Self-organizing Feature Map Network Research Articles

Classification of Urban Agricultural Functional Regions and Their Carbon Effects at the County Level in the Pearl River Delta, China

Exploring the transformation process of urban agricultural functions and its interaction with carbon effects based on regional differences is of great positive significance for achieving a low-carbon sustainable development of agriculture in metropolitan areas. By using the index system method, self-organizing feature maps (SOFM) network modeling, and Granger causality analysis, we divided the agricultural regional types of the Pearl River Delta (PRD) based on the spatio-temporal changes in urban agricultural functions and carbon effects at the county level in the PRD from 2002 to 2020, and analyzed the carbon effects generated by the agricultural functions according to the differences between the three agricultural regional types. The results show the following: (1) The changes in the basic functions of agriculture, the intermediate functions of agriculture, and the advanced functions of agriculture were different from the perspectives of both time and space. (2) The carbon effects produced by the areas with weak agricultural functions, the areas with medium agricultural functions, and the areas with strong agricultural functions were different. (3) The evolution of agricultural production types aggravated the grain risk in the PRD, and urban agriculture has potential in improving food security. (4) Based on the regional types of agricultural functions and considering the constraints of land and water, strategic suggestions such as integrating natural resources, improving utilization efficiency, upgrading technical facilities, and avoiding production pollution are put forward. (5) The green and low-carbon transformation of urban agriculture has its boundaries. The positive effects of the factors, namely the innovation of agricultural production methods, the change in agricultural organization modes, the impact of market orientation, and the transfer of the agricultural labor force, is limited. The findings of this paper provide valuable and meaningful insights for academia, policy makers, producers, and ultimately for the local population in general, driving the development of urban agriculture in a low-carbon and sustainable direction.

Design of network information visualization security cognition system based on QSOFM network and FR algorithm

ABSTRACT Network information is complex, there is no lack of hidden risks of information to the user caused by bad effects. But analyzing and evaluating them is complex and requires more diverse and powerful techniques. This research will combine Fruchterman-Reingold (FR) information visualization algorithm and information security risk assessment method based on Quantum self-organizing feature map (QSOFM) network to build information visualization security cognitive system. By introducing quantum neurons into self-organizing feature mapping network (SOFM), a network information security evaluation model is constructed. The system can evaluate the security level of network information and visualize the evaluation results. The experimental results show that the system has fast response speed and strong interactivity. The accuracy of QSOFM algorithm is 86%, 12% higher than the traditional algorithm, which can provide more powerful technical support for the visual security cognition of network information.

Comparative assessment of back propagation neural network and self organising feature map for iris-based access control system

Iris recognition is considered as one of the best biometric methods used for human identification and verification because of its unique features that differ from one person to another. Self-Organizing Feature Map (SOFM) and Back Propagation Neural Network (BPNN) are two techniques that have been used previously for iris recognition but their performance comparison has not been adequately investigated. This research, therefore, carried out a comparative analysis between SOFM and BPNN in iris recognition. Three hundred (300) iris images from one hundred and fifty (150) subjects were acquired from Covenant University Iris dataset. The acquired iris images were pre-processed by segmenting the iris portion using Hough Transform and were normalized using Daugman’s Rubber Sheet Model. Local Binary Pattern was used for feature extraction and dimension reduction of the iris images. Each of the two algorithms, SOFM and BPNN was used individually as iris image classifier, this technique was implemented using MATLAB (R2016a). The performance of the two iris classifiers was evaluated individually and compared at 0.75 threshold value based on Recognition Accuracy (RA), False Acceptance Rate (FAR), False Rejection Rate (FRR), Equal Error Rate (EER), Training Time (TT) and Recognition Time (RT). The SOFM and BPNN techniques were validated by carrying out a t-test to compare the differences between the two techniques at 5% significance level. The SOFM technique gave RA, FAR, FRR, EER, TT and RT of 97.14%, 1.67%, 3.75%, 3.18%, 104.47s and 81.98s, respectively, while the corresponding values for BPNN were 94.29%, 5.00%, 6.25%, 5.91%, 116.23s and 101.77s respectively. The P value between the SOFM and BPNN techniques was 0.002. This research outcome revealed that SOFM outperformed BPNN in iris recognition system with respect to RA, FAR, FRR, EER, TT and RT. The SOFM technique could be used for more robust iris recognition system than BPNN in security surveillance systems or other related systems.

Key Information Extraction Algorithm of Different Types of Digital Archives for Cultural Operation and Management.

In order to improve the effect of key information extraction from digital archives, a key information extraction algorithm for different types of digital archives is designed. Preprocess digital archive information, taking part of speech and marks as key information. Self-organizing feature mapping network is used to extract the key information features of digital archives, and the semantic similarity calculation results are obtained by combining the feature extraction results. Combine with mutual information collection, take that word with the highest mutual information value as the collection cent, traverse all keywords, and take the central word as the key information of digital archives to complete the extraction of key information. Experiments show that the recall rate of the algorithm ranges from 96% to 99%, the extraction accuracy of key information of digital archives is between 96 and 98%, and the average extraction time of key information of digital archives is 0.63 s. The practical application effect is good.

A Dynamic Convolution Kernel Generation Method Based on Regularized Pattern for Image Super-Resolution.

Image super-resolution aims to reconstruct a high-resolution image from its low-resolution counterparts. Conventional image super-resolution approaches share the same spatial convolution kernel for the whole image in the upscaling modules, which neglect the specificity of content information in different positions of the image. In view of this, this paper proposes a regularized pattern method to represent spatially variant structural features in an image and further exploits a dynamic convolution kernel generation method to match the regularized pattern and improve image reconstruction performance. To be more specific, first, the proposed approach extracts features from low-resolution images using a self-organizing feature mapping network to construct regularized patterns (RP), which describe different contents at different locations. Second, the meta-learning mechanism based on the regularized pattern predicts the weights of the convolution kernels that match the regularized pattern for each different location; therefore, it generates different upscaling functions for images with different content. Extensive experiments are conducted using the benchmark datasets Set5, Set14, B100, Urban100, and Manga109 to demonstrate that the proposed approach outperforms the state-of-the-art super-resolution approaches in terms of both PSNR and SSIM performance.

Health Assessment and Remaining Useful Life Prediction of Wind Turbine High-Speed Shaft Bearings

Vibration signals contain abundant information that reflects the health status of wind turbine high-speed shaft bearings ((HSSBs). Accurate health assessment and remaining useful life (RUL) prediction are the keys to the scientific maintenance of wind turbines. In this paper, a method based on the combination of a comprehensive evaluation function and a self-organizing feature map (SOM) network is proposed to construct a health indicator (HI) curve to characterizes the health state of HSSBs. Considering the difficulty in obtaining life cycle data of similar equipment in a short time, the exponential degradation model is selected as the degradation trajectory of HSSBs on the basis of the constructed HI curve, the Bayesian update model, and the expectation–maximization (EM) algorithm are used to predict the RUL of HSSBs. First, the time domain, frequency domain, and time–frequency domain degradation features of HSSBs are extracted. Second, a comprehensive evaluation function is constructed and used to select the degradation features with good performance. Third, the SOM network is used to fuse the selected degradation features to construct a one-dimensional HI curve. Finally, the exponential degradation model is selected as the degradation trajectory of HSSBs, and the Bayesian update and EM algorithm are used to predict the RUL of the HSSB. The monitoring data of a wind turbine HSSB in actual operation is used to validate the model. The HI curve constructed by the method in this paper can better reflect the degradation process of HSSBs. In terms of life prediction, the method in this paper has better prediction accuracy than the SVR model.

A Clustering Application Scenario Based on an Improved Self-Organizing Feature Mapping Network System

Categorizing national football teams by level is challenging because there is no standard of reference. Therefore, the self-organizing feature mapping network is used to solve this problem. In this paper, appropriate sample data were collected and an appropriate self-organizing feature mapping network model was built. After training, we obtained the classification results of 4 grades of 16 major Asian football national teams. As for the classification results, it is different to normalize the input data and not to normalize the input data. The classification results accord with our subjective cognition, which indicates the rationality of self-organizing feature mapping network in solving the classification problem of national football teams. In addition, the paper makes a detailed analysis of the classification results of the Chinese team and compares the gap between the Chinese team and the top Asian teams. It also analyses the impact of the normalization of input data on the classification results, taking Saudi Arabia as an example.

Identifying Critical Area of Ecosystem Service Supply and Demand at Different Scales Based on Spatial Heterogeneity Assessment and SOFM Neural Network

The purpose of this study was to establish a spatial multi-scale integrated assessment framework for critical areas of ecosystem service supply and demand, in order to provide theoretical support for regional ecological protection planning and refined management. Taking the typical hilly area of the upper reaches of the Yangtze River in China as an example, based on the assessment matrix of land use and ecosystem services, we used the method of spatial heterogeneity assessment and self-organizing feature mapping (SOFM) to explore the identification and regionalization of critical areas of ecosystem services at regional and small scales. The results show that there was spatial heterogeneity and scale effects of ecosystem services under the two scales. The small-scale supply–demand pattern was greatly affected by microtopography and land use patterns, and the importance of ecosystem services was as follows: forest area in the upper part of the mountain > orchard and dry area in the middle and lower part of the mountain > valley farming area > flat town and farming area. The regional-scale supply–demand pattern was greatly affected by landscape structure, location conditions and social economy, and the importance of ecosystem services was as follows: south > west > north > central. The SOFM network quantitatively identified four types of ecological areas with clear dominant functions at regional and small scales. The balance between supply and demand in the studied ecosystem service areas was I < II < III < IV, in which IV was the critical area in terms of supply and I was the critical area in terms of demand. This assessment framework can improve the spatial accuracy and objectivity of the quantification and mapping of ecosystem services, and provide new ideas for multi-scale identification and expression of ecosystem services.

A Multi-Swarm ABC Algorithm for Parameters Optimization of SOFM Neural Network in Dynamic Environment

Self-organizing feature map (SOFM) neural network is a kind of competitive unsupervised learning neural network, which has strong self-organizing and self-learning capabilities. It has been widely used in the fields of data classification and data clustering. A crucial step for SOFM neural network is to set its weight parameters correctly because the output accuracy and efficiency of the network depend much on these parameters. Most of current methods for parameter setting are based on static data. However, in a dynamic environment, the statistical characteristics of the generated data will change unpredictably over time. If the SOFM network cannot react to the changes of the environment, its performance will degrade. To deal with this problem, a more powerful multi-swarm artificial bee colony algorithm (MABC) is proposed. In the algorithm, the classic ABC algorithm is improved with multi-swarm and exclusive operation strategies to make it suitable for tracking optimal parameter settings of the SOFM network, so that the SOFM network can be applied to a dynamic environment. Two real data streams, which are regarded as coming from dynamic environments, are used to evaluate the effectiveness of the algorithm. Results show that the proposed algorithm is superior to the classic SOFM algorithm in terms of clustering purity and effectiveness. It is a promising method for the classification of data streams from dynamic environments.

Fusion Fault Diagnosis Model for Six-Rotor UAVs Based on Conformal Fourier Transform and Improved Self-Organizing Feature Map

If the fault sources can be located in a timely and accurate manner when an unmanned aerial vehicle (UAV) has an early minor fault, a major accident can be avoided. In light of the early fault of the six-rotor UAV motors, this paper proposes a fusion fault diagnosis model based on Conformal Fourier Transform (CFT) and the improved Self-Organizing Feature Map (SOM) neural network. Firstly, to overcome the weakening of UAV fault information caused by external interference and solve the problem that the non-uniform distribution of the collected flight data affects the accuracy of the frequency domain processing, on the basis of changing the processing method of the Fourier integral kernel and using high-order numerical integration, an improved Conformal Fourier Transform (CFT) algorithm optimized by spectrum refinement strategy is proposed. Then this algorithm is used to further intensify the main features and build a clear fault state in a cycle processing method. Secondly, an improved SOM neural network is designed. We use the unweighted average distance (UPGMA) of the agglomerative hierarchical clustering algorithm to detect the clustering areas of each pattern category of the data samples, and the weight vectors of different clustering areas are used to randomly initialize the connection weights of SOM network, thereby improving the clustering speed and convergence effect. On this basis, CFT algorithm is integrated into the improved SOM network to realize the multi-module collaboration strategy and finally form a new fusion fault diagnosis model.

An improved de-interleaving algorithm of radar pulses based on SOFM with self-adaptive network topology

As a core part of the electronic warfare (EW) system, de-interleaving is used to separate interleaved radar signals. As interleaved radar pulses become more complex and denser, intelligent classification of radar signals has become very important. The self-organizing feature map (SOFM) is an excellent artificial neural network, which has huge advantages in intelligent classification of complex data. However, the de-interleaving process based on SOFM is faced with the problems that the initialization of the map size relies on prior information and the network topology cannot be adaptively adjusted. In this paper, an SOFM with self-adaptive network topology (SANT-SOFM) algorithm is proposed to solve the above problems. The SANT-SOFM algorithm first proposes an adaptive proliferation algorithm to adjust the map size, so that the initialization of the map size is no longer dependent on prior information but is gradually adjusted with the input data. Then, structural optimization algorithms are proposed to gradually optimize the topology of the SOFM network in the iterative process, constructing an optimal SANT. Finally, the optimized SOFM network is used for de-interleaving radar signals. Simulation results show that SANT-SOFM could get excellent performance in complex EW environments and the probability of getting the optimal map size is over 95% in the absence of priori information.

Early warning of debris flow using optimized self-organizing feature mapping network

Abstract Early warning of debris flow is one of the core contents of disaster prevention and mitigation work for debris flow disasters. There are few early warning methods based on the combination of rainfall threshold and geological environment conditions. In this paper, we presented an early warning method for debris flow based on the infinite irrelevance method (IIM) and self-organizing feature mapping (SOFM), and applied it to Liaoning Province, China. The proposed model consisted of three stages. Firstly, eight geological environmental conditions and two rainfall-inducing conditions were selected by analyzing the factors affecting the development of debris flow in the study area, and the rainfall threshold for debris flow outbreak was 150 mm. Secondly, the correlation between various factors was analyzed by IIM, which prevented the blindness of parameter selection and improved the prediction accuracy of the model. Finally, SOFM was employed to predict the test data. Experimental results showed that the IIM-SOFM model had a strong early warning ability. When 25 samples of low-frequency debris flow area were selected, the accuracy rate of the IIM-SOFM model with optimized network structure parameters was 100%, which it was obviously superior to the rainfall threshold method, BP neural network and competitive neural network. Consequently, it is feasible to use the IIM-SOFM model for early warning of debris flow, outperforming traditional machine learning methods.

Research on Error Monitoring Model of CNC Machine Tool Based on Artificial Intelligence

In recent years, according to the rapid development and increasing application of artificial intelligence technology, the mechanical structure of modern CNC machine tools is becoming more and more complicated, and the automation level of CNC machine tools is constantly increasing. Research on a set of artificial intelligence-based CNC machine tool error monitoring model is of great significance to China’s industrial development. This article is a more in-depth and systematic study of the health monitoring system of CNC machine tools, especially high-end (such as five-axis linkage) CNC machine tools, multi-source fusion technology that supports high-reliability maintenance decisions, and key components of CNC machine tools based on artificial intelligence Fault monitoring and early warning. Based on the artificial intelligence SOM neural network learning algorithm, this paper designs a rolling bearing fault monitoring and early warning model architecture, studies the multi-source data fusion method based on DS evidence theory, and proposes and implements a self-organizing feature mapping network fault monitoring algorithm and adaptive ARMA The fault early warning algorithm improves the calculation efficiency of the rolling bearing monitoring diagnosis and early warning under the premise of ensuring accuracy. The experimental results show that when the sampling value is greater than 980 groups, the degradation value increases more until the bearing is in a failure state.

Intelligent fault diagnosis of rolling bearings using variational mode decomposition and self-organizing feature map

Rotating machinery contains numerous rolling bearings, which are critical for ensuring the normal working position and accurate operation of individual shaft systems. However, damage to rolling bearings can change their damping, stiffness, and elastic force. As a result, fault signals appear nonlinear and nonstationary. Vibration signals thus become difficult to diagnose clearly, especially in the incipient fault stage. To solve this problem, this article proposes an intelligent approach based on variational mode decomposition and the self-organizing feature map for rolling bearing fault diagnosis. First, the intrinsic mode function components of rolling bearing vibration signals are effectively separated by variational mode decomposition. Then, permutation entropy is used to extract feature vectors, which are used as training and testing data for the self-organizing feature map network. Finally, the various fault types of states are clustered on an intuitive visualization map. Clustering results of the experimental signal and the measured signal prove that the proposed method can successfully extract and cluster the rolling bearing faults in engineering applications. The proposed method improves the fault recognition rate to some extent over traditional methods.

PSO–SOM Neural Network Algorithm for Series Arc Fault Detection

Self-organizing feature map (SOM) neural network is a kind of competitive neural network with unsupervised learning. It has the strong abilities of self-organization and self-learning. However, the classification accuracy of SOM neural network may decrease when the features of tested object are not obvious. In this paper, the particle swarm optimization (PSO) algorithm is used to optimize the weight values of SOM network. Three indexes, i.e., intra-class density, standard deviation and sample difference, are used to judge the weight value, which can improve the classification accuracy of the SOM network. PSO–SOM network is applied to the detection of series arc fault in electrical circuits and compared with conventional SOM network and learning vector quantization (LVQ) network. The detection accuracy of the PSO–SOM network is 95%, which is higher than conventional SOM network and LVQ network.

Development of a Heterogeneity Analysis Framework for Collaborative Sponge City Management

Rapid urbanization, inappropriate urban planning and the changing climate in many countries have resulted in flooding, water shortage and water pollution around the world. Although the sponge city concept has been applied in both macro-scales and micro-scales to address those challenges, research on the heterogeneity of different cities for sponge city construction and the collaborative management between cities is insufficient. Therefore, this paper proposes a multivariate cluster analysis framework and conducts an empirical study using 96 Chinese cities. By considering the local infrastructure, economic development, water resource distribution, water quality and precipitation characteristics in each city, and integrating the principal component analysis and a self-organizing feature mapping network, this paper shows the potential of regional and interregional sponge city collaborative management. This will provide an opportunity for developing a new sponge city management mechanism and will promote the establishment of multi-functional departments for urban flood control and water quality improvement.

Evaluation of the biomass gasification-based combined cooling, heating and power system using the maximum generalized entropy principle

In order to promote the environmental conservation and energy efficiency, sufficient attention has been paid to biomass gasification-based combined cooling, heating and power (BGBCCHP) systems. Accurate evaluation of BGBCCHP systems is helpful to improving its performance. The maximum generalized entropy principle was introduced to reveal the essential characteristics of BGBCCHP systems. The BGBCCHP system was regarded as an open and evolutionary information network. Annual total cost, annual primary energy consumption, annual carbon dioxide emissions and exergy efficiency were used as evaluation criteria. Reasonable weights were conferred to the criteria so as to make the system stable. Moreover, an evaluation model based on the maximum generalized entropy principle was established to determine the eigenvalues of the BGBCCHP system. Self-organizing feature map network was used to simulate the evaluation model of the BGBCCHP system. A case study based on an office building in Beijing, China, was carried out. Three operating strategies (following the thermal load, following the electric load and following the hybrid electric-thermal load) were considered in the evaluation of the BGBCCHP system. Sensitivity analysis was carried out to investigate the impact of economic and technical parameters on the evaluation results. Results indicated that the evaluation model based on the maximum generalized entropy principle could be used to evaluate the BGBCCHP system operated under different operating strategies. The BGBCCHP system operated following the electric load achieved the maximum eigenvalue, which showed that its best integrated performance. On the contrary, the BGBCCHP system operated following the thermal load achieved the minimum eigenvalue, which showed that its worst integrated performance. The impact of sensitivity factors on the eigenvalues of the BGBCCHP system was different, which showed that the integrated performance of the BGBCCHP system was closely related to such factors.

Degradation state mining and identification for railway point machines

Critical point machine failure in railway-signal systems can lead to fatal accidents. Hence, early identification of anomalies is vital in guaranteeing reliable and safe transportation. However, most of the existing early fault diagnosis methods can only estimate the degradation trend under a specific fault mode. How to analyze the diversified degradation conditions under multiple fault modes is still a key problem. Considering the diversity of fault modes, this study proposes an early fault diagnosis method based on self-organizing feature map network and support vector machine, focusing on the use of non-fault data to simultaneously mine and accurately identify degradation states under different fault modes, to provide guidance for proactive machine maintenance. The experimental results obtained via application of this scheme to field data for railway point machines demonstrate that the proposed methodology can effectively mine and accurately identify degradation states with different machine characteristics.

Insulator detection and recognition of explosion based on convolutional neural networks

Unmanned aerial vehicles (UAVs) equipped with high definition (HD) cameras can obtain a large number of detailed inspection images. The insulator is an indispensable component in the transmission lines. Detecting insulator in image video quickly and accurately can provide a reliable basis for the ranging and the obstacle avoidance flight of UAV close to the tower and transmission line. At the same time, the insulator is a serious threat to the safety of the power grid due to the multiple faults of the insulator, and the computer technology should be fully utilized to diagnose the fault. Detection of the insulator images with the complex aerial background is implemented by constructing a convolutional neural network (CNN), which has the classic architecture of five modules of convolution and pooling, two modules of fully connected layers. In this paper, we propose a recognition algorithm for explosion fault based on saliency detection, which uses the trained network model to extract the features. Then, we put the saliency maps into a self-organizing feature map (SOM) network and build the mathematical module via super pixel segmentation, contour detection and other image processing methods. The test shows that the algorithm can reduce the error that may be caused by manual analysis. It also demonstrates that the detection of the insulator and the recognition of explosion fault can effectively improve the efficiency and intelligence level.

Application of a new clustering algorithm to analyze FT-IR spectrum data of lubricating oils

Aiming at monitoring contaminated oil samples of marine engines, the FT-IR spectroscopy is used to analysis the oil samples. Under the condition of laboratory, 18 oil samples with different concentrations and different types of contaminants were measured. The types of contaminants were water, fuel dilution, ethylene glycol and oxidation. The FT-IR spectral data of oil samples is obtained. Firstly, the original FT-IR spectral data are pre-processed by the baseline correction and the data normalization. Then, the dimensions of FT-IR spectral data pre-processed are reduced by the principal component analysis (PCA) and the four different kinds of contaminant oil samples are shown by figures. Lastly, the low dimensional data are clustered by the self-organizing feature map network and the clustered results which stand for different kinds of contaminant oil samples are demonstrated in the digital form. The results showed that the accuracy of oxidation samples clustering reached 100%, the accuracy of contaminant water samples clustering reached 83%, and the accuracy of fuel or ethylene glycol contaminant samples clustering were unsatisfactory.