getting the optimal solution; finally, taking the haidian district of Beijing as an example, the model and algorithm of the subject are validated.

Application of Self-organizing Feature Maps Neural Network on Hydrographic Zones Partitioning

Hydrographic zones partitioning is the critical issue in hydrological station network planning and a hydrographic zones partition method that can divide the hydrographic zones objectively is desirable for any region. As a kind of pattern classification problem, the hydrographic zones partitioning of Shandong province is achieved by the self-organizing feature map neural network (SOFM network) which has been successfully applied to pattern classification problems. Based on 50 hydrological stations and 8 basic factors which reflect the land surface and hydroclimate characteristics, Shandong province is automatically divided into 2 hydrographic zones by SOFM network. The average watershed characteristics of each sub-zone are consistent with the local terrain and surface conditions. And based on the partitioning results of SOFM network method, the maximum peak flow and the accuracy are analyzed which are proved reasonable and achieve pass rate of 82%. Which indicate that it is an effective method to use SOFM neural network to divide the hydrographic zones.

Classification of Landscape Functions Using SOFM Neural Network: A Case Study from Beijing and Its Peripheral Area

Landscape multifunction is a hotspot in the fields of landscape ecology.In order to explore a method which can reflect both integrity and independence of landscape multifunction,this research focuses on the clustering of landscape functions,taking Beijing and its peripheral area,China,as the study area.Five landscape function intensities,material production,carbon storage,soil retention,habitat conservation,and population support,are calculated using a variety of ecological models and indices in a grid map.Then,based on the results of landscape multi-function calculation,the study area are clustered through self-organizing feature map model.The quantitative results show that different regions turned out to have different and relative unique effects on the regional priority functions.Beijing and its peripheral area can be divided into four landscape function regions: agricultural region,whose dominant function is material production;urban region,whose dominant functions are population support and carbon storage;ecological region,whose dominant functions are soil retention and habitat conservation;and transition region,which does not have dominant functions,but reflects the interaction between human and nature.The validation of the results also shows that the presented SOFM neural network model is an effective and appropriate method for cluster analysis.Clustering results based on the SOFM model exhibit significant regional heterogeneity,with notable regional differences in the four clustering types within the research area.This spatial comprehensive dataset,combined with the independence from mechanistic ecological assumptions of the SOFM network approach provides a unique opportunity to validate and assess modeling efforts.The dominant landscape functions influencing regional development differ from one area to another.Furthermore,characteristics of the landscape indices and functions vary with region.Despite its limitations and uncertainty,the application of the presented method on clustering landscapes function using the SOFM model organization in connection with high performance computers is encouraged as a very interesting and important goal for future studies.The approaches to achieve sustainable regional development were illustrated and their importance highlighted for policy makers and stakeholders.

Analysis on E-consumers’ Purchasing Behavior Based on Data-driving Model

It is the Internet world with vasty purchasing data sea online that makes research model of e-consumers’ purchasing behavior very different from traditional ones. Firstly this paper proposes three kinds of research models of consumers’ purchasing behavior, and then pointed out that data-driving model is the best one to analyze e-consumers’ purchasing behavior on the Internet. Secondly, it adopts the improved SOFM Neural Network as the tool of data-driving model to detailedly analyze e-consumers’ purchasing behavior of Internet marketing. Lastly experiment results demonstrate that the method has more visualization, exactness and robustness. Because consumers’ purchasing behavior analysis based on the SOFM Neural Network is a comparatively novel method, the research fruit in this paper is just for reference.

Research on Machine Vision in Forestry Pluck System

Forestry industry is an important part of nation's economy. In this paper, a machine vision system is presented as a key module of Camellia oleifera pluck robot. In order to cut fruit image up from complicate background, SOFM neural network and gray thresh is used in image segmentation. In SOFM method, take R-B,G-R,G-B and hue H tunnel as input feature vectors, use self-organization network to clustering can get the best effect. in gray threshold method can take various of method to get the best threshold, such as PSO and GA algorithm, and MATLAB includes the toolboxes. At last use noise ratio, area ratio, divided time, Fourier boundary descriptors and other indicators to assess the accuracy of segmentation. The methods have the significance to the current and subsequent research of forestry pluck device.